aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorzsloan2021-06-16 21:57:03 +0000
committerzsloan2021-06-16 21:57:03 +0000
commit6e1b4d1c53b96ed0bb6335deebd888c24b28d366 (patch)
tree75849eb2927530fd627a088b763468f659950081
parentf2e035bb4ff5a1dd5b465ae694105b1a7de956c8 (diff)
downloadgenenetwork2-6e1b4d1c53b96ed0bb6335deebd888c24b28d366.tar.gz
Rewrote show_corr_results.py to remove all code calculating correlations (that was moved to correlation_gn3_api.py, which will probably be renamed at some point) and only include the code generating the table JSON and some template variables
-rw-r--r--wqflask/wqflask/correlation/show_corr_results.py588
1 files changed, 139 insertions, 449 deletions
diff --git a/wqflask/wqflask/correlation/show_corr_results.py b/wqflask/wqflask/correlation/show_corr_results.py
index 2f3df67a..6c6d8f4e 100644
--- a/wqflask/wqflask/correlation/show_corr_results.py
+++ b/wqflask/wqflask/correlation/show_corr_results.py
@@ -18,474 +18,145 @@
#
# This module is used by GeneNetwork project (www.genenetwork.org)
-import collections
import json
-import scipy
-import numpy
-# import rpy2.robjects as ro # R Objects
-import utility.logger
-import utility.webqtlUtil
-from base.trait import create_trait
+from base.trait import create_trait, jsonable
+from base.data_set import create_dataset
-from base import data_set
-from utility import helper_functions
-from utility import corr_result_helpers
from utility import hmac
-from wqflask.correlation import correlation_functions
-from utility.benchmark import Bench
-
-from utility.type_checking import is_str
-from utility.type_checking import get_float
-from utility.type_checking import get_int
-from utility.type_checking import get_string
-from utility.db_tools import escape
-
-from flask import g
-
-logger = utility.logger.getLogger(__name__)
-
-METHOD_LIT = "3"
-METHOD_TISSUE_PEARSON = "4"
-METHOD_TISSUE_RANK = "5"
-
-TISSUE_METHODS = [METHOD_TISSUE_PEARSON, METHOD_TISSUE_RANK]
-
-TISSUE_MOUSE_DB = 1
-
-
-class CorrelationResults:
- def __init__(self, start_vars):
- # get trait list from db (database name)
- # calculate correlation with Base vector and targets
-
- # Check parameters
- assert('corr_type' in start_vars)
- assert(is_str(start_vars['corr_type']))
- assert('dataset' in start_vars)
- # assert('group' in start_vars) permitted to be empty?
- assert('corr_sample_method' in start_vars)
- assert('corr_samples_group' in start_vars)
- assert('corr_dataset' in start_vars)
- assert('corr_return_results' in start_vars)
- if 'loc_chr' in start_vars:
- assert('min_loc_mb' in start_vars)
- assert('max_loc_mb' in start_vars)
-
- with Bench("Doing correlations"):
- if start_vars['dataset'] == "Temp":
- self.dataset = data_set.create_dataset(
- dataset_name="Temp", dataset_type="Temp", group_name=start_vars['group'])
- self.trait_id = start_vars['trait_id']
- self.this_trait = create_trait(dataset=self.dataset,
- name=self.trait_id,
- cellid=None)
- else:
- helper_functions.get_species_dataset_trait(self, start_vars)
-
- corr_samples_group = start_vars['corr_samples_group']
-
- self.sample_data = {}
- self.corr_type = start_vars['corr_type']
- self.corr_method = start_vars['corr_sample_method']
- self.min_expr = get_float(start_vars, 'min_expr')
- self.p_range_lower = get_float(start_vars, 'p_range_lower', -1.0)
- self.p_range_upper = get_float(start_vars, 'p_range_upper', 1.0)
-
-
- if ('loc_chr' in start_vars
- and 'min_loc_mb' in start_vars
- and 'max_loc_mb' in start_vars):
-
- self.location_type = get_string(start_vars, 'location_type')
- self.location_chr = get_string(start_vars, 'loc_chr')
- self.min_location_mb = get_int(start_vars, 'min_loc_mb')
- self.max_location_mb = get_int(start_vars, 'max_loc_mb')
- else:
- self.location_type = self.location_chr = self.min_location_mb = self.max_location_mb = None
