comparison small_rna_maps.py @ 26:376fae7c9f32 draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_maps commit 32eba59fa52705ae74fd9fe65f6f55be783bfc74

25:07aa8f928d4b

def Parser():
    the_parser = argparse.ArgumentParser()
    the_parser.add_argument('--inputs', dest='inputs', required=True,
                            nargs='+', help='list of input BAM files')
    the_parser.add_argument('--minsize', dest='minsize', type=int,
                            default=0, help='minimal size of reads')
    the_parser.add_argument('--maxsize', dest='maxsize', type=int,
                            default=10000, help='maximal size of reads')
    the_parser.add_argument('--cluster', dest='cluster', type=int,
                            default=0, help='clustering distance')
    the_parser.add_argument('--sample_names', dest='sample_names',
                            required=True, nargs='+',
                            help='list of sample names')

        else:
            self.nostrand = True
        self.bam_object = pysam.AlignmentFile(bam_file, 'rb')
        self.chromosomes = dict(zip(self.bam_object.references,
                                self.bam_object.lengths))
        self.map_dict = self.create_map(self.bam_object, self.minsize,
                                        self.maxsize, self.nostrand)
        if self.cluster:
            self.map_dict = self.tile_map(self.map_dict, self.cluster)

    def create_map(self, bam_object, minsize, maxsize, nostrand=False):
        '''
        Returns a map_dictionary {(chromosome,read_position,polarity):
                                                    [read_length, ...]}
        '''
        map_dictionary = defaultdict(list)

        Dataset, Chromosome, Chrom_length, <category (size)>, <some value>
        from a dictionary of sizes: {chrom: {polarity: {size: nbre of reads}}}
        out is an *open* file handler
        '''
        for chrom in sorted(sizedic):
            sizes = sizedic[chrom]['F'].keys()
            sizes.extend(sizedic[chrom]['R'].keys())
            strandness = defaultdict(int)
            sizeness = defaultdict(int)
            for polarity in sizedic[chrom]:
                for size in range(min(sizes), max(sizes)+1):
                    try:
                        strandness[polarity] += sizedic[chrom][polarity][size]
                    except KeyError:
                        pass
                    sizeness[size] += sizedic[chrom][polarity][size]
            Strandbias = strandness['F'] + strandness['R']
            if Strandbias:
                Strandbias = strandness['F'] / float(Strandbias)
            else:

                if StDev:
                    sizeness[size] = (sizeness[size] - Mean) / StDev
                else:
                    sizeness[size] = 0
            for polarity in sorted(sizedic[chrom]):
                for size in range(min(sizes), max(sizes)+1):
                    try:
                        line = [self.sample_name, chrom, polarity, size,
                                sizedic[chrom][polarity][size],
                                Strandbias, sizeness[size]]
                    except KeyError:

26:376fae7c9f32

def Parser():
    the_parser = argparse.ArgumentParser()
    the_parser.add_argument('--inputs', dest='inputs', required=True,
                            nargs='+', help='list of input BAM files')
    the_parser.add_argument('--minsize', dest='minsize', type=int,
                            default=19, help='minimal size of reads')
    the_parser.add_argument('--maxsize', dest='maxsize', type=int,
                            default=29, help='maximal size of reads')
    the_parser.add_argument('--cluster', dest='cluster', type=int,
                            default=0, help='clustering distance')
    the_parser.add_argument('--sample_names', dest='sample_names',
                            required=True, nargs='+',
                            help='list of sample names')

        else:
            self.nostrand = True
        self.bam_object = pysam.AlignmentFile(bam_file, 'rb')
        self.chromosomes = dict(zip(self.bam_object.references,
                                self.bam_object.lengths))
        self.map_dict = self.create_map(self.bam_object, self.nostrand)
        if self.cluster:
            self.map_dict = self.tile_map(self.map_dict, self.cluster)

    def create_map(self, bam_object, nostrand=False):
        '''
        Returns a map_dictionary {(chromosome,read_position,polarity):
                                                    [read_length, ...]}
        '''
        map_dictionary = defaultdict(list)

        Dataset, Chromosome, Chrom_length, <category (size)>, <some value>
        from a dictionary of sizes: {chrom: {polarity: {size: nbre of reads}}}
        out is an *open* file handler
        '''
        for chrom in sorted(sizedic):
            sizes = range(self.minsize, self.maxsize+1)
            strandness = defaultdict(int)
            sizeness = defaultdict(int)
            for polarity in sizedic[chrom]:
                for size in sizes:
                    strandness[polarity] += sizedic[chrom][polarity][size]
                    sizeness[size] += sizedic[chrom][polarity][size]
            Strandbias = strandness['F'] + strandness['R']
            if Strandbias:
                Strandbias = strandness['F'] / float(Strandbias)
            else:

                if StDev:
                    sizeness[size] = (sizeness[size] - Mean) / StDev
                else:
                    sizeness[size] = 0
            for polarity in sorted(sizedic[chrom]):
                for size in sizes:
                    try:
                        line = [self.sample_name, chrom, polarity, size,
                                sizedic[chrom][polarity][size],
                                Strandbias, sizeness[size]]
                    except KeyError: