comparison Tryp_V_T.py @ 21:1b5bf8383973 draft

Uploaded

20:26ec953069b3

    return  #we have saved out the relevent name.bam, name.sorted and name.sorted.bai files

# we will not have the .gtf file so call cufflinks without -G option
def transcriptAbundance(inputname):
    argString = "cufflinks -o "+inputname+".cuff -u -p 8 "+inputname+".sorted"
    subprocess.call(argString, shell = True)
    os.remove(inputname+".sorted")  #remove name.sorted
    os.remove(inputname+".sorted.bai")
    os.remove(inputname+".bam")
    return

    refBase = os.path.basename(refFastq)
    ref = os.path.splitext(refBase)[0]  # 'mydata/test.fasta' -> 'test'
    dir_path = os.path.dirname(os.path.realpath(__file__))  # directory of this file
    refPath = dir_path + "/data/Reference/" + ref + "/" + refBase   # eg refPath = data/Reference/Trinity/Trinity.fasta
    # used for dirty # refPath = 'Trinity.fasta' # dirty one
    track_df = pd.read_csv(name+'.cuff/genes.fpkm_tracking', sep='\t')
    names = track_df['locus']
    # print(len(names))
    # print(names[:5])

    nlist = []

def getPhyloNumber(sac):
    i = sac.find('_')
    return int(sac[1:i])

def combineFPMK(tdict):
    fpkm_df = pd.read_csv(tdict['name']+'.cuff/genes.fpkm_tracking', sep='\t')

    #fpkm_df = pd.read_csv('genes.fpkm_tracking',sep='\t')
    #print(fpkm_df.head())
    fpkm_df['locus'] = fpkm_df['locus'].apply(lambda names: names[:names.find(':')])
    #print(fpkm_df.head())
    reducedBlast_df = pd.read_csv(tdict['name']+'_transcript.csv')
    # reducedBlast_df = pd.read_csv('TrinityVT_transcript.csv')
    saccverSet = set(reducedBlast_df['saccver'])
    saccverList = list(saccverSet)
    saccverList.sort()
    # print(saccverList[:5])

    pass

# argdict = {'name':2, 'pdfexport': 3, 'refFastq': 4, 'forward': 5, 'reverse': 6, 'html_file': 7, 'html_resource': 8}

def transcriptomicProcess(args,argdict):
    tdict = {}
    tdict['name'] = args[argdict['name']]
    tdict['refFastq'] = args[argdict['refFastq']]
    tdict['forward'] = args[argdict['forward']]
    tdict['reverse'] = args[argdict['reverse']]
    tdict['vivax_trans_database'] = 'data/vivax/Database/Phylotype_typeseqs.fas'
    tdict['pdf'] = args[argdict['pdfexport']]
    tdict['html_file'] = args[argdict['html_file']]
    tdict['html_resource'] = args[argdict['html_resource']]
    
    uploadUserReferenceFastq(tdict['refFastq'])
    transcriptMapping(tdict['name'], tdict['refFastq'], tdict['forward'], tdict['reverse'])        #uses bowtie
    processSamFiles(tdict['name'])                              #uses samtools
    transcriptAbundance(tdict['name'])                          #uses cufflinks -> ?.cuff/*.*
    transcriptsForBlast(tdict['name'], tdict['refFastq'])       #creates name+4blast.fa
    blastContigs(tdict['name'], tdict['html_resource'], 'data/vivax/Database/Phylotype_typeseqs.fas')
    sum_df, sum2_df = combineFPMK(tdict)
    doBarChart(tdict, sum2_df)
    createHTML(tdict, sum_df)

21:1b5bf8383973

    return  #we have saved out the relevent name.bam, name.sorted and name.sorted.bai files

# we will not have the .gtf file so call cufflinks without -G option
def transcriptAbundance(inputname):
    argString = "cufflinks -o "+inputname+".cuff -u -p 8 "+inputname+".sorted"
    subprocess.call(argString, shell=True)
    os.remove(inputname+".sorted")  #remove name.sorted
    os.remove(inputname+".sorted.bai")
    os.remove(inputname+".bam")
    return

    refBase = os.path.basename(refFastq)
    ref = os.path.splitext(refBase)[0]  # 'mydata/test.fasta' -> 'test'
    dir_path = os.path.dirname(os.path.realpath(__file__))  # directory of this file
    refPath = dir_path + "/data/Reference/" + ref + "/" + refBase   # eg refPath = data/Reference/Trinity/Trinity.fasta
    # used for dirty # refPath = 'Trinity.fasta' # dirty one
    track_df = pd.read_csv(dir_path+'/' + name + '.cuff/genes.fpkm_tracking', sep='\t')
    names = track_df['locus']
    # print(len(names))
    # print(names[:5])

    nlist = []

def getPhyloNumber(sac):
    i = sac.find('_')
    return int(sac[1:i])

def combineFPMK(tdict):
    dir_path = os.path.dirname(os.path.realpath(__file__))+'/'

    fpkm_df = pd.read_csv(dir_path++tdict['name']+'.cuff/genes.fpkm_tracking', sep='\t')

    #fpkm_df = pd.read_csv('genes.fpkm_tracking',sep='\t')
    #print(fpkm_df.head())
    fpkm_df['locus'] = fpkm_df['locus'].apply(lambda names: names[:names.find(':')])
    #print(fpkm_df.head())

    reducedBlast_df = pd.read_csv(dir_path + tdict['name']+'_transcript.csv')
    # reducedBlast_df = pd.read_csv('TrinityVT_transcript.csv')
    saccverSet = set(reducedBlast_df['saccver'])
    saccverList = list(saccverSet)
    saccverList.sort()
    # print(saccverList[:5])

    pass

# argdict = {'name':2, 'pdfexport': 3, 'refFastq': 4, 'forward': 5, 'reverse': 6, 'html_file': 7, 'html_resource': 8}

def transcriptomicProcess(args,argdict):
    dir_path = os.path.dirname(os.path.realpath(__file__))
    tdict = {}
    tdict['name'] = args[argdict['name']]
    tdict['refFastq'] = args[argdict['refFastq']]
    tdict['forward'] = args[argdict['forward']]
    tdict['reverse'] = args[argdict['reverse']]
    dir_path = os.path.dirname(os.path.realpath(__file__))
    tdict['vivax_trans_database'] = dir_path+'/data/vivax/Database/Phylotype_typeseqs.fas'
    tdict['pdf'] = args[argdict['pdfexport']]
    tdict['html_file'] = args[argdict['html_file']]
    tdict['html_resource'] = args[argdict['html_resource']]
    
    uploadUserReferenceFastq(tdict['refFastq'])
    transcriptMapping(tdict['name'], tdict['refFastq'], tdict['forward'], tdict['reverse'])        #uses bowtie
    processSamFiles(tdict['name'])                              #uses samtools
    transcriptAbundance(tdict['name'])                          #uses cufflinks -> ?.cuff/*.*
    transcriptsForBlast(tdict['name'], tdict['refFastq'])       #creates name+4blast.fa
    blastContigs(tdict['name'], tdict['html_resource'], tdict['vivax_trans_database'])
    sum_df, sum2_df = combineFPMK(tdict)
    doBarChart(tdict, sum2_df)
    createHTML(tdict, sum_df)