-
- self.get_formatted_corr_type()
- self.return_number = int(start_vars['corr_return_results'])
-
- # The two if statements below append samples to the sample list based upon whether the user
- # rselected Primary Samples Only, Other Samples Only, or All Samples
-
- primary_samples = self.dataset.group.samplelist
- if self.dataset.group.parlist != None:
- primary_samples += self.dataset.group.parlist
- if self.dataset.group.f1list != None:
- primary_samples += self.dataset.group.f1list
-
- # If either BXD/whatever Only or All Samples, append all of that group's samplelist
- if corr_samples_group != 'samples_other':
- self.process_samples(start_vars, primary_samples)
-
- # If either Non-BXD/whatever or All Samples, get all samples from this_trait.data and
- # exclude the primary samples (because they would have been added in the previous
- # if statement if the user selected All Samples)
- if corr_samples_group != 'samples_primary':
- if corr_samples_group == 'samples_other':
- primary_samples = [x for x in primary_samples if x not in (
- self.dataset.group.parlist + self.dataset.group.f1list)]
- self.process_samples(start_vars, list(
- self.this_trait.data.keys()), primary_samples)
-
- self.target_dataset = data_set.create_dataset(
- start_vars['corr_dataset'])
- self.target_dataset.get_trait_data(list(self.sample_data.keys()))
-
- self.header_fields = get_header_fields(
- self.target_dataset.type, self.corr_method)
-
- if self.target_dataset.type == "ProbeSet":
- self.filter_cols = [7, 6]
- elif self.target_dataset.type == "Publish":
- self.filter_cols = [6, 0]
- else:
- self.filter_cols = [4, 0]
-
- self.correlation_results = []
+def set_template_vars(start_vars, correlation_data):
+ corr_type = start_vars['corr_type']
+ corr_method = start_vars['corr_sample_method']
- self.correlation_data = {}
+ this_dataset_ob = create_dataset(dataset_name=start_vars['dataset'])
+ this_trait = create_trait(dataset=this_dataset_ob,
+ name=start_vars['trait_id'])
- if self.corr_type == "tissue":
- self.trait_symbol_dict = self.dataset.retrieve_genes("Symbol")
+ correlation_data['this_trait'] = jsonable(this_trait, this_dataset_ob)
+ correlation_data['this_dataset'] = this_dataset_ob.as_dict()
- tissue_corr_data = self.do_tissue_correlation_for_all_traits()
- if tissue_corr_data != None:
- for trait in list(tissue_corr_data.keys())[:self.return_number]:
- self.get_sample_r_and_p_values(
- trait, self.target_dataset.trait_data[trait])
- else:
- for trait, values in list(self.target_dataset.trait_data.items()):
- self.get_sample_r_and_p_values(trait, values)
-
- elif self.corr_type == "lit":
- self.trait_geneid_dict = self.dataset.retrieve_genes("GeneId")
- lit_corr_data = self.do_lit_correlation_for_all_traits()
-
- for trait in list(lit_corr_data.keys())[:self.return_number]:
- self.get_sample_r_and_p_values(
- trait, self.target_dataset.trait_data[trait])
-
- elif self.corr_type == "sample":
- for trait, values in list(self.target_dataset.trait_data.items()):
- self.get_sample_r_and_p_values(trait, values)
-
- self.correlation_data = collections.OrderedDict(sorted(list(self.correlation_data.items()),
- key=lambda t: -abs(t[1][0])))
-
- # ZS: Convert min/max chromosome to an int for the location range option
- range_chr_as_int = None
- for order_id, chr_info in list(self.dataset.species.chromosomes.chromosomes.items()):
- if 'loc_chr' in start_vars:
- if chr_info.name == self.location_chr:
- range_chr_as_int = order_id
-
- for _trait_counter, trait in enumerate(list(self.correlation_data.keys())[:self.return_number]):
- trait_object = create_trait(
- dataset=self.target_dataset, name=trait, get_qtl_info=True, get_sample_info=False)
- if not trait_object:
- continue
-
- chr_as_int = 0
- for order_id, chr_info in list(self.dataset.species.chromosomes.chromosomes.items()):
