''' from utils.workflow import Workflow '''---------------------------------------------------------------------------- Workflow script for Gazelles-Zebras RAD-data -----------------------------------------------------------------------------''' testing = False experiment_name = '10percent-test' description = 'A larger test set to test out the data on' # Preprocessing #=============================================================================== W = Workflow() W.create_new(name='zebras-gazelles-test', testing=testing) # Make sure barcodes and datafiles are in their right folders if testing: W.add_datafiles(data_files='testset_500.fastq.bgzf' , barcode_files='*[8].txt') else: W.add_datafiles(data_files='lane6*bgzf' , barcode_files='*[6].txt') W.add_datafiles(data_files='lane8*bgzf' , barcode_files='*[8].txt') # Set parameters p = {'filtering' : {'propN': 0.1, 'phred': 25, 'cutsite_edit_dist' : 2,
from utils.workflow import Workflow """---------------------------------------------------------------------------- Workflow script for Gazelles-Zebras RAD-data -----------------------------------------------------------------------------""" experiment_name = "" description = "" dataset_name = "" testing = False # Preprocessing # =============================================================================== W = Workflow() W.create_new(name=dataset_name, testing=testing) # Make sure barcodes and datafiles are in their right folders if testing: W.add_datafiles(data_files="testset_500.fastq.bgzf", barcode_files="*[8].txt") else: W.add_datafiles(data_files="*.bgzf", barcode_files="*.txt") W.add_datafiles(data_files="*.bgzf", barcode_files="*.txt") # Set parameters p = { "filtering": {"propN": 0.1, "phred": 25, "cutsite_edit_dist": 2, "overhang_edit_dist": 0}, "cleaning": {"max_edit_dist": 1},
''' from utils.workflow import Workflow '''---------------------------------------------------------------------------- Workflow script Template for adding experiment to Gazelles-Zebras RAD-data -----------------------------------------------------------------------------''' experiment_name = '' description = '' dataset_name = '' # Load previously processed data info #=============================================================================== W = Workflow() W.load(name=dataset_name) # Clustering #=============================================================================== W.add_experiment_name(experiment_name, description) default_params = { 'c_thresh' : 0.90, 'n_filter' : 8, 'maskN' : False} #=============================================================================== # Choose method to split files #===============================================================================
''' from utils.workflow import Workflow '''---------------------------------------------------------------------------- Workflow script for Gazelles-Zebras RAD-data -----------------------------------------------------------------------------''' testing = False experiment_name = 'gz_MIDs_95g1' description = 'Cluster all MID tags separately at 95% identity all v all.' # Load previously processed data info #=============================================================================== W = Workflow() W.load(name='gazelles-zebras') # W.create_new(name='gazelles-zebras', testing=testing) # Clustering #=============================================================================== if testing: W.add_experiment_name('gz-subgroups-test', 'Test for splitting files by subgroups') else: W.add_experiment_name(experiment_name, description) default_params = { 'c_thresh' : 0.90, 'n_filter' : 8, 'maskN' : False}