diff options
Diffstat (limited to 'wqflask/wqflask/api/mapping.py')
| -rw-r--r-- | wqflask/wqflask/api/mapping.py | 105 |
1 files changed, 75 insertions, 30 deletions
diff --git a/wqflask/wqflask/api/mapping.py b/wqflask/wqflask/api/mapping.py index d1cc368e..5eacc83a 100644 --- a/wqflask/wqflask/api/mapping.py +++ b/wqflask/wqflask/api/mapping.py @@ -1,19 +1,12 @@ -import string - from base import data_set -from base import webqtlConfig from base.trait import create_trait, retrieve_sample_data -from utility import helper_functions -from wqflask.marker_regression import gemma_mapping, rqtl_mapping, qtlreaper_mapping, plink_mapping - -import utility.logger -logger = utility.logger.getLogger(__name__) - +from wqflask.marker_regression import gemma_mapping, rqtl_mapping +from wqflask.show_trait.show_trait import normf def do_mapping_for_api(start_vars): - assert('db' in start_vars) - assert('trait_id' in start_vars) + if ('db' not in start_vars) or ("trait_id" not in start_vars): + raise ValueError("Mapping: db and trait_id are not in start_vars") dataset = data_set.create_dataset(dataset_name=start_vars['db']) dataset.group.get_markers() @@ -23,33 +16,67 @@ def do_mapping_for_api(start_vars): samples = [] vals = [] - for sample in dataset.group.samplelist: - in_trait_data = False - for item in this_trait.data: - if this_trait.data[item].name == sample: - value = str(this_trait.data[item].value) - samples.append(item) - vals.append(value) - in_trait_data = True - break - if not in_trait_data: - vals.append("x") - mapping_params = initialize_parameters(start_vars, dataset, this_trait) - # ZS: It seems to take an empty string as default. This should probably be changed. + genofile_samplelist = [] + if mapping_params.get('genofile'): + dataset.group.genofile = mapping_params['genofile'] + genofile_samplelist = get_genofile_samplelist(dataset) + + if (len(genofile_samplelist) > 0): + samplelist = genofile_samplelist + for sample in samplelist: + in_trait_data = False + for item in this_trait.data: + if this_trait.data[item].name == sample: + value = str(this_trait.data[item].value) + samples.append(item) + vals.append(value) + in_trait_data = True + break + if not in_trait_data: + vals.append("x") + else: + samplelist = dataset.group.samplelist + for sample in samplelist: + in_trait_data = False + for item in this_trait.data: + if this_trait.data[item].name == sample: + value = str(this_trait.data[item].value) + samples.append(item) + vals.append(value) + in_trait_data = True + break + if not in_trait_data: + vals.append("x") + + if mapping_params.get('transform') == "qnorm": + vals_minus_x = [float(val) for val in vals if val != "x"] + qnorm_vals = normf(vals_minus_x) + qnorm_vals_with_x = [] + counter = 0 + for val in vals: + if val == "x": + qnorm_vals_with_x.append("x") + else: + qnorm_vals_with_x.append(qnorm_vals[counter]) + counter += 1 + + vals = qnorm_vals_with_x + + # It seems to take an empty string as default. This should probably be changed. covariates = "" - if mapping_params['mapping_method'] == "gemma": + if mapping_params.get('mapping_method') == "gemma": header_row = ["name", "chr", "Mb", "lod_score", "p_value"] - # ZS: gemma_mapping returns both results and the filename for LOCO, so need to only grab the former for api - if mapping_params['use_loco'] == "True": + # gemma_mapping returns both results and the filename for LOCO, so need to only grab the former for api + if mapping_params.get('use_loco') == "True": result_markers = gemma_mapping.run_gemma( this_trait, dataset, samples, vals, covariates, mapping_params['use_loco'], mapping_params['maf'])[0] else: result_markers = gemma_mapping.run_gemma( this_trait, dataset, samples, vals, covariates, mapping_params['use_loco'], mapping_params['maf']) - elif mapping_params['mapping_method'] == "rqtl": + elif mapping_params.get('mapping_method') == "rqtl": header_row = ["name", "chr", "cM", "lod_score"] if mapping_params['num_perm'] > 0: _sperm_output, _suggestive, _significant, result_markers = rqtl_mapping.run_rqtl(this_trait.name, vals, samples, dataset, None, "Mb", mapping_params['rqtl_model'], @@ -62,10 +89,10 @@ def do_mapping_for_api(start_vars): mapping_params['do_control'], mapping_params['control_marker'], mapping_params['manhattan_plot'], None) - if mapping_params['limit_to']: + if mapping_params.get('limit_to'): result_markers = result_markers[:mapping_params['limit_to']] - if mapping_params['format'] == "csv": + if mapping_params.get('format') == "csv": output_rows = [] output_rows.append(header_row) for marker in result_markers: @@ -138,4 +165,22 @@ def initialize_parameters(start_vars, dataset, this_trait): except: mapping_params['perm_check'] = False + mapping_params['transform'] = False + if 'transform' in start_vars: + mapping_params['transform'] = start_vars['transform'] + + mapping_params['genofile'] = False + if 'genofile' in start_vars: + mapping_params['genofile'] = start_vars['genofile'] + return mapping_params + +def get_genofile_samplelist(dataset): + genofile_samplelist = [] + + genofile_json = dataset.group.get_genofiles() + for genofile in genofile_json: + if genofile['location'] == dataset.group.genofile and 'sample_list' in genofile: + genofile_samplelist = genofile['sample_list'] + + return genofile_samplelist |