- if self.location_type == "highest_lod":
- if chr_info.name == trait_object.locus_chr:
- chr_as_int = order_id
- else:
- if chr_info.name == trait_object.chr:
- chr_as_int = order_id
-
-
- if (float(self.correlation_data[trait][0]) >= self.p_range_lower
- and float(self.correlation_data[trait][0]) <= self.p_range_upper):
-
- if (self.target_dataset.type == "ProbeSet" or self.target_dataset.type == "Publish") and bool(trait_object.mean):
- if (self.min_expr != None) and (float(trait_object.mean) < self.min_expr):
- continue
-
- if range_chr_as_int != None and (chr_as_int != range_chr_as_int):
- continue
- if self.location_type == "highest_lod":
- if (self.min_location_mb != None) and (float(trait_object.locus_mb) < float(self.min_location_mb)):
- continue
- if (self.max_location_mb != None) and (float(trait_object.locus_mb) > float(self.max_location_mb)):
- continue
- else:
- if (self.min_location_mb != None) and (float(trait_object.mb) < float(self.min_location_mb)):
- continue
- if (self.max_location_mb != None) and (float(trait_object.mb) > float(self.max_location_mb)):
- continue
-
- (trait_object.sample_r,
- trait_object.sample_p,
- trait_object.num_overlap) = self.correlation_data[trait]
-
- # Set some sane defaults
- trait_object.tissue_corr = 0
- trait_object.tissue_pvalue = 0
- trait_object.lit_corr = 0
- if self.corr_type == "tissue" and tissue_corr_data != None:
- trait_object.tissue_corr = tissue_corr_data[trait][1]
- trait_object.tissue_pvalue = tissue_corr_data[trait][2]
- elif self.corr_type == "lit":
- trait_object.lit_corr = lit_corr_data[trait][1]
-
- self.correlation_results.append(trait_object)
-
- if self.corr_type != "lit" and self.dataset.type == "ProbeSet" and self.target_dataset.type == "ProbeSet":
- self.do_lit_correlation_for_trait_list()
-
- if self.corr_type != "tissue" and self.dataset.type == "ProbeSet" and self.target_dataset.type == "ProbeSet":
- self.do_tissue_correlation_for_trait_list()
-
- self.json_results = generate_corr_json(
- self.correlation_results, self.this_trait, self.dataset, self.target_dataset)
-
-############################################################################################################################################
-
- def get_formatted_corr_type(self):
- self.formatted_corr_type = ""
- if self.corr_type == "lit":
- self.formatted_corr_type += "Literature Correlation "
- elif self.corr_type == "tissue":
- self.formatted_corr_type += "Tissue Correlation "
- elif self.corr_type == "sample":
- self.formatted_corr_type += "Genetic Correlation "
-
- if self.corr_method == "pearson":
- self.formatted_corr_type += "(Pearson's r)"
- elif self.corr_method == "spearman":
- self.formatted_corr_type += "(Spearman's rho)"
- elif self.corr_method == "bicor":
- self.formatted_corr_type += "(Biweight r)"
-
- def do_tissue_correlation_for_trait_list(self, tissue_dataset_id=1):
- """Given a list of correlation results (self.correlation_results), gets the tissue correlation value for each"""
-
- # Gets tissue expression values for the primary trait
- primary_trait_tissue_vals_dict = correlation_functions.get_trait_symbol_and_tissue_values(
- symbol_list=[self.this_trait.symbol])
-
- if self.this_trait.symbol.lower() in primary_trait_tissue_vals_dict:
- primary_trait_tissue_values = primary_trait_tissue_vals_dict[self.this_trait.symbol.lower(
- )]
- gene_symbol_list = [
- trait.symbol for trait in self.correlation_results if trait.symbol]
-
- corr_result_tissue_vals_dict = correlation_functions.get_trait_symbol_and_tissue_values(
- symbol_list=gene_symbol_list)
-
- for trait in self.correlation_results:
- if trait.symbol and trait.symbol.lower() in corr_result_tissue_vals_dict:
- this_trait_tissue_values = corr_result_tissue_vals_dict[trait.symbol.lower(
- )]
-
- result = correlation_functions.cal_zero_order_corr_for_tiss(primary_trait_tissue_values,
