Python UI.cleanUpLine方法代码示例

# 需要导入模块: import UI [as 别名]
# 或者: from UI import cleanUpLine [as 别名]
def importExpressionValues(filename):
    """ Imports tab-delimited expression values"""

    header = True
    sample_expression_db = {}
    fn = unique.filepath(filename)
    for line in open(fn, "rU").xreadlines():
        data = UI.cleanUpLine(line)
        if header:
            sample_names = string.split(data, "\t")
            header = False
        else:
            exp_values = string.split(data, "\t")
            gene = exp_values[0]
            index = 1
            for value in exp_values[1:]:
                sample_name = sample_names[index]
                if sample_name in sample_expression_db:
                    gene_expression_db = sample_expression_db[sample_name]
                    gene_expression_db[gene] = value
                else:
                    gene_expression_db = {}
                    gene_expression_db[gene] = value
                    sample_expression_db[sample_name] = gene_expression_db
                index += 1
    return sample_expression_db

# 需要导入模块: import UI [as 别名]
# 或者: from UI import cleanUpLine [as 别名]
def importAgilentExpressionValues(filename,array,channel_to_extract):
    """ Imports Agilent Feature Extraction files for one or more channels """
    print '.',
    red_expr_db={}
    green_expr_db={}
    parse=False
    fn=unique.filepath(filename)
    for line in open(fn,'rU').xreadlines():
        data = UI.cleanUpLine(line)
        if parse==False:
            if 'ProbeName' in data:
                headers = string.split(data,'\t')
                pn = headers.index('ProbeName')
                try: gc = headers.index('gProcessedSignal')
                except Exception: pass
                try: rc = headers.index('rProcessedSignal')
                except Exception: pass
                parse = True
        else:
            t = string.split(data,'\t')
            probe_name = t[pn]
            try: green_channel = math.log(float(t[gc])+1,2) #min is 0
            except Exception: pass
            try: red_channel = math.log(float(t[rc])+1,2) #min is 0
            except Exception: pass
            if 'red' in channel_to_extract:
                red_expr_db[probe_name] = red_channel
            if 'green' in channel_to_extract:
                green_expr_db[probe_name] = green_channel

    if 'red' in channel_to_extract:
        red_channel_db[array] = red_expr_db
    if 'green' in channel_to_extract:
        green_channel_db[array] = green_expr_db

# 需要导入模块: import UI [as 别名]
# 或者: from UI import cleanUpLine [as 别名]
def annotateMetaProbesetGenes(summary_exp_file, expression_file, metaprobeset_file, species):
    metaprobeset_cv_file = string.replace(metaprobeset_file,species+'_',species+'_Conversion_')
    metaprobeset_cv_file = string.replace(metaprobeset_cv_file,'.mps','.txt')

    fn=filepath(metaprobeset_cv_file); uid_db={}
    for line in open(fn,'rU').xreadlines():
        data = UI.cleanUpLine(line)
        uid,ens_gene = string.split(data,'\t')
        uid_db[uid] = ens_gene

    export_data = export.ExportFile(expression_file)        
    fn=filepath(summary_exp_file); x=0
    for line in open(fn,'rU').xreadlines():
        if line[0] == '#': null=[]
        elif x == 0: export_data.write(line); x+=1
        else:
            data = cleanUpLine(line)
            t = string.split(data,'\t')
            uid = t[0]; ens_gene = uid_db[uid]
            export_data.write(string.join([ens_gene]+t[1:],'\t')+'\n')
    export_data.close()

# 需要导入模块: import UI [as 别名]
# 或者: from UI import cleanUpLine [as 别名]
def compareImportedTables(file_list,outputDir,importDir=False,considerNumericDirection=False,display=True):
    ### added for AltAnalyze
    print 'Creating Venn Diagram from input files...'
    import UI
    import export
    file_id_db={}
    file_list2=[]
    for file in file_list:
        x=0
        if '.txt' in file:
            if importDir !=False: ### When all files in a directory are analyzed
                fn=UI.filepath(import_dir+'/'+file)
            else:
                fn = file
                file = export.findFilename(fn) ### Only report the actual filename
            file_list2.append(file)
            for line in open(fn,'rU').xreadlines():
                if x == 0:
                    data_type = examineFields(line)
                    x+=1
                else:
                    data = UI.cleanUpLine(line)
                    t = string.split(data,'\t')
                    uid = t[0]
                    valid = True
                    if data_type != 'first':
                        if data_type == 'comparison':
                            score = float(string.split(t[6],'|')[0])
                            if 'yes' not in t[5]:
                                valid = False ### not replicated independently
                        if data_type == 'reciprocal':
                            uid = t[8]+'-'+t[10]
                            score = float(t[1])
                        if data_type == 'single':
                            uid = t[6]
                            score = float(t[1])
                    else:
                        try:
                            score = float(t[1]) #t[2]
                        except Exception: score = None
                    if score != None and considerNumericDirection: ### change the UID so that it only matches if the same direction
                        if score>0:
                            uid+='+' ### encode the ID with a negative sign
                        else:
                            uid+='-' ### encode the ID with a negative sign
                    #if score>0:
                    if valid:
                        try: file_id_db[file].append(uid)
                        except Exception: file_id_db[file] = [uid]
                    
    id_lists=[]
    new_file_list=[]
    for file in file_list2: ### Use the sorted names
        if file in file_id_db:
            uids = file_id_db[file]
            id_lists.append(uids)
            new_file_list.append(file)
            #print file, len(new_file_list), len(uids)
            
    if len(file_id_db):
        if len(new_file_list)==2 or len(new_file_list)==3:
            SimpleMatplotVenn(new_file_list,id_lists,outputDir=outputDir,display=False) ### display both below
        venn(id_lists, new_file_list, fill="number", show_names=False, outputDir=outputDir, show_plot=display)