Python IlluminaFiles示例

示例#1

文件： pipelineprocessor.py 项目： msGenDev/py_mbl_sequencing_pipeline

def illumina_files(runobj):  
    utils = PipelneUtils()
    start = time.time()
#     illumina_files_demultiplex_only(runobj)
    illumina_files = IlluminaFiles(runobj)    
    if runobj.do_perfect: 
#         illumina_files.perfect_reads()
        script_file_name = illumina_files.perfect_reads_cluster()
        utils.run_until_done_on_cluster(script_file_name)
    else:
#         illumina_files.partial_overlap_reads()
#         pass
# TODO: test utils.run_until_done_on_cluster(illumina_files.partial_overlap_reads_cluster())
        script_file_name = illumina_files.partial_overlap_reads_cluster()         
        utils.run_until_done_on_cluster(script_file_name)
        
        script_file_name = illumina_files.filter_mismatches_cluster()
        utils.run_until_done_on_cluster(script_file_name)
        
#         illumina_files.filter_mismatches()
#     illumina_files.uniq_fa()
    script_file_name = illumina_files.uniq_fa_cluster()
    utils.run_until_done_on_cluster(script_file_name)
#     illumina_chimera(runobj)
    elapsed = (time.time() - start)
    print "illumina_files time = %s" % str(elapsed)

示例#2

def illumina_files_demultiplex_only(runobj):  
    start = time.time()
    illumina_files = IlluminaFiles(runobj)
    illumina_files.open_dataset_files()
    illumina_files.split_files(compressed = runobj.compressed)
    elapsed = (time.time() - start)
    print "illumina_files demultiplex only time = %s" % str(elapsed)

示例#3

文件： pipelineprocessor.py 项目： annaship/py_mbl_sequencing_pipeline

def illumina_files_demultiplex_only(runobj):
    logger.debug("Start Demultiplex Illumina files by index/run_key/lane")

    start = time.time()
    illumina_files_inst = IlluminaFiles(runobj)
    illumina_files_inst.open_dataset_files()
    illumina_files_inst.split_files(compressed = runobj.compressed)
    elapsed = (time.time() - start)
    logger.debug("illumina_files demultiplex only time = %s" % str(elapsed))

示例#4

def illumina_files(runobj):
    logger.debug("Start Overlap, filter and unique reads")

    utils = PipelneUtils()
    start = time.time()
    #     illumina_files_demultiplex_only(runobj)
    illumina_files_inst = IlluminaFiles(runobj)
    if runobj.do_perfect:
        #         illumina_files_inst.perfect_reads()
        script_file_name = illumina_files_inst.merge_perfect()
        utils.run_until_done_on_cluster(script_file_name)

        script_file_name = illumina_files_inst.trim_primers_perfect()
        utils.run_until_done_on_cluster(script_file_name)

    else:
        #         illumina_files_inst.partial_overlap_reads()
        #         pass
        # TODO: test utils.run_until_done_on_cluster(illumina_files_inst.partial_overlap_reads_cluster())
        # TODO: add cutting to 251
        script_file_name = illumina_files_inst.partial_overlap_reads_cluster()
        utils.run_until_done_on_cluster(script_file_name)

        script_file_name = illumina_files_inst.filter_mismatches_cluster()
        utils.run_until_done_on_cluster(script_file_name)

    #         illumina_files_inst.filter_mismatches()
    #     illumina_files_inst.uniq_fa()
    script_file_name = illumina_files_inst.uniq_fa_cluster()
    utils.run_until_done_on_cluster(script_file_name)
    #     illumina_chimera(runobj)
    elapsed = (time.time() - start)
    logger.debug("illumina_files time = %s" % str(elapsed))

示例#5

文件： pipelineprocessor.py 项目： annaship/py_mbl_sequencing_pipeline

def illumina_files(runobj):
    logger.debug("Start Overlap, filter and unique reads")

    utils = PipelneUtils()
    start = time.time()
    #     illumina_files_demultiplex_only(runobj)
    illumina_files_inst = IlluminaFiles(runobj)
    if runobj.do_perfect:
        #         illumina_files_inst.perfect_reads()
        script_file_name = illumina_files_inst.merge_perfect()
        utils.run_until_done_on_cluster(script_file_name)

        script_file_name = illumina_files_inst.trim_primers_perfect()
        utils.run_until_done_on_cluster(script_file_name)

    else:
        #         illumina_files_inst.partial_overlap_reads()
        #         pass
        # TODO: test utils.run_until_done_on_cluster(illumina_files_inst.partial_overlap_reads_cluster())
        # TODO: add cutting to 251
        script_file_name = illumina_files_inst.partial_overlap_reads_cluster()
        utils.run_until_done_on_cluster(script_file_name)

        script_file_name = illumina_files_inst.filter_mismatches_cluster()
        utils.run_until_done_on_cluster(script_file_name)

    #         illumina_files_inst.filter_mismatches()
    #     illumina_files_inst.uniq_fa()
    script_file_name = illumina_files_inst.uniq_fa_cluster()
    utils.run_until_done_on_cluster(script_file_name)
    #     illumina_chimera(runobj)
    elapsed = (time.time() - start)
    logger.debug("illumina_files time = %s" % str(elapsed))

示例#6

文件： pipelineprocessor.py 项目： MBL-Woods-Hole/py_mbl_sequencing_pipeline

def illumina_files(runobj):
    start = time()
    #    if os.uname()[1] == 'ashipunova.mbl.edu':
    #        import shutil
    #        shutil.rmtree('/Users/ashipunova/BPC/py_mbl_sequencing_pipeline/test/data/fastq/illumina_files_test/output/analysis/')
    illumina_files = IlluminaFiles(runobj)
    illumina_files.split_files(compressed=runobj.compressed)
    illumina_files.perfect_reads()
    illumina_files.uniq_fa()

    elapsed = time() - start
    print "illumina_files time = %s" % str(elapsed)

示例#7

def illumina_files_demultiplex_only(runobj):
    logger.debug("Start Demultiplex Illumina files by index/run_key/lane")

    start = time.time()
    illumina_files_inst = IlluminaFiles(runobj)
    illumina_files_inst.open_dataset_files()
    illumina_files_inst.split_files(compressed=runobj.compressed)
    elapsed = (time.time() - start)
    logger.debug("illumina_files demultiplex only time = %s" % str(elapsed))

示例#8

文件： pipelineprocessor.py 项目： icefoxx/py_mbl_sequencing_pipeline

def illumina_files(runobj):  
    start = time()
    illumina_files = IlluminaFiles(runobj)
    illumina_files.open_dataset_files()
    illumina_files.split_files(compressed = runobj.compressed)
    if runobj.do_perfect: 
        illumina_files.perfect_reads()
    else:
        illumina_files.partial_overlap_reads()
        illumina_files.filter_mismatches()
    illumina_files.uniq_fa()
    
    elapsed = (time() - start)
    print "illumina_files time = %s" % str(elapsed)