def addLineToReturn(lineData):
modLine = {}
for c, x in zip(dfCols, lineData):
if x == '':
modLine[c] = None
else:
modLine[c] = x
convData.addRow(DataRow.fromDict(modLine))
def dfSummary(cls, thisObservation, mc=10):
df = DataFrame()
madeObs = cls.summarizeKmers(thisObservation, mc)
for idx, obs in enumerate(madeObs):
if idx == 0: # header
cols = [x for x in obs]
df.addColumns(cols)
dfrow = DataRow.fromDict(obs)
df.addRow(dfrow)
return df
'elem_id': setElem,
'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)
"<a href=\"https://www.ncbi.nlm.nih.gov/pubmed/?term=" + x +
"+" +
mirna.getStringFromParts([miRNAPART.MATURE, miRNAPART.ID]) +
"\">Search PUBMED</a>"
"</br><a href=\"" + dianaLink + "\">Search DIANA</a>",
'PubMed':
"",
'MIRECORD':
'',
'MIRTARBASE':
"",
'MIRWALK':
""
}
row = DataRow.fromDict(addRow)
missingDF.addRow(row)
linkedDF.addRow(row)
print("Total Missing miRNAs", totalMissing)
def makeLinks(mylist, lnkFnc):
return [lnkFnc(x) for x in mylist]
print("Accepted miRNAs")
for x in foundAcceptedInteractions:
geneCap = x.upper()
geneLow = x.lower()
pmidt = getPMIDTitles(ntd)
for x in sorted([x for x in pmidt]):
dataDict = {
'SET':
'NTinfect',
'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 ntg
}
res.addRow(DataRow.fromDict(dataDict))
print(x, pmidt[x])
print("\n\n\n\n\n")
print(ntg)
print("NTG", len(ntg))
pmidt = getPMIDTitles(ntg)
for x in sorted([x for x in pmidt]):
dataDict = {
'SET':
'NTinflamm',
'PMID_ID':
"<a href='https://www.ncbi.nlm.nih.gov/pubmed/" + str(x) +
"' target='_blank'>" + str(x) + "</a>",
sample2stats = makeplot(sample2genecount, defile.name, sample2stats,
args.output[fidx])
columns = list()
for sample in sample2stats:
for x in sample2stats[sample]:
if not x in columns:
columns.append(x)
outdf = DataFrame()
outdf.addColumns(columns)
for sample in sample2stats:
dr = DataRow.fromDict(sample2stats[sample])
outdf.addRow(dr)
print(outdf)
if dfGroups != None:
allGenes = set()
for sample in sample2genecount:
for x in sample2genecount[sample]:
allGenes.add(x[0])
for group in dfGroups:
for gm in group:
if not gm in sample2genecount:
print([x for x in sample2genecount])
for pset in allPowerSets:
if len(pset) == 0:
continue
setPMIDs = set([x for x in allPMIDs])
for dim in pset:
setPMIDs = setPMIDs.intersection( dbs2pmids[dim] )
print(pset, len(setPMIDs))
drdict = {
"Subset": ", ".join(pset),
"Number of PMIDs": len(setPMIDs)
}
dr = DataRow.fromDict(drdict)
outdf.addRow(dr)
print(outdf._makeLatex())
cellElems.append(elem['name'] + " (" + elem['termid'] +
")")
else:
for elem in restricts[restrictType]:
otherElems.append(elem['name'] + " (" + elem['termid'] +
")")
networkDRdict['Cells'] = "\makecell[l]{" + "\\\\".join(
sorted(cellElems)) + "}"
networkDRdict['Disease'] = "\makecell[l]{" + "\\\\".join(
sorted(diseaseElems)) + "}"
networkDRdict['Other'] = "\makecell[l]{" + "\\\\".join(
sorted(otherElems)) + "}"
dr = DataRow.fromDict(networkDRdict)
restrictDF.addRow(dr)
print(restrictDF._makeLatex())
#exit()
allMissing = {}
figidx = 0
mirna2cellOut = open("/mnt/d/yanc_network/important_process.txt", 'w')
for network in networks:
figidx += 1
networkGraph = nx.Graph()
cellElems.append(elem['name'] + " (" + elem['termid'] +
")")
else:
for elem in restricts[restrictType]:
otherElems.append(elem['name'] + " (" + elem['termid'] +
")")
networkDRdict['Cells'] = "\makecell[l]{" + "\\\\".join(
sorted(cellElems)) + "}"
networkDRdict['Disease'] = "\makecell[l]{" + "\\\\".join(
sorted(diseaseElems)) + "}"
networkDRdict['Other'] = "\makecell[l]{" + "\\\\".join(
sorted(otherElems)) + "}"
dr = DataRow.fromDict(networkDRdict)
restrictDF.addRow(dr)
print(restrictDF._makeLatex())
mirna2cellOut = open("/mnt/d/yanc_network/important_networks.txt", 'w')
def acceptEvidence(ev):
return True
figidx = 0
for network in networks:
figidx += 1
cells = tuple(sorted(mirna2cells[mirna]))
cells2mirnas[cells].add(mirna)
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()
for org in mc + nmc:
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 = []