#!/usr/bin/env python3 """ Comprehensive 23andMe Genome Analysis Script Analyzes Bill Syrros's raw genotype data for health-relevant SNP associations """ import json from collections import defaultdict from pathlib import Path # SNP database with health associations SNP_DATABASE = { # Cardiovascular / Heart Health 'rs1801133': { 'gene': 'MTHFR', 'variant': 'C677T', 'category': 'Cardiovascular', 'affects': 'Folate metabolism, homocysteine levels', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'Normal folate metabolism, homocysteine levels optimal', 'CT': 'Heterozygous, mildly reduced enzyme activity (~35% reduction)', 'TT': 'Homozygous, significantly reduced enzyme activity (~65% reduction), elevated homocysteine risk' }, 'clinical_significance': 'moderate', 'notes': 'Elevated homocysteine increases cardiovascular and thrombotic risk' }, 'rs1801131': { 'gene': 'MTHFR', 'variant': 'A1298C', 'category': 'Cardiovascular', 'affects': 'Folate metabolism (secondary site)', 'risk_allele': 'C', 'genotype_interpretation': { 'AA': 'Normal enzyme activity', 'AC': 'Mildly reduced enzyme activity', 'CC': 'Moderately reduced enzyme activity' }, 'clinical_significance': 'low', 'notes': 'Less severe than C677T variant' }, 'rs1799963': { 'gene': 'F2 (Prothrombin)', 'variant': 'G20210A', 'category': 'Cardiovascular', 'affects': 'Blood clotting risk', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal, no increased clotting risk', 'GA': 'Heterozygous, 2-3x increased thrombosis risk', 'AA': 'Rare homozygous, significantly increased thrombosis risk' }, 'clinical_significance': 'moderate', 'notes': 'One of the most common hereditary thrombophilias' }, 'rs6025': { 'gene': 'F5 (Factor V)', 'variant': 'Leiden (R506Q)', 'category': 'Cardiovascular', 'affects': 'Blood clotting resistance to anticoagulant protein C', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Wild-type, normal anticoagulation response', 'GA': '3-8x increased thrombosis risk', 'AA': 'Rare, severe increased thrombosis risk' }, 'clinical_significance': 'high', 'notes': 'Factor V Leiden - most common inherited thrombophilia in Europeans' }, 'rs429358': { 'gene': 'APOE', 'variant': 'ε2/ε3/ε4 (Cys112Arg)', 'category': 'Cardiovascular', 'affects': 'Cholesterol metabolism, Alzheimer\'s disease risk', 'risk_allele': 'C (ε4)', 'genotype_interpretation': { 'TT': 'ε2/ε2 genotype (APOE2) - lowest Alzheimer\'s risk, lower LDL', 'TC': 'ε2/ε3 or ε3/ε4 genotype - depends on rs7412', 'CC': 'ε3/ε3 or ε4/ε4 genotype - depends on rs7412' }, 'clinical_significance': 'high', 'notes': 'Requires rs7412 to determine full APOE status' }, 'rs7412': { 'gene': 'APOE', 'variant': 'ε2/ε3/ε4 (Arg158Cys)', 'category': 'Cardiovascular', 'affects': 'Cholesterol metabolism, Alzheimer\'s disease risk', 'risk_allele': 'T (ε2)', 'genotype_interpretation': { 'CC': 'ε3 or ε4 allele', 'CT': 'ε2 or ε3 allele', 'TT': 'ε2/ε2 or ε2/ε3 genotype' }, 'clinical_significance': 'high', 'notes': 'Combined with rs429358 to determine APOE2/3/4 status' }, 'rs1801282': { 'gene': 'PPARG', 'variant': 'Pro12Ala', 'category': 'Metabolic', 'affects': 'Insulin sensitivity, metabolic syndrome risk', 'risk_allele': 'G', 'genotype_interpretation': { 'CC': 'Normal insulin sensitivity', 'CG': 'Ala allele, protective against type 2 diabetes, improved insulin sensitivity', 'GG': 'Pro/Pro, increased metabolic syndrome and obesity risk' }, 'clinical_significance': 'moderate', 'notes': 'Ala allele is protective, reduces diabetes risk by ~25%' }, 'rs662': { 'gene': 'PON1', 'variant': 'Q192R', 'category': 'Cardiovascular', 'affects': 'Oxidative stress protection, HDL function', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'R allele, better protection against oxidative stress', 'GA': 'Heterozygous, intermediate protection', 'AA': 'Q allele, reduced antioxidant capacity' }, 'clinical_significance': 'low', 'notes': 'Affects HDL\'s ability to protect against LDL oxidation' }, 'rs4340': { 'gene': 'ACE', 'variant': 'I/D proxy (Alu repeat)', 'category': 'Cardiovascular', 'affects': 'Blood pressure, ACE enzyme levels', 'risk_allele': 'None (functional variant)', 'genotype_interpretation': { 'AA': 'I/I genotype - lower ACE levels, better endurance capacity', 'GA': 'I/D genotype - intermediate ACE levels', 'GG': 'D/D genotype - higher ACE levels, increased hypertension risk' }, 'clinical_significance': 'moderate', 'notes': 