diff options
Diffstat (limited to 'bh20sequploader')
-rw-r--r-- | bh20sequploader/bh20seq-schema.yml | 36 | ||||
-rw-r--r-- | bh20sequploader/main.py | 56 | ||||
-rw-r--r-- | bh20sequploader/qc_metadata.py | 21 |
3 files changed, 113 insertions, 0 deletions
diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml new file mode 100644 index 0000000..6e0973a --- /dev/null +++ b/bh20sequploader/bh20seq-schema.yml @@ -0,0 +1,36 @@ +$graph: + +- name: sampleInformationSchema + type: record + fields: + location: string + host: string + sequenceTechnology: string + assemblyMethod: string + +- name: InstituteInformationSchema + type: record + fields: + OriginatingLab: string + SubmittingLab: string + +- name: SubmitterInformationSchema + type: record + fields: + Submitter: string + submissionDate: string + +- name: VirusDetailSchema + type: record + fields: + VirusName: string + AccessionId: string + +- name: MainSchema + type: record + documentRoot: true + fields: + sampleInformation: sampleInformationSchema + InstituteInformation: InstituteInformationSchema + SubmitterInformation: SubmitterInformationSchema + VirusDetail: VirusDetailSchema diff --git a/bh20sequploader/main.py b/bh20sequploader/main.py new file mode 100644 index 0000000..8b8fefe --- /dev/null +++ b/bh20sequploader/main.py @@ -0,0 +1,56 @@ +import argparse +import time +import arvados +import arvados.collection +import json +import urllib.request +import socket +import getpass +from .qc_metadata import qc_metadata + +ARVADOS_API_HOST='lugli.arvadosapi.com' +ARVADOS_API_TOKEN='2fbebpmbo3rw3x05ueu2i6nx70zhrsb1p22ycu3ry34m4x4462' +UPLOAD_PROJECT='lugli-j7d0g-n5clictpuvwk8aa' + +def main(): + parser = argparse.ArgumentParser(description='Upload SARS-CoV-19 sequences for analysis') + parser.add_argument('sequence', type=argparse.FileType('r'), help='sequence FASTA') + parser.add_argument('metadata', type=argparse.FileType('r'), help='sequence metadata json') + args = parser.parse_args() + + api = arvados.api(host=ARVADOS_API_HOST, token=ARVADOS_API_TOKEN, insecure=True) + + qc_metadata(args.metadata.name) + + col = arvados.collection.Collection(api_client=api) + + print("Reading FASTA") + with col.open("sequence.fasta", "w") as f: + r = args.sequence.read(65536) + print(r[0:20]) + while r: + f.write(r) + r = args.sequence.read(65536) + + print("Reading metadata") + with col.open("metadata.yaml", "w") as f: + r = args.metadata.read(65536) + print(r[0:20]) + while r: + f.write(r) + r = args.metadata.read(65536) + + external_ip = urllib.request.urlopen('https://ident.me').read().decode('utf8') + + properties = { + "upload_app": "bh20-seq-uploader", + "upload_ip": external_ip, + "upload_user": "%s@%s" % (getpass.getuser(), socket.gethostname()) + } + + col.save_new(owner_uuid=UPLOAD_PROJECT, name="Uploaded by %s from %s" % + (properties['upload_user'], properties['upload_ip']), + properties=properties, ensure_unique_name=True) + +if __name__ == "__main__": + main() diff --git a/bh20sequploader/qc_metadata.py b/bh20sequploader/qc_metadata.py new file mode 100644 index 0000000..78b31b2 --- /dev/null +++ b/bh20sequploader/qc_metadata.py @@ -0,0 +1,21 @@ +import schema_salad.schema +import logging +import pkg_resources + +def qc_metadata(metadatafile): + schema_resource = pkg_resources.resource_stream(__name__, "bh20seq-schema.yml") + cache = {"https://raw.githubusercontent.com/arvados/bh20-seq-resource/master/bh20sequploader/bh20seq-schema.yml": schema_resource.read().decode("utf-8")} + (document_loader, + avsc_names, + schema_metadata, + metaschema_loader) = schema_salad.schema.load_schema("https://raw.githubusercontent.com/arvados/bh20-seq-resource/master/bh20sequploader/bh20seq-schema.yml", cache=cache) + + if not isinstance(avsc_names, schema_salad.avro.schema.Names): + print(avsc_names) + return False + + try: + doc, metadata = schema_salad.schema.load_and_validate(document_loader, avsc_names, metadatafile, True) + return True + except: + return False |