Initial commit: chrXatlas chromosome X evidence atlas

Pipeline (src/xatlas + scripts 00-14), curated panel configs,
scoring weights, docs, test suite, and interactive frontend
(site/ with homepage, panel detail, trait detail, search).

Author: smkwray

.gitignore

@@ -0,0 +1,43 @@
+# Environment
+.env
+.venv/
+
+# Python
+__pycache__/
+*.pyc
+*.egg-info/
+dist/
+build/
+
+# Data (large, not tracked)
+data/
+site/data/
+
+# Tabix index files
+*.tbi
+*.bgz.tbi
+
+# Caches
+.pytest_cache/
+.ruff_cache/
+.mypy_cache/
+.cache/
+
+# OS
+.DS_Store
+
+# Playwright / screenshots
+.playwright-mcp/
+*.png
+
+# Agent / plan / working notes (not for repo)
+do/
+CODEX_HANDOFF.md
+CLAUDE.md
+.claude/
+*.plan
+*.plan.md
+*handoff*
+*todo*
+uv.lock
+*.tbi

Makefile

@@ -0,0 +1,33 @@
+PYTHON ?= python
+
+setup:
+	$(PYTHON) -m venv .venv
+	. .venv/bin/activate && pip install -r requirements.txt && pip install -e .
+
+fetch-manifests:
+	$(PYTHON) scripts/00_fetch_panukb_manifests.py
+	$(PYTHON) scripts/04_prepare_eqtl_index.py
+
+select-traits:
+	$(PYTHON) scripts/01_select_seed_traits.py --panel config/panel_small.csv
+
+extract-x:
+	$(PYTHON) scripts/02_extract_panukb_x.py
+
+genes:
+	$(PYTHON) scripts/03_build_x_gene_catalog.py
+
+loci:
+	$(PYTHON) scripts/05_call_x_loci.py
+
+eqtl:
+	$(PYTHON) scripts/06_fetch_eqtl_region_hits.py
+
+map-genes:
+	$(PYTHON) scripts/07_map_loci_to_genes.py
+
+release:
+	$(PYTHON) scripts/08_export_release_tables.py
+
+test:
+	$(PYTHON) -m pytest

README.md

@@ -0,0 +1,11 @@
+study_id,priority,reason
+GTEx,1,Imported broad tissue resource with chrX support
+CommonMind,2,Brain tissue with chrX support
+Braineac2,3,Brain tissue with chrX support
+Young_2019,4,Microglia chrX support
+CEDAR,5,Immune cell / tissue chrX support
+Fairfax_2012,6,B-cell chrX support
+Fairfax_2014,7,Monocyte chrX support
+Naranbhai_2015,8,Neutrophil chrX support
+FUSION,9,Muscle and adipose nonPAR support
+iPSCORE,10,iPSC nonPAR support

config/eqtl_priority_studies.csv

@@ -0,0 +1,22 @@
+query_id,domain,priority,query,preferred_trait_type,preferred_pheno_sex,notes
+albumin,biochemistry,1,Albumin,biomarkers,both_sexes,High-yield core protein marker from the independent-set build
+alanine_aminotransferase,biochemistry,2,Alanine aminotransferase,biomarkers,both_sexes,High-yield liver-adjacent biochemistry marker
+alkaline_phosphatase,biochemistry,3,Alkaline phosphatase,biomarkers,both_sexes,Strong chrX biochemistry signal
+apolipoprotein_a,lipoproteins,4,Apolipoprotein A,biomarkers,both_sexes,Supported lipid transport marker
+apolipoprotein_b,lipoproteins,5,Apolipoprotein B,biomarkers,both_sexes,Supported atherogenic lipid marker
+c_reactive_protein,inflammation,6,C-reactive protein,biomarkers,both_sexes,Inflammation marker with broad support
+calcium,mineral,7,Calcium,biomarkers,both_sexes,Supported mineral marker
+cholesterol,lipoproteins,8,Cholesterol,biomarkers,both_sexes,General lipid anchor
+creatinine,kidney,9,Creatinine,biomarkers,both_sexes,Renal biochemistry anchor
+cystatin_c,kidney,10,Cystatin C,biomarkers,both_sexes,Creatinine-independent renal marker
+gamma_glutamyltransferase,liver,11,Gamma glutamyltransferase,biomarkers,both_sexes,Strong liver enzyme signal
+glycated_haemoglobin_hba1c,glycemic,12,Glycated haemoglobin (HbA1c),biomarkers,both_sexes,Glycemic axis anchor
+hdl_cholesterol,lipoproteins,13,HDL cholesterol,biomarkers,both_sexes,Supported protective lipid marker
+igf_1,endocrine,14,IGF-1,biomarkers,both_sexes,Strong endocrine growth-axis marker
+ldl_direct,lipoproteins,15,LDL direct,biomarkers,both_sexes,Supported LDL anchor
+phosphate,mineral,16,Phosphate,biomarkers,both_sexes,Smaller but clean supported mineral signal
+shbg,endocrine,17,SHBG,biomarkers,both_sexes,Supported endocrine transport marker
+total_protein,biochemistry,18,Total protein,biomarkers,both_sexes,Supported circulating protein marker
+triglycerides,lipoproteins,19,Triglycerides,biomarkers,both_sexes,Strong lipid metabolism signal
+urea,kidney,20,Urea,biomarkers,both_sexes,Strong renal/metabolic marker
+vitamin_d,micronutrients,21,Vitamin D,biomarkers,both_sexes,Supported micronutrient anchor

