diff options
Diffstat (limited to 'bh20simplewebuploader')
| -rw-r--r-- | bh20simplewebuploader/api.py | 116 | ||||
| -rw-r--r-- | bh20simplewebuploader/main.py | 26 | ||||
| -rw-r--r-- | bh20simplewebuploader/static/main.css | 1 | ||||
| -rw-r--r-- | bh20simplewebuploader/templates/home.html | 71 |
4 files changed, 161 insertions, 53 deletions
diff --git a/bh20simplewebuploader/api.py b/bh20simplewebuploader/api.py index b1b505f..761ad03 100644 --- a/bh20simplewebuploader/api.py +++ b/bh20simplewebuploader/api.py @@ -3,20 +3,26 @@ import os import requests import sys +import types from flask import Flask, request, redirect, send_file, send_from_directory, render_template, jsonify from bh20simplewebuploader.main import app, sparqlURL +PUBSEQ="http://covid19.genenetwork.org" +ARVADOS="https://collections.lugli.arvadosapi.com/c=" + # Helper functions -def fetch_sample_metadata(id): - query = """ +def fetch_sample(id, query=None): + default_query = """ + PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> PREFIX sio: <http://semanticscience.org/resource/> PREFIX edam: <http://edamontology.org/> PREFIX efo: <http://www.ebi.ac.uk/efo/> PREFIX evs: <http://ncicb.nci.nih.gov/xml/owl/EVS/Thesaurus.owl#> PREFIX obo: <http://purl.obolibrary.org/obo/> + select distinct ?id ?seq ?date ?info ?specimen ?sequencer ?mapper { ?sample sio:SIO_000115 "%s" ; @@ -24,15 +30,49 @@ def fetch_sample_metadata(id): evs:C25164 ?date . ?seq pubseq:technology ?tech ; pubseq:sample ?sample . - ?tech efo:EFO_0002699 ?mapper ; - obo:OBI_0600047 ?sequencer . + optional { ?tech efo:EFO_0002699 ?mapper } . + optional { ?tech obo:OBI_0600047 ?sequencer . } optional { ?sample edam:data_2091 ?info } . optional { ?sample obo:OBI_0001479 ?specimen } . } limit 5 + """ % id + if not query: query = default_query + print(query) payload = {'query': query, 'format': 'json'} r = requests.get(sparqlURL, params=payload) - return r.json()['results']['bindings'] + res = r.json() + print(res) + return res['results']['bindings'],res['head']['vars'] + +def fetch_one_sample(id, query=None): + """Get the top sample and return a SimpleNamespace""" + + result,varlist = fetch_sample(id,query) + h = {} + row = result[0] + for key in varlist: + if key in row: + h[key] = row[key]['value'] + print(h) + h['arv_id'] = os.path.basename(h['seq']) + return types.SimpleNamespace(**h) + +def fetch_one_record(id): + m = fetch_one_sample(id) + arv_id = m.arv_id + rec = { "id": id, + 'arv_id': arv_id, + "permalink": PUBSEQ+'/resource/'+id, + "collection": m.seq, + 'collection_date': m.date, + 'fasta': ARVADOS+arv_id+'/sequence.fasta', + 'metadata': ARVADOS+arv_id+'/metadata.yaml', + } + h = m.__dict__ # for optional items + if 'mapper' in h: rec['mapper'] = m.mapper + if 'sequencer' in h: rec['sequencer']= m.sequencer + return rec # Main API routes @@ -42,54 +82,40 @@ def version(): @app.route('/api/sample/<id>.json') def sample(id): - # metadata = file.name(seq)+"/metadata.yaml" - meta = fetch_sample_metadata(id) - print(meta) - return jsonify([{ - 'id': x['id']['value'], - 'fasta': x['seq']['value'], - 'collection': os.path.dirname(x['seq']['value']), - 'date': x['date']['value'], - 'info': x['info']['value'], - 'specimen': x['specimen']['value'], - 'sequencer': x['sequencer']['value'], - 'mapper': x['mapper']['value'], - } for x in meta]) + """ + +API sample should return a record pointing to other resources, +notably: permalink, original metadata record and the fasta +data. + +curl http://localhost:5067/api/sample/MT533203.1.json +{ + "id": "MT533203.1", + "permalink": "http://covid19.genenetwork.org/resource/MT533203.1", + "collection": "http://covid19.genenetwork.org/resource/lugli-4zz18-uovend31hdwa5ks", + "collection_date": "2020-04-27", + "fasta": "https://collections.lugli.arvadosapi.com/c=lugli-4zz18-uovend31hdwa5ks/sequence.fasta", + "metadata": "https://collections.lugli.arvadosapi.com/c=lugli-4zz18-uovend31hdwa5ks/metadata.yaml", + "mapper": "minimap v. 2.17", + "sequencer": "http://www.ebi.ac.uk/efo/EFO_0008632" +} + +""" + + return jsonify([fetch_one_record(id)]) @app.route('/api/ebi/sample-<id>.xml', methods=['GET']) def ebi_sample(id): - meta = fetch_sample_metadata(id)[0] + meta,varlist = fetch_sample(id)[0] page = render_template('ebi-sample.xml',sampleid=id,sequencer=meta['sequencer']['value'],date=meta['date']['value'],specimen=meta['specimen']['value']) return page @app.route('/api/search', methods=['GET']) def search(): """ - Execute a 'global search' + Execute a 'global search'. Currently just duplicates fetch one + sample. Should be more flexible FIXME. """ s = request.args.get('s') - if s == "": - s = "MT326090.1" - query = """ - PREFIX pubseq: <http://biohackathon.org/bh20-seq-schema#MainSchema/> - PREFIX sio: <http://semanticscience.org/resource/> - PREFIX edam: <http://edamontology.org/> - select distinct ?id ?seq ?info - { - ?sample sio:SIO_000115 "%s" . - ?sample sio:SIO_000115 ?id . - ?seq pubseq:sample ?sample . - ?sample edam:data_2091 ?info . - } limit 100 - """ % s - payload = {'query': query, 'format': 'json'} - r = requests.get(sparqlURL, params=payload) - result = r.json()['results']['bindings'] - # metadata = file.name(seq)+"/metadata.yaml" - print(result) - return jsonify([{ - 'id': x['id']['value'], - 'fasta': x['seq']['value'], - 'collection': os.path.dirname(x['seq']['value']), - 'info': x['info']['value'], - } for x in result]) + if s == "": s = "MT326090.1" + return jsonify([fetch_one_record(s)]) diff --git a/bh20simplewebuploader/main.py b/bh20simplewebuploader/main.py index b620946..504f03c 100644 --- a/bh20simplewebuploader/main.py +++ b/bh20simplewebuploader/main.py @@ -34,6 +34,7 @@ if not os.path.isfile('bh20sequploader/main.py'): print("WARNING: run FLASK from the root of the source repository!", file=sys.stderr) app = Flask(__name__, static_url_path='/static', static_folder='static') +app.config['JSON_SORT_KEYS'] = False # Limit file upload size. We shouldn't be working with anything over 1 MB; these are small genomes. # We will enforce the limit ourselves and set a higher safety limit here. @@ -252,7 +253,7 @@ FORM_ITEMS = load_schema_generate_form() def get_feed_items(name, start=0, stop=9): redis_client = redis.Redis(host=os.environ.get('HOST', 'localhost'), port=os.environ.get('PORT', 6379), - db=os.environ.get('REDIS_DB', 0)) + db=os.environ.get('REDIS_DB', 0)) feed_items = [] try: for el in redis_client.zrevrange(name, start, stop): @@ -272,12 +273,23 @@ def send_home(): """ Send the front page. """ + (tweets, + commits, + pubmed_articles, + arxiv_articles) = [get_feed_items(x) for x in ["bh20-tweet-score:", + "bh20-commit-score:", + "bh20-pubmed-score:", + "bh20-arxiv-score:"]] return render_template( 'home.html', menu='HOME', - tweets=get_feed_items("bh20-tweet-score:"), - commits=get_feed_items("bh20-commit-score:"), - pubmed_articles=get_feed_items("bh20-pubmed-score:"), - arxiv_articles=get_feed_items("bh20-arxiv-score:"), + all_items=list(itertools.chain(tweets, + commits, + pubmed_articles, + arxiv_articles)), + tweets=tweets, + commits=commits, + pubmed_articles=pubmed_articles, + arxiv_articles=arxiv_articles, load_map=True) @@ -750,8 +762,8 @@ union # http://covid19.genenetwork.org/resource/lugli-4zz18-gx0ifousk9yu0ql m = re.match(r"http://collections.lugli.arvadosapi.com/c=([^/]*)/sequence.fasta|http://covid19.genenetwork.org/resource/(.