comparison Tryp_G.py @ 3:4432e4183ebd draft

planemo upload for repository https://github.com/johnheap/VAPPER-Galaxy

2:82770f07a036

def contigTranslation(name):
    argString = "transeq " + name + ".fa " + name + "_6frame.fas -frame=6 " #+quietString
    print(argString)
    returncode = subprocess.call(argString, shell=True)
    #subprocess.call('ls -l *.fa', shell = True)
    #sys.exit(1)
    #if returncode != 0:
    #    return "Error in Transeq"
    #return 'ok'


def HMMerMotifSearch(name):
    motifs = ['1', '2a', '2b', '3', '4a', '4b', '4c', '5', '6', '7', '8a', '8b', '9a', '9b',
              '9c', '10a', '10b', '11a', '11b', '12', '13a', '13b', '13c', '13d', '14', '15a', '15b', '15c']

    countList.append(totalCount)
    #print(countList)
    #print("--------")
    return countList

"""
def HMMerMotifSearch(name):
    motifs = ['1', '2a', '2b', '3', '4a', '4b', '4c', '5', '6', '7', '8a', '8b', '9a', '9b',
              '9c', '10a', '10b', '11a', '11b', '12', '13a', '13b', '13c', '13d', '14', '15a', '15b', '15c']
    lineCounts = []
    compoundList = []
    dir_path = os.path.dirname(os.path.realpath(__file__))
    phylopath = dir_path+"/data/Motifs/Phylotype"
    for m in motifs:
        argString = "hmmsearch "+phylopath + m + ".hmm " + name + "_6frame.fas > Phy" + m + ".out"  #+quietString
        #argString = "hmmsearch "+phylopath + m + ".hmm " + dir_path+"/data/Test_6frame.fas > Phy" + m + ".out"
        print(argString)
        subprocess.call(argString, shell=True)

        hmmResult = open("Phy" + m + ".out", 'r')
        tempout = open(dir_path+"/data/"+"Phy" + m + ".txt", 'w')
        regex = r"NODE_[0-9]{1,7}_length_[0-9]{1,7}_cov_[0-9]{1,10}.[0-9]{1,7}_[0-9]{1,2}"
        n = 0
        outList = []
        for line in hmmResult:
            m = re.search(regex, line)
            if m:
                tempout.write(m.group() + "\n")
                outList.append(""+m.group()+"\n")
                n += 1
            if re.search(r"inclusion", line):
                print("inclusion threshold reached")
                break
        compoundList.append(outList)
        lineCounts.append(n)
        hmmResult.close()
        #tempout.close()
    print(lineCounts)
    motifGroups = [['1'], ['2a', '2b'], ['3'], ['4a', '4b', '4c'], ['5'], ['6'], ['7'], ['8a', '8b'], ['9a', '9b',
                                                                                                   '9c'],
               ['10a', '10b'], ['11a', '11b'], ['12'], ['13a', '13b', '13c', '13d'], ['14'], ['15a', '15b', '15c']]
    concatGroups = [1, 2, 1, 3, 1, 1, 1, 2, 3, 2, 2, 1, 4, 1, 3]
    countList = []
    countIndex = 0
    totalCount = 0

    for c in concatGroups:
        a = []
        for n in range(0, c):
            a = a + compoundList.pop(0)
        t = set(a)
        countList.append(len(t))
        totalCount += len(t)
    countList.append(totalCount)
    print(countList)
    print("--------")
    return countList
"""



def relativeFrequencyTable(countList, name, htmlresource):
    relFreqList = []
    c = float(countList[15])

    j_fname = dir_path+"/data/congodata.csv"
    #print(dir_path)
    congo_df = pd.read_csv(j_fname)
    congo_df.drop('Colour', axis=1, inplace=True)
    congo_df.loc[congo_df.index.max() + 1] = localFreqList
    congo_df.set_index('Strain', inplace=True)

    cg = sns.clustermap(congo_df, method='ward', cmap = "RdBu_r", col_cluster=False, yticklabels = congo_df.index.values)
    plt.setp(cg.ax_heatmap.yaxis.get_ticklabels(), rotation=0, fontsize=8)  # get y labels printed horizontally
    ax=cg.ax_heatmap
    title = "Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$ estimated as the phylotype proportion across the\nsample cohort. "
    title += "Dendrogram reflects the relationships amongst the VSG repertoires of each strain. "
    title += "Strains\nwere isolated from multiple African countries as described in Silva Pereira et al. (2018)."

