diff options
34 files changed, 1656 insertions, 724 deletions
diff --git a/bh20seqanalyzer/main.py b/bh20seqanalyzer/main.py index 0b52e6b..b3a439d 100644 --- a/bh20seqanalyzer/main.py +++ b/bh20seqanalyzer/main.py @@ -16,277 +16,308 @@ logging.basicConfig(format="[%(asctime)s] %(levelname)s %(message)s", datefmt="% level=logging.INFO) logging.getLogger("googleapiclient.discovery").setLevel(logging.WARN) -def validate_upload(api, collection, validated_project, - fastq_project, fastq_workflow_uuid, - revalidate): - col = arvados.collection.Collection(collection["uuid"]) - - if not revalidate and collection["properties"].get("status") in ("validated", "rejected"): - return False - - # validate the collection here. Check metadata, etc. - logging.info("Validating upload '%s' (%s)" % (collection["name"], collection["uuid"])) - - errors = [] - - if collection["owner_uuid"] != validated_project: - dup = api.collections().list(filters=[["owner_uuid", "=", validated_project], - ["portable_data_hash", "=", col.portable_data_hash()]]).execute() - if dup["items"]: - # This exact collection has been uploaded before. - errors.append("Duplicate of %s" % ([d["uuid"] for d in dup["items"]])) - - if not errors: - if "metadata.yaml" not in col: - errors.append("Missing metadata.yaml", collection["name"]) - else: +class SeqAnalyzer: + + def __init__(self, api, keepclient, + uploader_project, + pangenome_analysis_project, + fastq_project, + validated_project, + workflow_def_project, + pangenome_workflow_uuid, + fastq_workflow_uuid, + exclude_list, + latest_result_collection): + self.api = api + self.keepclient = keepclient + self.uploader_project = uploader_project + self.pangenome_analysis_project = pangenome_analysis_project + self.fastq_project = fastq_project + self.validated_project = validated_project + self.workflow_def_project = workflow_def_project + self.pangenome_workflow_uuid = pangenome_workflow_uuid + self.fastq_workflow_uuid = fastq_workflow_uuid + self.exclude_list = exclude_list + self.latest_result_uuid = latest_result_collection + self.schema_ref = None + + def validate_upload(self, collection, revalidate): + col = arvados.collection.Collection(collection["uuid"], api_client=self.api, keep_client=self.keepclient) + + if not revalidate and collection["properties"].get("status") in ("validated", "rejected"): + return False + + # validate the collection here. Check metadata, etc. + logging.info("Validating upload '%s' (%s)" % (collection["name"], collection["uuid"])) + + errors = [] + + if collection["owner_uuid"] != self.validated_project: + dup = self.api.collections().list(filters=[["owner_uuid", "=", self.validated_project], + ["portable_data_hash", "=", col.portable_data_hash()]]).execute() + if dup["items"]: + # This exact collection has been uploaded before. + errors.append("Duplicate of %s" % ([d["uuid"] for d in dup["items"]])) + + if not errors: + if "metadata.yaml" not in col: + errors.append("Missing metadata.yaml", collection["name"]) + else: + try: + with col.open("metadata.yaml") as md: + metadata_content = ruamel.yaml.round_trip_load(md) + metadata_content["id"] = "http://arvados.org/keep:%s/metadata.yaml" % collection["portable_data_hash"] + sample_id = metadata_content["sample"]["sample_id"] + add_lc_filename(metadata_content, metadata_content["id"]) + valid = qc_metadata(metadata_content) + if not valid: + errors.append("Failed metadata qc") + except Exception as e: + errors.append(str(e)) + + if not errors: try: - metadata_content = ruamel.yaml.round_trip_load(col.open("metadata.yaml")) - metadata_content["id"] = "http://arvados.org/keep:%s/metadata.yaml" % collection["portable_data_hash"] - sample_id = metadata_content["sample"]["sample_id"] - add_lc_filename(metadata_content, metadata_content["id"]) - valid = qc_metadata(metadata_content) - if not valid: - errors.append("Failed metadata qc") - except Exception as e: - errors.append(str(e)) - - if not errors: - try: - tgt = None - paired = {"reads_1.fastq": "reads.fastq", "reads_1.fastq.gz": "reads.fastq.gz"} - for n in ("sequence.fasta", "reads.fastq", "reads.fastq.gz", "reads_1.fastq", "reads_1.fastq.gz"): - if n not in col: - continue - with col.open(n, 'rb') as qf: - tgt = qc_fasta(qf)[0] - if tgt != n and tgt != paired.get(n): - errors.append("Expected %s but magic says it should be %s", n, tgt) - elif tgt in ("reads.fastq", "reads.fastq.gz", "reads_1.fastq", "reads_1.fastq.gz"): - start_fastq_to_fasta(api, collection, fastq_project, fastq_workflow_uuid, n, sample_id) - return False - if tgt is None: - errors.append("Upload '%s' does not contain sequence.fasta, reads.fastq or reads_1.fastq", collection["name"]) - except Exception as v: - errors.append(str(v)) - - - if not errors: - # Move it to the "validated" project to be included in the next analysis - if "errors" in collection["properties"]: - del collection["properties"]["errors"] - collection["properties"]["status"] = "validated" - api.collections().update(uuid=collection["uuid"], body={ - "owner_uuid": validated_project, - "name": "%s (%s)" % (collection["name"], time.asctime(time.gmtime())), - "properties": collection["properties"]}).execute() - logging.info("Added '%s' to validated sequences" % collection["name"]) - return True - else: - # It is invalid - logging.warn("'%s' (%s) has validation errors: %s" % ( - collection["name"], collection["uuid"], "\n".join(errors))) - collection["properties"]["status"] = "rejected" - collection["properties"]["errors"] = errors - api.collections().update(uuid=collection["uuid"], body={"properties": collection["properties"]}).execute() - return False - - -def run_workflow(api, parent_project, workflow_uuid, name, inputobj): - project = api.groups().create(body={ - "group_class": "project", - "name": name, - "owner_uuid": parent_project, - }, ensure_unique_name=True).execute() - - with tempfile.NamedTemporaryFile() as tmp: - tmp.write(json.dumps(inputobj, indent=2).encode('utf-8')) - tmp.flush() - cmd = ["arvados-cwl-runner", - "--submit", - "--no-wait", - "--project-uuid=%s" % project["uuid"], - "arvwf:%s" % workflow_uuid, - tmp.name] - logging.info("Running %s" % ' '.join(cmd)) - comp = subprocess.run(cmd, capture_output=True) - logging.info("Submitted %s", comp.stdout) - if comp.returncode != 0: - logging.error(comp.stderr.decode('utf-8')) - - return project - - -def start_fastq_to_fasta(api, collection, - analysis_project, - fastq_workflow_uuid, - tgt, - sample_id): - - params = { - "metadata": { - "class": "File", - "location": "keep:%s/metadata.yaml" % collection["portable_data_hash"] - }, - "ref_fasta": { - "class": "File", - "location": "keep:ffef6a3b77e5e04f8f62a7b6f67264d1+556/SARS-CoV2-NC_045512.2.fasta" - }, - "sample_id": sample_id - } - - if tgt.startswith("reads.fastq"): - params["fastq_forward"] = { - "class": "File", - "location": "keep:%s/%s" % (collection["portable_data_hash"], tgt) - } - elif tgt.startswith("reads_1.fastq"): - params["fastq_forward"] = { - "class": "File", - "location": "keep:%s/reads_1.%s" % (collection["portable_data_hash"], tgt[8:]) - } - params["fastq_reverse"] = { - "class": "File", - "location": "keep:%s/reads_2.%s" % (collection["portable_data_hash"], tgt[8:]) + tgt = None + paired = {"reads_1.fastq": "reads.fastq", "reads_1.fastq.gz": "reads.fastq.gz"} + for n in ("sequence.fasta", "reads.fastq", "reads.fastq.gz", "reads_1.fastq", "reads_1.fastq.gz"): + if n not in col: + continue + with col.open(n, 'rb') as qf: + tgt = qc_fasta(qf)[0] + if tgt != n and tgt != paired.get(n): + errors.append("Expected %s but magic says it should be %s", n, tgt) + elif tgt in ("reads.fastq", "reads.fastq.gz", "reads_1.fastq", "reads_1.fastq.gz"): + self.start_fastq_to_fasta(collection, n, sample_id) + return False + if tgt is None: + errors.append("Upload '%s' does not contain sequence.fasta, reads.fastq or reads_1.fastq", collection["name"]) + except Exception as v: + errors.append(str(v)) + + + if not errors: + # Move it to the "validated" project to be included in the next analysis + if "errors" in collection["properties"]: + del collection["properties"]["errors"] + collection["properties"]["status"] = "validated" + self.api.collections().update(uuid=collection["uuid"], body={ + "owner_uuid": self.validated_project, + "name": "%s (%s)" % (collection["name"], time.asctime(time.gmtime())), + "properties": collection["properties"]}).execute() + logging.info("Added '%s' to validated sequences" % collection["name"]) + return True + else: + # It is invalid + logging.warn("'%s' (%s) has validation errors: %s" % ( + collection["name"], collection["uuid"], "\n".join(errors))) + collection["properties"]["status"] = "rejected" + collection["properties"]["errors"] = errors + self.api.collections().update(uuid=collection["uuid"], body={"properties": collection["properties"]}).execute() + return False + + + def run_workflow(self, parent_project, workflow_uuid, name, inputobj): + project = self.api.groups().create(body={ + "group_class": "project", + "name": name, + "owner_uuid": parent_project, + }, ensure_unique_name=True).execute() + + with tempfile.NamedTemporaryFile() as tmp: + tmp.write(json.dumps(inputobj, indent=2).encode('utf-8')) + tmp.flush() + cmd = ["arvados-cwl-runner", + "--submit", + "--no-wait", + "--project-uuid=%s" % project["uuid"], + "arvwf:%s" % workflow_uuid, + tmp.name] + logging.info("Running %s" % ' '.join(cmd)) + comp = subprocess.run(cmd, capture_output=True) + logging.info("Submitted %s", comp.stdout) + if comp.returncode != 0: + logging.error(comp.stderr.decode('utf-8')) + + return project + + + def start_fastq_to_fasta(self, collection, + tgt, + sample_id): + + params = { + "metadata": { + "class": "File", + "location": "keep:%s/metadata.yaml" % collection["portable_data_hash"] + }, + "ref_fasta": { + "class": "File", + "location": "keep:ffef6a3b77e5e04f8f62a7b6f67264d1+556/SARS-CoV2-NC_045512.2.fasta" + }, + "sample_id": sample_id } - newproject = run_workflow(api, analysis_project, fastq_workflow_uuid, "FASTQ to FASTA", params) - api.collections().update(uuid=collection["uuid"], - body={"owner_uuid": newproject["uuid"]}).execute() - -def start_pangenome_analysis(api, - analysis_project, - pangenome_workflow_uuid, - validated_project, - schema_ref, - exclude_list): - validated = arvados.util.list_all(api.collections().list, filters=[ - ["owner_uuid", "=", validated_project], - ["properties.status", "=", "validated"]]) - inputobj = { - "inputReads": [], - "metadata": [], - "subjects": [], - "metadataSchema": { - "class": "File", - "location": schema_ref - }, - "exclude": { - "class": "File", - "location": exclude_list + if tgt.startswith("reads.fastq"): + params["fastq_forward"] = { + "class": "File", + "location": "keep:%s/%s" % (collection["portable_data_hash"], tgt) + } + elif tgt.startswith("reads_1.fastq"): + params["fastq_forward"] = { + "class": "File", + "location": "keep:%s/reads_1.%s" % (collection["portable_data_hash"], tgt[8:]) + } + params["fastq_reverse"] = { + "class": "File", + "location": "keep:%s/reads_2.%s" % (collection["portable_data_hash"], tgt[8:]) + } + + newproject = self.run_workflow(self.fastq_project, self.fastq_workflow_uuid, "FASTQ to FASTA", params) + self.api.collections().update(uuid=collection["uuid"], + body={"owner_uuid": newproject["uuid"]}).execute() + + def start_pangenome_analysis(self): + + if self.schema_ref is None: + self.upload_schema() + + validated = arvados.util.list_all(self.api.collections().list, filters=[ + ["owner_uuid", "=", self.validated_project], + ["properties.status", "=", "validated"]]) + inputobj = { + "inputReads": [], + "metadata": [], + "subjects": [], + "metadataSchema": { + "class": "File", + "location": self.schema_ref + }, + "exclude": { + "class": "File", + "location": self.exclude_list + } } - } - validated.sort(key=lambda v: v["portable_data_hash"]) - for v in validated: - inputobj["inputReads"].append({ - "class": "File", - "location": "keep:%s/sequence.fasta" % v["portable_data_hash"] - }) - inputobj["metadata"].append({ - "class": "File", - "location": "keep:%s/metadata.yaml" % v["portable_data_hash"] - }) - inputobj["subjects"].append("http://collections.lugli.arvadosapi.com/c=%s/sequence.fasta" % v["portable_data_hash"]) - run_workflow(api, analysis_project, pangenome_workflow_uuid, "Pangenome analysis", inputobj) - - -def get_workflow_output_from_project(api, uuid): - cr = api.container_requests().list(filters=[['owner_uuid', '=', uuid], - ["requesting_container_uuid", "=", None]]).execute() - if cr["items"] and cr["items"][0]["output_uuid"]: - container = api.containers().get(uuid=cr["items"][0]["container_uuid"]).execute() - if container["state"] == "Complete" and container["exit_code"] == 0: - return cr["items"][0] - return None - - -def copy_most_recent_result(api, analysis_project, latest_result_uuid): - most_recent_analysis = api.groups().list(filters=[['owner_uuid', '=', analysis_project]], - order="created_at desc").execute() - for m in most_recent_analysis["items"]: - wf = get_workflow_output_from_project(api, m["uuid"]) - if wf: - src = api.collections().get(uuid=wf["output_uuid"]).execute() - dst = api.collections().get(uuid=latest_result_uuid).execute() - if src["portable_data_hash"] != dst["portable_data_hash"]: - logging.info("Copying latest result from '%s' to %s", m["name"], latest_result_uuid) - api.collections().update(uuid=latest_result_uuid, - body={"manifest_text": src["manifest_text"], - "description": "Result from %s %s" % (m["name"], wf["uuid"])}).execute() - break - + validated.sort(key=lambda v: v["portable_data_hash"]) + for v in validated: + inputobj["inputReads"].append({ + "class": "File", + "location": "keep:%s/sequence.fasta" % v["portable_data_hash"] + }) + inputobj["metadata"].append({ + "class": "File", + "location": "keep:%s/metadata.yaml" % v["portable_data_hash"] + }) + inputobj["subjects"].append("http://collections.lugli.arvadosapi.com/c=%s/sequence.fasta" % v["portable_data_hash"]) + self.run_workflow(self.pangenome_analysis_project, self.pangenome_workflow_uuid, "Pangenome analysis", inputobj) + + + def get_workflow_output_from_project(self, uuid): + cr = self.api.container_requests().list(filters=[['owner_uuid', '=', uuid], + ["requesting_container_uuid", "=", None]]).execute() + if cr["items"] and cr["items"][0]["output_uuid"]: + container = self.api.containers().get(uuid=cr["items"][0]["container_uuid"]).execute() + if container["state"] == "Complete" and container["exit_code"] == 0: + return cr["items"][0] + return None + + + def copy_most_recent_result(self): + most_recent_analysis = self.api.groups().list(filters=[['owner_uuid', '=', self.pangenome_analysis_project]], + order="created_at desc").execute() + for m in most_recent_analysis["items"]: + wf = self.get_workflow_output_from_project(m["uuid"]) + if wf: + src = self.api.collections().get(uuid=wf["output_uuid"]).execute() + dst = self.api.collections().get(uuid=self.latest_result_uuid).execute() + if src["portable_data_hash"] != dst["portable_data_hash"]: + logging.info("Copying latest result from '%s' to %s", m["name"], self.latest_result_uuid) + self.api.collections().update(uuid=self.latest_result_uuid, + body={"manifest_text": src["manifest_text"], + "description": "Result from %s %s" % (m["name"], wf["uuid"])}).execute() + break + + + def move_fastq_to_fasta_results(self): + projects = self.api.groups().list(filters=[['owner_uuid', '=', self.fastq_project], + ["properties.moved_output", "!