'Note: rs4340 is a proxy SNP for the functional I/D polymorphism' }, 'rs5186': { 'gene': 'AGTR1', 'variant': 'A1166C', 'category': 'Cardiovascular', 'affects': 'Blood pressure regulation', 'risk_allele': 'C', 'genotype_interpretation': { 'AA': 'Lower risk for hypertension', 'AC': 'Intermediate risk', 'CC': 'Increased hypertension and cardiovascular disease risk' }, 'clinical_significance': 'moderate', 'notes': 'Affects angiotensin II signaling in blood vessels' }, 'rs1799983': { 'gene': 'NOS3', 'variant': 'G894T', 'category': 'Cardiovascular', 'affects': 'Nitric oxide production, vascular function', 'risk_allele': 'T', 'genotype_interpretation': { 'GG': 'Normal nitric oxide production, better endothelial function', 'GT': 'Intermediate nitric oxide levels', 'TT': 'Reduced nitric oxide production, impaired vascular relaxation, hypertension risk' }, 'clinical_significance': 'moderate', 'notes': 'Affects endothelial function and vascular health' }, 'rs1800796': { 'gene': 'IL6', 'variant': '-174G/C', 'category': 'Cardiovascular', 'affects': 'Inflammation, IL-6 levels', 'risk_allele': 'C', 'genotype_interpretation': { 'GG': 'Higher IL-6 production, pro-inflammatory', 'GC': 'Intermediate IL-6 levels', 'CC': 'Lower IL-6 production, anti-inflammatory benefit' }, 'clinical_significance': 'low', 'notes': 'IL-6 is a key inflammatory cytokine' }, 'rs1800795': { 'gene': 'IL6', 'variant': '-174G>C', 'category': 'Cardiovascular', 'affects': 'IL-6 levels and inflammation', 'risk_allele': 'G', 'genotype_interpretation': { 'GG': 'Increased IL-6 levels', 'GC': 'Intermediate levels', 'CC': 'Lower IL-6 levels' }, 'clinical_significance': 'low', 'notes': 'May be same as rs1800796' }, 'rs1800629': { 'gene': 'TNF', 'variant': '-308G/A', 'category': 'Cardiovascular', 'affects': 'TNF-alpha inflammation marker', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Lower TNF-alpha production', 'GA': 'Intermediate TNF-alpha levels', 'AA': 'Higher TNF-alpha production, pro-inflammatory' }, 'clinical_significance': 'low', 'notes': 'TNF-alpha is a major inflammatory cytokine' }, 'rs3798220': { 'gene': 'LPA', 'variant': 'IVS25+323C/G', 'category': 'Cardiovascular', 'affects': 'Lipoprotein(a) levels, cardiovascular risk', 'risk_allele': 'G', 'genotype_interpretation': { 'CC': 'Lower Lp(a) levels', 'CG': 'Intermediate Lp(a) levels', 'GG': 'Higher Lp(a) levels, increased cardiovascular risk' }, 'clinical_significance': 'moderate', 'notes': 'Elevated Lp(a) is independent cardiovascular risk factor' }, 'rs10455872': { 'gene': 'LPA', 'variant': 'Pentanucleotide repeat', 'category': 'Cardiovascular', 'affects': 'Lipoprotein(a) levels, cardiovascular risk', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'Lower Lp(a) levels', 'CT': 'Intermediate Lp(a) levels', 'TT': 'Higher Lp(a) levels, increased cardiovascular risk' }, 'clinical_significance': 'moderate', 'notes': 'Works with rs3798220 to determine Lp(a) phenotype' }, # Metabolic / Diabetes / Weight 'rs7903146': { 'gene': 'TCF7L2', 'variant': 'rs7903146', 'category': 'Metabolic', 'affects': 'Type 2 diabetes risk (strongest known locus)', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'Normal diabetes risk (~7%)', 'CT': '~1.4x increased diabetes risk', 'TT': '~2-4x increased type 2 diabetes risk' }, 'clinical_significance': 'high', 'notes': 'Most significant T2D susceptibility gene; each T allele ~20% increased risk' }, 'rs5219': { 'gene': 'KCNJ11', 'variant': 'E23K', 'category': 'Metabolic', 'affects': 'Insulin secretion and glucose control', 'risk_allele': 'A', 'genotype_interpretation': { 'CC': 'K allele, normal insulin secretion', 'CA': 'Heterozygous, intermediate risk', 'AA': 'E allele, increased type 2 diabetes risk' }, 'clinical_significance': 'moderate', 'notes': 'Affects ATP-sensitive potassium channel in pancreatic beta cells' }, 'rs13266634': { 'gene': 'SLC30A8', 'variant': 'R325W', 'category': 'Metabolic', 'affects': 'Zinc transporter, insulin secretion', 'risk_allele': 'A', 'genotype_interpretation': { 'CC': 'Normal, protective', 'CA': 'Intermediate', 'AA': 'Increased diabetes risk' }, 'clinical_significance': 'moderate', 'notes': 'Zinc transport critical for insulin secretion' }, 'rs4402960': { 'gene': 'IGF2BP2', 'variant': 'rs4402960', 'category': 'Metabolic', 'affects': 'Type 2 diabetes risk', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'Lower diabetes risk', 'CT': 'Intermediate risk', 'TT': 'Increased diabetes risk' }, 'clinical_significance': 'low', 'notes': 'Involved in glucose metabolism' }, 'rs10811661': { 'gene': 'CDKN2A/B', 'variant': 'rs10811661', 'category': 'Metabolic', 'affects': 'Type 2 diabetes and pancreatic cancer risk', 'risk_allele': 'A', 'genotype_interpretation': { 'CC': 'Lower risk', 'CA': 'Intermediate risk', 'AA': 'Increased diabetes risk' }, 'clinical_significance': 'moderate', 'notes': 'Cell cycle regulator' }, 'rs9939609': { 'gene': 'FTO', 'variant': 'A/T', 'category': 'Metabolic', 'affects': 'Obesity risk, appetite regulation', 'risk_allele': 'A', 'genotype_interpretation': { 'TT': 'Lower obesity risk', 'TA': 'Intermediate obesity risk (~1.3x)', 'AA': 'Significantly increased obesity risk (~1.6x higher BMI)' }, 'clinical_significance': 'moderate', 'notes': 'Most significant obesity-associated SNP; affects appetite circuits' }, 'rs17782313': { 'gene': 'MC4R', 'variant': 'rs17782313', 'category': 'Metabolic', 'affects': 'Obesity risk, appetite/satiety', 'risk_allele': 'C', 'genotype_interpretation': { 'AA': 'Normal satiety, lower obesity risk', 'AC': 'Intermediate obesity risk', 'CC': 'Increased appetite, higher obesity risk' }, 'clinical_significance': 'moderate', 'notes': 'Melanocortin-4 receptor crucial for appetite control' }, 'rs1042713': { 'gene': 'ADRB2', 'variant': 'Arg16Gly', 'category': 'Metabolic', 'affects': 'Beta-2 adrenergic receptor, metabolic rate', 'risk_allele': 'C', 'genotype_interpretation': { 'AA': 'Arg/Arg, higher metabolic rate and norepinephrine sensitivity', 'AC': 'Intermediate', 'CC': 'Gly/Gly, lower metabolic rate' }, 'clinical_significance': 'low', 'notes': 'Affects sympathetic nervous system response' }, 'rs1042714': { 'gene': 'ADRB2', 'variant': 'Gln27Glu', 'category': 'Metabolic', 'affects': 'Beta-2 adrenergic receptor, weight regulation', 'risk_allele': 'G', 'genotype_interpretation': { 'AA': 'Gln/Gln, lower weight gain risk', 'AG': 'Intermediate', 'GG': 'Glu/Glu, greater weight gain risk' }, 'clinical_significance': 'low', 'notes': 'Works with rs1042713 for metabolic effects' }, 'rs4994': { 'gene': 'ADRB3', 'variant': 'Trp64Arg', 'category': 'Metabolic', 'affects': 'Beta-3 adrenergic receptor, metabolic efficiency', 'risk_allele': 'C', 'genotype_interpretation': { 'TT': 'Trp/Trp, normal metabolism', 'TC': 'Trp/Arg, intermediate', 'CC': 'Arg/Arg, reduced metabolic efficiency, higher obesity risk' }, 'clinical_significance': 'low', 'notes': 'Involved in thermogenesis and fat mobilization' }, # Nutrient Metabolism / Diet 'rs4988235': { 'gene': 'MCM6/LCT', 'variant': 'C/T (-13910)', 'category': 'Nutrient Metabolism', 'affects': 'Lactose tolerance', 'risk_allele': 'A (old nomenclature)', 'genotype_interpretation': { 'CC': 'Lactose intolerant (likely)', 'CT': 'Lactose tolerant (heterozygous)', 'TT': 'Lactose tolerant (homozygous)' }, 'clinical_significance': 'moderate', 'notes': 'Determines adult lactase persistence; common in Northern European ancestry' }, 'rs1801394': { 'gene': 'MTRR', 'variant': 'A66G', 'category': 'Nutrient Metabolism', 'affects': 'B12 metabolism, methionine cycle', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal B12 metabolism', 'AG': 'Intermediate enzyme activity', 'AA': 'Reduced methionine synthase reductase activity, potential B12/folate issues' }, 'clinical_significance': 'low', 'notes': 'Related to homocysteine metabolism' }, 'rs1805087': { 'gene': 'MTR', 'variant': 'A2756G', 'category': 'Nutrient Metabolism', 'affects': 'B12 and methionine metabolism', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal methionine synthase activity', 'AG': 'Intermediate', 'AA': 'Potential B12/methionine metabolism issues' }, 'clinical_significance': 'low', 'notes': 'Cofactor required for methylation reactions' }, 'rs602662': { 'gene': 'FUT2', 'variant': 'A/G', 'category': 'Nutrient Metabolism', 'affects': 'B12 absorption, gut microbiota', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Secretor status, better B12 absorption', 'GA': 'Intermediate', 'AA': 'Non-secretor, reduced B12 absorption from food' }, 'clinical_significance': 'low', 'notes': 'FUT2 secretor status affects B12 and micronutrient availability' }, 'rs7041': { 'gene': 'GC/VDBP', 'variant': 'D432E', 'category': 'Nutrient Metabolism', 'affects': 'Vitamin D binding protein, vitamin D status', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Type 