config/panel_blood_biochemistry_core.csv

@@ -0,0 +1,49 @@
+query_id,domain,priority,query,preferred_trait_type,preferred_pheno_sex,notes
+bmi,anthropometrics,1,body mass index,continuous,both_sexes,Core anthropometric trait
+height,anthropometrics,1,standing height,continuous,both_sexes,Core anthropometric trait
+waist,anthropometrics,2,waist circumference,continuous,both_sexes,Adiposity distribution
+hip,anthropometrics,3,hip circumference,continuous,both_sexes,Adiposity distribution
+body_fat_mass,body_composition,1,Whole body fat mass,continuous,both_sexes,Whole-body adiposity complement to BMI waist hip
+grip_strength,musculoskeletal,1,Hand grip strength (left),continuous,both_sexes,Objective strength trait
+heel_bmd,bone_health,1,Heel bone mineral density (BMD),continuous,both_sexes,Skeletal trait with strong ascertainment
+sbp,cardiometabolic,1,systolic blood pressure,continuous,both_sexes,Cardiovascular trait
+dbp,cardiometabolic,2,diastolic blood pressure,continuous,both_sexes,Cardiovascular trait
+current_smoking,substance_use,3,Current tobacco smoking,continuous,both_sexes,Exposure trait with observed chrX loci in probe panel
+ldl,lipids,1,LDL direct,biomarkers,both_sexes,Lipid trait
+hdl,lipids,2,HDL cholesterol,biomarkers,both_sexes,Lipid trait
+tg,lipids,3,triglycerides,biomarkers,both_sexes,Lipid trait
+apolipoprotein_a,lipids,4,Apolipoprotein A,biomarkers,both_sexes,Additional lipid transport biology
+apolipoprotein_b,lipids,5,Apolipoprotein B,biomarkers,both_sexes,Atherogenic lipid marker
+hba1c,glycemic,1,glycated haemoglobin,biomarkers,both_sexes,Glycemic trait
+glucose,glycemic,2,glucose,biomarkers,both_sexes,Glycemic trait
+t2d,disease,1,type 2 diabetes,phecode,both_sexes,Common disease anchor
+coronary_atherosclerosis,disease,2,Coronary atherosclerosis,phecode,both_sexes,Disease anchor with observed chrX loci in probe panel
+bilirubin_total,liver,5,Total bilirubin,biomarkers,both_sexes,Observed chrX-signal biomarker replacement for zero-locus seed
+hypothyroidism,disease,4,Hypothyroidism,phecode,both_sexes,Common endocrine disease anchor
+hb,hematology,1,Haemoglobin concentration,continuous,both_sexes,Hematologic trait
+rbc,hematology,2,red blood cell (erythrocyte) count,continuous,both_sexes,Hematologic trait
+plt,hematology,3,platelet count,biomarkers,both_sexes,Hematologic trait
+lymphocyte,hematology,4,Lymphocyte count,continuous,both_sexes,Immune cell count anchor
+crp,inflammation,1,C-reactive protein,biomarkers,both_sexes,Inflammation anchor
+alt,liver,1,alanine aminotransferase,biomarkers,both_sexes,Liver biomarker
+alp,liver,2,alkaline phosphatase,biomarkers,both_sexes,Liver biomarker
+ast,liver,3,Aspartate aminotransferase,biomarkers,both_sexes,Complementary liver enzyme
+ggt,liver,4,Gamma glutamyltransferase,biomarkers,both_sexes,Complementary liver enzyme
+albumin,inflammation_nutrition,1,Albumin,biomarkers,both_sexes,Nutritional / inflammatory biomarker
+creatinine,kidney,1,creatinine,biomarkers,both_sexes,Kidney biomarker
+urate,kidney,2,urate,biomarkers,both_sexes,Metabolic / renal
+egfr,kidney,3,"Estimated glomerular filtration rate, serum creatinine",continuous,both_sexes,Renal function estimate
+cystatin_c,kidney,4,Cystatin C,biomarkers,both_sexes,Creatinine-independent filtration marker
+urea,kidney,5,Urea,biomarkers,both_sexes,Renal / metabolic complement
+testosterone,endocrine,1,testosterone,biomarkers,both_sexes,Endocrine trait
+shbg,endocrine,2,SHBG,biomarkers,both_sexes,Exact SHBG manifest label to avoid prior mis-selection
+igf_1,endocrine,3,IGF-1,biomarkers,both_sexes,Growth / aging endocrine axis
+vitamin_d,micronutrients,1,Vitamin D,biomarkers,both_sexes,Micronutrient biology
+fev1,respiratory,1,Forced expiratory volume in 1-second (FEV1),continuous,both_sexes,Core lung function trait
+fvc,respiratory,2,Forced vital capacity (FVC),continuous,both_sexes,Complementary lung function trait
+insomnia,neuropsychiatric,1,Sleeplessness / insomnia,continuous,both_sexes,Neuropsychiatric proxy
+depression,neuropsychiatric,2,Frequency of depressed mood in last 2 weeks,continuous,both_sexes,Neuropsychiatric proxy
+neuroticism,behavioral,1,neuroticism score,continuous,both_sexes,Behavioral trait
+fluid_intelligence,cognitive,1,fluid intelligence score,continuous,both_sexes,Cognitive trait
+menarche,reproductive,1,Age when periods started (menarche),continuous,both_sexes,Sex-specific trait
+menopause,reproductive,2,age at menopause,continuous,females,Sex-specific trait

config/panel_expanded.csv

@@ -0,0 +1,18 @@
+query_id,domain,priority,query,preferred_trait_type,preferred_pheno_sex,notes
+fluid_intelligence,cognitive,1,fluid intelligence score,continuous,both_sexes,Core reasoning trait
+reaction_time,cognitive,1,Mean time to correctly identify matches,continuous,both_sexes,Processing speed trait
+prospective_memory,cognitive,2,Prospective memory result,continuous,both_sexes,Memory task summary
+numeric_memory,cognitive,2,Maximum digits remembered correctly,continuous,both_sexes,Numeric memory task
+neuroticism,behavioral,1,neuroticism score,continuous,both_sexes,Aggregate affect trait
+risk_taking,behavioral,2,Risk taking,categorical,both_sexes,Risk preference proxy
+mood_swings,behavioral,3,Mood swings,categorical,both_sexes,Mood instability proxy
+irritability,behavioral,4,Irritability,categorical,both_sexes,Aggression-adjacent proxy
+depressed_mood,mental_health,1,Frequency of depressed mood in last 2 weeks,continuous,both_sexes,Mood symptom
+trouble_relaxing,mental_health,2,Recent trouble relaxing,continuous,both_sexes,Anxiety symptom
+worry_cannot_stop,mental_health,3,Frequency of inability to stop worrying during worst period of anxiety,continuous,both_sexes,Worry severity
+anxious_month,mental_health,4,"Ever felt worried, tense, or anxious for most of a month or longer",categorical,both_sexes,Anxiety propensity
+insomnia,sleep,1,Sleeplessness / insomnia,continuous,both_sexes,Sleep disruption trait
+sleep_duration,sleep,2,Sleep duration,continuous,both_sexes,Core sleep trait
+current_smoking,substance_use,1,Current tobacco smoking,continuous,both_sexes,Behavioral exposure
+alcohol_frequency,substance_use,2,Alcohol intake frequency,continuous,both_sexes,Alcohol behavior
+heavy_drinking,substance_use,3,Frequency of consuming six or more units of alcohol,continuous,both_sexes,Binge-drinking proxy