=", True]], + order="created_at asc",).execute() + for p in projects["items"]: + wf = self.get_workflow_output_from_project(p["uuid"]) + if not wf: + continue -def move_fastq_to_fasta_results(api, analysis_project, uploader_project): - projects = api.groups().list(filters=[['owner_uuid', '=', analysis_project], - ["properties.moved_output", "!=", True]], - order="created_at desc",).execute() - for p in projects["items"]: - wf = get_workflow_output_from_project(api, p["uuid"]) - if wf: logging.info("Moving completed fastq2fasta result %s back to uploader project", wf["output_uuid"]) - api.collections().update(uuid=wf["output_uuid"], - body={"owner_uuid": uploader_project}).execute() - p["properties"]["moved_output"] = True - api.groups().update(uuid=p["uuid"], body={"properties": p["properties"]}).execute() - break + col = arvados.collection.Collection(wf["output_uuid"], api_client=self.api, keep_client=self.keepclient) + with col.open("metadata.yaml") as md: + metadata_content = ruamel.yaml.round_trip_load(md) + + colprop = col.get_properties() + colprop["sequence_label"] = metadata_content["sample"]["sample_id"] + self.api.collections().update(uuid=wf["output_uuid"], + body={"owner_uuid": self.uploader_project, + "properties": colprop}).execute() -def upload_schema(api, workflow_def_project): - schema_resource = pkg_resources.resource_stream('bh20sequploader.qc_metadata', "bh20seq-schema.yml") - c = arvados.collection.Collection() - with c.open("schema.yml", "wb") as f: - f.write(schema_resource.read()) - pdh = c.portable_data_hash() - wd = api.collections().list(filters=[["owner_uuid", "=", workflow_def_project], - ["portable_data_hash", "=", pdh]]).execute() - if len(wd["items"]) == 0: - c.save_new(owner_uuid=workflow_def_project, name="Metadata schema", ensure_unique_name=True) - return "keep:%s/schema.yml" % pdh - - -def print_status(api, uploader_project, fmt): - pending = arvados.util.list_all(api.collections().list, filters=[["owner_uuid", "=", uploader_project]]) - out = [] - status = {} - for p in pending: - prop = p["properties"] - out.append(prop) - if "status" not in prop: - prop["status"] = "pending" - prop["created_at"] = p["created_at"] - prop["uuid"] = p["uuid"] - status[prop["status"]] = status.get(prop["status"], 0) + 1 - if fmt == "html": - print( -""" -<html> -<body> -""") - print("<p>Total collections in upload project %s</p>" % len(out)) - print("<p>Status %s</p>" % status) - print( -""" -<table> -<tr><th>Collection</th> -<th>Sequence label</th> -<th>Status</th> -<th>Errors</th></tr> -""") - for r in out: - print("<tr valign='top'>") - print("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) - print("<td>%s</td>" % r["sequence_label"]) - print("<td>%s</td>" % r["status"]) - print("<td><pre>%s</pre></td>" % "\n".join(r.get("errors", []))) - print("</tr>") - print( -""" -</table> -</body> -</html> -""") - else: - print(json.dumps(out, indent=2)) + p["properties"]["moved_output"] = True + self.api.groups().update(uuid=p["uuid"], body={"properties": p["properties"]}).execute() + + + def upload_schema(self): + schema_resource = pkg_resources.resource_stream('bh20sequploader.qc_metadata', "bh20seq-schema.yml") + c = arvados.collection.Collection(api_client=self.api, keep_client=self.keepclient) + with c.open("schema.yml", "wb") as f: + f.write(schema_resource.read()) + pdh = c.portable_data_hash() + wd = self.api.collections().list(filters=[["owner_uuid", "=", self.workflow_def_project], + ["portable_data_hash", "=", pdh]]).execute() + if len(wd["items"]) == 0: + c.save_new(owner_uuid=self.workflow_def_project, name="Metadata schema", ensure_unique_name=True) + self.schema_ref = "keep:%s/schema.yml" % pdh + + + def print_status(self, fmt): + pending = arvados.util.list_all(self.api.collections().list, filters=[["owner_uuid", "=", self.uploader_project]]) + out = [] + status = {} + for p in pending: + prop = p["properties"] + out.append(prop) + if "status" not in prop: + prop["status"] = "pending" + prop["created_at"] = p["created_at"] + prop["uuid"] = p["uuid"] + status[prop["status"]] = status.get(prop["status"], 0) + 1 + if fmt == "html": + print( + """ + <html> + <body> + """) + print("<p>Total collections in upload project %s</p>" % len(out)) + print("<p>Status %s</p>" % status) + print( + """ + <table> + <tr><th>Collection</th> + <th>Sequence label</th> + <th>Status</th> + <th>Errors</th></tr> + """) + for r in out: + print("<tr valign='top'>") + print("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) + print("<td>%s</td>" % r["sequence_label"]) + print("<td>%s</td>" % r["status"]) + print("<td><pre>%s</pre></td>" % "\n".join(r.get("errors", []))) + print("</tr>") + print( + """ + </table> + </body> + </html> + """) + else: + print(json.dumps(out, indent=2)) def main(): parser = argparse.ArgumentParser(description='Analyze collections uploaded to a project') @@ -310,50 +341,45 @@ def main(): args = parser.parse_args() api = arvados.api() - - - - schema_ref = upload_schema(api, args.workflow_def_project) + keepclient = arvados.keep.KeepClient(api_client=api) + + seqanalyzer = SeqAnalyzer(api, keepclient, + args.uploader_project, + args.pangenome_analysis_project, + args.fastq_project, + args.validated_project, + args.workflow_def_project, + args.pangenome_workflow_uuid, + args.fastq_workflow_uuid, + args.exclude_list, + args.latest_result_collection) if args.kickoff: logging.info("Starting a single analysis run") - start_pangenome_analysis(api, - args.pangenome_analysis_project, - args.pangenome_workflow_uuid, - args.validated_project, - schema_ref, - args.exclude_list) + seqanalyzer.start_pangenome_analysis() return if args.print_status: - print_status(api, args.uploader_project, args.print_status) + seqanalyzer.print_status(args.print_status) exit(0) logging.info("Starting up, monitoring %s for uploads" % (args.uploader_project)) while True: - move_fastq_to_fasta_results(api, args.fastq_project, args.uploader_project) - - new_collections = arvados.util.list_all(api.collections().list, filters=[["owner_uuid", "=", args.uploader_project]]) - at_least_one_new_valid_seq = False - for c in new_collections: - at_least_one_new_valid_seq = validate_upload(api, c, - args.validated_project, - args.fastq_project, - args.fastq_workflow_uuid, - args.revalidate) or at_least_one_new_valid_seq - - if at_least_one_new_valid_seq and not args.no_start_analysis: - start_pangenome_analysis(api, - args.pangenome_analysis_project, - args.pangenome_workflow_uuid, - args.validated_project, - schema_ref, - args.exclude_list) - - copy_most_recent_result(api, - args.pangenome_analysis_project, - args.latest_result_collection) + try: + seqanalyzer.move_fastq_to_fasta_results() + + new_collections = arvados.util.list_all(api.collections().list, filters=[["owner_uuid", "=", args.uploader_project]]) + at_least_one_new_valid_seq = False + for c in new_collections: + at_least_one_new_valid_seq = seqanalyzer.validate_upload(c, args.revalidate) or at_least_one_new_valid_seq + + if at_least_one_new_valid_seq and not args.no_start_analysis: + seqanalyzer.start_pangenome_analysis() + + seqanalyzer.copy_most_recent_result() + except Exception as e: + logging.exeception("Error in main loop") if args.once: break diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index ee852fa..0aead3b 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -16,7 +16,7 @@ $graph: fields: license_type: doc: License types as defined in https://wiki.creativecommons.org/images/d/d6/Ccrel-1.0.pdf - type: string? + type: string jsonldPredicate: _id: https://creativecommons.org/ns#License title: @@ -264,7 +264,7 @@ $graph: virus: virusSchema technology: technologySchema submitter: submitterSchema - license: licenseSchema + license: ["null", licenseSchema] id: doc: The subject (eg the fasta/fastq file) that the metadata describes type: string diff --git a/bh20sequploader/bh20seq-shex.rdf b/bh20sequploader/bh20seq-shex.rdf index 7331e86..bbc7309 100644 --- a/bh20sequploader/bh20seq-shex.rdf +++ b/bh20sequploader/bh20seq-shex.rdf @@ -17,7 +17,7 @@ PREFIX wikidata: <http://www.wikidata.org/entity/> MainSchema:submitter @:submitterShape ; MainSchema:technology @:technologyShape ; MainSchema:virus @:virusShape; - MainSchema:license @:licenseShape; + MainSchema:license @:licenseShape ?; } :hostShape { @@ -71,7 +71,7 @@ PREFIX wikidata: <http://www.wikidata.org/entity/> } :licenseShape{ - cc:License xsd:string ?; + cc:License xsd:string ; dc:Title xsd:string ?; cc:attributionName xsd:string ?; cc:attributionURL xsd:string ?; diff --git a/bh20sequploader/main.py b/bh20sequploader/main.py index f744a8c..6049bf9 100644 --- a/bh20sequploader/main.py +++ b/bh20sequploader/main.py @@ -29,11 +29,10 @@ def qc_stuff(metadata, sequence_p1, sequence_p2, do_qc=True): try: log.debug("Checking metadata" if do_qc else "Skipping metadata check") if do_qc and not qc_metadata(metadata.name): - log.warning("Failed metadata qc") + log.warning("Failed metadata QC") failed = True except Exception as e: - log.debug(e) - print(e) + log.exception("Failed metadata QC") failed = True target = [] @@ -45,8 +44,7 @@ def qc_stuff(metadata, sequence_p1, sequence_p2, do_qc=True): target[0] = ("reads_1."+target[0][0][6:], target[0][1]) target[1] = ("reads_2."+target[1][0][6:], target[0][1]) except Exception as e: - log.debug(e) - print(e) + log.exception("Failed sequence QC") failed = True if failed: @@ -82,7 +80,7 @@ def main(): seqlabel = target[0][1] if args.validate: - print("Valid") + log.info("Valid") exit(0) col = arvados.collection.Collection(api_client=api) @@ -91,10 +89,10 @@ def main(): if args.sequence_p2: upload_sequence(col, target[1], args.sequence_p2) - print("Reading metadata") + log.info("Reading metadata") with col.open("metadata.yaml", "w") as f: r = args.metadata.read(65536) - print(r[0:20]) + log.info(r[0:20]) while r: f.write(r) r = args.metadata.read(65536) @@ -118,7 +116,7 @@ def main(): ["portable_data_hash", "=", col.portable_data_hash()]]).execute() if dup["items"]: # This exact collection has been uploaded before. - print("Duplicate of %s" % ([d["uuid"] for d in dup["items"]])) + log.error("Duplicate of %s" % ([d["uuid"] for d in dup["items"]])) exit(1) if args.trusted: @@ -131,9 +129,9 @@ def main(): (seqlabel, properties['upload_user'], properties['upload_ip']), properties=properties, ensure_unique_name=True) - print("Saved to %s" % col.manifest_locator()) - - print("Done") + log.info("Saved to %s" % col.manifest_locator()) + log.info("Done") + exit(0) if __name__ == "__main__": main() diff --git a/bh20sequploader/qc_fasta.py b/bh20sequploader/qc_fasta.py index 37eb4e8..0c7e16d 100644 --- a/bh20sequploader/qc_fasta.py +++ b/bh20sequploader/qc_fasta.py @@ -84,10 +84,8 @@ def qc_fasta(arg_sequence, check_with_clustalw=True): except Exception as e: logging.warn("QC against reference sequence using 'minimap2': %s", e, exc_info=e) - if similarity and similarity < 70.0: + if similarity < 70.0: raise ValueError("QC fail: alignment to reference was less than 70%% (was %2.2f%%)" % (similarity)) - if similarity == 0: - raise ValueError("QC fail") return ("sequence.fasta"+gz, seqlabel) elif seq_type == "text/fastq": diff --git a/bh20simplewebuploader/main.py b/bh20simplewebuploader/main.py index 77b3832..206f884 100644 --- a/bh20simplewebuploader/main.py +++ b/bh20simplewebuploader/main.py @@ -8,7 +8,7 @@ import os import sys import re import string -import yaml +import ruamel.yaml as yaml import pkg_resources from flask import Flask, request, redirect, send_file, send_from_directory, render_template, jsonify import os.path @@ -16,6 +16,9 @@ import requests import io import arvados from markupsafe import Markup +from schema_salad.sourceline import add_lc_filename +from schema_salad.schema import shortname +from typing import MutableSequence, MutableMapping ARVADOS_API = 'lugli.arvadosapi.com' ANONYMOUS_TOKEN = '5o42qdxpxp5cj15jqjf7vnxx5xduhm4ret703suuoa3ivfglfh' @@ -47,6 +50,8 @@ def type_to_heading(type_name): Turn a type name like "sampleSchema" from the metadata schema into a human-readable heading. """ + type_name = shortname(type_name) + print(type_name,file=sys.stderr) # Remove camel case decamel = re.sub('([A-Z])', r' \1', type_name) @@ -78,7 +83,7 @@ def is_iri(string): return string.startswith('http') -def generate_form(schema, options): +def generate_form(components, options): """ Linearize the schema into a list of dicts. @@ -101,9 +106,6 @@ def generate_form(schema, options): IRI. """ - # Get the list of form components, one of which is the root - components = schema.get('$graph', []) - # Find the root root_name = None # And also index components by type name @@ -131,55 +133,54 @@ def generate_form(schema, options): # First make a heading, if we aren't the very root of the form yield {'heading': type_to_heading(type_name)} - for field_name, field_type in by_name.get(type_name, {}).get('fields', {}).items(): + for field in by_name.get(type_name, {}).get('fields', []): + field_name = shortname(field["name"]) + field_type = field["type"] # For each field ref_iri = None docstring = None - if not isinstance(field_type, str): - # If the type isn't a string - - # It may have documentation - docstring = field_type.get('doc', None) - - # See if it has a more info/what goes here URL - predicate = field_type.get('jsonldPredicate', {}) - # Predicate may be a URL, a dict with a URL in _id, maybe a - # dict with a URL in _type, or a dict with _id and _type but no - # URLs anywhere. Some of these may not technically be allowed - # by the format, but if they occur, we might as well try to - # handle them. - if isinstance(predicate, str): - if is_iri(predicate): - ref_iri = predicate - else: - # Assume it's a dict. Look at the fields we know about. - for field in ['_id', 'type']: - field_value = predicate.get(field, None) - if isinstance(field_value, str) and is_iri(field_value) and ref_iri is None: - # Take the first URL-looking thing we find - ref_iri = field_value - break - - # Now overwrite the field type with the actual type string - field_type = field_type.get('type', '') - - # Decide if the field is optional (type ends in ?) optional = False - if field_type.endswith('?'): - # It's optional - optional = True - # Drop the ? - field_type = field_type[:-1] - - # Decide if the field is a list (type ends in []) is_list = False - if field_type.endswith('[]'): - # It's a list - is_list = True - # Reduce to the normal type - field_type = field_type[:-2] + + # It may have documentation + docstring = field.get('doc', None) + + # See if it has a more info/what goes here URL + predicate = field.get('jsonldPredicate', {}) + # Predicate may be a URL, a dict with a URL in _id, maybe a + # dict with a URL in _type, or a dict with _id and _type but no + # URLs anywhere. Some of these may not technically be allowed + # by the format, but if they occur, we might as well try to + # handle them. + if isinstance(predicate, str): + if is_iri(predicate): + ref_iri = predicate + else: + # Assume it's a dict. Look at the fields we know about. + for field in ['_id', 'type']: + field_value = predicate.get(field, None) + if isinstance(field_value, str) and is_iri(field_value) and ref_iri is None: + # Take the first URL-looking thing we find + ref_iri = field_value + break + + if isinstance(field_type, MutableSequence): + if field_type[0] == "null" and len(field_type) == 2: + optional = True + field_type = field_type[1] + else: + raise Exception("Can't handle it") + + if isinstance(field_type, MutableMapping): + if field_type["type"] == "array": + # Now replace the field type with the actual type string + is_list = True + field_type = field_type.get('items', '') + else: + field_type = field_type.get('type', '') + pass if field_type in by_name: # This is a subrecord. We need to recurse @@ -227,15 +228,24 @@ def generate_form(schema, options): return list(walk_fields(root_name)) -# At startup, we need to load the metadata schema from the uploader module, so we can make a form for it -if os.path.isfile("bh20sequploader/bh20seq-schema.yml"): - METADATA_SCHEMA = yaml.safe_load(open("bh20sequploader/bh20seq-schema.yml","r").read()) - METADATA_OPTION_DEFINITIONS = yaml.safe_load(open("bh20sequploader/bh20seq-options.yml","r").read()) -else: - METADATA_SCHEMA = yaml.safe_load(pkg_resources.resource_stream("bh20sequploader", "bh20seq-schema.yml")) - METADATA_OPTION_DEFINITIONS = yaml.safe_load(pkg_resources.resource_stream("bh20sequploader", "bh20seq-options.yml")) -# print(METADATA_SCHEMA,file=sys.stderr) -FORM_ITEMS = generate_form(METADATA_SCHEMA, METADATA_OPTION_DEFINITIONS) +import schema_salad.schema +def load_schema_generate_form(): + # At startup, we need to load the metadata schema from the uploader module, so we can make a form for it + if os.path.isfile("bh20sequploader/bh20seq-schema.yml"): + METADATA_SCHEMA = yaml.round_trip_load(open("bh20sequploader/bh20seq-schema.yml","r").read()) + METADATA_OPTION_DEFINITIONS = yaml.safe_load(open("bh20sequploader/bh20seq-options.yml","r").read()) + else: + METADATA_SCHEMA = yaml.round_trip_load(pkg_resources.resource_stream("bh20sequploader", "bh20seq-schema.yml")) + METADATA_OPTION_DEFINITIONS = yaml.safe_load(pkg_resources.resource_stream("bh20sequploader", "bh20seq-options.yml")) + + METADATA_SCHEMA["name"] = "bh20seq-schema.yml" + add_lc_filename(METADATA_SCHEMA, "bh20seq-schema.yml") + metaschema_names, _metaschema_doc, metaschema_loader = schema_salad.schema.get_metaschema() + schema_doc, schema_metadata = metaschema_loader.resolve_ref(METADATA_SCHEMA, "") + + return generate_form(schema_doc, METADATA_OPTION_DEFINITIONS) + +FORM_ITEMS = load_schema_generate_form() @app.route('/') def send_home(): @@ -243,7 +253,7 @@ def send_home(): Send the front page. """ - return render_template('home.html', menu='HOME') + return render_template('home.html', menu='HOME', load_map=True) @app.route('/upload') @@ -435,12 +445,12 @@ def receive_files(): if result.returncode != 0: # It didn't work. Complain. - error_message="Uploader returned value {} and said:".format(result.returncode) + str(result.stderr.decode('utf-8')) + error_message="Uploader returned value {} and said:\n".format(result.returncode) + str(result.stderr.decode('utf-8')) print(error_message, file=sys.stderr) return (render_template('error.html', error_message=error_message), 403) else: # It worked. Say so. - return render_template('success.html', log=result.stdout.decode('utf-8', errors='replace')) + return render_template('success.html', log=result.stderr.decode('utf-8', errors='replace')) finally: shutil.rmtree(dest_dir) @@ -479,10 +489,13 @@ def pending_table(output, items): for r in items: if r["status"] != "pending": continue - output.write("<tr>") - output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) - output.write("<td>%s</td>" % Markup.escape(r["sequence_label"])) - output.write("</tr>") + try: + output.write("<tr>") + output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) + output.write("<td>%s</td>" % Markup.escape(r.get("sequence_label"))) + output.write("</tr>") + except: + pass output.write( """ </table> @@ -497,18 +510,69 @@ def rejected_table(output, items): <th>Errors</th></tr> """) for r in items: - if r["status"] != "rejected": - continue + try: + if r["status"] != "rejected": + continue + output.write("<tr>") + output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) + output.write("<td>%s</td>" % Markup.escape(r.get("sequence_label"))) + output.write("<td><pre>%s</pre></td>" % Markup.escape("\n".join(r.get("errors", [])))) + output.write("</tr>") + except: + pass + output.write( +""" +</table> +""") + +def workflows_table(output, items): + output.write( +""" +<table> +<tr> +<th>Name</th> +<th>Sample id</th> +<th>Started</th> +<th>Container request</th> +</tr> +""") + for r in items: output.write("<tr>") - output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) - output.write("<td>%s</td>" % Markup.escape(r["sequence_label"])) - output.write("<td><pre>%s</pre></td>" % Markup.escape("\n".join(r.get("errors", [])))) + try: + sid = r["mounts"]["/var/lib/cwl/cwl.input.json"]["content"]["sample_id"] + output.write("<td>%s</td>" % Markup.escape(r["name"])) + output.write("<td>%s</td>" % Markup.escape(sid)) + output.write("<td>%s</td>" % Markup.escape(r["created_at"])) + output.write("<td><a href='https://workbench.lugli.arvadosapi.com/container_requests/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) + except: + pass output.write("</tr>") output.write( """ </table> """) +def validated_table(output, items): + output.write( +""" +<table> +<tr> +<th>Collection</th> +<th>Sequence label</th> +</tr> +""") + for r in items: + try: + output.write("<tr>") + output.write("<td><a href='https://workbench.lugli.arvadosapi.com/collections/%s'>%s</a></td>" % (r["uuid"], r["uuid"])) + output.write("<td>%s</td>" % Markup.escape(r["properties"].get("sequence_label"))) + output.write("</tr>") + except: + pass + output.write( +""" +</table> +""") @app.route('/status') def status_page(): @@ -529,25 +593,42 @@ def status_page(): prop["uuid"] = p["uuid"] status[prop["status"]] = status.get(prop["status"], 0) + 1 + workflows = arvados.util.list_all(api.container_requests().list, + filters=[["name", "in", ["fastq2fasta.cwl"]], ["state", "=", "Committed"]], + order="created_at asc") + output = io.StringIO() validated = api.collections().list(filters=[["owner_uuid", "=", VALIDATED_PROJECT]], limit=1).execute() status["passed"] = validated["items_available"] - for s in (("passed", "/download"), ("pending", "#pending"), ("rejected", "#rejected")): + for s in (("passed", "/validated"), ("pending", "#pending"), ("rejected", "#rejected")): output.write("<p><a href='%s'>%s sequences QC %s</a></p>" % (s[1], status.get(s[0], 0), s[0])) - output.write("<a id='pending'><h1>Pending</h1>") + output.write("<p><a href='%s'>%s analysis workflows running</a></p>" % ('#workflows', len(workflows))) + + output.write("<a id='pending'><h1>Pending</h1></a>") pending_table(output, out) - output.write("<a id='rejected'><h1>Rejected</h1>") + output.write("<a id='rejected'><h1>Rejected</h1></a>") rejected_table(output, out) + output.write("<a id='workflows'><h1>Running Workflows</h1></a>") + workflows_table(output, workflows) + return render_template('status.html', table=Markup(output.getvalue()), menu='STATUS') +@app.route('/validated') +def validated_page(): + api = arvados.api(host=ARVADOS_API, token=ANONYMOUS_TOKEN, insecure=True) + output = io.StringIO() + validated = arvados.util.list_all(api.collections().list, filters=[["owner_uuid", "=", VALIDATED_PROJECT]]) + validated_table(output, validated) + return render_template('validated.html', table=Markup(output.getvalue()), menu='STATUS') + @app.route('/demo') def demo_page(): - return render_template('demo.html',menu='DEMO') + return render_template('demo.html',menu='DEMO',load_map=True) @app.route('/blog',methods=['GET']) def blog_page(): @@ -563,12 +644,6 @@ def about_page(): buf = get_html_body('doc/web/about.html','https://github.com/arvados/bh20-seq-resource/blob/master/doc/web/about.org') return render_template('about.html',menu='ABOUT',embed=buf) -## -@app.route('/map') -def map_page(): - return render_template('map.html',menu='DEMO') - - ## Dynamic API functions starting here ## This is quick and dirty for now, just to get something out and demonstrate the queries diff --git a/bh20simplewebuploader/static/image/curii.logo.ai.png b/bh20simplewebuploader/static/image/curii.logo.ai.png new file mode 100644 index 0000000..401afad --- /dev/null +++ b/bh20simplewebuploader/static/image/curii.logo.ai.png Binary files differdiff --git a/bh20simplewebuploader/static/image/curii.logo.ai.svg b/bh20simplewebuploader/static/image/curii.logo.ai.svg new file mode 100644 index 0000000..e87ea05 --- /dev/null +++ b/bh20simplewebuploader/static/image/curii.logo.ai.svg @@ -0,0 +1,3 @@ +<?xml version="1.0" encoding="UTF-8"?> +<!-- Created with Inkscape (http://www.inkscape.org/) --> +<svg width="1333.3" height="1333.3" version="1.1" viewBox="0 0 1333.3 1333.3" xml:space="preserve" xmlns="http://www.w3.org/2000/svg" xmlns:cc="http://creativecommons.org/ns#" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#"><metadata><rdf:RDF><cc:Work rdf:about=""><dc:format>image/svg+xml</dc:format><dc:type rdf:resource="http://purl.org/dc/dcmitype/StillImage"/><dc:title/></cc:Work></rdf:RDF></metadata><defs><clipPath id="clipPath18"><path d="m0 1e3h1e3v-1e3h-1e3z"/></clipPath></defs><g transform="matrix(1.3333 0 0 -1.3333 0 1333.3)"><g clip-path="url(#clipPath18)"><g transform="translate(473.7 553.52)"><path d="m0 0c-23.91 0-41.063-17.932-41.063-44.182 0-26.251 17.153-44.179 41.063-44.179 17.414 0 31.448 5.714 40.805 16.63l16.63-16.63c-12.476-16.377-32.488-25.735-58.734-25.735-41.063 0-69.653 28.329-69.653 69.914 0 41.843 28.59 70.428 69.653 70.428 24.95 0 44.439-8.053 57.174-22.611l-16.37-19.229c-9.619 9.876-22.875 15.851-39.505 15.594" fill="#008a82"/></g><g transform="translate(681.34 578.73)"><path d="m0 0v-138.26h-29.889v27.029c-9.355-19.232-26.765-27.806-49.377-28.07-31.707 0-50.676 20.276-50.676 53.281v86.022h29.884v-77.707c0-20.792 12.216-33.526 32.228-33.526 23.911 0.523 37.941 18.972 37.941 43.143v68.09z" fill="#008a82"/></g><g transform="translate(796.73 579.77)"><path d="m0 0v-28.585c-27.809 1.556-45.481-14.815-47.818-38.468v-72.248h-29.887v138.26h29.887v-27.546c9.356 18.71 25.99 28.585 47.818 28.585" fill="#008a82"/></g><g transform="translate(847.15 618.24)"><path d="m0 0c0-10.136-7.54-17.673-17.412-17.673-9.877 0-17.413 7.537-17.413 17.673 0 10.396 7.536 17.933 17.413 17.933 9.872 0 17.412-7.537 17.412-17.933" fill="#f15a29"/></g><path d="m844.54 440.47h-29.625v138.26h29.625z" fill="#008a82"/><g transform="translate(914.46 618.24)"><path d="m0 0c0-10.136-7.541-17.673-17.413-17.673-9.876 0-17.413 7.537-17.413 17.673 0 10.396 7.537 17.933 17.413 17.933 9.872 0 17.413-7.537 17.413-17.933" fill="#f15a29"/></g><path d="m911.85 440.47h-29.625v138.26h29.625z" fill="#008a82"/><g transform="translate(131.67 492.85)"><path d="m0 0c0.628 4.633 3.756 8.256 7.824 9.843l-9.454 65.551c-0.213 0.021-0.426-0.01-0.638 0.021-2.008 0.27-3.807 1.046-5.367 2.126l-57.718-52.611c2.31-21.875 9.31-42.198 19.929-60.052l46.065 29.321c-0.641 1.805-0.924 3.766-0.641 5.801" fill="#f15a29"/></g><g transform="translate(135.54 569.04)"><path d="m0 0 9.451-65.545c0.223-0.018 0.432 0.01 0.648-0.02 0.975-0.131 1.887-0.395 2.767-0.737l38.262 56.827-44.955 14.619c-1.414-2.373-3.608-4.149-6.173-5.144" fill="#f15a29"/></g><g transform="translate(280.25 609.22)"><path d="m0 0-48.729-0.574c-1.211-5.586-6.039-9.562-11.655-9.744l-24.468-36.342 53.617-17.44c0 0.809-0.074 1.62-0.051 2.43 0.912 25.152 12.634 47.22 31.286 61.67" fill="#f15a29"/></g><g transform="translate(217.14 623.42)"><path d="m0 0 2.255 58.382c-4.958 0.183-9.984 0.112-15.047-0.205-15.084-0.972-29.49-4.186-42.934-9.259l51.399-50.633c1.31 0.834 2.768 1.411 4.327 1.715" fill="#f15a29"/></g><g transform="translate(132.75 592.86)"><path d="m0 0c6.582-0.901 11.22-6.828 10.639-13.386l46.505-15.128 24.123 35.815c-4.675 2.295-7.615 7.341-6.872 12.785 0.239 1.772 0.867 3.403 1.748 4.824l-53.093 52.29c-12.31-5.236-23.718-12.06-34.013-20.225l9.958-56.937c0.33-0.028 0.661 6e-3 1.005-0.038" fill="#f15a29"/></g><g transform="translate(135.28 482.35)"><path d="m0 0-46.12-29.351c14.73-22.781 35.474-41.144 59.841-53.023l-6.781 78.911c-2.738 0.383-5.104 1.664-6.94 3.463" fill="#008a82"/></g><g transform="translate(118.77 582.23)"><path d="m0 0c0.611 4.509 3.588 8.073 7.483 9.721l-9.4 53.816c-33.716-29.174-53.94-73.126-51.126-121.01l54.559 49.732c-1.283 2.272-1.897 4.952-1.516 7.74" fill="#f15a29"/></g><g transform="translate(361.67 546.89)"><path d="m0 0c-7.048-4.637-14.905-8.13-23.401-10.048-23.806-5.372-49.043-2.852-73.21-5.508 3.301-19.489 10.484-39.441 11.517-59.119 1.522-29.071-4.033-57.766-26.257-78.143-2.545-2.344-5.248-4.393-8.036-6.28 72.262 13.991 124.59 79.812 119.73 155.21-0.078 1.306-0.227 2.592-0.345 3.888" fill="#008a82"/></g><g transform="translate(250.67 529.01)"><path d="m0 0c-8.863-1.971-17.477-5.104-25.76-9.947 7.733-9.046 15.469-18.091 23.188-27.143 4.901-5.729-4.405-12.76-9.275-7.059-7.844 9.184-15.692 18.355-23.533 27.543-3.244-2.674-6.116-5.496-8.563-8.494 13.566-16.281 27.111-32.576 40.666-48.876 4.826-5.793-4.486-12.83-9.286-7.061-12.67 15.225-25.348 30.468-38.019 45.701-2.14-4.209-3.767-8.604-4.84-13.168 