comparison small_rna_map.py @ 7:35d3f8ac99cf draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_map commit 975e2303944d19a4124210741e5a0d1feb546e45

6:f924a33e1eef

    return args


class Map:

    def __init__(self, bam_file, sample):
        self.sample_name = sample
        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.max = self.compute_max(self.map_dict)
        self.mean = self.compute_mean(self.map_dict)
        self.median = self.compute_median(self.map_dict)
        self.coverage = self.compute_coverage(self.map_dict)
        self.size = self.compute_size(self.map_dict)

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

        return coverage_dictionary

    def compute_size(self, map_dictionary):
        '''
        Takes a map_dictionary and returns a dictionary of sizes:
        {chrom: {size: {polarity: nbre of reads}}}
        '''
        size_dictionary = defaultdict(lambda: defaultdict(
                                      lambda: defaultdict( int )))
        for key in map_dictionary:
            if len(map_dictionary) == 0:
                #  to track empty chromosomes
                size_dictionary[key[0]][key[2]][size] = 0
                continue
            for size in map_dictionary[key]:
                size_dictionary[key[0]][key[2]][size] += 1
        return size_dictionary

    def write_size_table(self, out):

    F.write('\t'.join(header) + '\n')
    if size_file_out:
        Fs = open(size_file_out, 'w')
        header = ["Dataset", "Chromosome", "Polarity", "Size", "Nbr_reads"]
        Fs.write('\t'.join(header) + '\n')
    for file, sample in zip(inputs, samples):
        mapobj = Map(file, sample)
        mapobj.write_table(F)
        if size_file_out:
            mapobj.write_size_table(Fs)
    F.close()
    if size_file_out:
        Fs.close()


if __name__ == "__main__":
    args = Parser()
    # if identical sample names # to be tested
    if len(set(args.sample_name)) != len(args.sample_name):
        args.sample_name = [name + '_' + str(i) for
                            i, name in enumerate(args.sample_name)]
    main(args.input, args.sample_name, args.output, args.sizes)

7:35d3f8ac99cf

    return args


class Map:

    def __init__(self, bam_file, sample, computeSize=False):
        self.sample_name = sample
        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.max = self.compute_max(self.map_dict)
        self.mean = self.compute_mean(self.map_dict)
        self.median = self.compute_median(self.map_dict)
        self.coverage = self.compute_coverage(self.map_dict)
        if computeSize:
            self.size = self.compute_size(self.map_dict)

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

        return coverage_dictionary

    def compute_size(self, map_dictionary):
        '''
        Takes a map_dictionary and returns a dictionary of sizes:
        {chrom: {polarity: {size: nbre of reads}}}
        '''
        size_dictionary = defaultdict(lambda: defaultdict(
                                      lambda: defaultdict( int )))
        #  to track empty chromosomes
        for chrom in self.chromosomes:
            if self.bam_object.count(chrom) == 0:
                size_dictionary[chrom]['F'][10] = 0
        for key in map_dictionary:
            for size in map_dictionary[key]:
                size_dictionary[key[0]][key[2]][size] += 1
        return size_dictionary

    def write_size_table(self, out):

    F.write('\t'.join(header) + '\n')
    if size_file_out:
        Fs = open(size_file_out, 'w')
        header = ["Dataset", "Chromosome", "Polarity", "Size", "Nbr_reads"]
        Fs.write('\t'.join(header) + '\n')
        for file, sample in zip(inputs, samples):
            mapobj = Map(file, sample, computeSize=True)
            mapobj.write_table(F)
            mapobj.write_size_table(Fs)
        Fs.close()
    else:
        for file, sample in zip(inputs, samples):
            mapobj = Map(file, sample, computeSize=False)
            mapobj.write_table(F)
        F.close()


if __name__ == "__main__":
    args = Parser()
    # if identical sample names
    if len(set(args.sample_name)) != len(args.sample_name):
        args.sample_name = [name + '_' + str(i) for
                            i, name in enumerate(args.sample_name)]
    main(args.input, args.sample_name, args.output, args.sizes)