当前位置: 首页>>代码示例>>Python>>正文


Python Helper.get_cds_seq方法代码示例

本文整理汇总了Python中annogesiclib.helper.Helper.get_cds_seq方法的典型用法代码示例。如果您正苦于以下问题:Python Helper.get_cds_seq方法的具体用法?Python Helper.get_cds_seq怎么用?Python Helper.get_cds_seq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annogesiclib.helper.Helper的用法示例。


在下文中一共展示了Helper.get_cds_seq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: SubLocal

# 需要导入模块: from annogesiclib.helper import Helper [as 别名]
# 或者: from annogesiclib.helper.Helper import get_cds_seq [as 别名]
class SubLocal(object):

    def __init__(self, args_sub):
        self.multiparser = Multiparser()
        self.helper = Helper()
        self.fixer = FormatFixer()
        self.gff_path = os.path.join(args_sub.gffs, "tmp")
        self.fasta_path = os.path.join(args_sub.fastas, "tmp")
        if args_sub.trans is not None:
            self.tran_path = os.path.join(args_sub.trans, "tmp")
        else:
            self.tran_path = None
        self.out_all = os.path.join(args_sub.out_folder, "all_CDS")
        self.out_express = os.path.join(args_sub.out_folder, "expressed_CDS")
        self.all_tmp_path = os.path.join(self.out_all, "tmp")
        self.express_tmp_path = os.path.join(self.out_express, "tmp")
        self.all_stat_path = os.path.join(self.out_all, "statistics")
        self.express_stat_path = os.path.join(self.out_express, "statistics")
        self.all_tmp_result = os.path.join(self.out_all, "tmp_results")
        self.express_tmp_result = os.path.join(self.out_express, "tmp_results")
        self.all_result = os.path.join(self.out_all, "psortb_results")
        self.express_result = os.path.join(self.out_express, "psortb_results")
        self.endfix_table = "table.csv"
        self.endfix_raw = "raw.txt"
        self._make_folder()

    def _make_folder(self):
        self.helper.check_make_folder(self.out_all)
        self.helper.check_make_folder(self.out_express)
        self.helper.check_make_folder(self.all_stat_path)
        self.helper.check_make_folder(self.express_stat_path)
        self.helper.check_make_folder(self.all_result)
        self.helper.check_make_folder(self.express_result)

    def _compare_cds_tran(self, gff_file, tran_file):
        out = open(os.path.join(self.out_all, "tmp_cds.gff"), "w")
        cdss = []
        fh = open(gff_file)
        th = open(tran_file)
        for entry in Gff3Parser().entries(fh):
            if entry.feature == "CDS":
                cdss.append(entry)
        trans = []
        for entry in Gff3Parser().entries(th):
            trans.append(entry)
        for cds in cdss:
            for ta in trans:
                if (cds.strand == ta.strand) and (
                        cds.seq_id == ta.seq_id):
                    if ((cds.end < ta.end) and (
                             cds.end > ta.start) and (
                             cds.start <= ta.start)) or (
                            (cds.start > ta.start) and (
                             cds.start < ta.end) and (
                             cds.end >= ta.end)) or (
                            (cds.end >= ta.end) and (
                             cds.start <= ta.start)) or (
                            (cds.end <= ta.end) and (
                             cds.start >= ta.start)):
                        out.write(cds.info + "\n")
                        break
        fh.close()
        th.close()
        out.close()

    def _get_protein_seq(self, gff, tmp_path, tran_path):
        prefix = gff.replace(".gff", "")
        fasta = self.helper.get_correct_file(self.fasta_path, ".fa",
                                             prefix, None, None)
        dna_seq_file = os.path.join(tmp_path, "_".join([prefix, "dna.fa"]))
        print("Generate CDS fasta files of {0}".format(prefix))
        if tran_path is not None:
            self._compare_cds_tran(os.path.join(self.gff_path, gff),
                                   os.path.join(tran_path, "_".join([
                                       prefix, "transcript.gff"])))
            self.helper.get_cds_seq(os.path.join(self.out_all, "tmp_cds.gff"),
                                    fasta, dna_seq_file)
            os.remove(os.path.join(self.out_all, "tmp_cds.gff"))
        else:
            self.helper.get_cds_seq(os.path.join(self.gff_path, gff),
                                    fasta, dna_seq_file)
        print("transfer DNA seq to protein seq of {0}".format(prefix))
        self.helper.translation(dna_seq_file, "tmp")
        prot_seq_file = os.path.join(
                tmp_path, "_".join([prefix, "protein.fa"]))
        self.fixer.fix_emboss("tmp", prot_seq_file)
        os.remove("tmp")
        return prefix

    def _psortb(self, psortb_path, strain_type, prot_seq_file,
                out_raw, out_err):
        call([psortb_path, strain_type, prot_seq_file],
             stdout=out_raw, stderr=out_err)

    def _run_psortb(self, args_sub, prefix, out_folder, tmp_path, tmp_result):
        print("Running psortb of {0}".format(prefix))
        out_err = open(os.path.join(out_folder, "tmp_log"), "w")
        out_raw = open(os.path.join(tmp_result,
                       "_".join([prefix, self.endfix_raw])), "w")
        prot_seq_file = os.path.join(tmp_path,
#.........这里部分代码省略.........
开发者ID:malvikasharan,项目名称:ANNOgesic,代码行数:103,代码来源:sublocal.py