1f, higher Vitamin D bioavailability', 'GA': 'Type 1s/1f intermediate', 'AA': 'Type 1s, lower Vitamin D bioavailability' }, 'clinical_significance': 'moderate', 'notes': 'Affects vitamin D distribution and bioavailability' }, 'rs4588': { 'gene': 'GC/VDBP', 'variant': 'T436K', 'category': 'Nutrient Metabolism', 'affects': 'Vitamin D binding protein', 'risk_allele': 'T', 'genotype_interpretation': { 'GG': 'Isoform 1f or 2', 'GA': 'Intermediate', 'AA': 'Isoform 2' }, 'clinical_significance': 'moderate', 'notes': 'Works with rs7041 to determine VDBP isoform' }, 'rs10741657': { 'gene': 'CYP2R1', 'variant': 'rs10741657', 'category': 'Nutrient Metabolism', 'affects': 'Vitamin D metabolism, 25-OHD levels', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Higher vitamin D levels', 'GA': 'Intermediate', 'AA': 'Lower vitamin D levels, impaired metabolism' }, 'clinical_significance': 'moderate', 'notes': 'Primary vitamin D 25-hydroxylase in liver' }, 'rs1800562': { 'gene': 'HFE', 'variant': 'C282Y', 'category': 'Nutrient Metabolism', 'affects': 'Iron overload risk (hemochromatosis)', 'risk_allele': 'A', 'genotype_interpretation': { 'CC': 'Normal iron metabolism', 'CA': 'Heterozygous carrier, typically no hemochromatosis', 'AA': 'Homozygous, significant hemochromatosis risk (85% penetrance)' }, 'clinical_significance': 'high', 'notes': 'Most common genetic cause of hemochromatosis' }, 'rs1799945': { 'gene': 'HFE', 'variant': 'H63D', 'category': 'Nutrient Metabolism', 'affects': 'Iron overload risk (secondary)', 'risk_allele': 'G', 'genotype_interpretation': { 'CC': 'Normal', 'CG': 'Heterozygous carrier', 'GG': 'Homozygous, mild risk if combined with C282Y' }, 'clinical_significance': 'low', 'notes': 'Secondary hemochromatosis mutation; rarely causes disease alone' }, 'rs855791': { 'gene': 'TMPRSS6', 'variant': 'A736V', 'category': 'Nutrient Metabolism', 'affects': 'Iron levels and hepcidin regulation', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'A allele, normal iron regulation', 'CT': 'Intermediate', 'TT': 'V allele, lower iron levels' }, 'clinical_significance': 'low', 'notes': 'Regulates iron absorption through hepcidin' }, 'rs12325817': { 'gene': 'BCMO1', 'variant': 'rs12325817', 'category': 'Nutrient Metabolism', 'affects': 'Beta-carotene to vitamin A conversion', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal beta-carotene conversion to vitamin A', 'GA': 'Intermediate conversion', 'AA': 'Poor beta-carotene converter, need more dietary vitamin A' }, 'clinical_significance': 'moderate', 'notes': 'Affects plant-based vitamin A sufficiency' }, 'rs234706': { 'gene': 'CBS', 'variant': 'C699T', 'category': 'Nutrient Metabolism', 'affects': 'Homocysteine and sulfur metabolism', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'Normal cystathionine beta-synthase activity', 'CT': 'Intermediate', 'TT': 'Reduced CBS activity, elevated homocysteine and ammonia' }, 'clinical_significance': 'low', 'notes': 'CBS is gateway to sulfur metabolism' }, 'rs1695': { 'gene': 'GSTP1', 'variant': 'A313G (Ile105Val)', 'category': 'Nutrient Metabolism', 'affects': 'Detoxification, glutathione S-transferase activity', 'risk_allele': 'G', 'genotype_interpretation': { 'AA': 'Normal detox capacity', 'AG': 'Intermediate', 'GG': 'Reduced GSTP1 activity, lower detoxification capacity' }, 'clinical_significance': 'low', 'notes': 'Phase II detox enzyme for environmental toxins' }, 'rs1048943': { 'gene': 'CYP1A1', 'variant': 'A2455G', 'category': 'Nutrient Metabolism', 'affects': 'Phase I detoxification (CYP1A1 induction)', 'risk_allele': 'G', 'genotype_interpretation': { 'AA': 'Normal CYP1A1 induction', 'AG': 'Intermediate', 'GG': 'Increased inducibility, higher detox capacity but more metabolites' }, 'clinical_significance': 'low', 'notes': 'Affects polycyclic aromatic hydrocarbon metabolism' }, 'rs4680': { 'gene': 'COMT', 'variant': 'Val158Met', 'category': 'Mental/Cognitive', 'affects': 'Catechol metabolism, dopamine/norepinephrine breakdown', 'risk_allele': 'A (Met allele)', 'genotype_interpretation': { 'GG': 'Val/Val, faster catechol breakdown, more anxiety-resistant but potentially less focused', 'GA': 'Val/Met, intermediate metabolism', 'AA': 'Met/Met, slower catechol breakdown, higher dopamine/norepinephrine, better focus/motivation, higher stress sensitivity' }, 'clinical_significance': 'moderate', 'notes': 'Warrior vs Worrier phenotype; also affects pain sensitivity' }, # Fitness / Performance / Recovery 'rs1815739': { 'gene': 'ACTN3', 'variant': 'R577X', 'category': 'Fitness', 'affects': 'Fast-twitch muscle fiber composition', 'risk_allele': 'X', 'genotype_interpretation': { 'CC': 'R/R, alpha-actinin-3 present, good sprint/power performance', 'CT': 'R/X, intermediate phenotype', 'TT': 'X/X, no alpha-actinin-3, endurance advantage, may have poor sprint capacity' }, 'clinical_significance': 'moderate', 'notes': 'ACTN3 R allele associated with elite sprinters; X/X with elite endurance athletes' }, 'rs4253778': { 'gene': 'PPARA', 'variant': 'rs4253778', 'category': 'Fitness', 'affects': 'Fat vs carbohydrate fuel preference', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Better carbohydrate utilization', 'GA': 'Intermediate fuel usage', 'AA': 'Better fat utilization, favorable for endurance' }, 'clinical_significance': 'low', 'notes': 'Affects metabolic substrate preference' }, 'rs8192678': { 'gene': 'PPARGC1A', 'variant': 'Gly482Ser', 'category': 'Fitness', 'affects': 'Aerobic capacity, mitochondrial biogenesis', 'risk_allele': 'A', 'genotype_interpretation': { 'CC': 'Gly/Gly, superior aerobic capacity and mitochondrial function', 'CA': 'Intermediate aerobic capacity', 'AA': 'Ser/Ser, lower aerobic capacity baseline' }, 'clinical_significance': 'moderate', 'notes': 'PGC-1alpha is master regulator of mitochondrial biogenesis' }, 'rs1800012': { 'gene': 'COL1A1', 'variant': 'Sp1 promoter (Xbal)', 'category': 'Fitness', 'affects': 'Collagen synthesis, connective tissue strength', 'risk_allele': 'S', 'genotype_interpretation': { 'SS': 'Higher collagen production, stronger connective tissue', 'Ss': 'Intermediate collagen levels', 'ss': 'Lower collagen production, higher tendon/ligament injury risk' }, 'clinical_significance': 'low', 'notes': 'Affects injury susceptibility in athletes' }, 'rs1799752': { 'gene': 'ACE', 'variant': 'I/D (Alu repeat)', 'category': 'Fitness', 'affects': 'ACE enzyme levels, endurance vs power performance', 'risk_allele': 'D', 'genotype_interpretation': { 'II': 'I/I, lower circulating ACE, endurance advantage', 'ID': 'I/D, intermediate phenotype', 'DD': 'D/D, higher ACE, power/strength advantage' }, 'clinical_significance': 'moderate', 'notes': 'Affects oxygen utilization and altitude adaptation; classic performance gene' }, 'rs7136446': { 'gene': 'COL5A1', 'variant': 'rs7136446', 'category': 'Fitness', 'affects': 'Collagen V synthesis, ligament/tendon properties', 'risk_allele': 'C', 'genotype_interpretation': { 'AA': 'Normal collagen flexibility', 'AC': 'Intermediate', 'CC': 'Increased tendon/ligament stiffness, injury risk' }, 'clinical_significance': 'low', 'notes': 'Type V collagen affects soft tissue properties' }, # Sleep / Circadian 'rs1801260': { 'gene': 'CLOCK', 'variant': 'A3111T', 'category': 'Sleep/Circadian', 'affects': 'Circadian rhythm, sleep timing', 'risk_allele': 'T', 'genotype_interpretation': { 'AA': 'Morning preference, earlier sleep/wake timing', 'AT': 'Intermediate chronotype', 'TT': 'Evening preference, later sleep/wake timing' }, 'clinical_significance': 'low', 'notes': 'CLOCK is master circadian regulator; affects chronotype' }, 'rs57875989': { 'gene': 'DEC2/BHLHE41', 'variant': 'rs57875989', 'category': 'Sleep/Circadian', 'affects': 'Sleep duration, short sleep phenotype', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal sleep need, requires 7-9 hours', 'GA': 'Intermediate', 'AA': 'Short sleep gene, may function well on 4-6 hours (rare)' }, 'clinical_significance': 'moderate', 'notes': 'Only 1-3% carry short sleep variants; very rare' }, 'rs73598374': { 'gene': 'ADA', 'variant': 'rs73598374', 'category': 'Sleep/Circadian', 'affects': 'Deep sleep efficiency', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal deep sleep', 'GA': 'Intermediate', 'AA': 'Reduced deep sleep efficiency' }, 'clinical_significance': 'low', 'notes': 'Adenosine deaminase affects adenosine-mediated sleep pressure' }, # Longevity / Aging 'rs2802292': { 'gene': 'FOXO3', 'variant': 'rs2802292', 'category': 'Longevity', 'affects': 'Longevity and healthy aging', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Common allele', 'GA': 'Intermediate', 'AA': 'Associated with increased longevity and healthy aging (meta-analyses)' }, 'clinical_significance': 