8.495-9.946 16.998-19.892 25.493-29.843 4.898-5.729-4.411-12.758-9.281-7.061-6.019 7.032-12.026 14.071-18.048 21.114 0 0-4.766-16.237-0.865-52.291-1.66 0.746-3.085 2.109-3.847 4.189-9.88 27.309-16.654 62.017 0.85 88.074 12.678 18.854 32.288 30.459 53.735 36.456l-51.115 16.627-39.174-58.167c2.461-2.63 3.791-6.261 3.274-10.104-0.661-4.881-4.104-8.68-8.509-10.1l7.041-82.087c11.054-4.806 22.783-8.293 34.971-10.297 31.35 2.055 62.177 14.151 70.26 48.559 4.169 17.775 3.976 36.163 0.456 54.069-2.558 13.035-7.277 26.098-9.819 39.366" fill="#008a82"/></g><g transform="translate(312.28 562.6)"><path d="m0 0c-9.515 0-17.227 7.709-17.227 17.228 0 9.514 7.712 17.227 17.227 17.227 9.519 0 17.228-7.713 17.228-17.227 0-9.519-7.709-17.228-17.228-17.228m-87.342 118.87-2.248-58.267c4.425-1.198 7.753-4.685 8.799-9.009l56.965 0.679c7.689 4.574 16.285 7.993 25.578 9.991 2.66 0.576 4.931-0.281 6.548-1.786l-2.677 1.573c-28.575-13.342-42.238-34.715-48.462-48.807-2.258-4.6-3.79-9.265-4.739-13.983-0.01-0.048-0.03-0.179-0.03-0.179-1.08-5.452-1.428-10.967-1.175-16.536 30.725 3.518 70.847-3.875 96.101 16.526-12.633 65.686-68.086 114.92-134.66 119.8" fill="#f15a29"/></g></g></g></svg> \ No newline at end of file diff --git a/bh20simplewebuploader/static/main.css b/bh20simplewebuploader/static/main.css index 47fb408..6e651a4 100644 --- a/bh20simplewebuploader/static/main.css +++ b/bh20simplewebuploader/static/main.css @@ -47,7 +47,7 @@ h2 > svg { float: right; } -#map { +#mapid { width: 800px; height: 440px; border: 1px solid #AAA; @@ -178,7 +178,7 @@ span.dropt:hover {text-decoration: none; background: #ffffff; z-index: 6; } .about { display: grid; - grid-template-columns: repeat(2, 1fr); + grid-template-columns: 1fr 1fr; grid-auto-flow: row; } @@ -229,7 +229,7 @@ a { #metadata_fill_form { column-count: 4; margin-top: 0.5em; - column-width: 250px; + column-width: 15em; } .record, .record .field-group, .record .field-group .field { @@ -238,6 +238,8 @@ a { -webkit-column-break-inside: avoid; /* Chrome, Safari, Opera */ page-break-inside: avoid; /* Firefox */ break-inside: avoid; + display: block; + width: 90%; } .record { @@ -258,6 +260,10 @@ a { width: max-content; } +.control { + width: 100%; +} + .filter-options { width: 100%; } @@ -304,9 +310,10 @@ footer { } .sponsors img { - width: 80%; - display:block; - margin:auto; + width: auto; + display: block; + margin: auto; + height: 4em; } .loader { @@ -378,6 +385,11 @@ div.status { border-bottom: 1px solid #ddd; } +.map { + padding: 20px 32px; + // display: inline-block; +} + .editbutton { float: right; text-align: right; diff --git a/bh20simplewebuploader/static/main.js b/bh20simplewebuploader/static/main.js index 4703047..1633c25 100644 --- a/bh20simplewebuploader/static/main.js +++ b/bh20simplewebuploader/static/main.js @@ -13,70 +13,41 @@ function myFunction() { } } -let map = L.map( 'map', { - center: [37.0902, -95.7129], // Default to U.S.A - minZoom: 3, - zoom: 0 -}); -L.tileLayer( 'http://{s}.tile.openstreetmap.org/{z}/{x}/{y}.png', { - attribution: '© <a href="https://www.openstreetmap.org/copyright">OpenStreetMap</a>', - subdomains: ['a','b','c'] -}).addTo( map ); - -let markers = L.markerClusterGroup().addTo(map) - - function fetchAPI(apiEndPoint) { - fetch(scriptRoot + apiEndPoint) - .then(response => { - return response.json(); - }) - .then(data => { - console.log(data); - markers.clearLayers(); - document.getElementById("results").classList.remove("invisible"); - document.getElementById("loader").classList.add("invisible"); - if (!(apiEndPoint === "/api/getAllaccessions")) { - for (let i = 0; i < data.length; i++) { - let {"count": fastaCount, GPS, LocationLabel: label } = data[i]; - let coordinates = GPS.split(" "); - if (!(coordinates == null)) { - let lat, lon; - [lon, lat] = coordinates.map(parseFloat); - let point = L.point() - let marker = L.marker([lat, lon]); - marker.bindPopup("<b>" + label + "</b><br/>" + "FastaCount: " +fastaCount); - markers.addLayer(marker) - }} - } - // Reload the map - map.invalidateSize(); - }); - document.getElementById("results").classList.add("invisible"); - document.getElementById("loader").classList.remove("invisible"); - -} - -// Copy from function above but now added as table instead of plain json -function fetchAPIV2(apiEndPoint) { - fetch(scriptRoot + apiEndPoint) - .then(response => { - return response.json(); - }) - .then(data => { - console.log(data) - htmlString="<table>" - - // Depending on what we want to explore we'd have to call a different function ....? But how to Include that? - for (var i=0; i<data.length;i++) { - htmlString=htmlString+"<tr><td><a href='#' onclick='fetchSEQByLocation(\""+data[i]["key"]+"\");'>"+data[i]["label"]+"</a></td><td>"+data[i]["count"]+"<td></tr>" - } - htmlString=htmlString+"</table>" - - document.getElementById("table").innerHTML = htmlString - }); - - document.getElementById("results").classList.add("invisible"); + fetch(scriptRoot + apiEndPoint) + .then(response => { + return response.json(); + }) + .then(data => { + console.log(data); + }); + document.getElementById("map_view").classList.add("invisible"); + document.getElementById("loader").classList.remove("invisible"); +} + +// Copy from function above but now output HTML table instead of plain json +function fetchHTMLTable(apiEndPoint) { + fetch(scriptRoot + apiEndPoint) + .then(response => { + return response.json(); + }) + .then(data => { + console.log(data) + htmlString="<table>" + + // Depending on what we want to explore we'd have to call a different function ....? But how to Include that? + /* + for (var i=0; i<data.length;i++) { + htmlString=htmlString+"<tr><td><a href='#' onclick='fetchSEQByLocation(\""+data[i]["key"]+"\");'>"+data[i]["label"]+"</a></td><td>"+data[i]["count"]+"<td></tr>" + } +*/ + for (var i=0; i<data.length;i++) { + htmlString=htmlString+"<tr><td>"+data[i]["label"]+"</td><td>"+data[i]["count"]+"<td></tr>" + } + htmlString=htmlString+"</table>" + + document.getElementById("table").innerHTML = htmlString + }); } @@ -85,36 +56,39 @@ let search = () => { fetchAPI(scriptRoot + "/api/getDetailsForSeq?seq=" + encodeURIComponent(m)); } +// Get count from Arvados let fetchCount = () => { fetchAPI("/api/getCount"); } +// Get count from Virtuoso let fetchCountDB = () => { fetchAPI("/api/getCountDB"); } let fetchSEQCountBySpecimen = () => { - fetchAPIV2("/api/getSEQCountbySpecimenSource"); + fetchHTMLTable("/api/getSEQCountbySpecimenSource"); } let fetchSEQCountByLocation = () => { - fetchAPIV2("/api/getSEQCountbyLocation"); + fetchHTMLTable("/api/getSEQCountbyLocation"); } let fetchSEQCountByTech = () => { - fetchAPIV2("/api/getSEQCountbytech"); + fetchHTMLTable("/api/getSEQCountbytech"); } let fetchAllaccessions = () => { - fetchAPI("/api/getAllaccessions"); + fetchHTMLTable("/api/getAllaccessions"); }; -let fetchCountByGPS = () => { - fetchAPI("/api/getCountByGPS"); +let fetchMap = () => { + fetchAPI("/api/getCountByGPS"); + updateMapMarkers(); }; let fetchSEQCountbyLocation = () => { - fetchAPIV2("/api/getSEQCountbyLocation"); + fetchHTMLTable("/api/getSEQCountbyLocation"); }; let fetchSEQByLocation = () => { @@ -122,7 +96,7 @@ let fetchSEQByLocation = () => { }; let fetchSEQCountbyContinent = () => { - fetchAPIV2("/api/getSEQCountbyContinent"); + fetchHTMLTable("/api/getSEQCountbyContinent"); } @@ -252,36 +226,3 @@ function on_submit_button() { return false; } } - - - -// - -function drawMap(){ - -// initialize the map on the "map" div with a given center and zoom -var mymap = L.map('mapid').setView([51.505, -0.09], 1); - -L.tileLayer('https://{s}.tile.openstreetmap.org/{z}/{x}/{y}.png', { - attribution: '© <a href="https://www.openstreetmap.org/copyright">OpenStreetMap</a> contributors' -}).addTo(mymap); - -fetch(scriptRoot + "api/getCountByGPS") - .then(response => { - console.log(response) - return response.json(); - }) - .then(data => { - - for (var i=0; i<data.length;i++) { - gps=data[i]["GPS"].split(" ") - var circle = L.circle([gps[1], gps[0]], { - color: 'red', - fillColor: '#f03', - fillOpacity: 0.5, - radius: parseInt(data[i]["count"]) //not working for whatever reason - }).addTo(mymap); - } - - }); -} diff --git a/bh20simplewebuploader/static/map.js b/bh20simplewebuploader/static/map.js new file mode 100644 index 0000000..1003f7d --- /dev/null +++ b/bh20simplewebuploader/static/map.js @@ -0,0 +1,50 @@ + +var map = L.map( 'mapid', { + center: [51.505, -0.09], // Default to U.S.A + minZoom: 2, + zoom: 0 +}); + +L.tileLayer( 'http://{s}.tile.openstreetmap.org/{z}/{x}/{y}.png', { + attribution: '© <a href="https://www.openstreetmap.org/copyright">OpenStreetMap</a> | <a href="http://covid19.genenetwork.org/">COVID-19 PubSeq</a>', + subdomains: ['a','b','c'] +}).addTo(map); + + +function drawMap(){ + var mymap = map; + + fetch(scriptRoot + "api/getCountByGPS") + .then(response => { + console.log(response) + return response.json(); + }) + .then(data => { + updateMapMarkers(data); + + }); + document.getElementById("map_view").classList.remove("invisible"); + map.invalidateSize(); +} + + + +/* This function updates the map with markers + * +*/ +function updateMapMarkers(data) { + let markers = L.markerClusterGroup(); + for (let i = 0; i < data.length; i++) { + let {"count": fastaCount, GPS, LocationLabel: label } = data[i]; + let coordinates = GPS.split(" "); + if (!(coordinates == null)) { + let lat, lon; + [lon, lat] = coordinates.map(parseFloat); + let point = L.point() + marker = (L.marker([lat, lon])); + marker.bindPopup("<b>" + label + "</b><br/>" + "SARS-CoV-2<br/>sequences: " +fastaCount); + markers.addLayer(marker); + } + } + map.addLayer(markers); +} diff --git a/bh20simplewebuploader/templates/blog.html b/bh20simplewebuploader/templates/blog.html index 823f8a1..f4c2a85 100644 --- a/bh20simplewebuploader/templates/blog.html +++ b/bh20simplewebuploader/templates/blog.html @@ -63,6 +63,14 @@ We explore the Arvados command line and API </div> </div> + <div class="blog-table-row"> + <div class="blog-table-cell"> + <a href="/blog?id=using-covid-19-pubseq-part6">Prepare for uploading to EBI/ENA</a> + </div> + <div class="blog-table-cell"> + Generate the files needed for uploading to EBI/ENA + </div> + </div> </div> </div> </section> diff --git a/bh20simplewebuploader/templates/demo-run.html b/bh20simplewebuploader/templates/demo-run.html deleted file mode 100644 index a8f9edc..0000000 --- a/bh20simplewebuploader/templates/demo-run.html +++ /dev/null @@ -1,26 +0,0 @@ -<section class="search-section"> - <div class="filter-options" action="#"> - <p>[Demo] Display content sequences by: </p> - <div> - <button class="button" onclick="fetchSEQCountBySpecimen()">Count by Specimen source</button> - <button class="button" onclick="fetchSEQCountByLocation()">Count by Location</button> - <button class="button" onclick="fetchSEQCountByTech()">Count by Sequencer</button> - <button class="button" onclick="fetchAllaccessions()">Show All accessions</button> - <button class="button" onclick="fetchSEQCountbyContinent()">Count by Continent</button> - <button class="button" onclick="fetchCountByGPS()">Map</button> - - </div> - - </div> - -</section> -<div id="loader" class="loader invisible"> -</div> - -<section id="results" class="invisible"> - <div id="map"></div> -</section> - - <section> - <div id="table"></div> - </section> diff --git a/bh20simplewebuploader/templates/demo.html b/bh20simplewebuploader/templates/demo.html index 44aded0..75bc0e2 100644 --- a/bh20simplewebuploader/templates/demo.html +++ b/bh20simplewebuploader/templates/demo.html @@ -1,13 +1,51 @@ <!DOCTYPE html> <html> {% include 'header.html' %} + {% include 'mapheader.html' %} <body> {% include 'banner.html' %} {% include 'menu.html' %} - {% include 'search.html' %} - <p>The Virtuoso database contains <span id="CounterDB"></span> public sequences!</p> - {% include 'demo-run.html' %} - {% include 'footer.html' %} + + <p>The Virtuoso database contains <span id="CounterDB"></span> public sequences!</p> + + <!-- + <div class="search"> + <input id="search-input" type="search" placeholder="FASTA uri" required> + <button class="button search-button" type="submit" onclick="search()"> + <span class="icon ion-search"> + <span class="sr-only">Search</span> + </span> + </button> + <span class="dropt" title="http://collections.lugli.arvadosapi.com/c=00fede2c6f52b053a14edca01cfa02b7+126/sequence.fasta">(example)<span style="width:500px;"></span></span> + </div> + --> + + <section class="search-section"> + <div class="filter-options" action="#"> + <p>[Demo] Display content sequences by: </p> + <div> + <button class="button" onclick="fetchSEQCountBySpecimen()">Count by Specimen source</button> + <button class="button" onclick="fetchSEQCountByLocation()">Count by Location</button> + <button class="button" onclick="fetchSEQCountByTech()">Count by Sequencer</button> + <!-- <button class="button" onclick="fetchAllaccessions()">Show All accessions</button> --> + <button class="button" onclick="fetchSEQCountbyContinent()">Count by Continent</button> + </div> + + </div> + + </section> + <div id="loader" class="loader invisible"> + </div> + + <section id="map_view" class="map"> + <div id="mapid"></div> + </section> + + <section> + <div id="table"></div> + </section> + + {% include 'footer.html' %} <script type="text/javascript"> let scriptRoot = {{ request.script_root|tojson|safe }}; // examples @@ -24,7 +62,10 @@ }); }); + drawMap() + </script> + </body> </html> diff --git a/bh20simplewebuploader/templates/error.html b/bh20simplewebuploader/templates/error.html index b1d9402..fc08aed 100644 --- a/bh20simplewebuploader/templates/error.html +++ b/bh20simplewebuploader/templates/error.html @@ -15,7 +15,7 @@ </pre> </p> <p> - <a href="/">Click here to try again.</a> + <a href="/upload">Click here to try again.