Complex traits

dataset/config/complex_traits.csv

@@ -0,0 +1,120 @@
+trait
+AD
+AFib
+AG
+Age_at_Menarche
+Age_at_Menopause
+AID
+Alb
+ALP
+ALT
+Alzheimer
+AMD
+ApoA
+ApoB
+AST
+Asthma
+Balding_Type4
+Baso
+Benign_Neoplasms
+BFP
+Blood_Clot_Lung
+BMI
+BrC
+BW
+Ca
+CAD
+Carpal_Tunnel_Syndrome
+Cataract
+CD
+Cholelithiasis
+Cirrhosis
+College
+COPD
+Coxarthrosis
+CRC
+CRP
+DBP
+Depression
+Diverticulosis
+DVT
+eBMD
+EduYears
+eGFR
+eGFRcys
+Eosino
+FedUp_Feelings
+FEV1FVC
+Fibroblastic_Disorders
+GGT
+Glaucoma
+Glucose
+Guilty_Feelings
+Hb
+HbA1c
+HDLC
+Height
+Ht
+Hypothyroidism
+IBD
+IGF1
+Inguinal_Hernia
+Insomnia
+Irritability
+IS
+LDLC
+LipoA
+Loneliness
+LOY
+LuC
+Lym
+Malignant_Neoplasms
+MAP
+MCH
+MCHC
+MCP
+MCV
+MI
+Migraine
+Miserableness
+Mono
+Mood_Swings
+Morning_Person
+NAP
+Nervous_Feelings
+Neuroticism
+Neutro
+P
+Plt
+PP
+PrC
+RA
+RBC
+Risk_Taking
+SBP
+sCr
+Sensitivity
+SHBG
+SkC
+Smoking_CPD
+Smoking_Ever_Never
+Suffer_from_Nerves
+T1D
+T2D
+TBil
+TC
+Tense
+Testosterone_F
+Testosterone_M
+TG
+TP
+UA
+UF
+Urea
+Urolithiasis
+Varicose_Veins
+VitD
+WBC
+WHRadjBMI
+Worrier
+Worry_Too_Long

dataset/config/config.yaml

@@ -1,4 +1,5 @@
 annotation_url: "http://ftp.ensembl.org/pub/release-107/gtf/homo_sapiens/Homo_sapiens.GRCh38.107.chr.gtf.gz"
+genome_url: "http://ftp.ensembl.org/pub/release-107/fasta/homo_sapiens/dna/Homo_sapiens.GRCh38.dna_sm.primary_assembly.fa.gz"
 
 clinvar:
   release: 20251019

dataset/workflow/Snakefile

@@ -9,3 +9,13 @@ include: "rules/gnomad.smk"
 include: "rules/hgmd.smk"
 include: "rules/mendelian_traits.smk"
 include: "rules/smedley_et_al.smk"
+include: "rules/complex_traits.smk"
+include: "rules/ldscore.smk"
+
+
+rule all:
+    input:
+        "results/dataset/mendelian_traits_matched_9/test.parquet",
+        "results/feature_performance/mendelian_traits_matched_9.parquet",
+        "results/dataset/complex_traits_matched_9/test.parquet",
+        "results/feature_performance/complex_traits_matched_9.parquet",

dataset/workflow/rules/common.smk

@@ -1,9 +1,10 @@
+from gpn.data import Genome
 import pandas as pd
 import polars as pl
 from cyvcf2 import VCF
 from sklearn.metrics import average_precision_score
 
-from traitgym.intervals import add_exon, add_tss
+from traitgym.intervals import add_exon, add_tss, build_dataset
 from traitgym.matching import match_features
 from traitgym.variants import (
     COORDINATES,
@@ -12,4 +13,12 @@ from traitgym.variants import (
     filter_snp,
     filter_chroms,
     lift_hg19_to_hg38,
+    check_ref_alt,
 )
+
+
+rule download_genome:
+    output:
+        "results/genome.fa.gz",
+    shell:
+        "wget {config[genome_url]} -O {output}"