'moderate', 'notes': 'FOXO3 is major longevity gene; G allele associated with longer lifespan' }, 'rs1042522': { 'gene': 'TP53', 'variant': 'Arg72Pro', 'category': 'Longevity', 'affects': 'Tumor suppression, cancer risk', 'risk_allele': 'G', 'genotype_interpretation': { 'CC': 'Pro/Pro, potentially more efficient tumor suppression', 'CG': 'Arg/Pro, intermediate', 'GG': 'Arg/Arg, may have slightly different apoptosis response' }, 'clinical_significance': 'moderate', 'notes': 'p53 is guardian of the genome; affects cancer risk' }, 'rs1800566': { 'gene': 'NQO1', 'variant': 'C609T (Pro187Ser)', 'category': 'Longevity', 'affects': 'Antioxidant defense, NAD(P)H quinone oxidoreductase', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'Normal NQO1 activity', 'CT': 'Heterozygous, ~50% activity', 'TT': 'Homozygous null, no functional NQO1, increased oxidative stress' }, 'clinical_significance': 'moderate', 'notes': 'Deficiency increases cancer risk from benzene and other quinones' }, 'rs4880': { 'gene': 'SOD2', 'variant': 'Ala16Val (Val9Ala)', 'category': 'Longevity', 'affects': 'Mitochondrial antioxidant defense', 'risk_allele': 'A (Val)', 'genotype_interpretation': { 'TT': 'Ala/Ala, better mitochondrial antioxidant capacity', 'TA': 'Intermediate', 'AA': 'Val/Val, reduced mitochondrial superoxide dismutase activity' }, 'clinical_significance': 'moderate', 'notes': 'MnSOD is key mitochondrial antioxidant defense' }, # Mental / Cognitive 'rs6265': { 'gene': 'BDNF', 'variant': 'Val66Met', 'category': 'Mental/Cognitive', 'affects': 'Brain-derived neurotrophic factor, neuroplasticity, learning', 'risk_allele': 'A (Met)', 'genotype_interpretation': { 'GG': 'Val/Val, higher BDNF, better episodic memory and learning capacity', 'GA': 'Val/Met, intermediate neuroplasticity', 'AA': 'Met/Met, lower activity-dependent BDNF, potential learning/memory challenges' }, 'clinical_significance': 'moderate', 'notes': 'Met allele associated with anxiety-like traits and depression risk' }, 'rs53576': { 'gene': 'OXTR', 'variant': 'rs53576', 'category': 'Mental/Cognitive', 'affects': 'Oxytocin receptor, social bonding, empathy', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Lower oxytocin receptor expression, less empathy/social sensitivity', 'GA': 'Intermediate social sensitivity', 'AA': 'Higher oxytocin sensitivity, greater empathy and social bonding' }, 'clinical_significance': 'low', 'notes': 'Affects social bonding, parenting, and stress response' }, 'rs4570625': { 'gene': 'TPH2', 'variant': 'G/A (-703)', 'category': 'Mental/Cognitive', 'affects': 'Tryptophan hydroxylase, serotonin synthesis', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Higher serotonin production', 'GA': 'Intermediate serotonin levels', 'AA': 'Lower serotonin synthesis, mood-lowering risk' }, 'clinical_significance': 'low', 'notes': 'Polymorphism affects serotonin availability' }, 'rs6311': { 'gene': 'HTR2A', 'variant': '-1438G/A', 'category': 'Mental/Cognitive', 'affects': 'Serotonin 2A receptor, mood, aggression', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal serotonin 2A receptor expression', 'GA': 'Intermediate', 'AA': 'Higher HTR2A expression, increased serotonergic response' }, 'clinical_significance': 'low', 'notes': 'Associated with depression, suicidality, and aggression' }, 'rs1800497': { 'gene': 'DRD2/ANKK1', 'variant': 'Taq1A', 'category': 'Mental/Cognitive', 'affects': 'Dopamine receptor density, motivation, reward', 'risk_allele': 'T (A1 allele)', 'genotype_interpretation': { 'CC': 'A2/A2, higher dopamine D2 receptor density, better motivation', 'CT': 'A1/A2, intermediate dopamine sensitivity', 'TT': 'A1/A1, lower dopamine receptor density, lower motivation, addiction risk' }, 'clinical_significance': 'moderate', 'notes': 'A1 allele associated with lower dopamine sensitivity and addiction' }, # Caffeine / Alcohol / Drug Metabolism 'rs762551': { 'gene': 'CYP1A2', 'variant': 'C163A (-163)', 'category': 'Drug Metabolism', 'affects': 'Caffeine metabolism speed', 'risk_allele': 'A', 'genotype_interpretation': { 'CC': 'Fast caffeine metabolizer, can handle more caffeine', 'CA': 'Intermediate caffeine sensitivity', 'AA': 'Slow caffeine metabolizer, jitteriness/anxiety at normal doses' }, 'clinical_significance': 'low', 'notes': 'Explains individual caffeine sensitivity; affects 1-2 day half-life' }, 'rs1229984': { 'gene': 'ADH1B', 