</a> </p> <hr> </body> diff --git a/bh20simplewebuploader/templates/footer.html b/bh20simplewebuploader/templates/footer.html index 37a6b64..f84cef5 100644 --- a/bh20simplewebuploader/templates/footer.html +++ b/bh20simplewebuploader/templates/footer.html @@ -21,12 +21,15 @@ <img src="static/image/covid19biohackathon.png"></a> </div> <div class="sponsorimg"> - <a href="https://www.commonwl.org/"><img src="static/image/CWL.png"></a> + <a href="https://www.curii.com/"><img src="static/image/curii.logo.ai.png"></a> </div> <div class="sponsorimg"> <a href="https://arvados.org/"><img src="static/image/arvados-logo.png"></a> </div> <div class="sponsorimg"> + <a href="https://www.commonwl.org/"><img src="static/image/CWL.png"></a> + </div> + <div class="sponsorimg"> <a href="https://uthsc.edu/"><img src="static/image/UTHSC-primary-stacked-logo-4c.png"></a> </div> <div class="sponsorimg"> @@ -44,6 +47,9 @@ </center> </div> </section> +{% if load_map %} +<script type="text/javascript" src="/static/map.js"></script> +{% endif %} <script type="text/javascript" src="/static/main.js"></script> <script type="text/javascript"> diff --git a/bh20simplewebuploader/templates/header.html b/bh20simplewebuploader/templates/header.html index 0ac5157..1d66590 100644 --- a/bh20simplewebuploader/templates/header.html +++ b/bh20simplewebuploader/templates/header.html @@ -6,22 +6,4 @@ {% if blog %} <link rel="Blog stylesheet" type="text/css" href="/static/blog.css" /> {% endif %} - <link rel="stylesheet" href="https://unpkg.com/leaflet@1.6.0/dist/leaflet.css" - integrity="sha512-xwE/Az9zrjBIphAcBb3F6JVqxf46+CDLwfLMHloNu6KEQCAWi6HcDUbeOfBIptF7tcCzusKFjFw2yuvEpDL9wQ==" - crossorigin=""/> - <link rel="stylesheet" href="https://unpkg.com/leaflet.markercluster@1.4.1/dist/MarkerCluster.css" - integrity="sha512-RLEjtaFGdC4iQMJDbMzim/dOvAu+8Qp9sw7QE4wIMYcg2goVoivzwgSZq9CsIxp4xKAZPKh5J2f2lOko2Ze6FQ==" - crossorigin=""/> - - <link rel="stylesheet" href="https://unpkg.com/leaflet.markercluster@1.4.1/dist/MarkerCluster.Default.css" - integrity="sha512-BBToHPBStgMiw0lD4AtkRIZmdndhB6aQbXpX7omcrXeG2PauGBl2lzq2xUZTxaLxYz5IDHlmneCZ1IJ+P3kYtQ==" - crossorigin=""/> - - <script src="https://unpkg.com/leaflet@1.6.0/dist/leaflet.js" - integrity="sha512-gZwIG9x3wUXg2hdXF6+rVkLF/0Vi9U8D2Ntg4Ga5I5BZpVkVxlJWbSQtXPSiUTtC0TjtGOmxa1AJPuV0CPthew==" - crossorigin=""></script> - - <script src="https://unpkg.com/leaflet.markercluster@1.4.1/dist/leaflet.markercluster.js" - integrity="sha512-MQlyPV+ol2lp4KodaU/Xmrn+txc1TP15pOBF/2Sfre7MRsA/pB4Vy58bEqe9u7a7DczMLtU5wT8n7OblJepKbg==" - crossorigin=""></script> </head> diff --git a/bh20simplewebuploader/templates/home.html b/bh20simplewebuploader/templates/home.html index b90a18d..bede611 100644 --- a/bh20simplewebuploader/templates/home.html +++ b/bh20simplewebuploader/templates/home.html @@ -1,6 +1,7 @@ <!DOCTYPE html> <html> {% include 'header.html' %} + {% include 'mapheader.html' %} <body> {% include 'banner.html' %} {% include 'menu.html' %} @@ -44,7 +45,19 @@ </div> </section> -{% include 'footer.html' %} + <section id="map_view" class="map"> + <div id="mapid"></div> + </section> + + {% include 'footer.html' %} + + + <script type="text/javascript"> + let scriptRoot = {{ request.script_root|tojson|safe }}; // examples + + drawMap() + + </script> </body> </html> diff --git a/bh20simplewebuploader/templates/map.html b/bh20simplewebuploader/templates/map.html deleted file mode 100644 index 595af0c..0000000 --- a/bh20simplewebuploader/templates/map.html +++ /dev/null @@ -1,33 +0,0 @@ -<!DOCTYPE html> -<html> - {% include 'header.html' %} -<link rel="stylesheet" href="https://unpkg.com/leaflet@1.6.0/dist/leaflet.css" - integrity="sha512-xwE/Az9zrjBIphAcBb3F6JVqxf46+CDLwfLMHloNu6KEQCAWi6HcDUbeOfBIptF7tcCzusKFjFw2yuvEpDL9wQ==" - crossorigin=""/> - - {% include 'banner.html' %} - {% include 'menu.html' %} - <div id="mapid" style="height: 500px;"></div> - - {% include 'footer.html' %} - - - - - <script type="text/javascript"> - let scriptRoot = {{ request.script_root|tojson|safe }}; // examples - </script> - -<!-- Make sure you put this AFTER Leaflet's CSS --> - <script src="https://unpkg.com/leaflet@1.6.0/dist/leaflet.js" - integrity="sha512-gZwIG9x3wUXg2hdXF6+rVkLF/0Vi9U8D2Ntg4Ga5I5BZpVkVxlJWbSQtXPSiUTtC0TjtGOmxa1AJPuV0CPthew==" - crossorigin=""></script> - - <script> - //drawMap - drawMap() - </script> - - </body> - -</html> diff --git a/bh20simplewebuploader/templates/mapheader.html b/bh20simplewebuploader/templates/mapheader.html new file mode 100644 index 0000000..ca62051 --- /dev/null +++ b/bh20simplewebuploader/templates/mapheader.html @@ -0,0 +1,16 @@ + <link rel="stylesheet" href="https://unpkg.com/leaflet@1.6.0/dist/leaflet.css" + integrity="sha512-xwE/Az9zrjBIphAcBb3F6JVqxf46+CDLwfLMHloNu6KEQCAWi6HcDUbeOfBIptF7tcCzusKFjFw2yuvEpDL9wQ==" + crossorigin=""/> + <link rel="stylesheet" href="https://unpkg.com/leaflet.markercluster@1.4.1/dist/MarkerCluster.css" + integrity="sha512-RLEjtaFGdC4iQMJDbMzim/dOvAu+8Qp9sw7QE4wIMYcg2goVoivzwgSZq9CsIxp4xKAZPKh5J2f2lOko2Ze6FQ==" + crossorigin=""/> + <link rel="stylesheet" href="https://unpkg.com/leaflet.markercluster@1.4.1/dist/MarkerCluster.Default.css" + integrity="sha512-BBToHPBStgMiw0lD4AtkRIZmdndhB6aQbXpX7omcrXeG2PauGBl2lzq2xUZTxaLxYz5IDHlmneCZ1IJ+P3kYtQ==" + crossorigin=""/> + + <script src="https://unpkg.com/leaflet@1.6.0/dist/leaflet.js" + integrity="sha512-gZwIG9x3wUXg2hdXF6+rVkLF/0Vi9U8D2Ntg4Ga5I5BZpVkVxlJWbSQtXPSiUTtC0TjtGOmxa1AJPuV0CPthew==" + crossorigin=""></script> + <script src="https://unpkg.com/leaflet.markercluster@1.4.1/dist/leaflet.markercluster.js" + integrity="sha512-MQlyPV+ol2lp4KodaU/Xmrn+txc1TP15pOBF/2Sfre7MRsA/pB4Vy58bEqe9u7a7DczMLtU5wT8n7OblJepKbg==" + crossorigin=""></script> diff --git a/bh20simplewebuploader/templates/search.html b/bh20simplewebuploader/templates/search.html index dbdca90..e69de29 100644 --- a/bh20simplewebuploader/templates/search.html +++ b/bh20simplewebuploader/templates/search.html @@ -1,10 +0,0 @@ -<div class="search"> - <input id="search-input" type="search" placeholder="FASTA uri" required> - <button class="button search-button" type="submit" onclick="search()"> - <span class="icon ion-search"> - <span class="sr-only">Search</span> - </span> - </button> - <span class="dropt" title="http://collections.lugli.arvadosapi.com/c=00fede2c6f52b053a14edca01cfa02b7+126/sequence.fasta">(example)<span style="width:500px;"></span></span> -</div> - diff --git a/bh20simplewebuploader/templates/status.html b/bh20simplewebuploader/templates/status.html index a1cf28f..e89437e 100644 --- a/bh20simplewebuploader/templates/status.html +++ b/bh20simplewebuploader/templates/status.html @@ -7,7 +7,8 @@ <h1>Sequence upload processing status</h1> - <div class="status"> + <div class="status"> + {{ table }} </div> diff --git a/bh20simplewebuploader/templates/success.html b/bh20simplewebuploader/templates/success.html index 9f0987c..c2302fa 100644 --- a/bh20simplewebuploader/templates/success.html +++ b/bh20simplewebuploader/templates/success.html @@ -9,7 +9,7 @@ <h1>Upload Successful</h1> <hr> <p> - Your files have been uploaded. They should soon appear as output of the <a href="/download">Public SARS-CoV-2 Sequence Resource</a>. + Your files have been uploaded. You can track their <a href="/status">QC status</a>, once validated they will be part of the <a href="/download">Public SARS-CoV-2 Sequence Resource</a>. </p> <p> The upload log was: diff --git a/bh20simplewebuploader/templates/validated.html b/bh20simplewebuploader/templates/validated.html new file mode 100644 index 0000000..cee94bd --- /dev/null +++ b/bh20simplewebuploader/templates/validated.html @@ -0,0 +1,17 @@ +<!DOCTYPE html> +<html> + {% include 'header.html' %} + <body> + {% include 'banner.html' %} + {% include 'menu.html' %} + + <h1>Validated sequences</h1> + + <div class="status"> + {{ table }} + </div> + +{% include 'footer.html' %} + + </body> +</html> diff --git a/doc/blog/using-covid-19-pubseq-part1.html b/doc/blog/using-covid-19-pubseq-part1.html index 1959fac..0e6136c 100644 --- a/doc/blog/using-covid-19-pubseq-part1.html +++ b/doc/blog/using-covid-19-pubseq-part1.html @@ -3,7 +3,7 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"> <head> -<!-- 2020-05-29 Fri 12:06 --> +<!-- 2020-07-17 Fri 05:05 --> <meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <title>COVID-19 PubSeq (part 1)</title> @@ -248,20 +248,20 @@ for the JavaScript code in this tag. <h2>Table of Contents</h2> <div id="text-table-of-contents"> <ul> -<li><a href="#org9afe6ab">1. What does this mean?</a></li> -<li><a href="#orgf4bc3d4">2. Fetch sequence data</a></li> -<li><a href="#org9d7d482">3. Predicates</a></li> -<li><a href="#orgc6046bb">4. Fetch submitter info and other metadata</a></li> -<li><a href="#orgdcb216b">5. Fetch all sequences from Washington state</a></li> -<li><a href="#org7060f51">6. Discussion</a></li> -<li><a href="#orgdc51ccc">7. Acknowledgements</a></li> +<li><a href="#org0db5db0">1. What does this mean?</a></li> +<li><a href="#orge5267fd">2. Fetch sequence data</a></li> +<li><a href="#orgfbd3adc">3. Predicates</a></li> +<li><a href="#org08e70e1">4. Fetch submitter info and other metadata</a></li> +<li><a href="#org9194557">5. Fetch all sequences from Washington state</a></li> +<li><a href="#org76317ad">6. Discussion</a></li> +<li><a href="#orgeb871a1">7. Acknowledgements</a></li> </ul> </div> </div> -<div id="outline-container-org9afe6ab" class="outline-2"> -<h2 id="org9afe6ab"><span class="section-number-2">1</span> What does this mean?</h2> +<div id="outline-container-org0db5db0" class="outline-2"> +<h2 id="org0db5db0"><span class="section-number-2">1</span> What does this mean?</h2> <div class="outline-text-2" id="text-1"> <p> This means that when someone uploads a SARS-CoV-2 sequence using one @@ -274,24 +274,24 @@ expressed in a <a href="https://github.com/arvados/bh20-seq-resource/blob/master type: record fields: host_species: - doc: Host species as defined in NCBITaxon, e.g. http://purl.obolibrary.org/obo/NCBITaxon_<span style="color: #8bc34a;">9606</span> for Homo sapiens + doc: Host species as defined in NCBITaxon, e.g. http://purl.obolibrary.org/obo/NCBITaxon_9606 for Homo sapiens type: string jsonldPredicate: - _id: http://www.ebi.ac.uk/efo/EFO_<span style="color: #8bc34a;">0000532</span> - _type: <span style="color: #9ccc65;">"@id"</span> - noLinkCheck: <span style="color: #8bc34a;">true</span> + _id: http://www.ebi.ac.uk/efo/EFO_0000532 + _type: "@id" + noLinkCheck: true host_sex: - doc: Sex of the host as defined in PATO, expect male <span style="color: #e91e63;">()</span> or female <span style="color: #e91e63;">()</span> + doc: Sex of the host as defined in PATO, expect male () or female () type: string? jsonldPredicate: - _id: http://purl.obolibrary.org/obo/PATO_<span style="color: #8bc34a;">0000047</span> - _type: <span style="color: #9ccc65;">"@id"</span> - noLinkCheck: <span style="color: #8bc34a;">true</span> + _id: http://purl.obolibrary.org/obo/PATO_0000047 + _type: "@id" + noLinkCheck: true host_age: - doc: Age of the host as number <span style="color: #e91e63;">(</span>e.g. <span style="color: #8bc34a;">50</span><span style="color: #e91e63;">)</span> + doc: Age of the host as number (e.g. 50) type: int? jsonldPredicate: - _id: http://purl.obolibrary.org/obo/PATO_<span style="color: #8bc34a;">0000011</span> + _id: http://purl.obolibrary.org/obo/PATO_0000011 </pre> </div> @@ -314,8 +314,8 @@ initiative! </div> -<div id="outline-container-orgf4bc3d4" class="outline-2"> -<h2 id="orgf4bc3d4"><span class="section-number-2">2</span> Fetch sequence data</h2> +<div id="outline-container-orge5267fd" class="outline-2"> +<h2 id="orge5267fd"><span class="section-number-2">2</span> Fetch sequence data</h2> <div class="outline-text-2" id="text-2"> <p> The latest run of the pipeline can be viewed <a href="https://workbench.lugli.arvadosapi.com/collections/lugli-4zz18-z513nlpqm03hpca">here</a>. Each of these @@ -339,8 +339,8 @@ these identifiers throughout. </div> </div> -<div id="outline-container-org9d7d482" class="outline-2"> -<h2 id="org9d7d482"><span class="section-number-2">3</span> Predicates</h2> +<div id="outline-container-orgfbd3adc" class="outline-2"> +<h2 id="orgfbd3adc"><span class="section-number-2">3</span> Predicates</h2> <div class="outline-text-2" id="text-3"> <p> To explore an RDF dataset, the first query we can do is open and gets @@ -350,10 +350,10 @@ the following in a SPARQL end point </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?p -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">select distinct ?p +{ ?o ?p ?s -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -364,10 +364,10 @@ To get a <a href="http://sparql.genenetwork.org/sparql/?default-graph-uri=&q </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?g -<span style="color: #e91e63;">{</span> - GRAPH ?g <span style="color: #2196F3;">{</span>?s ?p ?o<span style="color: #2196F3;">}</span> -<span style="color: #e91e63;">}</span> +<pre class="src src-sql">select distinct ?g +{ + GRAPH ?g {?s ?p ?o} +} </pre> </div> @@ -383,10 +383,10 @@ To list all submitters, try </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?s -<span style="color: #e91e63;">{</span> - ?o <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/submitter"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/submitter">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/submitter">#MainSchema/submitter></a> ?s -<span style="color: #e91e63;">}</span> +<pre class="src src-sql">select distinct ?s +{ + ?o <http://biohackathon.org/bh20-seq-schema#MainSchema/submitter> ?s +} </pre> </div> @@ -397,11 +397,11 @@ and by </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?s -<span style="color: #e91e63;">{</span> - ?o <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/submitter"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/submitter">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/submitter">#MainSchema/submitter></a> ?id . +<pre class="src src-sql">select distinct ?s +{ + ?o <http://biohackathon.org/bh20-seq-schema#MainSchema/submitter> ?id . ?id ?p ?s -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -415,12 +415,12 @@ To lift the full URL out of the query you can use a header like </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">#MainSchema/></a> -<span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?dataset ?submitter -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +select distinct ?dataset ?submitter +{ ?dataset pubseq:submitter ?id . ?id ?p ?submitter -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -438,32 +438,32 @@ Now we got this far, lets <a href="http://sparql.genenetwork.org/sparql/?default </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">#MainSchema/></a> -<span style="color: #fff59d;">select</span> <span style="color: #e91e63;">(</span><span style="color: #ff8A65;">COUNT</span><span style="color: #2196F3;">(</span><span style="color: #fff59d;">distinct</span> ?dataset<span style="color: #2196F3;">)</span> <span style="color: #fff59d;">as</span> ?num<span style="color: #e91e63;">)</span> -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +select (COUNT(distinct ?dataset) as ?num) +{ ?dataset pubseq:submitter ?id . ?id ?p ?submitter -<span style="color: #e91e63;">}</span> +} </pre> </div> </div> </div> -<div id="outline-container-orgc6046bb" class="outline-2"> -<h2 id="orgc6046bb"><span class="section-number-2">4</span> Fetch