- this_trait_tissue_values,
- self.corr_method)
-
- trait.tissue_corr = result[0]
- trait.tissue_pvalue = result[2]
-
- def do_tissue_correlation_for_all_traits(self, tissue_dataset_id=1):
- # Gets tissue expression values for the primary trait
- primary_trait_tissue_vals_dict = correlation_functions.get_trait_symbol_and_tissue_values(
- symbol_list=[self.this_trait.symbol])
-
- if self.this_trait.symbol.lower() in primary_trait_tissue_vals_dict:
- primary_trait_tissue_values = primary_trait_tissue_vals_dict[self.this_trait.symbol.lower(
- )]
-
- #print("trait_gene_symbols: ", pf(trait_gene_symbols.values()))
- corr_result_tissue_vals_dict = correlation_functions.get_trait_symbol_and_tissue_values(
- symbol_list=list(self.trait_symbol_dict.values()))
-
- #print("corr_result_tissue_vals: ", pf(corr_result_tissue_vals_dict))
-
- #print("trait_gene_symbols: ", pf(trait_gene_symbols))
-
- tissue_corr_data = {}
- for trait, symbol in list(self.trait_symbol_dict.items()):
- if symbol and symbol.lower() in corr_result_tissue_vals_dict:
- this_trait_tissue_values = corr_result_tissue_vals_dict[symbol.lower(
- )]
+ target_dataset_ob = create_dataset(correlation_data['target_dataset'])
+ correlation_data['target_dataset'] = target_dataset_ob.as_dict()
- result = correlation_functions.cal_zero_order_corr_for_tiss(primary_trait_tissue_values,
- this_trait_tissue_values,
- self.corr_method)
+ table_json = correlation_json_for_table(correlation_data,
+ correlation_data['this_trait'],
+ correlation_data['this_dataset'],
+ target_dataset_ob)
- tissue_corr_data[trait] = [symbol, result[0], result[2]]
+ correlation_data['table_json'] = table_json
- tissue_corr_data = collections.OrderedDict(sorted(list(tissue_corr_data.items()),
- key=lambda t: -abs(t[1][1])))
+ if target_dataset_ob.type == "ProbeSet":
+ filter_cols = [7, 6]
+ elif target_dataset_ob.type == "Publish":
+ filter_cols = [6, 0]
+ else:
+ filter_cols = [4, 0]
- return tissue_corr_data
+ correlation_data['corr_method'] = corr_method
+ correlation_data['filter_cols'] = filter_cols
+ correlation_data['header_fields'] = get_header_fields(target_dataset_ob.type, correlation_data['corr_method'])
+ correlation_data['formatted_corr_type'] = get_formatted_corr_type(corr_type, corr_method)
- def do_lit_correlation_for_trait_list(self):
+ return correlation_data
- input_trait_mouse_gene_id = self.convert_to_mouse_gene_id(
- self.dataset.group.species.lower(), self.this_trait.geneid)
+def correlation_json_for_table(correlation_data, this_trait, this_dataset, target_dataset_ob):
+ """Return JSON data for use with the DataTable in the correlation result page
- for trait in self.correlation_results:
+ Keyword arguments:
+ correlation_data -- Correlation results
+ this_trait -- Trait being correlated against a dataset, as a dict
+ this_dataset -- Dataset of this_trait, as a dict
+ target_dataset_ob - Target dataset, as a Dataset ob
+ """
+ this_trait = correlation_data['this_trait']
+ this_dataset = correlation_data['this_dataset']
+ target_dataset = target_dataset_ob.as_dict()
- if trait.geneid:
- trait.mouse_gene_id = self.convert_to_mouse_gene_id(
- self.dataset.group.species.lower(), trait.geneid)
- else:
- trait.mouse_gene_id = None
-
- if trait.mouse_gene_id and str(trait.mouse_gene_id).find(";") == -1:
- result = g.db.execute(
- """SELECT value
- FROM LCorrRamin3
- WHERE GeneId1='%s' and
- GeneId2='%s'
- """ % (escape(str(trait.mouse_gene_id)), escape(str(input_trait_mouse_gene_id)))
- ).fetchone()
- if not result:
- result = g.db.execute("""SELECT value
- FROM LCorrRamin3
- WHERE GeneId2='%s' and
- GeneId1='%s'
- """ % (escape(str(trait.mouse_gene_id)), escape(str(input_trait_mouse_gene_id)))
- ).fetchone()
-
- if result:
- lit_corr = result.value
- trait.lit_corr = lit_corr
- else:
- trait.lit_corr = 0