'variant': 'Arg47His', 'category': 'Drug Metabolism', 'affects': 'Alcohol metabolism speed', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Slow alcohol metabolism', 'GA': 'Intermediate metabolism', 'AA': 'Fast alcohol metabolism' }, 'clinical_significance': 'moderate', 'notes': 'Asian populations enriched for fast metabolism; protective against alcoholism' }, 'rs671': { 'gene': 'ALDH2', 'variant': 'Glu504Lys', 'category': 'Drug Metabolism', 'affects': 'Aldehyde dehydrogenase, alcohol flush reaction', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'Normal acetaldehyde metabolism', 'GA': 'Heterozygous, alcohol flush reaction, protective against alcoholism', 'AA': 'Deficient ALDH2, severe flush reaction, strong alcohol avoidance' }, 'clinical_significance': 'moderate', 'notes': 'East Asian variant; 50% of populations in China, Japan, Korea have deficiency' }, 'rs4149056': { 'gene': 'SLCO1B1', 'variant': 'T521C', 'category': 'Drug Metabolism', 'affects': 'Statin metabolism, drug interactions', 'risk_allele': 'C', 'genotype_interpretation': { 'TT': 'Normal statin metabolism', 'TC': 'Increased statin levels', 'CC': 'High statin levels, increased myopathy risk' }, 'clinical_significance': 'moderate', 'notes': 'Important for statin dosing and side effect risk' }, # Immune / Autoimmune 'rs2187668': { 'gene': 'HLA-DQ2.5', 'variant': 'rs2187668', 'category': 'Immune', 'affects': 'Celiac disease susceptibility', 'risk_allele': 'A', 'genotype_interpretation': { 'GG': 'No HLA-DQ2.5, very low celiac risk', 'GA': 'Carriers, increased risk', 'AA': 'Homozygous DQ2.5, ~30% develop celiac disease' }, 'clinical_significance': 'high', 'notes': '95% of celiac disease patients carry HLA-DQ2 or HLA-DQ8' }, 'rs7454108': { 'gene': 'HLA-DQ8', 'variant': 'rs7454108', 'category': 'Immune', 'affects': 'Celiac disease susceptibility', 'risk_allele': 'T', 'genotype_interpretation': { 'CC': 'No HLA-DQ8', 'CT': 'Carriers', 'TT': 'DQ8 homozygous, increased celiac risk' }, 'clinical_significance': 'high', 'notes': 'Accounts for ~5% of celiac patients; complementary to DQ2' } } def parse_genome_file(filepath): """Parse 23andMe raw data file into dictionary""" genotypes = {} with open(filepath, 'r') as f: for line in f: line = line.strip() if not line or line.startswith('#'): continue parts = line.split('\t') if len(parts) >= 4: rsid, chromosome, position, genotype = parts[0], parts[1], parts[2], parts[3] genotypes[rsid] = { 'chromosome': chromosome, 'position': position, 'genotype': genotype } return genotypes def determine_apoe_status(rs429358_gt, rs7412_gt): """Determine APOE e2/e3/e4 status from two SNPs rs429358 (Cys112Arg): C=Cys, T=Arg rs7412 (Arg158Cys): C=Arg, T=Cys APOE2: Cys112/Cys158 = rs429358 T + rs7412 T = TT/TT APOE3: Cys112/Arg158 = rs429358 T + rs7412 C = TT/CC or heterozygous APOE4: Arg112/Arg158 = rs429358 C + rs7412 C = CC/CC """ if rs429358_gt == '--' or rs7412_gt == '--': return None, "No-call genotypes" # Convert alleles to APOE alleles # Each SNP position contributes one allele to the APOE determination apoe_alleles = [] # For each chromosome copy (diploid) for i in range(2): allele_429358 = rs429358_gt[i] if i < len(rs429358_gt) else None allele_7412 = rs7412_gt[i] if i < len(rs7412_gt) else None if allele_429358 and allele_7412: # Determine APOE allele from combination if allele_429358 == 'T' and allele_7412 == 'T': apoe_alleles.append('ε2') elif (allele_429358 == 'T' and allele_7412 == 'C') or (allele_429358 == 'C' and allele_7412 == 'T'): apoe_alleles.append('ε3') elif allele_429358 == 'C' and allele_7412 == 'C': apoe_alleles.append('ε4') if len(apoe_alleles) == 2: # Sort to display in standard order (highest first) apoe_alleles_sorted = sorted(apoe_alleles, key=lambda x: {'ε4': 0, 'ε3': 1, 'ε2': 2}.get(x, 3)) apoe_status = ''.join(apoe_alleles_sorted) return apoe_status, apoe_alleles return None, "Unable to determine" def get_interpretation_from_alleles(user_gt, snp_info, rsid): """Get interpretation by trying various allele naming conventions""" interpretations = snp_info['genotype_interpretation'] # Try direct match if user_gt in interpretations: return interpretations[user_gt] # Some SNPs might use different reference/alternate alleles in the database # Try reverse complement logic or alternative naming for key in interpretations: if len(key) == len(user_gt) and len(user_gt) == 2: # Check if it's