comparison small_rna_maps.py @ 25:07aa8f928d4b draft

planemo upload for repository https://github.com/ARTbio/tools-artbio/tree/master/tools/small_rna_maps commit a4aa17f675a9caaca0859fee210fae6ada74460f

24:e75a10eba0a6

    def write_size_table(self, sizedic, out):
        '''
        Writer of a tabular file
        Dataset, Chromosome, Chrom_length, <category (size)>, <some value>
        out is an *open* file handler
        '''
        for chrom in sorted(sizedic):
            sizes = sizedic[chrom]['F'].keys()
            sizes.extend(sizedic[chrom]['R'].keys())
            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]]
                    except KeyError:
                        line = [self.sample_name, chrom, polarity, size, 0]
                    line = [str(i) for i in line]
                    out.write('\t'.join(line) + '\n')

    def write_cluster_table(self, clustered_dic, out, bedpath):
        '''

def main(inputs, samples, methods, outputs, minsize, maxsize, cluster,
         nostrand, bedfile=None, bed_skipsize=0):
    for method, output in zip(methods, outputs):
        out = open(output, 'w')
        if method == 'Size':
            header = ["Dataset", "Chromosome", "Polarity", method, "Counts"]
        elif cluster:
            header = ["Dataset", "Chromosome", "Chrom_length", "Coordinate",
                      "Polarity", method, "Start-End", "Cluster Size",
                      "density"]
        else:

25:07aa8f928d4b

    def write_size_table(self, sizedic, out):
        '''
        Writer of a tabular file
        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:
                Strandbias = 2
            Mean = numpy.mean(sizeness.values())
            StDev = numpy.std(sizeness.values())
            for size in sizeness:
                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:
                        line = [self.sample_name, chrom, polarity, size, 0,
                                Strandbias, sizeness[size]]
                    line = [str(i) for i in line]
                    out.write('\t'.join(line) + '\n')

    def write_cluster_table(self, clustered_dic, out, bedpath):
        '''

def main(inputs, samples, methods, outputs, minsize, maxsize, cluster,
         nostrand, bedfile=None, bed_skipsize=0):
    for method, output in zip(methods, outputs):
        out = open(output, 'w')
        if method == 'Size':
            header = ["Dataset", "Chromosome", "Polarity", method, "Counts",
                      "Strandness", "z-score"]
        elif cluster:
            header = ["Dataset", "Chromosome", "Chrom_length", "Coordinate",
                      "Polarity", method, "Start-End", "Cluster Size",
                      "density"]
        else: