"<a href=\"https://www.ncbi.nlm.nih.gov/pubmed/" + lid
+ "\">" + lid + "</a>"
if not lid.startswith('PMC') else
"<a href=\"https://www.ncbi.nlm.nih.gov/pmc/articles/"
+ lid + "\">" + lid + "</a>")),
'MIRECORD':
", ".join(
makeLinks(
mirecordEvs, lambda lid:
"<a href=\"https://www.ncbi.nlm.nih.gov/pubmed/" + lid
+ "\">" + lid + "</a>")),
'MIRTARBASE':
", ".join(mirtarbaseEvs),
'MIRWALK':
", ".join(mirwalkEvs)
}
row = DataRow.fromDict(addRow)
linkedDF.addRow(row)
print("Total Additional miRNAs", totalAdditional)
missingDF.export(
"/mnt/c/ownCloud/data/miRExplore/overview_no_mirwalk_sase.xlsx",
ExportTYPE.XLSX)
linkedDF.export(
"/mnt/c/ownCloud/data/miRExplore/overview_no_mirwalk_sase.html",
ExportTYPE.HTML)
#CytoscapeGrapher.showGraph(graph, location=dirTemp, name='chemokines', title='Chemokines', nodeLabel=lambda x: x, edgeLabel=lambda x: '')
'population_size': populationSize,
'success_population': numSuccInPopulation,
'sample_size': sampleSize,
'success_samples': drawnSuccesses,
'pval': pval,
'sample_success_fraction': fractionOfHitSamples,
'genes': ";".join(successIntersection),
'direction': direction
}
setToResult[setElem] = resultObj
sortedElems = [x for x in setToResult]
elemPvals = [setToResult[x]["pval"] for x in sortedElems]
rej, elemAdjPvals, _, _ = multipletests(elemPvals,
alpha=0.05,
method='fdr_bh',
is_sorted=False,
returnsorted=False)
for eidx, elem in enumerate(sortedElems):
assert (setToResult[elem]['pval'] == elemPvals[eidx])
setToResult[elem]['adj_pval'] = elemAdjPvals[eidx]
for elem in sortedElems:
dr = DataRow.fromDict(setToResult[elem])
outdf.addRow(dr)
outdf.export(args.output.name)
if args.fpkm:
#print(curGeneID, geneLength)
fpkmValue = row[sample] / (sample2total[sample] *
geneLength) * pow(10, 9)
rowDict[sample + ".FPKM"] = fpkmValue
if args.tpm:
tpmValue = row[sample] / (geneLength *
sample2ratio[sample]) * pow(10, 6)
rowDict[sample + ".TPM"] = tpmValue
allRowUpdates.append(rowDict)
allCols = set()
for x in allRowUpdates:
for y in x:
if not y in featureCountsColumns:
allCols.add(y)
outdf.addColumns(featureCountsColumns)
outdf.addColumns(sorted(allCols), default=0, ignoreDuplicates=True)
outdf.updateRowIndexed("Geneid",
allRowUpdates,
ignoreMissingCols=True,
addIfNotFound=True)
outdf.export(args.output.name, exType=ExportTYPE.TSV)
data[x] = row[x]
for x in df1Col2New:
data[df1Col2New[x]] = row[x]
id2dataDf[data["id"]] = data
for row in indf2:
data = id2dataDf.get(row["id"], {})
for x in df12CommonCols:
data[x] = row[x]
for x in df2UniqueCols + df2SampleCols:
if args.prefix_counts:
data[args.prefix2 + "_" + x] = row[x]
else:
data[x] = row[x]
for x in df2Col2New:
data[df2Col2New[x]] = row[x]
allRowUpdates = [id2dataDf[x] for x in sorted([y for y in id2dataDf])]
outdf.updateRowIndexed("id",
allRowUpdates,
ignoreMissingCols=True,
addIfNotFound=True)
outdf.export(args.output.name, ExportTYPE.TSV)
dataDict = {
'SET':
'NTinflamm',
'PMID_ID':
"<a href='https://www.ncbi.nlm.nih.gov/pubmed/" + str(x) +
"' target='_blank'>" + str(x) + "</a>",
'PMID_TITLE':
pmidt[x],
'Common':
x in ntd
}
res.addRow(DataRow.fromDict(dataDict))
print(x, pmidt[x])
res.export("/home/mjoppich/win/Desktop/soehnlein_overview.html",