    j_fname = dir_path+ "/data/congodata_deviationfromthemean.csv"
    #j_fname = r"data/congodata_deviationfromthemean.csv"
    congo_df = pd.read_csv(j_fname)
    congo_df.drop('Colour', axis=1, inplace=True)
    congo_df.loc[congo_df.index.max() + 1] = localDevList
    congo_df.set_index('Strain', inplace=True)
    cg = sns.clustermap(congo_df, method='ward',cmap = "RdBu_r", col_cluster=False, yticklabels = congo_df.index.values)
    plt.setp(cg.ax_heatmap.yaxis.get_majorticklabels(), rotation=0, fontsize=8)  # get y labels printed horizontally
    ax = cg.ax_heatmap
    title = "Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$ expressed as the deviation from the mean phylotypes "
    title +="\nproportions of the sample cohort. Dendrogram reflects the relationships amongst the VSG repertoires of "
    title +="each \nstrain. Strains were isolated from multiple African countries as described in Silva Pereira et al. (2018)."

    for item in pcaResult.Y:
        col = myCountries.index(myColours[i])
        compoundList[col].append(-item[0])
        compoundList[col].append(item[1])
        i = i + 1
    cols = ['r', 'g', 'b', 'c', 'm', 'y', 'grey', 'k']

    fig, ax = plt.subplots(figsize=(9, 6))
    #plt.figure(num=1,figsize=(12, 6))
    i = 0
    for d in myCountries:
        a = compoundList[i]

3:4432e4183ebd

def contigTranslation(name):
    argString = "transeq " + name + ".fa " + name + "_6frame.fas -frame=6 " #+quietString
    print(argString)
    returncode = subprocess.call(argString, shell=True)


def HMMerMotifSearch(name):
    motifs = ['1', '2a', '2b', '3', '4a', '4b', '4c', '5', '6', '7', '8a', '8b', '9a', '9b',
              '9c', '10a', '10b', '11a', '11b', '12', '13a', '13b', '13c', '13d', '14', '15a', '15b', '15c']

    countList.append(totalCount)
    #print(countList)
    #print("--------")
    return countList



def relativeFrequencyTable(countList, name, htmlresource):
    relFreqList = []
    c = float(countList[15])

    j_fname = dir_path+"/data/congodata.csv"
    #print(dir_path)
    congo_df = pd.read_csv(j_fname)
    congo_df.drop('Colour', axis=1, inplace=True)
    congo_df.loc[congo_df.index.max() + 1] = localFreqList
    ysize = len(congo_df) * 20 / 97.0  # make vertical size equivlanet 20' is ok for 97.

    congo_df.set_index('Strain', inplace=True)

    cg = sns.clustermap(congo_df, method='ward', cmap = "RdBu_r", col_cluster=False, yticklabels = congo_df.index.values,figsize = (10,ysize))
    plt.setp(cg.ax_heatmap.yaxis.get_ticklabels(), rotation=0, fontsize=8)  # get y labels printed horizontally
    ax=cg.ax_heatmap
    title = "Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$ estimated as the phylotype proportion across the\nsample cohort. "
    title += "Dendrogram reflects the relationships amongst the VSG repertoires of each strain. "
    title += "Strains\nwere isolated from multiple African countries as described in Silva Pereira et al. (2018)."

    j_fname = dir_path+ "/data/congodata_deviationfromthemean.csv"
    #j_fname = r"data/congodata_deviationfromthemean.csv"
    congo_df = pd.read_csv(j_fname)
    congo_df.drop('Colour', axis=1, inplace=True)
    congo_df.loc[congo_df.index.max() + 1] = localDevList
    ysize = len(congo_df) * 20 / 97.0  # make vertical size equivlanet 20' is ok for 97.
    congo_df.set_index('Strain', inplace=True)
    cg = sns.clustermap(congo_df, method='ward',cmap = "RdBu_r", col_cluster=False, yticklabels = congo_df.index.values,figsize = (10,ysize))
    plt.setp(cg.ax_heatmap.yaxis.get_majorticklabels(), rotation=0, fontsize=8)  # get y labels printed horizontally
    ax = cg.ax_heatmap
    title = "Variant Antigen Profiles of $\itTrypanosoma$ $\itcongolense$ expressed as the deviation from the mean phylotypes "
    title +="\nproportions of the sample cohort. Dendrogram reflects the relationships amongst the VSG repertoires of "
    title +="each \nstrain. Strains were isolated from multiple African countries as described in Silva Pereira et al. (2018)."

    for item in pcaResult.Y:
        col = myCountries.index(myColours[i])
        compoundList[col].append(-item[0])
        compoundList[col].append(item[1])
        i = i + 1
    colormap = plt.cm.tab20  # nipy_spectral, Set1,Paired
    cols = [colormap(i) for i in np.linspace(0, 1, 20)]
    fig, ax = plt.subplots(figsize=(9, 6))
    #plt.figure(num=1,figsize=(12, 6))
    i = 0
    for d in myCountries:
        a = compoundList[i]