- else:
- trait.lit_corr = 0
-
- def do_lit_correlation_for_all_traits(self):
- input_trait_mouse_gene_id = self.convert_to_mouse_gene_id(
- self.dataset.group.species.lower(), self.this_trait.geneid)
-
- lit_corr_data = {}
- for trait, gene_id in list(self.trait_geneid_dict.items()):
- mouse_gene_id = self.convert_to_mouse_gene_id(
- self.dataset.group.species.lower(), gene_id)
-
- if mouse_gene_id and str(mouse_gene_id).find(";") == -1:
- #print("gene_symbols:", input_trait_mouse_gene_id + " / " + mouse_gene_id)
- result = g.db.execute(
- """SELECT value
- FROM LCorrRamin3
- WHERE GeneId1='%s' and
- GeneId2='%s'
- """ % (escape(mouse_gene_id), escape(input_trait_mouse_gene_id))
- ).fetchone()
- if not result:
- result = g.db.execute("""SELECT value
- FROM LCorrRamin3
- WHERE GeneId2='%s' and
- GeneId1='%s'
- """ % (escape(mouse_gene_id), escape(input_trait_mouse_gene_id))
- ).fetchone()
- if result:
- #print("result:", result)
- lit_corr = result.value
- lit_corr_data[trait] = [gene_id, lit_corr]
+ corr_results = correlation_data['correlation_results']
+ results_list = []
+ for i, trait_dict in enumerate(corr_results):
+ trait_name = list(trait_dict.keys())[0]
+ trait = trait_dict[trait_name]
+ target_trait_ob = create_trait(dataset=target_dataset_ob,
+ name=trait_name,
+ get_qtl_info=True)
+ target_trait = jsonable(target_trait_ob, target_dataset_ob)
+ if target_trait['view'] == False:
+ continue
+ results_dict = {}
+ results_dict['index'] = i + 1
+ results_dict['trait_id'] = target_trait['name']
+ results_dict['dataset'] = target_dataset['name']
+ results_dict['hmac'] = hmac.data_hmac(
+ '{}:{}'.format(target_trait['name'], target_dataset['name']))
+ results_dict['sample_r'] = f"{float(trait['corr_coeffient']):.3f}"
+ results_dict['num_overlap'] = trait['num_overlap']
+ results_dict['sample_p'] = f"{float(trait['p_value']):.3e}"
+ if target_dataset['type'] == "ProbeSet":
+ results_dict['symbol'] = target_trait['symbol']
+ results_dict['description'] = "N/A"
+ results_dict['location'] = target_trait['location']
+ results_dict['mean'] = "N/A"
+ results_dict['additive'] = "N/A"
+ if bool(target_trait['description']):
+ results_dict['description'] = target_trait['description']
+ if bool(target_trait['mean']):
+ results_dict['mean'] = f"{float(target_trait['mean']):.3f}"
+ try:
+ results_dict['lod_score'] = f"{float(target_trait['lrs_score']) / 4.61:.1f}"
+ except:
+ results_dict['lod_score'] = "N/A"
+ results_dict['lrs_location'] = target_trait['lrs_location']
+ if bool(target_trait['additive']):
+ results_dict['additive'] = f"{float(target_trait['additive']):.3f}"
+ results_dict['lit_corr'] = "--"
+ results_dict['tissue_corr'] = "--"
+ results_dict['tissue_pvalue'] = "--"
+ if this_dataset['type'] == "ProbeSet":
+ if 'lit_corr' in trait:
+ results_dict['lit_corr'] = f"{float(trait['lit_corr']):.3f}"
+ if 'tissue_corr' in trait:
+ results_dict['tissue_corr'] = f"{float(trait['tissue_corr']):.3f}"
+ results_dict['tissue_pvalue'] = f"{float(trait['tissue_p_val']):.3e}"
+ elif target_dataset['type'] == "Publish":
+ results_dict['abbreviation_display'] = "N/A"
+ results_dict['description'] = "N/A"
+ results_dict['mean'] = "N/A"
+ results_dict['authors_display'] = "N/A"
+ results_dict['additive'] = "N/A"
+ results_dict['pubmed_link'] = "N/A"
+ results_dict['pubmed_text'] = "N/A"
+
+ if bool(target_trait['abbreviation']):
+ results_dict['abbreviation_display'] = target_trait['abbreviation']
+ if bool(target_trait['description']):
+ results_dict['description'] = target_trait['description']
+ if bool(target_trait['mean']):
+ results_dict['mean'] = f"{float(target_trait['mean']):.3f}"
+ if bool(target_trait['authors']):
+ authors_list = target_trait['authors'].split(',')
+ if len(authors_list) > 6:
+ results_dict['authors_display'] = ", ".join(
+ authors_list[:6]) + ", et al."