ExportTYPE.HTML)
with open('/home/mjoppich/win/Desktop/soehnlein.svg', 'w') as f:
f.write(
render_four_set_venn(allelems['NEUTROPHIL'],
allelems['TISSUES'],
allelems['DOID'],
allelems['INFLAMM'],
titles={
'A': 'NEUTROPHIL',
'B': 'TISSUES',
'C': 'Infection',
'D': 'Inflammation'
}))
", ".join(
makeLinks(
sorted([
x[1] for x in findEdgeInfo(x, interact, ['PUBMED'])
]), lambda lid:
"<a href=\"https://www.ncbi.nlm.nih.gov/pubmed/" + lid
+ "\">" + lid + "</a>")),
'MIRTARBASE':
", ".join(
makeLinks(
sorted([
x[1]
for x in findEdgeInfo(x, interact, ['MIRTARBASE'])
]), lambda lid:
"<a href=\"http://mirtarbase.mbc.nctu.edu.tw/php/search.php?opt=search_box&kw="
+ x + "&sort=id\">" + lid + "</a>"))
}
row = DataRow.fromDict(addRow)
linkedDF.addRow(row)
print("Total Missing miRNAs", totalMissing)
print("Total Additional miRNAs", totalAdditional)
missingDF.export("/mnt/c/ownCloud/data/miRExplore/overview_weber.xlsx",
ExportTYPE.XLSX)
linkedDF.export("/mnt/c/ownCloud/data/miRExplore/overview_weber.html",
ExportTYPE.HTML)
#CytoscapeGrapher.showGraph(graph, location=dirTemp, name='chemokines', title='Chemokines', nodeLabel=lambda x: x, edgeLabel=lambda x: '')
print(
"Gene:", gene, "Status: ", ", ".join([
": ".join([x, str(typeByGene[gene][x])])
for x in typeByGene[gene]
]), "Missing miRNAs: " +
",".join(elemsByGene[gene]['missing']))
print()
print()
print()
print()
networkGraphs[network] = networkGraph
htmlDF.export(
"/mnt/d/yanc_network/" + network.replace(" ", "_") + ".html",
ExportTYPE.HTML)
htmlDF.export(
"/mnt/d/yanc_network/" + network.replace(" ", "_") + ".tsv",
ExportTYPE.TSV)
figidx = 0
for stages in makeStory:
mergedGraph = networkGraphs[stages[0]]
for i in range(1, len(stages)):
mergedGraph = nx.compose(mergedGraph, networkGraphs[stages[i]])
hasLargeStage = any(['large' in stage for stage in stages])
for cells in cells2mirnas:
ncells = []
for cell in cells:
ncells.append( ""+cell+"}" )
rowdict = {
'miRNA': "\\makecell[l]{" + "\\\\".join(sorted(cells2mirnas[cells])) + "}",
'cells': "\\makecell[l]{" + "\\\\".join(cells) + "}"
}
cellCommunicatorDF.addRow(DataRow.fromDict(rowdict))
cellCommunicatorDF.export("/mnt/d/yanc_network/stage_cells_cliques"+stage+".latex", ExportTYPE.LATEX)
cellCommunicatorDF.export("/mnt/d/yanc_network/stage_cells_cliques"+stage+".tsv", ExportTYPE.TSV)
CytoscapeGrapher.showGraph(cellgraph, '/mnt/d/yanc_network/', name="stage_cells_" + stage)
figidx = CytoscapeGrapher.plotNXGraph(cellgraph, stage, ["/mnt/d/yanc_network/stage_cells_" + stage.replace(" ", "_") + ".png", "/mnt/d/yanc_network/stage_cells_" + stage.replace(" ", "_") + ".pdf"], figidx)
print()
print()
print()
print()
print()
plotKeys = []
plotValues = []
for (cell, count) in cellCounter.most_common(20):
rowdict = {'sample': org}
for homid in targetHOMIDS:
homID = homid
val = homDB.get_cluster(homID)
if org in val:
rowdict[homID] = 1
else:
rowdict[homID] = 0
dfrow = DataRow.fromDict(rowdict)
df.addRow(dfrow)
df.export(outFile=None)
print(allorgs)
print(len(homClusterIDs))
if len(homClusterIDs) < 10:
print(homClusterIDs)
orgMatrix = {}
for org in mc + nmc:
orgRes = []
for homID in homClusterIDs:
val = org in homDB.get_homology_cluster(homID)