diff options
| -rwxr-xr-x | wqflask/base/trait.py | 17 | ||||
| -rw-r--r-- | wqflask/wqflask/correlation/show_corr_results.py | 126 | ||||
| -rw-r--r-- | wqflask/wqflask/search_results.py | 2 | ||||
| -rw-r--r-- | wqflask/wqflask/templates/correlation_page.html | 33 |
4 files changed, 98 insertions, 80 deletions
diff --git a/wqflask/base/trait.py b/wqflask/base/trait.py index f333d5a7..82e013ae 100755 --- a/wqflask/base/trait.py +++ b/wqflask/base/trait.py @@ -28,7 +28,7 @@ class GeneralTrait(object): """ - def __init__(self, **kw): + def __init__(self, get_qtl_info=False, **kw): # xor assertion assert bool(kw.get('dataset')) != bool(kw.get('dataset_name')), "Needs dataset ob. xor name"; if kw.get('dataset_name'): @@ -41,6 +41,14 @@ class GeneralTrait(object): self.haveinfo = kw.get('haveinfo', False) self.sequence = kw.get('sequence') # Blat sequence, available for ProbeSet self.data = kw.get('data', {}) + + # Sets defaultst + self.locus = None + self.lrs = None + self.pvalue = None + self.mean = None + self.num_overlap = None + if kw.get('fullname'): name2 = value.split("::") @@ -52,8 +60,9 @@ class GeneralTrait(object): # Todo: These two lines are necessary most of the time, but perhaps not all of the time # So we could add a simple if statement to short-circuit this if necessary - self.retrieve_info() + self.retrieve_info(get_qtl_info=get_qtl_info) self.retrieve_sample_data() + def get_name(self): @@ -237,7 +246,7 @@ class GeneralTrait(object): #def items(self): # return self.__dict__.items() - def retrieve_info(self, QTL=False): + def retrieve_info(self, get_qtl_info=False): assert self.dataset, "Dataset doesn't exist" if self.dataset.type == 'Publish': query = """ @@ -347,7 +356,7 @@ class GeneralTrait(object): if result: self.homologeneid = result[0] - if QTL: + if get_qtl_info: if self.dataset.type == 'ProbeSet' and not self.cellid: traitQTL = g.db.execute(""" SELECT diff --git a/wqflask/wqflask/correlation/show_corr_results.py b/wqflask/wqflask/correlation/show_corr_results.py index 3b8b7ba2..3b1ac87d 100644 --- a/wqflask/wqflask/correlation/show_corr_results.py +++ b/wqflask/wqflask/correlation/show_corr_results.py @@ -13,19 +13,10 @@ # This program is available from Source Forge: at GeneNetwork Project # (sourceforge.net/projects/genenetwork/). # -# Contact Drs. Robert W. Williams and Xiaodong Zhou (2010) -# at rwilliams@uthsc.edu and xzhou15@uthsc.edu -# +# Contact Dr. Robert W. Williams at rwilliams@uthsc.edu # # # This module is used by GeneNetwork project (www.genenetwork.org) -# -# Created by GeneNetwork Core Team 2010/08/10 -# -# Last updated by NL 2011/02/11 -# Last updated by Christian Fernandez 2012/04/07 -# Refactored correlation calculation into smaller functions in preparation of -# separating html from existing code from __future__ import absolute_import, print_function, division @@ -34,7 +25,6 @@ import string import cPickle import os import time -#import pyXLWriter as xl import pp import math import collections @@ -103,29 +93,29 @@ class CorrelationResults(object): with Bench("Doing correlations"): helper_functions.get_species_dataset_trait(self, start_vars) self.dataset.group.read_genotype_file() - + corr_samples_group = start_vars['corr_samples_group'] - + self.sample_data = {} self.corr_method = start_vars['corr_sample_method'] - + #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.parlist + self.dataset.group.f1list + self.dataset.group.samplelist) - + #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': self.process_samples(start_vars, self.this_trait.data.keys(), primary_samples) - + self.target_dataset = data_set.create_dataset(start_vars['corr_dataset']) self.target_dataset.get_trait_data() @@ -141,61 +131,72 @@ class CorrelationResults(object): this_trait_values.append(sample_value) target_values.append(target_sample_value) - this_trait_values, target_values = normalize_values(this_trait_values, target_values) + this_trait_values, target_values, num_overlap = normalize_values(this_trait_values, + target_values) if self.corr_method == 'pearson': sample_r, sample_p = scipy.stats.pearsonr(this_trait_values, target_values) else: sample_r, sample_p = scipy.stats.spearmanr(this_trait_values, target_values) - self.correlation_data[trait] = [sample_r, sample_p] + self.correlation_data[trait] = [sample_r, sample_p, num_overlap] self.correlation_data = collections.OrderedDict(sorted(self.correlation_data.items(), key=lambda t: -abs(t[1][0]))) - self.correlation_data_slice = collections.OrderedDict() + self.correlation_results = [] + + #self.correlation_data_slice = collections.OrderedDict() for trait_counter, trait in enumerate(self.correlation_data.keys()[:300]): - trait_object = GeneralTrait(dataset=self.dataset, name=trait) - if self.dataset.type == 'ProbeSet': - trait_info = collections.OrderedDict( - correlation = float(self.correlation_data[trait][0]), - p_value = float(self.correlation_data[trait][1]), - symbol = trait_object.symbol, - alias = trait_object.alias, - description = trait_object.description, - chromosome = trait_object.chr, - mb = trait_object.mb - ) - if hasattr(trait_object, 'mean'): - trait_info[mean] = trait_object.mean - if hasattr(trait_object, 'lrs'): - trait_info[lrs] = trait_object.lrs - if hasattr(trait_object, 'locus_chr'): - trait_info[locus_chr] = trait_object.locus_chr - if hasattr(trait_object, 'locus_mb'): - trait_info[locus_mb] = trait_object.locus_mb - elif self.dataset.type == 'Geno': - trait_info = collections.OrderedDict( - correlation = float(self.correlation_data[trait][0]), - p_value = float(self.correlation_data[trait][1]), - symbol = trait_object.symbol, - alias = trait_object.alias, - description = trait_object.description, - chromosome = trait_object.chr, - mb = trait_object.mb - ) - else: # 'Publish' - trait_info = collections.OrderedDict( - correlation = float(self.correlation_data[trait][0]), - p_value = float(self.correlation_data[trait][1]), - symbol = trait_object.symbol, - alias = trait_object.alias, - description = trait_object.description, - chromosome = trait_object.chr, - mb = trait_object.mb - ) - self.correlation_data_slice[trait] = trait_info + trait_object = GeneralTrait(dataset=self.dataset, name=trait, get_qtl_info=True) + trait_object.sample_r = self.correlation_data[trait][0] + trait_object.sample_p = self.correlation_data[trait][1] + trait_object_num_overlap = self.correlation_data[trait][2] + self.correlation_results.append(trait_object) + + #self.correlation_data_slice[trait] = self.correlation_data[trait] + #self.correlation_data_slice[trait].append(trait_object) + #if self.dataset.type == 'ProbeSet': + # trait_info = collections.OrderedDict( + # correlation = float(self.correlation_data[trait][0]), + # p_value = float(self.correlation_data[trait][1]), + # symbol = trait_object.symbol, + # alias = trait_object.alias, + # description = trait_object.description, + # chromosome = trait_object.chr, + # mb = trait_object.mb + # ) + # if trait_object.mean: + # trait_info[mean] = trait_object.mean + # if hasattr(trait_object, 'mean'): + # trait_info[mean] = trait_object.mean + # if hasattr(trait_object, 'lrs'): + # trait_info[lrs] = trait_object.lrs + # if hasattr(trait_object, 'locus_chr'): + # trait_info[locus_chr] = trait_object.locus_chr + # if hasattr(trait_object, 'locus_mb'): + # trait_info[locus_mb] = trait_object.locus_mb + #elif self.dataset.type == 'Geno': + # trait_info = collections.OrderedDict( + # correlation = float(self.correlation_data[trait][0]), + # p_value = float(self.correlation_data[trait][1]), + # symbol = trait_object.symbol, + # alias = trait_object.alias, + # description = trait_object.description, + # chromosome = trait_object.chr, + # mb = trait_object.mb + # ) + #else: # 'Publish' + # trait_info = collections.OrderedDict( + # correlation = float(self.correlation_data[trait][0]), + # p_value = float(self.correlation_data[trait][1]), + # symbol = trait_object.symbol, + # alias = trait_object.alias, + # description = trait_object.description, + # chromosome = trait_object.chr, + # mb = trait_object.mb + # ) #XZ, 09/18/2008: get all information about the user selected database. #target_db_name = fd.corr_dataset @@ -1067,8 +1068,9 @@ def normalize_values(values_1, values_2): if values_1[i]!= None and values_2[i]!= None: X.append(values_1[i]) Y.append(values_2[i]) + num_overlap = len(X) - return (X, Y) + return (X, Y, num_overlap) def cal_correlation(values_1, values_2): diff --git a/wqflask/wqflask/search_results.py b/wqflask/wqflask/search_results.py index e171f1ab..4238aa7f 100644 --- a/wqflask/wqflask/search_results.py +++ b/wqflask/wqflask/search_results.py @@ -107,7 +107,7 @@ class SearchResultPage(object): print("foo locals are:", locals()) trait_id = result[0] this_trait = GeneralTrait(dataset=self.dataset, name=trait_id) - this_trait.retrieve_info(QTL=True) + this_trait.retrieve_info(get_qtl_info=True) self.trait_list.append(this_trait) self.dataset.get_trait_info(self.trait_list, species) diff --git a/wqflask/wqflask/templates/correlation_page.html b/wqflask/wqflask/templates/correlation_page.html index b06f7096..efbf689c 100644 --- a/wqflask/wqflask/templates/correlation_page.html +++ b/wqflask/wqflask/templates/correlation_page.html @@ -17,30 +17,37 @@ <thead> <tr> <th>Trait</th> + <th>Symbol</th> + <th>Alias</th> + <th>Description</th> + <th>Location</th> + <th>Mean Expr</th> + <th>Max LRS</th> + <th>Max LRS Location</th> {% if corr_method == 'pearson' %} <th>Sample r</th> + <th>N Cases</th> <th>Sample p(r)</th> {% else %} <th>Sample rho</th> <th>Sample p(rho)</th> {% endif %} - <th>Symbol</th> - <th>Alias</th> - <th>Description</th> - <th>Location</th> </tr> </thead> <tbody> - {% for trait in correlation_data_slice %} + {% for trait in correlation_results %} <tr> - <td>{{ trait }}</td> - <td>{{ correlation_data_slice[trait].correlation }}</td> - <td>{{ correlation_data_slice[trait].p_value }}</td> - <td>{{ correlation_data_slice[trait].symbol }}</td> - <td>{{ correlation_data_slice[trait].alias }}</td> - <td>{{ correlation_data_slice[trait].description }}</td> - <td>Chr{{ correlation_data_slice[trait].chromosome }}: {{ correlation_data_slice[trait].mb }}</td> - {# <td>{{ correlation_data_slice[trait][2].__dict__ }}</td> #} + <td>{{ trait.name }}</td> + <td>{{ trait.symbol }}</td> + <td>{{ trait.alias }}</td> + <td>{{ trait.description }}</td> + <td>Chr{{ trait.chr }}: {{ trait.mb }}</td> + <td>{{ trait.mean }}</td> + <td>{{ trait.lrs }}</td> + <td>Chr{{ trait.locus_chr }}: {{ trait.locus_mb }}</td> + <td>{{ trait.sample_r }}</td> + <td>{{ trait.num_overlap }}</td> + <td>{{ trait.sample_p }}</td> </tr> {% endfor %} </tbody> |