示例2: SubLocal

# 需要导入模块: from annogesiclib.helper import Helper [as 别名]
# 或者: from annogesiclib.helper.Helper import get_cds_seq [as 别名]
class SubLocal(object):
    '''detection of subcellular localization'''

    def __init__(self, args_sub):
        self.multiparser = Multiparser()
        self.helper = Helper()
        self.fixer = FormatFixer()
        self.gff_path = os.path.join(args_sub.gffs, "tmp")
        self.fasta_path = os.path.join(args_sub.fastas, "tmp")
        if args_sub.trans is not None:
            self.tran_path = os.path.join(args_sub.trans, "tmp")
        else:
            self.tran_path = None
        self.out_all = os.path.join(args_sub.out_folder, "all_CDSs")
        self.out_express = os.path.join(args_sub.out_folder, "expressed_CDSs")
        self.all_tmp_path = os.path.join(self.out_all, "tmp")
        self.express_tmp_path = os.path.join(self.out_express, "tmp")
        self.all_stat_path = os.path.join(self.out_all, "statistics")
        self.express_stat_path = os.path.join(self.out_express, "statistics")
        self.all_tmp_result = os.path.join(self.out_all, "tmp_results")
        self.express_tmp_result = os.path.join(self.out_express, "tmp_results")
        self.all_result = os.path.join(self.out_all, "psortb_results")
        self.express_result = os.path.join(self.out_express, "psortb_results")
        self.endfix_table = "table.csv"
        self.endfix_raw = "raw.txt"
        self._make_folder()

    def _make_folder(self):
        self.helper.check_make_folder(self.out_all)
        self.helper.check_make_folder(self.out_express)
        self.helper.check_make_folder(self.all_stat_path)
        self.helper.check_make_folder(self.express_stat_path)
        self.helper.check_make_folder(self.all_result)
        self.helper.check_make_folder(self.express_result)

    def _compare_cds_tran(self, gff_file, tran_file, log):
        '''compare CDS and transcript to find the expressed CDS'''
        log.write("Comparing transcripts and CDSs to get expressed CDSs.\n")
        out = open(os.path.join(self.out_all, "tmp_cds.gff"), "w")
        cdss = []
        fh = open(gff_file)
        th = open(tran_file)
        for entry in Gff3Parser().entries(fh):
            if entry.feature == "CDS":
                cdss.append(entry)
        trans = []
        for entry in Gff3Parser().entries(th):
            trans.append(entry)
        for cds in cdss:
            for ta in trans:
                if (cds.strand == ta.strand) and (
                        cds.seq_id == ta.seq_id):
                    if ((cds.end < ta.end) and (
                             cds.end > ta.start) and (
                             cds.start <= ta.start)) or (
                            (cds.start > ta.start) and (
                             cds.start < ta.end) and (
                             cds.end >= ta.end)) or (
                            (cds.end >= ta.end) and (
                             cds.start <= ta.start)) or (
                            (cds.end <= ta.end) and (
                             cds.start >= ta.start)):
                        out.write(cds.info + "\n")
                        break
        fh.close()
        th.close()
        out.close()
        log.write("\t" + os.path.join(self.out_all, "tmp_cds.gff") + " is "
                  "temporary generated.\n")

    def _get_protein_seq(self, gff, tmp_path, tran_path, args_sub, log):
        prefix = gff.replace(".gff", "")
        fasta = self.helper.get_correct_file(self.fasta_path, ".fa",
                                             prefix, None, None)
        dna_seq_file = os.path.join(tmp_path, "_".join([prefix, "dna.fa"]))
        print("Generating CDS fasta files of {0}".format(prefix))
        if tran_path is not None:
            log.write("Predicting subcellular localization for expressed "
                      "CDSs for {0}.\n".format(prefix))
            self._compare_cds_tran(os.path.join(self.gff_path, gff),
                                   os.path.join(tran_path, "_".join([
                                       prefix, "transcript.gff"])), log)
            log.write("Running helper.py to extract sequences for CDSs.\n")
            self.helper.get_cds_seq(os.path.join(self.out_all, "tmp_cds.gff"),
                                    fasta, dna_seq_file)
            os.remove(os.path.join(self.out_all, "tmp_cds.gff"))
        else:
            log.write("Predicting subcellular localization for all CDSs for "
                      "{0}.\n".format(prefix))
            log.write("Running helper.py to extract sequences for CDSs.\n")
            self.helper.get_cds_seq(os.path.join(self.gff_path, gff),
                                    fasta, dna_seq_file)
        log.write("\t" + dna_seq_file + " is generated.\n")
        print("Transfering DNA sequences to protein sequence of {0}".format(
            prefix))
        log.write("Running helper.py to translate DNA sequences to Protein "
                  "sequences.\n")
        tmp_file = os.path.join(args_sub.out_folder, "tmp")
        self.helper.translation(dna_seq_file, tmp_file)
        prot_seq_file = os.path.join(
#.........这里部分代码省略.........
开发者ID:Sung-Huan,项目名称:ANNOgesic,代码行数:103,代码来源:sublocal.py


注:本文中的annogesiclib.helper.Helper.get_cds_seq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。