Skip to content

Commit

Permalink
Pull latest from biomodels; update scripts for newly-revealed problems.
Browse files Browse the repository at this point in the history
Don't include new 1075, since it's not an SBML model, and because the file sizes in it are too large for github.
  • Loading branch information
luciansmith committed Jun 1, 2024
1 parent 5f088be commit 24b8ecb
Show file tree
Hide file tree
Showing 3,462 changed files with 289,213 additions and 49,665 deletions.
The diff you're trying to view is too large. We only load the first 3000 changed files.
5 changes: 5 additions & 0 deletions create_metadata_rdf.py
Original file line number Diff line number Diff line change
Expand Up @@ -49,8 +49,10 @@ def get_uri(self):
"BIOMD0000000456" : NonStandardRef('Smallbone, Kieran. "Metabolic Control Analysis: Rereading Reder." arXiv preprint arXiv:1305.6449 (2013).', "http://arxiv.org/pdf/1305.6449v1.pdf", "Metabolic Control Analysis: Rereading Reder."),
"BIOMD0000000882" : NonStandardRef('Munz, Philip, et al. "When zombies attack!: mathematical modelling of an outbreak of zombie infection." Infectious disease modelling research progress 4 (2009): 133-150.', "http://identifiers.org/isbn/ISBN:1607413477", "When zombies attack!: Mathematical modelling of an outbreak of zombie infection"),
"BIOMD0000001045" : NonStandardRef('Smith, David, and Lang Moore. "The SIR model for spread of disease-the differential equation model." Convergence (2004).', "https://www.maa.org/press/periodicals/loci/joma/the-sir-model-for-spread-of-disease-the-differential-equation-model", "The SIR Model for Spread of Disease - The Differential Equation Model"),
"BIOMD0000001070" : NonStandardRef('Kong, Xiangzhe, Huang, Wenbing, and Yang Liu. "Conditional Antibody Design as 3D Equivariant Graph Translation.", arXiv preprint arXiv:2208.06073 (2022).', "http://identifiers.org/doi/10.48550/arXiv.2208.06073", "Conditional Antibody Design as 3D Equivariant Graph Translation."),
}


def parseDocAndAddToMetadata(filename, metadata, master, pubmedIDs, doiIDs):
doc = libsbml.readSBMLFromFile(filename)
model = doc.getModel()
Expand Down Expand Up @@ -89,6 +91,9 @@ def addCitationsToMetadata(pubmedIDs, doiIDs, masterID, metadata, id, temp_entry
mastercitation = get_reference(doi=doivec[-1])
else:
mastercitation = no_pubmed_or_doi[id]
if not mastercitation:
mastercitation = no_pubmed_or_doi[id]


for pmid in pubmedIDs:
citation = get_reference(pubmed_id=pmid)
Expand Down
45 changes: 25 additions & 20 deletions fix_sbml_validity.py
Original file line number Diff line number Diff line change
Expand Up @@ -264,6 +264,7 @@ def fixIdentifiersNS(file, oldns, id):
"uniprot/GO:0005893": "go/GO:0005893",
"uniprot/PR:000050007": "pr/PR:000050007",
"unists/P00734": "uniprot/P00734",
"org/GO:": "org/go/GO:",
}