submitter info and other metadata</h2> +<div id="outline-container-org08e70e1" class="outline-2"> +<h2 id="org08e70e1"><span class="section-number-2">4</span> Fetch submitter info and other metadata</h2> <div class="outline-text-2" id="text-4"> <p> To get dataests with submitters we can do the above </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">#MainSchema/></a> -<span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?dataset ?p ?submitter -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +select distinct ?dataset ?p ?submitter +{ ?dataset pubseq:submitter ?id . ?id ?p ?submitter -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -480,13 +480,13 @@ Let's focus on one sample with </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">#MainSchema/></a> -<span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?dataset ?submitter -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +select distinct ?dataset ?submitter +{ ?dataset pubseq:submitter ?id . ?id ?p ?submitter . - FILTER<span style="color: #2196F3;">(</span><span style="color: #fff59d;">CONTAINS</span><span style="color: #EF6C00;">(</span>?submitter,"Roychoudhury"<span style="color: #EF6C00;">)</span><span style="color: #2196F3;">)</span> . -<span style="color: #e91e63;">}</span> + FILTER(CONTAINS(?submitter,"Roychoudhury")) . +} </pre> </div> @@ -496,12 +496,12 @@ see if we can get a sample ID by listing sample predicates </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">#MainSchema/></a> -<span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?p -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +select distinct ?p +{ ?dataset ?p ?o . ?dataset pubseq:submitter ?id . -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -513,15 +513,15 @@ Let's zoom in on those of Roychoudhury with <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/">#MainSchema/></a> -<span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?sid ?sample ?p1 ?dataset ?submitter -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +select distinct ?sid ?sample ?p1 ?dataset ?submitter +{ ?dataset pubseq:submitter ?id . ?id ?p ?submitter . - FILTER<span style="color: #2196F3;">(</span><span style="color: #fff59d;">CONTAINS</span><span style="color: #EF6C00;">(</span>?submitter,"Roychoudhury"<span style="color: #EF6C00;">)</span><span style="color: #2196F3;">)</span> . + FILTER(CONTAINS(?submitter,"Roychoudhury")) . ?dataset pubseq:sample ?sid . ?sid ?p1 ?sample -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -532,18 +532,13 @@ this database. Let's focus on one sample "MT326090.1" with predicate </p> <div class="org-src-container"> -<pre class="src src-sql"><span style="color: #fff59d;">PREFIX</span> pubseq: <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/> -PREFIX sio: <http://semanticscience.org/resource/"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/> -PREFIX sio: <http://semanticscience.org/resource/">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/> -PREFIX sio: <http://semanticscience.org/resource/">#MainSchema/> -</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/> -PREFIX sio: <http://semanticscience.org/resource/">PREFIX</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/> -PREFIX sio: <http://semanticscience.org/resource/"> sio: <http://semanticscience.org/resource/></a> -<span style="color: #fff59d;">select</span> <span style="color: #fff59d;">distinct</span> ?sample ?p ?o -<span style="color: #e91e63;">{</span> +<pre class="src src-sql">PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> +PREFIX sio: <http://semanticscience.org/resource/> +select distinct ?sample ?p ?o +{ ?sample sio:SIO_000115 "MT326090.1" . ?sample ?p ?o . -<span style="color: #e91e63;">}</span> +} </pre> </div> @@ -561,8 +556,8 @@ to view/query the database. </div> </div> -<div id="outline-container-orgdcb216b" class="outline-2"> -<h2 id="orgdcb216b"><span class="section-number-2">5</span> Fetch all sequences from Washington state</h2> +<div id="outline-container-org9194557" class="outline-2"> +<h2 id="org9194557"><span class="section-number-2">5</span> Fetch all sequences from Washington state</h2> <div class="outline-text-2" id="text-5"> <p> Now we know how to get at the origin we can do it the other way round @@ -570,15 +565,11 @@ and fetch all sequences referring to Washington state </p> <div class="org-src-container"> -<pre class="src src-sql"> -<span style="color: #fff59d;">select</span> ?seq ?sample -<span style="color: #e91e63;">{</span> - ?seq <a href="http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample . - ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223"><http://biohackathon.org/bh20-seq-</a><span style="color: #fff59d;"><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample . - ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223">schema</a></span><a href="http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample . - ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223">#MainSchema/sample> ?sample . - ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223></a> -<span style="color: #e91e63;">}</span> +<pre class="src src-sql">select ?seq ?sample +{ + ?seq <http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample . + ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q1223> +} </pre> </div> @@ -586,11 +577,26 @@ and fetch all sequences referring to Washington state which lists 300 sequences originating from Washington state! Which is almost half of the set coming out of GenBank. </p> + +<p> +Likewise to list all sequences from Turkey we can find the wikidata +entity is <a href="https://www.wikidata.org/wiki/Q43">Q43</a>: +</p> + +<div class="org-src-container"> +<pre class="src src-sql">select ?seq ?sample +{ + ?seq <http://biohackathon.org/bh20-seq-schema#MainSchema/sample> ?sample . + ?sample <http://purl.obolibrary.org/obo/GAZ_00000448> <http://www.wikidata.org/entity/Q43> +} +</pre> </div> </div> +</div> + -<div id="outline-container-org7060f51" class="outline-2"> -<h2 id="org7060f51"><span class="section-number-2">6</span> Discussion</h2> +<div id="outline-container-org76317ad" class="outline-2"> +<h2 id="org76317ad"><span class="section-number-2">6</span> Discussion</h2> <div class="outline-text-2" id="text-6"> <p> The public sequence uploader collects sequences, raw data and @@ -601,8 +607,8 @@ referenced in publications and origins are citeable. </div> </div> -<div id="outline-container-orgdc51ccc" class="outline-2"> -<h2 id="orgdc51ccc"><span class="section-number-2">7</span> Acknowledgements</h2> +<div id="outline-container-orgeb871a1" class="outline-2"> +<h2 id="orgeb871a1"><span class="section-number-2">7</span> Acknowledgements</h2> <div class="outline-text-2" id="text-7"> <p> The overall effort was due to magnificent freely donated input by a @@ -617,7 +623,7 @@ Garrison this initiative would not have existed! </div> </div> <div id="postamble" class="status"> -<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-05-29 Fri 12:06</small>. +<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-07-17 Fri 05:02</small>. </div> </body> </html> diff --git a/doc/blog/using-covid-19-pubseq-part4.html b/doc/blog/using-covid-19-pubseq-part4.html index b5a05ca..c975c21 100644 --- a/doc/blog/using-covid-19-pubseq-part4.html +++ b/doc/blog/using-covid-19-pubseq-part4.html @@ -3,7 +3,7 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"> <head> -<!-- 2020-07-12 Sun 06:24 --> +<!-- 2020-07-17 Fri 05:04 --> <meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <title>COVID-19 PubSeq (part 4)</title> @@ -161,6 +161,19 @@ .footdef { margin-bottom: 1em; } .figure { padding: 1em; } .figure p { text-align: center; } + .equation-container { + display: table; + text-align: center; + width: 100%; + } + .equation { + vertical-align: middle; + } + .equation-label { + display: table-cell; + text-align: right; + vertical-align: middle; + } .inlinetask { padding: 10px; border: 2px solid gray; @@ -186,7 +199,7 @@ @licstart The following is the entire license notice for the JavaScript code in this tag. -Copyright (C) 2012-2018 Free Software Foundation, Inc. +Copyright (C) 2012-2020 Free Software Foundation, Inc. The JavaScript code in this tag is free software: you can redistribute it and/or modify it under the terms of the GNU @@ -235,15 +248,16 @@ for the JavaScript code in this tag. <h2>Table of Contents</h2> <div id="text-table-of-contents"> <ul> -<li><a href="#org8f8b64a">1. What does this mean?</a></li> -<li><a href="#orgcc7a403">2. Modify Workflow</a></li> +<li><a href="#orgc2ee09f">1. What does this mean?</a></li> +<li><a href="#org0d37881">2. Where can I find the workflows?</a></li> +<li><a href="#orgddb0531">3. Modify Workflow</a></li> </ul> </div> </div> -<div id="outline-container-org8f8b64a" class="outline-2"> -<h2 id="org8f8b64a"><span class="section-number-2">1</span> What does this mean?</h2> +<div id="outline-container-orgc2ee09f" class="outline-2"> +<h2 id="orgc2ee09f"><span class="section-number-2">1</span> What does this mean?</h2> <div class="outline-text-2" id="text-1"> <p> This means that when someone uploads a SARS-CoV-2 sequence using one @@ -253,18 +267,28 @@ which triggers a rerun of our workflows. </div> </div> - -<div id="outline-container-orgcc7a403" class="outline-2"> -<h2 id="orgcc7a403"><span class="section-number-2">2</span> Modify Workflow</h2> +<div id="outline-container-org0d37881" class="outline-2"> +<h2 id="org0d37881"><span class="section-number-2">2</span> Where can I find the workflows?</h2> <div class="outline-text-2" id="text-2"> <p> +Workflows are written in the common workflow language (CWL) and listed +on <a href="https://github.com/arvados/bh20-seq-resource/tree/master/workflows">github</a>. PubSeq being an open project these workflows can be studied +and modified! +</p> +</div> +</div> + +<div id="outline-container-orgddb0531" class="outline-2"> +<h2 id="orgddb0531"><span class="section-number-2">3</span> Modify Workflow</h2> +<div class="outline-text-2" id="text-3"> +<p> <i>Work in progress!</i> </p> </div> </div> </div> <div id="postamble" class="status"> -<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-07-12 Sun 06:24</small>. +<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-07-17 Fri 01:47</small>. </div> </body> </html> diff --git a/doc/blog/using-covid-19-pubseq-part5.html b/doc/blog/using-covid-19-pubseq-part5.html index 80bf559..4caa5ac 100644 --- a/doc/blog/using-covid-19-pubseq-part5.html +++ b/doc/blog/using-covid-19-pubseq-part5.html @@ -3,7 +3,7 @@ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> <html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"> <head> -<!-- 2020-07-12 Sun 06:24 --> +<!-- 2020-07-17 Fri 05:03 --> <meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> <meta name="viewport" content="width=device-width, initial-scale=1" /> <title>COVID-19 PubSeq (part 4)</title> @@ -161,6 +161,19 @@ .footdef { margin-bottom: 1em; } .figure { padding: 1em; } .figure p { text-align: center; } + .equation-container { + display: table; + text-align: center; + width: 100%; + } + .equation { + vertical-align: middle; + } + .equation-label { + display: table-cell; + text-align: right; + vertical-align: middle; + } .inlinetask { padding: 10px; border: 2px solid gray; @@ -186,7 +199,7 @@ @licstart The following is the entire license notice for the JavaScript code in this tag. -Copyright (C) 2012-2018 Free Software Foundation, Inc. +Copyright (C) 2012-2020 Free Software Foundation, Inc. The JavaScript code in this tag is free software: you can redistribute it and/or modify it under the terms of the GNU @@ -235,38 +248,40 @@ for the JavaScript code in this tag. <h2>Table of Contents</h2> <div id="text-table-of-contents"> <ul> -<li><a href="#org871ad58">1. Modify Metadata</a></li> -<li><a href="#org07e8755">2. What is the schema?</a></li> -<li><a href="#org4857280">3. How is the website generated?</a></li> -<li><a href="#orge709ae2">4. Modifying the schema</a></li> +<li><a href="#org758b923">1. Modify Metadata</a></li> +<li><a href="#orgec32c13">2. What is the schema?</a></li> +<li><a href="#org2e487b2">3. How is the website generated?</a></li> +<li><a href="#orge4dfe84">4. Modifying the schema</a></li> +<li><a href="#org564a7a8">5. Adding fields to the form</a></li> +<li><a href="#org633781a">6. <span class="todo TODO">TODO</span> Testing the license fields</a></li> </ul> </div> </div> -<div id="outline-container-org871ad58" class="outline-2"> -<h2 id="org871ad58"><span class="section-number-2">1</span> Modify Metadata</h2> +<div id="outline-container-org758b923" class="outline-2"> +<h2 id="org758b923"><span class="section-number-2">1</span> Modify Metadata</h2> <div class="outline-text-2" id="text-1"> <p> The public sequence resource uses multiple data formats listed on the -<a href="./download">DOWNLOAD</a> page. One of the most exciting features is the full support +<a href="http://covid19.genenetwork.org/download">download</a> page. One of the most exciting features is the full support for RDF and semantic web/linked data ontologies. This technology allows for querying data in unprescribed ways - that is, you can formulate your own queries without dealing with a preset model of that data (so typical of CSV files and SQL tables). Examples of exploring -data are listed <a href="./blog?id=using-covid-19-pubseq-part1">here</a>. +data are listed <a href="http://covid19.genenetwork.org/blog?id=using-covid-19-pubseq-part1">here</a>. </p> <p> In this BLOG we are going to look at the metadata entered on the -<a href="./">COVID-19 PubSeq</a> website (or command line client). It is important to +COVID-19 PubSeq website (or command line client). It is important to understand that anyone, including you, can change that information! </p> </div> </div> -<div id="outline-container-org07e8755" class="outline-2"> -<h2 id="org07e8755"><span class="section-number-2">2</span> What is the schema?</h2> +<div id="outline-container-orgec32c13" class="outline-2"> +<h2 id="orgec32c13"><span class="section-number-2">2</span> What is the schema?</h2> <div class="outline-text-2" id="text-2"> <p> The default metadata schema is listed <a href="https://github.com/arvados/bh20-seq-resource/blob/master/bh20sequploader/bh20seq-schema.yml">here</a>. @@ -274,8 +289,8 @@ The default metadata schema is listed <a href="https://github.com/arvados/bh20-s </div> </div> -<div id="outline-container-org4857280" class="outline-2"> -<h2 id="org4857280"><span class="section-number-2">3</span> How is the website generated?