当前位置: 首页>>代码示例>>Python>>正文


Python Genomics.convertStrand方法代码示例

本文整理汇总了Python中CGAT.Genomics.convertStrand方法的典型用法代码示例。如果您正苦于以下问题:Python Genomics.convertStrand方法的具体用法?Python Genomics.convertStrand怎么用?Python Genomics.convertStrand使用的例子?那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在CGAT.Genomics的用法示例。


在下文中一共展示了Genomics.convertStrand方法的2个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。

示例1: main

# 需要导入模块: from CGAT import Genomics [as 别名]
# 或者: from CGAT.Genomics import convertStrand [as 别名]

#.........这里部分代码省略.........

        for gff in GTF.iterator(options.stdin):
            ninput += 1
            gff.setAttribute("protein_id", gff.transcript_id)
            options.stdout.write("%s\n" % str(gff))
            noutput += 1
            nfeatures += 1

    elif "add-protein-id" == options.method:

        transcript2protein = IOTools.readMap(IOTools.openFile(options.filename_filter, "r"))

        missing = set()
        for gff in GTF.iterator(options.stdin):
            ninput += 1
            if gff.transcript_id not in transcript2protein:
                if gff.transcript_id not in missing:
                    E.debug(("removing transcript '%s' due to " "missing protein id") % gff.transcript_id)
                    missing.add(gff.transcript_id)
                ndiscarded += 1
                continue

            gff.setAttribute("protein_id", transcript2protein[gff.transcript_id])
            options.stdout.write("%s\n" % str(gff))
            noutput += 1
            nfeatures += 1

        E.info("transcripts removed due to missing protein ids: %i" % len(missing))

    elif "join-exons" == options.method:

        for exons in GTF.transcript_iterator(GTF.iterator(options.stdin)):
            ninput += 1
            strand = Genomics.convertStrand(exons[0].strand)
            contig = exons[0].contig
            transid = exons[0].transcript_id
            geneid = exons[0].gene_id
            biotype = exons[0].source
            all_start, all_end = min([x.start for x in exons]), max([x.end for x in exons])
            y = GTF.Entry()
            y.contig = contig
            y.source = biotype
            y.feature = "transcript"
            y.start = all_start
            y.end = all_end
            y.strand = strand
            y.transcript_id = transid
            y.gene_id = geneid
            options.stdout.write("%s\n" % str(y))

    elif "merge-genes" == options.method:
        # merges overlapping genes
        #
        gffs = GTF.iterator_sorted_chunks(
            GTF.flat_gene_iterator(GTF.iterator(options.stdin)), sort_by="contig-strand-start"
        )

        def iterate_chunks(gff_chunks):

            last = gff_chunks.next()
            to_join = [last]

            for gffs in gff_chunks:
                d = gffs[0].start - last[-1].end

                if gffs[0].contig == last[0].contig and gffs[0].strand == last[0].strand:
开发者ID:mmaarriiee,项目名称:cgat,代码行数:70,代码来源:gtf2gtf.py

示例2: main

# 需要导入模块: from CGAT import Genomics [as 别名]
# 或者: from CGAT.Genomics import convertStrand [as 别名]

#.........这里部分代码省略.........
            options.stdout.write("%s\n" % str(gff))
            noutput += 1
            nfeatures += 1

    elif options.add_protein_id:

        transcript2protein = IOTools.readMap(open(options.add_protein_id, "r"))

        missing = set()
        for gff in GTF.iterator(options.stdin):
            ninput += 1
            if gff.transcript_id not in transcript2protein:
                if gff.transcript_id not in missing:
                    E.debug(
                        ("removing transcript '%s' due to "
                         "missing protein id") % gff.transcript_id)
                    missing.add(gff.transcript_id)
                ndiscarded += 1
                continue

            gff.setAttribute(
                "protein_id", transcript2protein[gff.transcript_id])
            options.stdout.write("%s\n" % str(gff))
            noutput += 1
            nfeatures += 1

        E.info("transcripts removed due to missing protein ids: %i" %
               len(missing))

    elif options.join_exons:

        for exons in GTF.transcript_iterator(GTF.iterator(options.stdin)):
            ninput += 1
            strand = Genomics.convertStrand(exons[0].strand)
            contig = exons[0].contig
            transid = exons[0].transcript_id
            geneid = exons[0].gene_id
            biotype = exons[0].source
            all_start, all_end = min([x.start for x in exons]), max(
                [x.end for x in exons])
            y = GTF.Entry()
            y.contig = contig
            y.source = biotype
            y.feature = "transcript"
            y.start = all_start
            y.end = all_end
            y.strand = strand
            y.transcript_id = transid
            y.gene_id = geneid
            options.stdout.write("%s\n" % str(y))

    elif options.merge_genes:
        # merges overlapping genes
        #
        gffs = GTF.iterator_sorted_chunks(
            GTF.flat_gene_iterator(GTF.iterator(options.stdin)),
            sort_by="contig-strand-start")

        def iterate_chunks(gff_chunks):

            last = gff_chunks.next()
            to_join = [last]

            for gffs in gff_chunks:
                d = gffs[0].start - last[-1].end
开发者ID:jmadzo,项目名称:cgat,代码行数:69,代码来源:gtf2gtf.py


注:本文中的CGAT.Genomics.convertStrand方法示例由纯净天空整理自Github/MSDocs等开源代码及文档管理平台,相关代码片段筛选自各路编程大神贡献的开源项目,源码版权归原作者所有,传播和使用请参考对应项目的License;未经允许,请勿转载。