def fixURI(uri):
Expand All @@ -285,6 +286,8 @@ def retestAllIdentifiersURIs(file):
if "identifiers.org" in word:
for charstr in word.split('"'):
if "identifiers.org" in charstr:
if "org/GO:" in charstr:
bad_uris.append((file, charstr, "Missing 'go/'"))
# if "omim" in charstr:
# continue
# if "psimi" in charstr:
Expand Down Expand Up @@ -377,28 +380,30 @@ def run(id, sbml_files):
for charstr in word.split('"'):
if "identifiers.org" in charstr:
charvec = charstr.strip("'>/").split("/")
# print(charvec)
for n in range(len(charvec)):
if charvec[n] == "identifiers.org":
pmid = charvec[n+2]
if charvec[n+1] not in VALID_IDENTIFIERS_NAMESPACES:
# if checkAndAddIdentifiersNamespace(charvec[n+1]):
bad_identifiers_ns.add(charvec[n+1])
assert charvec[n-1] == ""
assert "http" in charvec[n-2]
if charvec[n+1] == "pubmed" and pmid not in good_pmids and pmid not in bad_pmids:
assert(len(pmid)>0)
url = "https://pubmed.ncbi.nlm.nih.gov/" + pmid
try:
if "+" in pmid:
#These make valid URLs, but are invalid URIs: they don't fit the pubmed id pattern.
bad_pmids.add(pmid)
elif urllib.request.urlopen(url).getcode() > 400:
bad_pmids.add(pmid)
else:
good_pmids.add(pmid)
pmids_changed = True
except:
bad_pmids.add(pmid)
if len(charvec) > n+2:
pmid = charvec[n+2]
if charvec[n+1] not in VALID_IDENTIFIERS_NAMESPACES:
# if checkAndAddIdentifiersNamespace(charvec[n+1]):
bad_identifiers_ns.add(charvec[n+1])
assert charvec[n-1] == ""
assert "http" in charvec[n-2]
if charvec[n+1] == "pubmed" and pmid not in good_pmids and pmid not in bad_pmids:
assert(len(pmid)>0)
url = "https://pubmed.ncbi.nlm.nih.gov/" + pmid
try:
if "+" in pmid:
#These make valid URLs, but are invalid URIs: they don't fit the pubmed id pattern.
bad_pmids.add(pmid)
elif urllib.request.urlopen(url).getcode() > 400:
bad_pmids.add(pmid)
else:
good_pmids.add(pmid)
pmids_changed = True
except:
bad_pmids.add(pmid)
f.close()
if pmids_changed:
gp_file = open("good_pmids.p", "wb")
Expand Down
26 changes: 13 additions & 13 deletions manual-fixes/BIOMD0000000001/manifest.xml
Original file line number Diff line number Diff line change
@@ -1,19 +1,19 @@
<?xml version="1.0" encoding="UTF-8"?>
<omexManifest xmlns="http://identifiers.org/combine.specifications/omex-manifest">
<content location="." format="https://identifiers.org/combine.specifications/omex" master="false"/>
<content location="./BIOMD0000000001-biopax2.owl" format="https://identifiers.org/combine.specifications/biopax.level-2" master="false"/>
<content location="./BIOMD0000000001-biopax3.owl" format="https://identifiers.org/combine.specifications/biopax.level-3" master="false"/>
<content location="./BIOMD0000000001.m" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000001.pdf" format="https://purl.org/NET/mediatypes/application/pdf" master="false"/>
<content location="./BIOMD0000000001.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="./BIOMD0000000001.sci" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000001.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000001.vcml" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000001.xpp" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000001_manual.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="./BIOMD0000000001_manual.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000001_url.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="true"/>
<content location="./BIOMD0000000001_urn.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="false"/>
<content location="./manifest.xml" format="https://identifiers.org/combine.specifications/omex-manifest" master="false"/>
<content location="./metadata.rdf" format="https://identifiers.org/combine.specifications/omex-metadata" master="false"/>
<content location="BIOMD0000000001-biopax2.owl" format="https://identifiers.org/combine.specifications/biopax.level-2" master="false"/>
<content location="BIOMD0000000001-biopax3.owl" format="https://identifiers.org/combine.specifications/biopax.level-3" master="false"/>
<content location="BIOMD0000000001.m" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000001.pdf" format="https://purl.org/NET/mediatypes/application/pdf" master="false"/>
<content location="BIOMD0000000001.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="BIOMD0000000001.sci" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000001.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000001.vcml" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000001.xpp" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000001_manual.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="BIOMD0000000001_manual.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000001_url.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="true"/>
<content location="BIOMD0000000001_urn.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="false"/>
</omexManifest>
26 changes: 13 additions & 13 deletions manual-fixes/BIOMD0000000002/manifest.xml
Original file line number Diff line number Diff line change
@@ -1,19 +1,19 @@
<?xml version="1.0" encoding="UTF-8"?>
<omexManifest xmlns="http://identifiers.org/combine.specifications/omex-manifest">
<content location="." format="https://identifiers.org/combine.specifications/omex" master="false"/>
<content location="./BIOMD0000000002-biopax2.owl" format="https://identifiers.org/combine.specifications/biopax.level-2" master="false"/>
<content location="./BIOMD0000000002-biopax3.owl" format="https://identifiers.org/combine.specifications/biopax.level-3" master="false"/>
<content location="./BIOMD0000000002.m" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000002.pdf" format="https://purl.org/NET/mediatypes/application/pdf" master="false"/>
<content location="./BIOMD0000000002.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="./BIOMD0000000002.sci" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000002.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000002.vcml" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000002.xpp" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000002_manual.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="./BIOMD0000000002_manual.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000002_url.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="true"/>
<content location="./BIOMD0000000002_urn.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="false"/>
<content location="./manifest.xml" format="https://identifiers.org/combine.specifications/omex-manifest" master="false"/>
<content location="./metadata.rdf" format="https://identifiers.org/combine.specifications/omex-metadata" master="false"/>
<content location="BIOMD0000000002-biopax2.owl" format="https://identifiers.org/combine.specifications/biopax.level-2" master="false"/>
<content location="BIOMD0000000002-biopax3.owl" format="https://identifiers.org/combine.specifications/biopax.level-3" master="false"/>
<content location="BIOMD0000000002.m" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000002.pdf" format="https://purl.org/NET/mediatypes/application/pdf" master="false"/>
<content location="BIOMD0000000002.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="BIOMD0000000002.sci" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000002.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000002.vcml" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000002.xpp" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000002_manual.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="BIOMD0000000002_manual.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000002_url.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="true"/>
<content location="BIOMD0000000002_urn.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="false"/>
</omexManifest>
26 changes: 13 additions & 13 deletions manual-fixes/BIOMD0000000003/manifest.xml
Original file line number Diff line number Diff line change
@@ -1,19 +1,19 @@
<?xml version="1.0" encoding="UTF-8"?>
<omexManifest xmlns="http://identifiers.org/combine.specifications/omex-manifest">
<content location="." format="https://identifiers.org/combine.specifications/omex" master="false"/>
<content location="./BIOMD0000000003-biopax2.owl" format="https://identifiers.org/combine.specifications/biopax.level-2" master="false"/>
<content location="./BIOMD0000000003-biopax3.owl" format="https://identifiers.org/combine.specifications/biopax.level-3" master="false"/>
<content location="./BIOMD0000000003.m" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000003.pdf" format="https://purl.org/NET/mediatypes/application/pdf" master="false"/>
<content location="./BIOMD0000000003.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="./BIOMD0000000003.sci" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000003.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000003.vcml" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000003.xpp" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="./BIOMD0000000003_manual.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="./BIOMD0000000003_manual.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="./BIOMD0000000003_url.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="true"/>
<content location="./BIOMD0000000003_urn.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="false"/>
<content location="./manifest.xml" format="https://identifiers.org/combine.specifications/omex-manifest" master="false"/>
<content location="./metadata.rdf" format="https://identifiers.org/combine.specifications/omex-metadata" master="false"/>
<content location="BIOMD0000000003-biopax2.owl" format="https://identifiers.org/combine.specifications/biopax.level-2" master="false"/>
<content location="BIOMD0000000003-biopax3.owl" format="https://identifiers.org/combine.specifications/biopax.level-3" master="false"/>
<content location="BIOMD0000000003.m" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000003.pdf" format="https://purl.org/NET/mediatypes/application/pdf" master="false"/>
<content location="BIOMD0000000003.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="BIOMD0000000003.sci" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000003.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000003.vcml" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000003.xpp" format="https://purl.org/NET/mediatypes/application/x.unknown" master="false"/>
<content location="BIOMD0000000003_manual.png" format="https://purl.org/NET/mediatypes/image/png" master="false"/>
<content location="BIOMD0000000003_manual.svg" format="https://purl.org/NET/mediatypes/application/xml" master="false"/>
<content location="BIOMD0000000003_url.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="true"/>
<content location="BIOMD0000000003_urn.xml" format="https://identifiers.org/combine.specifications/sbml.level-2.version-4" master="false"/>
</omexManifest>
Loading

0 comments on commit 24b8ecb

Please sign in to comment.