def main(): db = MongoDB() # Creates main supplementary table with GeVIR, LOEUF and VIRLoF scores # is required to run "draw_web_gene_scores" method in figures.py # enrichment_offset is used to calculate AD/AR fold-enrichment # 5% offset = 18,352 / 20 ~= 918 # 5% offset = 19,361 / 20 ~= 968 # Supplementary Table 2 export_gene_scores(db, enrichment_offset=AD_AR_ENRICHMENT_OFFSET, include_gene_groups=True)
def main():
db = MongoDB()
# Create "variant_regions" collection from gnomAD variants data
# This method does not have to be rerun to recreate GeVIR scores.
calculate_all_transcripts_regions(db)
# Create GeVIR scores, requires "variant_regions" collection
# If regions collection was created with INCLUDE_GNOMAD_OUTLIERS=True,
# only these methods have to be rerun with INCLUDE_GNOMAD_OUTLIERS=False
# to create gene scores for a dataset without outliers
# Creates Supplementary Tables 7 and 8
create_gevir_scores(db, no_gerp=True)
create_gevir_scores(db, no_gerp=False)
def main():
db = MongoDB()
# For the first run, please carefully read the comments and uncomment all of the following functions:
# These functions create "variants_hwe_pop" collection which stores
# data related to variant deviation from Hardy-Weinberg Equilibrium in each population.
# "variants_hwe_pop" collection is then updated with aggregated frequencies of alternative alleles (alt_af),
# which are used for further variant filtering (high alt_af might compromise HWE analysis results).
#analyse_gnomad_variants_deviations_from_hwe(db)
#add_alt_af_data(db)
# These functions create temporary "variants_hwe_regions" collection
# and add flags to "variants_hwe_pop" which indicate whether variants
# are located in tandem repeat and segmental duplication regions or not.
#create_hwe_variants_regions(db)
#update_variants_hwe_pop_with_region_data(db)
# This function obtains Allele Balance (AB) data from gnomAD for rare variants (i.e. 0.001<=AF<=RARE_HET_EXCESS_MAX_AF (0.1))
# It creates "rare_variants_ab" collection, which is used for further variant filtering (low AB might be a sign of sequencing errors).
# !!! IMPORTANT !!!
# It works with gnomAD API (i.e. requires internet connection) and can take up to a couple of days to run!!!
######create_rare_variants_ab(db)
# This function creates a dataset ("rare_het_excess_variants" collection) of variants with heterozygous excess (HetExc)
#create_rare_het_excess_variants(db)
# This function marks HetExc variants with skewed allele balance (>0.9 and 0.8)
#update_rare_het_excess_variants_with_skeweb_ab_stats(db, remove=False)
# These functions export HetExc variant chromosomal coordinates for LiftOver conversion (this has to be done manually),
# import converted variants (./tables/het_exc_variants_build_38.csv) back to the "rare_het_excess_variants" collection
# and use these new coordinates to get allele data from gnomAD v3 via API.
#export_rare_het_exc_variants_for_lift_over(db)
#import_rare_het_exc_variants_lift_over_results(db)
#update_rare_het_exc_variants_with_gnomad_3_data(db, clean=False)
# Multiple Test corrections, not used since they are too conservative.
# HBB example was found, but not CFTR:
#calculate_multiple_testing_adjustments(db)
#add_multiple_testing_adjustments(db, remove=False)
#export_adjusted_p_value_stats(db)
#calculate_eas_inbreeding_coeff_variants(db)
pass
def main():
db = MongoDB()
# Creates additional database (gerp) with gerp score for each chromosomal position
# IMPORTANT: this operation might require quite a lot of time to run (progress for each chromosome will be displayed)
# Final database size should be ~36.6 GB (storage size occupied on disk)
import_gerp(db)
# ENS CDS FASTA
import_ens_cds_fasta(db, ENS_CDS_FASTA, 'ens_cds_fasta')
import_ens_cds_fasta(db, ENS_AA_FASTA, 'ens_aa_fasta')
# gnomAD scores (22/10/18)
import_gnomad_scores(db, new_gnomad_file=False)
# OMIM data donwloaded (11/13/18)
import_omim(db)
# ClinVar data donwloaded (21/08/18)
import_clin_var(db)
# Conservative Coding RegionS
# https://s3.us-east-2.amazonaws.com/ccrs/ccr.html
import_ccrs(db)
count_gene_ccrs(db)
# Mac Arthur Datasets
# https://github.com/macarthur-lab/gene_lists
import_mac_arthur_gene_lists(db)
# Mouse Het Lethal Knockout Genes (5/02/19)
# http://www.mousemine.org/mousemine/templates.do
# Mammalian phenotypes (MP terms) --> Mouse genes and models
# Search for *lethal*
# Alternatively, use following method to query mousemine database:
# query_mousemine_to_create_mouse_het_lethal_knockout_genes()
import_mouse_het_lethal_knockout_genes(db)
# HUGO (15/11/19)
import_hugo_genes(db)
def main():
db = MongoDB()
import re
import requests
import pymongo
from flask import Blueprint, render_template, jsonify, request
from config import MONGO_IP
from interface.service import Assert
from common import generate_id, MongoDB
interface = Blueprint('interface', __name__, static_folder='interface_static', template_folder='interface_templates')
db = MongoDB(MONGO_IP, 27017)
@interface.route('/debug')
def page_debug():
return render_template('interface_debug.html')
@interface.route('/edit/<id>')
def page_edit(id):
return render_template('interface_edit.html')
@interface.route('/api/v2/load_api', methods=['POST'])
def load_api():
data = request.get_json()
db.switch_database_collection('interface', 'api')
return jsonify({
'status_code': 200,
'message': 'ok',
'data': db.find_one(data)
})
def main():
db = MongoDB()
create_common_gene_scores(db)