*)", sequenceuri) collection = m.group(1) or m.group(2) - fastauri = f"http://collections.lugli.arvadosapi.com/c={collection}/sequence.fasta" - metauri = f"http://collections.lugli.arvadosapi.com/c={collection}/metadata.yaml" + fastauri = f"https://collections.lugli.arvadosapi.com/c={collection}/sequence.fasta" + metauri = f"https://collections.lugli.arvadosapi.com/c={collection}/metadata.yaml" locationuri=sample['geo']['value'] location=sample['geoname']['value'] date=sample['date']['value'] diff --git a/bh20simplewebuploader/static/main.css b/bh20simplewebuploader/static/main.css index fbc721e..e2f0c83 100644 --- a/bh20simplewebuploader/static/main.css +++ b/bh20simplewebuploader/static/main.css @@ -567,6 +567,7 @@ input[name="feed-tabs"] ~ .tab { display: none; } +#tab-all-items:checked ~ .tab.content-all-items, #tab-pubmed-articles:checked ~ .tab.content-pubmed-articles, #tab-arxiv-articles:checked ~ .tab.content-arxiv-articles, #tab-tweets:checked ~ .tab.content-tweets, diff --git a/bh20simplewebuploader/templates/home.html b/bh20simplewebuploader/templates/home.html index a880f81..23f48bf 100644 --- a/bh20simplewebuploader/templates/home.html +++ b/bh20simplewebuploader/templates/home.html @@ -29,7 +29,9 @@ </div> <div id="feed"> - <input name="feed-tabs" type="radio" id="tab-arxiv-articles" checked/> + <input name="feed-tabs" type="radio" id="tab-all-items" checked/> + <label for="tab-all-items">All Items</label> + <input name="feed-tabs" type="radio" id="tab-arxiv-articles"/> <label for="tab-arxiv-articles">Arxiv</label> <input name="feed-tabs" type="radio" id="tab-pubmed-articles"/> <label for="tab-pubmed-articles">Pubmed</label> @@ -37,6 +39,73 @@ <label for="tab-tweets">Tweets</label> <input name="feed-tabs" type="radio" id="tab-commits"/> <label for="tab-commits">Commits</label> + <ul class="tab content-all-items"> + <!-- Begin News --> + {% if all_items %} + {% for item in all_items|sort(reverse=true, attribute="score")%} + <li> + {% if item['authors'] %} + <!-- Arxiv article --> + <p> + <b>[arxiv]</b> + <a href="{{ item['url'] }}" target="_blank"> + {{item['title']}} + </a> + <br/> + <b>Authors:</b> {{ item['authors'] }} + <br/> + <b>Abstract:</b> {{ item['abstract']}}... + <br/> + <b>Submitted:</b> {{ item['submission']}} + </p> + + {% elif item['full-authors'] %} + <!-- Pubmed Article --> + <p><b>[Pubmed]:</b> + <a href="https://pubmed.ncbi.nlm.nih.gov/{{ item['docsum-pmid'] }}" target="_blank"><b>Summary:</b> + {{ item['summary'] }} + </a> <br/> + <b>Full Authors:</b> {{ item['full-authors'] }} <br/> + <b>Short Authors:</b> {{ item['short-authors'] }} <br/> + <b>Citation:</b> {{ item['citation'] }} <br/> + <b>Short Journal Citation:</b> {{ item['short-journal-citation'] }} <br/> + </p> + + {% elif item['tweet'] %} + <!-- Tweets --> + <p> + <b>[Tweet]:</b> + {{ item['tweet']|urlize(40, target="_blank")}} + <small> + <a href="{{ item['url'] }}" target="_blank">source</a></small> + <br/> + by {{ item['author'] }} + <br/> + <small>{{ item['timeposted'] }}</small> + </p> + + {% elif item['repository-url'] %} + <!-- Commits --> + <p> + <b>[Commit]:</b> + <a href="{{ item.url }}" target="_blank"> + {{ item.hash.split(":")[-1][:7] }}: {{ item.content }} + </a> + <br/> + <small> + <a href="{{ item['repository-url'] }}" target="_blank"> {{ item.author }}/{{ item.repository }}</a> + on {{ item.timeposted }} + </small> + </p> + {% endif %} + </li> + {%endfor%} + + {% else %} + There are no items to display :( + {% endif %} + <!-- End News --> + </ul> <ul class="tab content-arxiv-articles"> {% if arxiv_articles %} {% for article in arxiv_articles|sort(reverse=true, attribute="score")%} |