else:
- lit_corr_data[trait] = [gene_id, 0]
- else:
- lit_corr_data[trait] = [gene_id, 0]
-
- lit_corr_data = collections.OrderedDict(sorted(list(lit_corr_data.items()),
- key=lambda t: -abs(t[1][1])))
-
- return lit_corr_data
-
- def convert_to_mouse_gene_id(self, species=None, gene_id=None):
- """If the species is rat or human, translate the gene_id to the mouse geneid
-
- If there is no input gene_id or there's no corresponding mouse gene_id, return None
-
- """
- if not gene_id:
- return None
-
- mouse_gene_id = None
-
- if species == 'mouse':
- mouse_gene_id = gene_id
-
- elif species == 'rat':
-
- query = """SELECT mouse
- FROM GeneIDXRef
- WHERE rat='%s'""" % escape(gene_id)
-
- result = g.db.execute(query).fetchone()
- if result != None:
- mouse_gene_id = result.mouse
-
- elif species == 'human':
-
- query = """SELECT mouse
- FROM GeneIDXRef
- WHERE human='%s'""" % escape(gene_id)
-
- result = g.db.execute(query).fetchone()
- if result != None:
- mouse_gene_id = result.mouse
-
- return mouse_gene_id
-
- def get_sample_r_and_p_values(self, trait, target_samples):
- """Calculates the sample r (or rho) and p-value
-
- Given a primary trait and a target trait's sample values,
- calculates either the pearson r or spearman rho and the p-value
- using the corresponding scipy functions.
-
- """
-
- self.this_trait_vals = []
- target_vals = []
- for index, sample in enumerate(self.target_dataset.samplelist):
- if sample in self.sample_data:
- sample_value = self.sample_data[sample]
- target_sample_value = target_samples[index]
- self.this_trait_vals.append(sample_value)
- target_vals.append(target_sample_value)
-
- self.this_trait_vals, target_vals, num_overlap = corr_result_helpers.normalize_values(
- self.this_trait_vals, target_vals)
-
- if num_overlap > 5:
- # ZS: 2015 could add biweight correlation, see http://www.ncbi.nlm.nih.gov/pmc/articles/PMC3465711/
- # if self.corr_method == 'bicor':
- # sample_r, sample_p = do_bicor(
- # self.this_trait_vals, target_vals)
- if self.corr_method == 'pearson':
- sample_r, sample_p = scipy.stats.pearsonr(
- self.this_trait_vals, target_vals)
- else:
- sample_r, sample_p = scipy.stats.spearmanr(
- self.this_trait_vals, target_vals)
-
- if numpy.isnan(sample_r):
- pass
- else:
- self.correlation_data[trait] = [
- sample_r, sample_p, num_overlap]
-
- def process_samples(self, start_vars, sample_names, excluded_samples=None):
- if not excluded_samples:
- excluded_samples = ()
+ results_dict['authors_display'] = target_trait['authors']
+ if 'pubmed_id' in target_trait:
+ results_dict['pubmed_link'] = target_trait['pubmed_link']
+ results_dict['pubmed_text'] = target_trait['pubmed_text']
+ try:
+ results_dict['lod_score'] = f"{float(target_trait['lrs_score']) / 4.61:.1f}"
+ except:
+ results_dict['lod_score'] = "N/A"
+ results_dict['lrs_location'] = target_trait['lrs_location']
+ if bool(target_trait['additive']):
+ results_dict['additive'] = f"{float(target_trait['additive']):.3f}"
+ else:
+ results_dict['location'] = target_trait['lrs_location']
- sample_val_dict = json.loads(start_vars['sample_vals'])
- for sample in sample_names:
- if sample not in excluded_samples:
- value = sample_val_dict[sample]
- if not value.strip().lower() == 'x':
- self.sample_data[str(sample)] = float(value)
+ results_list.append(results_dict)
+ return json.dumps(results_list)
# def do_bicor(this_trait_vals, target_trait_vals):
# r_library = ro.r["library"] # Map the library function
@@ -598,6 +269,25 @@ def generate_corr_json(corr_results, this_trait, dataset, target_dataset, for_ap
return json.dumps(results_list)
+def get_formatted_corr_type(corr_type, corr_method):
+ formatted_corr_type = ""
+ if corr_type == "lit":
+ formatted_corr_type += "Literature Correlation "
+ elif corr_type == "tissue":
+ formatted_corr_type += "Tissue Correlation "
+ elif corr_type == "sample":
+ formatted_corr_type += "Genetic Correlation "
+
+ if corr_method == "pearson":
+ formatted_corr_type += "(Pearson's r)"
+ elif corr_method == "spearman":
+ formatted_corr_type += "(Spearman's rho)"
+ elif corr_method == "bicor":
+ formatted_corr_type += "(Biweight r)"
+
+ return formatted_corr_type
+
+
def get_header_fields(data_type, corr_method):
if data_type == "ProbeSet":
if corr_method == "spearman":