comparison model_prediction.py @ 15:3f3c6dc38f3e draft

"planemo upload for repository https://github.com/bgruening/galaxytools/tree/master/tools/sklearn commit 5b2ac730ec6d3b762faa9034eddd19ad1b347476"

14:c33145a815ee

import argparse
import json
import numpy as np
import pandas as pd
import tabix
import warnings

from scipy.io import mmread
from sklearn.pipeline import Pipeline

from galaxy_ml.externals.selene_sdk.sequences import Genome
from galaxy_ml.utils import (load_model, read_columns,
                             get_module, try_get_attr)


N_JOBS = int(__import__('os').environ.get('GALAXY_SLOTS', 1))

            options['blacklist_regions'] = None

        pred_data_generator = klass(
            ref_genome_path=ref_seq, vcf_path=vcf_path, **options)

        pred_data_generator.fit()

        variants = pred_data_generator.variants
        # TODO : remove the following block after galaxy-ml v0.7.13
        blacklist_tabix = getattr(pred_data_generator.reference_genome_,
                                  '_blacklist_tabix', None)
        clean_variants = []
        if blacklist_tabix:
            start_radius = pred_data_generator.start_radius_
            end_radius = pred_data_generator.end_radius_

            for chrom, pos, name, ref, alt, strand in variants:
                center = pos + len(ref) // 2
                start = center - start_radius
                end = center + end_radius

                if isinstance(pred_data_generator.reference_genome_, Genome):
                    if "chr" not in chrom:
                        chrom = "chr" + chrom
                    if "MT" in chrom:
                        chrom = chrom[:-1]
                try:
                    rows = blacklist_tabix.query(chrom, start, end)
                    found = 0
                    for row in rows:
                        found = 1
                        break
                    if found:
                        continue
                except tabix.TabixError:
                    pass

                clean_variants.append((chrom, pos, name, ref, alt, strand))
        else:
            clean_variants = variants

        setattr(pred_data_generator, 'variants', clean_variants)

        variants = np.array(clean_variants)
        # predict 1600 sample at once then write to file
        gen_flow = pred_data_generator.flow(batch_size=1600)

        file_writer = open(outfile_predict, 'w')
        header_row = '\t'.join(['chrom', 'pos', 'name', 'ref',

15:3f3c6dc38f3e

import argparse
import json
import numpy as np
import pandas as pd
import warnings

from scipy.io import mmread
from sklearn.pipeline import Pipeline

from galaxy_ml.utils import (load_model, read_columns,
                             get_module, try_get_attr)


N_JOBS = int(__import__('os').environ.get('GALAXY_SLOTS', 1))

            options['blacklist_regions'] = None

        pred_data_generator = klass(
            ref_genome_path=ref_seq, vcf_path=vcf_path, **options)

        pred_data_generator.set_processing_attrs()

        variants = pred_data_generator.variants

        # predict 1600 sample at once then write to file
        gen_flow = pred_data_generator.flow(batch_size=1600)

        file_writer = open(outfile_predict, 'w')
        header_row = '\t'.join(['chrom', 'pos', 'name', 'ref',