comparison BlastParser_and_hits.py @ 11:87d250071bdc draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/msp_blastparser_and_hits commit 3048cdbea989bc7d28326bf9479fc3010ff8b33c

10:cf78a10bcfcf

    the_parser.add_argument('--filter_meanScore', action="store", type=float, default=0, help="filter out mean BitScores below the specified float number")
    the_parser.add_argument('--filter_term_in', action="store", type=str, default="", help="select the specified term in the subject list")
    the_parser.add_argument('--filter_term_out', action="store", type=str, default="", help="exclude the specified term from the subject list")
    the_parser.add_argument('--al_sequences', action="store", type=str, help="sequences that have been blast aligned")
    the_parser.add_argument('--un_sequences', action="store", type=str, help="sequences that have not been blast aligned")
    args = the_parser.parse_args()
    if not all ( (args.sequences, args.blast, args.fastaOutput, args.tabularOutput) ):
        the_parser.error('argument(s) missing, call the -h option of the script')
    if not args.flanking:
        args.flanking = 0

        leftCoordinate -= FlankingValue
    else:
        leftCoordinate = 1
    return getseq (fastadict, FastaHeader, leftCoordinate, rightCoordinate, polarity)
    
def outputParsing (F, Fasta, results, Xblastdict, fastadict, filter_relativeCov=0, filter_maxScore=0, filter_meanScore=0, filter_term_in="", filter_term_out="", mode="verbose"):
    def filter_results (results, filter_relativeCov=0, filter_maxScore=0, filter_meanScore=0, filter_term_in="", filter_term_out=""):
        for subject in results.keys():
            if results[subject]["RelativeSubjectCoverage"]<filter_relativeCov:
                del results[subject]
                continue

    for subject in results:
        for transcript in Xblastdict[subject]:
            blasted_transcripts.append(transcript)
    blasted_transcripts = list( set( blasted_transcripts))
    if mode == "verbose":
        print >>F, "# SeqId\t%Identity\tAlignLength\tStartSubject\tEndSubject\t%QueryHitCov\tE-value\tBitScore\n"
        for subject in sorted (results, key=lambda x: results[x]["meanBitScores"], reverse=True):
            print >> F, "#\n# %s" % subject
            print >> F, "# Suject Length: %s" % (results[subject]["subjectLength"])
            print >> F, "# Total Subject Coverage: %s" % (results[subject]["TotalCoverage"])
            print >> F, "# Relative Subject Coverage: %s" % (results[subject]["RelativeSubjectCoverage"])
            print >> F, "# Best Bit Score: %s" % (results[subject]["maxBitScores"])
            print >> F, "# Mean Bit Score: %s" % (results[subject]["meanBitScores"])

                    info = [transcript] + [percentIdentity, alignLenght, subjectStart, subjectEnd, queryCov, Eval, BitScore]
                    info = [str(i) for i in info]
                    info = "\t".join(info)
                    print >> F, info
    else:
        print >>F, "# subject\tsubject length\tTotal Subject Coverage\tRelative Subject Coverage\tBest Bit Score\tMean Bit Score"
        for subject in sorted (results, key=lambda x: results[x]["meanBitScores"], reverse=True):
            line = []
            line.append(subject)
            line.append(results[subject]["subjectLength"])

    fastadict = getfasta (args.sequences)
    Xblastdict = getblast (args.blast)
    results = defaultdict(dict)
    for subject in Xblastdict:
        results[subject]["HitDic"], results[subject]["subjectLength"], results[subject]["TotalCoverage"], results[subject]["RelativeSubjectCoverage"], results[subject]["maxBitScores"], results[subject]["meanBitScores"]  = subjectCoverage(fastadict, Xblastdict, subject, args.flanking)
    blasted_transcripts = outputParsing (args.tabularOutput, args.fastaOutput, results, Xblastdict, fastadict,
                                        filter_relativeCov=args.filter_relativeCov, filter_maxScore=args.filter_maxScore,
                                        filter_meanScore=args.filter_meanScore, filter_term_in=args.filter_term_in,
                                        filter_term_out=args.filter_term_out, mode=args.mode)
    dispatch_sequences (fastadict, blasted_transcripts, args.al_sequences, args.un_sequences)

11:87d250071bdc

    the_parser.add_argument('--filter_meanScore', action="store", type=float, default=0, help="filter out mean BitScores below the specified float number")
    the_parser.add_argument('--filter_term_in', action="store", type=str, default="", help="select the specified term in the subject list")
    the_parser.add_argument('--filter_term_out', action="store", type=str, default="", help="exclude the specified term from the subject list")
    the_parser.add_argument('--al_sequences', action="store", type=str, help="sequences that have been blast aligned")
    the_parser.add_argument('--un_sequences', action="store", type=str, help="sequences that have not been blast aligned")
    the_parser.add_argument('--dataset_name', action="store", type=str, default="", help="the name of the dataset that has been parsed, to be reported in the output")
    args = the_parser.parse_args()
    if not all ( (args.sequences, args.blast, args.fastaOutput, args.tabularOutput) ):
        the_parser.error('argument(s) missing, call the -h option of the script')
    if not args.flanking:
        args.flanking = 0

        leftCoordinate -= FlankingValue
    else:
        leftCoordinate = 1
    return getseq (fastadict, FastaHeader, leftCoordinate, rightCoordinate, polarity)
    
def outputParsing (dataset_name, F, Fasta, results, Xblastdict, fastadict, filter_relativeCov=0, filter_maxScore=0, filter_meanScore=0, filter_term_in="", filter_term_out="", mode="verbose"):
    def filter_results (results, filter_relativeCov=0, filter_maxScore=0, filter_meanScore=0, filter_term_in="", filter_term_out=""):
        for subject in results.keys():
            if results[subject]["RelativeSubjectCoverage"]<filter_relativeCov:
                del results[subject]
                continue

    for subject in results:
        for transcript in Xblastdict[subject]:
            blasted_transcripts.append(transcript)
    blasted_transcripts = list( set( blasted_transcripts))
    if mode == "verbose":
        print >>F, "--- %s ---" % (dataset_name)
        print >>F, "# SeqId\t%Identity\tAlignLength\tStartSubject\tEndSubject\t%QueryHitCov\tE-value\tBitScore"
        for subject in sorted (results, key=lambda x: results[x]["meanBitScores"], reverse=True):
            print >> F, " \n# %s" % subject
            print >> F, "# Suject Length: %s" % (results[subject]["subjectLength"])
            print >> F, "# Total Subject Coverage: %s" % (results[subject]["TotalCoverage"])
            print >> F, "# Relative Subject Coverage: %s" % (results[subject]["RelativeSubjectCoverage"])
            print >> F, "# Best Bit Score: %s" % (results[subject]["maxBitScores"])
            print >> F, "# Mean Bit Score: %s" % (results[subject]["meanBitScores"])

                    info = [transcript] + [percentIdentity, alignLenght, subjectStart, subjectEnd, queryCov, Eval, BitScore]
                    info = [str(i) for i in info]
                    info = "\t".join(info)
                    print >> F, info
    else:
        print >>F, "--- %s ---" % (dataset_name)
        print >>F, "# subject\tsubject length\tTotal Subject Coverage\tRelative Subject Coverage\tBest Bit Score\tMean Bit Score"
        for subject in sorted (results, key=lambda x: results[x]["meanBitScores"], reverse=True):
            line = []
            line.append(subject)
            line.append(results[subject]["subjectLength"])

    fastadict = getfasta (args.sequences)
    Xblastdict = getblast (args.blast)
    results = defaultdict(dict)
    for subject in Xblastdict:
        results[subject]["HitDic"], results[subject]["subjectLength"], results[subject]["TotalCoverage"], results[subject]["RelativeSubjectCoverage"], results[subject]["maxBitScores"], results[subject]["meanBitScores"]  = subjectCoverage(fastadict, Xblastdict, subject, args.flanking)
    blasted_transcripts = outputParsing (args.dataset_name, args.tabularOutput, args.fastaOutput, results, Xblastdict, fastadict,
                                        filter_relativeCov=args.filter_relativeCov, filter_maxScore=args.filter_maxScore,
                                        filter_meanScore=args.filter_meanScore, filter_term_in=args.filter_term_in,
                                        filter_term_out=args.filter_term_out, mode=args.mode)
    dispatch_sequences (fastadict, blasted_transcripts, args.al_sequences, args.un_sequences)