config/panel_mind_focus.csv

@@ -0,0 +1,11 @@
+query_id,domain,priority,query,preferred_trait_type,preferred_pheno_sex,notes
+reaction_time,cognitive,1,Mean time to correctly identify matches,continuous,both_sexes,Best-performing direct cognitive anchor
+fluid_intelligence,cognitive,2,fluid intelligence score,continuous,both_sexes,Keep one direct reasoning trait even though current support is weak
+neuroticism,behavioral,1,neuroticism score,continuous,both_sexes,Aggregate affect trait with usable chrX support
+risk_taking,behavioral,2,Risk taking,categorical,both_sexes,Risk preference proxy
+mood_swings,behavioral,3,Mood swings,categorical,both_sexes,Mood instability proxy
+irritability,behavioral,4,Irritability,categorical,both_sexes,Aggression-adjacent proxy with usable signal
+depressed_mood,mental_health,1,Frequency of depressed mood in last 2 weeks,continuous,both_sexes,Mood symptom with prior support
+insomnia,sleep,1,Sleeplessness / insomnia,continuous,both_sexes,Behaviorally relevant sleep-disruption trait
+current_smoking,substance_use,1,Current tobacco smoking,continuous,both_sexes,Robust behavior/exposure trait
+alcohol_frequency,substance_use,2,Alcohol intake frequency,continuous,both_sexes,Best-performing alcohol behavior trait

config/panel_mind_risk_core.csv

@@ -0,0 +1,9 @@
+query_id,domain,priority,query,preferred_trait_type,preferred_pheno_sex,notes
+coronary_atherosclerosis,disease,1,Coronary atherosclerosis,phecode,both_sexes,Probe replacement for myocardial infarction
+rheumatoid_arthritis,disease,2,Rheumatoid arthritis,phecode,both_sexes,Probe inflammatory disease anchor
+psoriasis,disease,3,Psoriasis,phecode,both_sexes,Probe dermatologic disease anchor
+sleep_duration,sleep,1,Sleep duration,continuous,both_sexes,Probe behavioral replacement for pulse rate
+current_smoking,substance_use,2,Current tobacco smoking,continuous,both_sexes,Probe exposure trait replacement for pulse rate
+bilirubin_total,liver,1,Total bilirubin,biomarkers,both_sexes,Probe biomarker replacement with likely chrX loci
+copd,respiratory,1,Doctor diagnosed COPD (chronic obstructive pulmonary disease),categorical,both_sexes,Probe respiratory disease replacement for asthma
+wheeze,respiratory,2,Wheeze or whistling in the chest in last year,categorical,both_sexes,Probe symptom-level respiratory replacement for asthma

config/panel_replacement_probe.csv

@@ -0,0 +1,12 @@
+query_id,domain,priority,query,preferred_trait_type,preferred_pheno_sex,notes
+insomnia,sleep,1,Sleeplessness / insomnia,continuous,both_sexes,Direct sleep-disruption trait
+sleep_duration,sleep,2,Sleep duration,continuous,both_sexes,Core sleep quantity trait
+risk_taking,behavioral,1,Risk taking,categorical,both_sexes,Risk preference proxy
+mood_swings,behavioral,2,Mood swings,categorical,both_sexes,Mood instability proxy
+irritability,behavioral,3,Irritability,categorical,both_sexes,Aggression-adjacent proxy
+trouble_relaxing,mental_health,1,Recent trouble relaxing,continuous,both_sexes,Anxiety symptom
+worry_cannot_stop,mental_health,2,Frequency of inability to stop worrying during worst period of anxiety,continuous,both_sexes,Worry severity
+depressed_mood,mental_health,3,Frequency of depressed mood in last 2 weeks,continuous,both_sexes,Mood symptom
+current_smoking,substance_use,1,Current tobacco smoking,continuous,both_sexes,Behavioral exposure
+alcohol_frequency,substance_use,2,Alcohol intake frequency,continuous,both_sexes,Alcohol behavior
+heavy_drinking,substance_use,3,Frequency of consuming six or more units of alcohol,continuous,both_sexes,Binge-drinking proxy