</h2> +<div id="outline-container-org2e487b2" class="outline-2"> +<h2 id="org2e487b2"><span class="section-number-2">3</span> How is the website generated?</h2> <div class="outline-text-2" id="text-3"> <p> Using the schema we use <a href="https://pypi.org/project/PyShEx/">pyshex</a> shex expressions and <a href="https://github.com/common-workflow-language/schema_salad">schema salad</a> to @@ -285,13 +300,13 @@ All from that one metadata schema. </div> </div> -<div id="outline-container-orge709ae2" class="outline-2"> -<h2 id="orge709ae2"><span class="section-number-2">4</span> Modifying the schema</h2> +<div id="outline-container-orge4dfe84" class="outline-2"> +<h2 id="orge4dfe84"><span class="section-number-2">4</span> Modifying the schema</h2> <div class="outline-text-2" id="text-4"> <p> -One of the first things we wanted to do is to add a field for the data -license. Initially we only support CC-4.0 as a license by default, but -now we want to give uploaders the option to make it an even more +One of the first things we want to do is to add a field for the data +license. Initially we only supported CC-4.0 as a license, but +we wanted to give uploaders the option to use an even more liberal CC0 license. The first step is to find a good ontology term for the field. Searching for `creative commons cc0 rdf' rendered this useful <a href="https://creativecommons.org/ns">page</a>. We also find an <a href="https://wiki.creativecommons.org/wiki/CC_License_Rdf_Overview">overview</a> where CC0 is represented as URI @@ -302,13 +317,148 @@ attributionName and attributionURL. </p> <p> -<i>Note: work in progress</i> +A minimal triple should be +</p> + +<pre class="example"> +id xhtml:license <http://creativecommons.org/licenses/by/4.0/> . +</pre> + + +<p> +Other suggestions are +</p> + +<pre class="example"> +id dc:title "Description" . +id cc:attributionName "Your Name" . +id cc:attributionURL <http://resource.org/id> +</pre> + + +<p> +and 'dc:source' which indicates the original source of any modified +work, specified as a URI. +The prefix 'cc:' is an abbreviation for <a href="http://creativecommons.org/ns">http://creativecommons.org/ns</a>#. +</p> + +<p> +Going back to the schema, where does it fit? Under host, sample, +virus, technology or submitter block? It could fit under sample, but +actually the license concerns the whole metadata block and sequence, +so I think we can fit under its own license tag. For example +</p> + + +<p> +id: placeholder +</p> + +<pre class="example"> +license: + license_type: http://creativecommons.org/licenses/by/4.0/ + attribution_title: "Sample ID" + attribution_name: "John doe, Joe Boe, Jonny Oe" + attribution_url: http://covid19.genenetwork.org/id + attribution_source: https://www.ncbi.nlm.nih.gov/pubmed/323088888 +</pre> + + +<p> +So, let's update the example. Notice the license info is optional - if it is missing +we just assume the default CC-4.0. +</p> + +<p> +One thing that is interesting is that in the name space <a href="https://creativecommons.org/ns">https://creativecommons.org/ns</a> there +is no mention of a title. I think it is useful, however, because we have no such field. +So, we'll add it simply as a title field. Now the draft schema is </p> + +<div class="org-src-container"> +<pre class="src src-js">- name: licenseSchema + type: record + fields: + license_type: + doc: License types as refined in https://wiki.creativecommons.org/images/d/d6/Ccrel-1.0.pdf + type: string? + jsonldPredicate: + _id: https://creativecommons.org/ns#License + title: + doc: Attribution title related to license + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_001167 + attribution_url: + doc: Attribution URL related to license + type: string? + jsonldPredicate: + _id: https://creativecommons.org/ns#Work + attribution_source: + doc: Attribution source URL + type: string? + jsonldPredicate: + _id: https://creativecommons.org/ns#Work +</pre> +</div> + +<p> +Now, we are no ontology experts, right? So, next we submit a patch to +our source tree and ask for feedback before wiring it up in the data +entry form. The pull request was submitted <a href="https://github.com/arvados/bh20-seq-resource/pull/97">here</a> and reviewed on the +gitter channel and I merged it. +</p> +</div> </div> + +<div id="outline-container-org564a7a8" class="outline-2"> +<h2 id="org564a7a8"><span class="section-number-2">5</span> Adding fields to the form</h2> +<div class="outline-text-2" id="text-5"> +<p> +To add the new fields to the form we have to modify it a little. If we +go to the upload form we need to add the license box. The schema is +loaded in <a href="https://github.com/arvados/bh20-seq-resource/blob/a0c8ebd57b875f265e8b0efec4abfaf892eb6c45/bh20simplewebuploader/main.py#L229">main.py</a> in the 'generate<sub>form</sub>' function. +</p> + +<p> +With this <a href="https://github.com/arvados/bh20-seq-resource/commit/b9691c7deae30bd6422fb7b0681572b7b6f78ae3">patch</a> the website adds the license input fields on the form. +</p> + +<p> +Finally, to make RDF output work we need to add expressions to bh20seq-shex.rdf. This +was done with this <a href="https://github.com/arvados/bh20-seq-resource/commit/f4ed46dae20abe5147871495ede2d6ac2b0854bc">patch</a>. In the end we decided to use the Dublin core title, +<a href="http://purl.org/metadata/dublin_core_elements#Title">http://purl.org/metadata/dublin_core_elements#Title</a>: +</p> + +<div class="org-src-container"> +<pre class="src src-js">:licenseShape{ + cc:License xsd:string; + dc:Title xsd:string ?; + cc:attributionName xsd:string ?; + cc:attributionURL xsd:string ?; + cc:attributionSource xsd:string ?; +} +</pre> +</div> + +<p> +Note that cc:AttributionSource is not really defined in the cc standard. +</p> + +<p> +When pushing the license info we discovered the workflow broke because +the existing data had no licensing info. So we changed the license +field to be optional - a missing license assumes it is CC-BY-4.0. +</p> +</div> +</div> + +<div id="outline-container-org633781a" class="outline-2"> +<h2 id="org633781a"><span class="section-number-2">6</span> <span class="todo TODO">TODO</span> Testing the license fields</h2> </div> </div> <div id="postamble" class="status"> -<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-07-12 Sun 06:24</small>. +<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-07-16 Thu 03:27</small>. </div> </body> </html> diff --git a/doc/blog/using-covid-19-pubseq-part6.html b/doc/blog/using-covid-19-pubseq-part6.html new file mode 100644 index 0000000..278abe8 --- /dev/null +++ b/doc/blog/using-covid-19-pubseq-part6.html @@ -0,0 +1,393 @@ +<?xml version="1.0" encoding="utf-8"?> +<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Strict//EN" +"http://www.w3.org/TR/xhtml1/DTD/xhtml1-strict.dtd"> +<html xmlns="http://www.w3.org/1999/xhtml" lang="en" xml:lang="en"> +<head> +<!-- 2020-07-17 Fri 06:05 --> +<meta http-equiv="Content-Type" content="text/html;charset=utf-8" /> +<meta name="viewport" content="width=device-width, initial-scale=1" /> +<title>COVID-19 PubSeq (part 6)</title> +<meta name="generator" content="Org mode" /> +<meta name="author" content="Pjotr Prins" /> +<style type="text/css"> + <!--/*--><![CDATA[/*><!--*/ + .title { text-align: center; + margin-bottom: .2em; } + .subtitle { text-align: center; + font-size: medium; + font-weight: bold; + margin-top:0; } + .todo { font-family: monospace; color: red; } + .done { font-family: monospace; color: green; } + .priority { font-family: monospace; color: orange; } + .tag { background-color: #eee; font-family: monospace; + padding: 2px; font-size: 80%; font-weight: normal; } + .timestamp { color: #bebebe; } + .timestamp-kwd { color: #5f9ea0; } + .org-right { margin-left: auto; margin-right: 0px; text-align: right; } + .org-left { margin-left: 0px; margin-right: auto; text-align: left; } + .org-center { margin-left: auto; margin-right: auto; text-align: center; } + .underline { text-decoration: underline; } + #postamble p, #preamble p { font-size: 90%; margin: .2em; } + p.verse { margin-left: 3%; } + pre { + border: 1px solid #ccc; + box-shadow: 3px 3px 3px #eee; + padding: 8pt; + font-family: monospace; + overflow: auto; + margin: 1.2em; + } + pre.src { + position: relative; + overflow: visible; + padding-top: 1.2em; + } + pre.src:before { + display: none; + position: absolute; + background-color: white; + top: -10px; + right: 10px; + padding: 3px; + border: 1px solid black; + } + pre.src:hover:before { display: inline;} + /* Languages per Org manual */ + pre.src-asymptote:before { content: 'Asymptote'; } + pre.src-awk:before { content: 'Awk'; } + pre.src-C:before { content: 'C'; } + /* pre.src-C++ doesn't work in CSS */ + pre.src-clojure:before { content: 'Clojure'; } + pre.src-css:before { content: 'CSS'; } + pre.src-D:before { content: 'D'; } + pre.src-ditaa:before { content: 'ditaa'; } + pre.src-dot:before { content: 'Graphviz'; } + pre.src-calc:before { content: 'Emacs Calc'; } + pre.src-emacs-lisp:before { content: 'Emacs Lisp'; } + pre.src-fortran:before { content: 'Fortran'; } + pre.src-gnuplot:before { content: 'gnuplot'; } + pre.src-haskell:before { content: 'Haskell'; } + pre.src-hledger:before { content: 'hledger'; } + pre.src-java:before { content: 'Java'; } + pre.src-js:before { content: 'Javascript'; } + pre.src-latex:before { content: 'LaTeX'; } + pre.src-ledger:before { content: 'Ledger'; } + pre.src-lisp:before { content: 'Lisp'; } + pre.src-lilypond:before { content: 'Lilypond'; } + pre.src-lua:before { content: 'Lua'; } + pre.src-matlab:before { content: 'MATLAB'; } + pre.src-mscgen:before { content: 'Mscgen'; } + pre.src-ocaml:before { content: 'Objective Caml'; } + pre.src-octave:before { content: 'Octave'; } + pre.src-org:before { content: 'Org mode'; } + pre.src-oz:before { content: 'OZ'; } + pre.src-plantuml:before { content: 'Plantuml'; } + pre.src-processing:before { content: 'Processing.js'; } + pre.src-python:before { content: 'Python'; } + pre.src-R:before { content: 'R'; } + pre.src-ruby:before { content: 'Ruby'; } + pre.src-sass:before { content: 'Sass'; } + pre.src-scheme:before { content: 'Scheme'; } + pre.src-screen:before { content: 'Gnu Screen'; } + pre.src-sed:before { content: 'Sed'; } + pre.src-sh:before { content: 'shell'; } + pre.src-sql:before { content: 'SQL'; } + pre.src-sqlite:before { content: 'SQLite'; } + /* additional languages in org.el's org-babel-load-languages alist */ + pre.src-forth:before { content: 'Forth'; } + pre.src-io:before { content: 'IO'; } + pre.src-J:before { content: 'J'; } + pre.src-makefile:before { content: 'Makefile'; } + pre.src-maxima:before { content: 'Maxima'; } + pre.src-perl:before { content: 'Perl'; } + pre.src-picolisp:before { content: 'Pico Lisp'; } + pre.src-scala:before { content: 'Scala'; } + pre.src-shell:before { content: 'Shell Script'; } + pre.src-ebnf2ps:before { content: 'ebfn2ps'; } + /* additional language identifiers per "defun org-babel-execute" + in ob-*.el */ + pre.src-cpp:before { content: 'C++'; } + pre.src-abc:before { content: 'ABC'; } + pre.src-coq:before { content: 'Coq'; } + pre.src-groovy:before { content: 'Groovy'; } + /* additional language identifiers from org-babel-shell-names in + ob-shell.el: ob-shell is the only babel language using a lambda to put + the execution function name together. */ + pre.src-bash:before { content: 'bash'; } + pre.src-csh:before { content: 'csh'; } + pre.src-ash:before { content: 'ash'; } + pre.src-dash:before { content: 'dash'; } + pre.src-ksh:before { content: 'ksh'; } + pre.src-mksh:before { content: 'mksh'; } + pre.src-posh:before { content: 'posh'; } + /* Additional Emacs modes also supported by the LaTeX listings package */ + pre.src-ada:before { content: 'Ada'; } + pre.src-asm:before { content: 'Assembler'; } + pre.src-caml:before { content: 'Caml'; } + pre.src-delphi:before { content: 'Delphi'; } + pre.src-html:before { content: 'HTML'; } + pre.src-idl:before { content: 'IDL'; } + pre.src-mercury:before { content: 'Mercury'; } + pre.src-metapost:before { content: 'MetaPost'; } + pre.src-modula-2:before { content: 'Modula-2'; } + pre.src-pascal:before { content: 'Pascal'; } + pre.src-ps:before { content: 'PostScript'; } + pre.src-prolog:before { content: 'Prolog'; } + pre.src-simula:before { content: 'Simula'; } + pre.src-tcl:before { content: 'tcl'; } + pre.src-tex:before { content: 'TeX'; } + pre.src-plain-tex:before { content: 'Plain TeX'; } + pre.src-verilog:before { content: 'Verilog'; } + pre.src-vhdl:before { content: 'VHDL'; } + pre.src-xml:before { content: 'XML'; } + pre.src-nxml:before { content: 'XML'; } + /* add a generic configuration mode; LaTeX export needs an additional + (add-to-list 'org-latex-listings-langs '(conf " ")) in .emacs */ + pre.src-conf:before { content: 'Configuration File'; } + + table { border-collapse:collapse; } + caption.t-above { caption-side: top; } + caption.t-bottom { caption-side: bottom; } + td, th { vertical-align:top; } + th.org-right { text-align: center; } + th.org-left { text-align: center; } + th.org-center { text-align: center; } + td.org-right { text-align: right; } + td.org-left { text-align: left; } + td.org-center { text-align: center; } + dt { font-weight: bold; } + .footpara { display: inline; } + .footdef { margin-bottom: 1em; } + .figure { padding: 1em; } + .figure p { text-align: center; } + .equation-container { + display: table; + text-align: center; + width: 100%; + } + .equation { + vertical-align: middle; + } + .equation-label { + display: table-cell; + text-align: right; + vertical-align: middle; + } + .inlinetask { + padding: 10px; + border: 2px solid gray; + margin: 10px; + background: #ffffcc; + } + #org-div-home-and-up + { text-align: right; font-size: 70%; white-space: nowrap; } + textarea { overflow-x: auto; } + .linenr { font-size: smaller } + .code-highlighted { background-color: #ffff00; } + .org-info-js_info-navigation { border-style: none; } + #org-info-js_console-label + { font-size: 10px; font-weight: bold; white-space: nowrap; } + .org-info-js_search-highlight + { background-color: #ffff00; color: #000000; font-weight: bold; } + .org-svg { width: 90%; } + /*]]>*/--> +</style> +<link rel="Blog stylesheet" type="text/css" href="blog.css" /> +<script type="text/javascript"> +/* +@licstart The following is the entire license notice for the +JavaScript code in this tag. + +Copyright (C) 2012-2020 Free Software Foundation, Inc. + +The JavaScript code in this tag is free software: you can +redistribute it and/or modify it under the terms of the GNU +General Public License (GNU GPL) as published by the Free Software +Foundation, either version 3 of the License, or (at your option) +any later version. The code is distributed WITHOUT ANY WARRANTY; +without even the implied warranty of MERCHANTABILITY or FITNESS +FOR A PARTICULAR PURPOSE. See the GNU GPL for more details. + +As additional permission under GNU GPL version 3 section 7, you +may distribute non-source (e.g., minimized or compacted) forms of +that code without the copy of the GNU GPL normally required by +section 4, provided you include this license notice and a URL +through which recipients can access the Corresponding Source. + + +@licend The above is the entire license notice +for the JavaScript code in this tag. +*/ +<!--/*--><![CDATA[/*><!--*/ + function CodeHighlightOn(elem, id) + { + var target = document.getElementById(id); + if(null != target) { + elem.cacheClassElem = elem.className; + elem.cacheClassTarget = target.className; + target.className = "code-highlighted"; + elem.className = "code-highlighted"; + } + } + function CodeHighlightOff(elem, id) + { + var target = document.getElementById(id); + if(elem.cacheClassElem) + elem.className = elem.cacheClassElem; + if(elem.cacheClassTarget) + target.className = elem.cacheClassTarget; + } +/*]]>*///--> +</script> +</head> +<body> +<div id="content"> +<h1 class="title">COVID-19 PubSeq (part 6)</h1> +<div id="table-of-contents"> +<h2>Table of Contents</h2> +<div id="text-table-of-contents"> +<ul> +<li><a href="#orge6aea9e">1. Generating output for EBI</a></li> +<li><a href="#org95e5e17">2. Defining the EBI study</a></li> +<li><a href="#org9181a73">3. Define the EBI sample</a></li> +<li><a href="#orga29cad0">4. Define the EBI sequence</a></li> +</ul> +</div> +</div> + + +<div id="outline-container-orge6aea9e" class="outline-2"> +<h2 id="orge6aea9e"><span class="section-number-2">1</span> Generating output for EBI</h2> +<div class="outline-text-2" id="text-1"> +<p> +Would it not be great an uploader to PubSeq also can export samples +to, say, EBI? That is what we discuss in this section. The submission +process is somewhat laborious and when you have submitted to PubSeq +why not export the same to EBI too with the least amount of effort? +</p> + +<p> +COVID-19 PubSeq is a data source - both sequence data and metadata - +that can be used to push data to other sources, such as EBI. You can +register <a href="https://ena-docs.readthedocs.io/en/latest/submit/samples/programmatic.html">samples programmatically</a> with a specific XML interface. Note +that (at this point) if you want to submit a sequence (FASTA) it can +only be done through the <a href="https://ena-docs.readthedocs.io/en/latest/submit/general-guide/webin-cli.html">Webin-CLI</a>. Raw data (FASTQ) can go through +the XML interface. +</p> + +<p> +EBI sequence resources are presented through ENA. For example +<a href="https://www.ebi.ac.uk/ena/browser/view/MT394864">Sequence: MT394864.1</a>. +</p> + +<p> +EBI has XML Formats for +</p> + +<ul class="org-ul"> +<li>SUBMISSION</li> +<li>STUDY</li> +<li>SAMPLE</li> +<li>EXPERIMENT</li> +<li>RUN</li> +<li>ANALYSIS</li> +<li>DAC</li> +<li>POLICY</li> +<li>DATASET</li> +<li>PROJECT</li> +</ul> + +<p> +with the schemas listed <a href="ftp://ftp.ebi.ac.uk/pub/databases/ena/doc/xsd/sra_1_5/">here</a>. Since we are submitting sequences we +should follow submitting <a href="https://ena-docs.readthedocs.io/en/latest/submit/assembly.html">full genome assembly guidelines</a> and +<a href="https://ena-docs.readthedocs.io/en/latest/submit/general-guide/programmatic.html">ENA guidelines</a>. The first step is to define the study, next the sample +and finally the sequence (assembly). +</p> +</div> +</div> + +<div id="outline-container-org95e5e17" class="outline-2"> +<h2 id="org95e5e17"><span class="section-number-2">2</span> Defining the EBI study</h2> +<div class="outline-text-2" id="text-2"> +<p> +A study is defined <a href="https://ena-docs.readthedocs.io/en/latest/submit/study/programmatic.html">here</a> and looks like +</p> + +<div class="org-src-container"> +<pre class="src src-xml"><PROJECT_SET> + <PROJECT alias="COVID-19 Washington DC"> + <TITLE>Sequencing SARS-CoV-2 in the Washington DC area</TITLE> + <DESCRIPTION>This study collects samples from COVID-19 patients in the Washington DC area</DESCRIPTION> + <SUBMISSION_PROJECT> + <SEQUENCING_PROJECT/> + </SUBMISSION_PROJECT> + </PROJECT> +</PROJECT_SET> +</pre> +</div> + +<p> +also a submission 'command' is required looking like +</p> + +<div class="org-src-container"> +<pre class="src src-xml"><SUBMISSION> + <ACTIONS> + <ACTION> + <ADD/> + </ACTION> + <ACTION> + <HOLD HoldUntilDate="TODO: release date"/> + </ACTION> + </ACTIONS> +</SUBMISSION> + +</pre> +</div> + +<p> +The webin system accepts such sources using a command like +</p> + +<pre class="example"> +curl -u username:password -F "SUBMISSION=@submission.xml" \ + -F "PROJECT=@project.xml" "https://wwwdev.ebi.ac.uk/ena/submit/drop-box/submit/" +</pre> + + +<p> +as described <a href="https://ena-docs.readthedocs.io/en/latest/submit/study/programmatic.html#submit-the-xmls-using-curl">here</a>. Note that this is the test server. For the final +version use www.ebi.ac.uk instead of wwwdev.ebi.ac.uk. You may also +need the –insecure switch to circumvent certificate checking. +</p> + +<p> +<i>work in progress (WIP)</i> +</p> +</div> +</div> + +<div id="outline-container-org9181a73" class="outline-2"> +<h2 id="org9181a73"><span class="section-number-2">3</span> Define the EBI sample</h2> +<div class="outline-text-2" id="text-3"> +<p> +<i>work in progress (WIP)</i> +</p> +</div> +</div> + +<div id="outline-container-orga29cad0" class="outline-2"> +<h2 id="orga29cad0"><span class="section-number-2">4</span> Define the EBI sequence</h2> +<div class="outline-text-2" id="text-4"> +<p> +<i>work in progress (WIP)</i> +</p> +</div> +</div> +</div> +<div id="postamble" class="status"> +<hr><small>Created by <a href="http://thebird.nl/">Pjotr Prins</a> (pjotr.public768 at thebird 'dot' nl) using Emacs org-mode and a healthy dose of Lisp!<br />Modified 2020-07-17 Fri 06:05</small>. +</div> +</body> +</html> diff --git a/doc/blog/using-covid-19-pubseq-part6.org b/doc/blog/using-covid-19-pubseq-part6.org new file mode 100644 index 0000000..8964700 --- /dev/null +++ b/doc/blog/using-covid-19-pubseq-part6.org @@ -0,0 +1,102 @@ +#+TITLE: COVID-19 PubSeq (part 6) +#+AUTHOR: Pjotr Prins +# C-c C-e h h publish +# C-c ! insert date (use . for active agenda, C-u C-c ! for date, C-u C-c . for time) +# C-c C-t task rotate +# RSS_IMAGE_URL: http://xxxx.xxxx.free.fr/rss_icon.png + +#+HTML_HEAD: <link rel="Blog stylesheet" type="text/css" href="blog.css" /> + + +* Table of Contents :TOC:noexport: + - [[#generating-output-for-ebi][Generating output for EBI]] + - [[#defining-the-ebi-study][Defining the EBI study]] + - [[#define-the-ebi-sample][Define the EBI sample]] + - [[#define-the-ebi-sequence][Define the EBI sequence]] + +* Generating output for EBI + +Would it not be great an uploader to PubSeq also can export samples +to, say, EBI? That is what we discuss in this section. The submission +process is somewhat laborious and when you have submitted to PubSeq +why not export the same to EBI too with the least amount of effort? + +COVID-19 PubSeq is a data source - both sequence data and metadata - +that can be used to push data to other sources, such as EBI. You can +register [[https://ena-docs.readthedocs.io/en/latest/submit/samples/programmatic.html][samples programmatically]] with a specific XML interface. Note +that (at this point) if you want to submit a sequence (FASTA) it can +only be done through the [[https://ena-docs.readthedocs.io/en/latest/submit/general-guide/webin-cli.html][Webin-CLI]]. Raw data (FASTQ) can go through +the XML interface. + +EBI sequence resources are presented through ENA. For example +[[https://www.ebi.ac.uk/ena/browser/view/MT394864][Sequence: MT394864.1]]. + +EBI has XML Formats for + +- SUBMISSION +- STUDY +- SAMPLE +- EXPERIMENT +- RUN +- ANALYSIS +- DAC +- POLICY +- DATASET +- PROJECT + +with the schemas listed [[ftp://ftp.ebi.ac.uk/pub/databases/ena/doc/xsd/sra_1_5/][here]]. Since we are submitting sequences we +should follow submitting [[https://ena-docs.readthedocs.io/en/latest/submit/assembly.html][full genome assembly guidelines]] and +[[https://ena-docs.readthedocs.io/en/latest/submit/general-guide/programmatic.html][ENA guidelines]]. The first step is to define the study, next the sample +and finally the sequence (assembly). + +* Defining the EBI study + +A study is defined [[https://ena-docs.readthedocs.io/en/latest/submit/study/programmatic.html][here]] and looks like + +#+BEGIN_SRC xml +<PROJECT_SET> + <PROJECT alias="COVID-19 Washington DC"> + <TITLE>Sequencing SARS-CoV-2 in the Washington DC area</TITLE> + <DESCRIPTION>This study collects samples from COVID-19 patients in the Washington DC area</DESCRIPTION> + <SUBMISSION_PROJECT> + <SEQUENCING_PROJECT/> + </SUBMISSION_PROJECT> + </PROJECT> +</PROJECT_SET> +#+END_SRC + +also a submission 'command' is required looking like + +#+BEGIN_SRC xml +<SUBMISSION> + <ACTIONS> + <ACTION> + <ADD/> + </ACTION> + <ACTION> + <HOLD HoldUntilDate="TODO: release date"/> + </ACTION> + </ACTIONS> +</SUBMISSION> + +#+END_SRC + +The webin system accepts such sources using a command like + +: curl -u username:password -F "SUBMISSION=@submission.xml" \ +: -F "PROJECT=@project.xml" "https://wwwdev.ebi.ac.uk/ena/submit/drop-box/submit/" + +as described [[https://ena-docs.readthedocs.io/en/latest/submit/study/programmatic.html#submit-the-xmls-using-curl][here]]. Note that this is the test server. For the final +version use www.ebi.ac.uk instead of wwwdev.ebi.ac.uk. You may also +need the --insecure switch to circumvent certificate checking. + +/work in progress (WIP)/ + +* Define the EBI sample + + +/work in progress (WIP)/ + +* Define the EBI sequence + +/work in progress (WIP)/ diff --git a/scripts/cleanup.py b/scripts/cleanup.py new file mode 100644 index 0000000..78f34c8 --- /dev/null +++ b/scripts/cleanup.py @@ -0,0 +1,41 @@ +import arvados +import arvados.util + +api = arvados.api() + +delete_patterns = [ + "%missing%`collection_location`%", + "%missing%`technology`%", + "%missing%`host_species`%", + "%QC fail: alignment%", + "%does not look like a valid URI%", + "%Duplicate of%", + "%No matching triples found for predicate obo:NCIT_C42781%", + "%does not look like a valid URI%" + ] + +revalidate_patterns = [ + "%missing%`license`%", + "%QC fail%" +] + +for p in delete_patterns: + c = arvados.util.list_all(api.collections().list, filters=[ + ["owner_uuid", "=", "lugli-j7d0g-n5clictpuvwk8aa"], + ["properties.errors", "like", p]]) + for i in c: + print("trashing %s %s" % (i["uuid"], i["properties"].get("sequence_label"))) + api.collections().delete(uuid=i["uuid"]).execute() + +for p in revalidate_patterns: + c = arvados.util.list_all(api.collections().list, filters=[ + ["owner_uuid", "=", "lugli-j7d0g-n5clictpuvwk8aa"], + ["properties.errors", "like", p]]) + for i in c: + print("clearing status %s %s" % (i["uuid"], i["properties"].get("sequence_label"))) + pr = i["properties"] + if "status" in pr: + del pr["status"] + if "errors" in pr: + del pr["errors"] + api.collections().update(uuid=i["uuid"], body={"properties": pr}).execute() diff --git a/scripts/submit_ebi/example/project-submission.xml b/scripts/submit_ebi/example/project-submission.xml new file mode 100644 index 0000000..1abb827 --- /dev/null +++ b/scripts/submit_ebi/example/project-submission.xml @@ -0,0 +1,12 @@ +<?xml version="1.0" encoding="UTF-8"?> +<SUBMISSION> + <ACTIONS> + <ACTION> + <ADD/> + </ACTION> + <ACTION> + <HOLD HoldUntilDate="2020-10-10"/> + </ACTION> + </ACTIONS> +</SUBMISSION> + diff --git a/scripts/submit_ebi/example/project.xml b/scripts/submit_ebi/example/project.xml new file mode 100644 index 0000000..6a817e7 --- /dev/null +++ b/scripts/submit_ebi/example/project.xml @@ -0,0 +1,10 @@ +<?xml version="1.0" encoding="UTF-8"?> +<PROJECT_SET> + <PROJECT alias="PubSeq01"> + <TITLE>Testing PubSeq Sample uploads</TITLE> + <DESCRIPTION>This is a test to allow for uploading sequences from PubSeq</DESCRIPTION> + <SUBMISSION_PROJECT> + <SEQUENCING_PROJECT/> + </SUBMISSION_PROJECT> + </PROJECT> +</PROJECT_SET> diff --git a/scripts/submit_ebi/example/sample-submission.xml b/scripts/submit_ebi/example/sample-submission.xml new file mode 100644 index 0000000..9d13512 --- /dev/null +++ b/scripts/submit_ebi/example/sample-submission.xml @@ -0,0 +1,8 @@ +<?xml version="1.0" encoding="UTF-8"?> +<SUBMISSION> + <ACTIONS> + <ACTION> + <ADD/> + </ACTION> + </ACTIONS> +</SUBMISSION> diff --git a/scripts/submit_ebi/example/sample.xml b/scripts/submit_ebi/example/sample.xml new file mode 100644 index 0000000..694c471 --- /dev/null +++ b/scripts/submit_ebi/example/sample.xml @@ -0,0 +1,68 @@ +<?xml version="1.0" encoding="UTF-8"?> +<SAMPLE_SET> + <SAMPLE alias="PubSeqSam0001" center_name="PubSeq01"> + <TITLE>human gastric microbiota, mucosal</TITLE> + <SAMPLE_NAME> + <TAXON_ID>1284369</TAXON_ID> + <SCIENTIFIC_NAME>stomach metagenome</SCIENTIFIC_NAME> + <COMMON_NAME></COMMON_NAME> + </SAMPLE_NAME> + <SAMPLE_ATTRIBUTES> + <SAMPLE_ATTRIBUTE> + <TAG>investigation type</TAG> + <VALUE>mimarks-survey</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>sequencing method</TAG> + <VALUE>pyrosequencing</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>collection date</TAG> + <VALUE>2010</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>host body site</TAG> + <VALUE>Mucosa of stomach</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>human-associated environmental package</TAG> + <VALUE>human-associated</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>geographic location (latitude)</TAG> + <VALUE>1.81</VALUE> + <UNITS>DD</UNITS> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>geographic location (longitude)</TAG> + <VALUE>-78.76</VALUE> + <UNITS>DD</UNITS> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>geographic location (country and/or sea)</TAG> + <VALUE>Colombia</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>geographic location (region and locality)</TAG> + <VALUE>Tumaco</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>environment (biome)</TAG> + <VALUE>coast</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>environment (feature)</TAG> + <VALUE>human-associated habitat</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>environment (material)</TAG> + <VALUE>gastric biopsy</VALUE> + </SAMPLE_ATTRIBUTE> + <SAMPLE_ATTRIBUTE> + <TAG>ENA-CHECKLIST</TAG> + <VALUE>ERC000011</VALUE> + </SAMPLE_ATTRIBUTE> + </SAMPLE_ATTRIBUTES> + </SAMPLE> +</SAMPLE_SET> + |