a reversed version if key == user_gt[::-1]: return interpretations[key] # Return generic interpretation based on allele frequency if available allele_counts = {} for base in user_gt: allele_counts[base] = allele_counts.get(base, 0) + 1 if len(allele_counts) == 1: # Homozygous return f"Homozygous {user_gt} genotype" else: # Heterozygous return f"Heterozygous genotype" def analyze_genome(genotypes_file): """Main analysis function""" print("=" * 80) print("COMPREHENSIVE 23andMe GENOME ANALYSIS") print("Individual: Bill Syrros (Vasilios Syrros)") print("=" * 80) # Parse genome file print("\nParsing genome data...") genotypes = parse_genome_file(genotypes_file) print(f"Total SNPs loaded: {len(genotypes):,}") # Calculate basic stats chrom_dist = defaultdict(int) no_calls = 0 for rsid, data in genotypes.items(): chrom = data['chromosome'] chrom_dist[chrom] += 1 if data['genotype'] == '--': no_calls += 1 no_call_rate = (no_calls / len(genotypes)) * 100 if genotypes else 0 print(f"\nBasic Statistics:") print(f" Total SNPs: {len(genotypes):,}") print(f" No-call rate: {no_call_rate:.2f}% ({no_calls:,} SNPs)") print(f" Chromosomes with data: {len(chrom_dist)}") # Analyze health-relevant SNPs print(f"\nSearching for {len(SNP_DATABASE)} health-relevant SNPs...") results = { 'metadata': { 'total_snps': len(genotypes), 'no_call_rate': no_call_rate, 'chromosomal_distribution': dict(chrom_dist) }, 'snp_findings': [], 'apoe_status': {}, 'summary_by_category': defaultdict(list) } found_count = 0 missing_snps = [] for rsid, snp_info in SNP_DATABASE.items(): if rsid in genotypes: found_count += 1 user_gt = genotypes[rsid]['genotype'] # Skip no-call genotypes if user_gt == '--': continue snp_result = { 'rsid': rsid, 'gene': snp_info['gene'], 'variant': snp_info['variant'], 'category': snp_info['category'], 'affects': snp_info['affects'], 'user_genotype': user_gt, 'risk_allele': snp_info['risk_allele'], 'chromosome': genotypes[rsid]['chromosome'], 'position': genotypes[rsid]['position'] } # Get interpretation with fallback logic interpretation = get_interpretation_from_alleles(user_gt, snp_info, rsid) snp_result['interpretation'] = interpretation snp_result['clinical_significance'] = snp_info['clinical_significance'] snp_result['notes'] = snp_info['notes'] results['snp_findings'].append(snp_result) results['summary_by_category'][snp_info['category']].append(snp_result) else: missing_snps.append(rsid) # Determine APOE status if available if 'rs429358' in genotypes and 'rs7412' in genotypes: gt429358 = genotypes['rs429358']['genotype'] gt7412 = genotypes['rs7412']['genotype'] if gt429358 != '--' and gt7412 != '--': apoe_status, alleles = determine_apoe_status(gt429358, gt7412) results['apoe_status'] = { 'rs429358_genotype': gt429358, 'rs7412_genotype': gt7412, 'apoe_status': apoe_status, 'alleles_detected': alleles, 'interpretation': get_apoe_interpretation(apoe_status) } print(f"\nFound {found_count}/{len(SNP_DATABASE)} health-relevant SNPs") print(f"Missing/no-call: {len(missing_snps)}") return results def get_apoe_interpretation(apoe_status): """Get human-readable APOE interpretation""" if not apoe_status: return "Unable to determine" interpretations = { 'ε2ε2': 'Lowest Alzheimer\'s disease risk, longer lifespan, lower LDL cholesterol', 'ε2ε3': 'Very low AD risk, favorable cholesterol profile', 'ε2ε4': 'Rare combination, mixed risk profile', 'ε3ε3': 'Common genotype, average AD risk, average cardiovascular risk', 'ε3ε4': 'Moderately increased AD risk, higher LDL cholesterol', 'ε4ε4': 'Highest AD risk (~55% by age 85), highest LDL, cardiovascular risk' } return interpretations.get(apoe_status, "Unknown") def generate_summary_report(results, output_file): """Generate human-readable summary report""" with open(output_file, 'w') as f: f.write("=" * 100 + "\n") f.write("23andMe GENOME ANALYSIS REPORT\n") f.write("Subject: Bill Syrros (Vasilios Syrros)\n") f.write("Date: 2026-04-02\n") f.write("=" * 100 + "\n\n") # Summary statistics f.write("SUMMARY STATISTICS\n") f.write("-" * 100 + "\n") f.write(f"Total SNPs analyzed: {results['metadata']['total_snps']:,}\n") f.write(f"No-call rate: {results['metadata']['no_call_rate']:.2f}%\n") f.write(f"Health-relevant SNPs found: {len(results['snp_findings'])}\n\n") # APOE Status if results['apoe_status']: f.write("APOE STATUS (Critical for Alzheimer's Disease Risk)\n") f.write("-" * 100 + "\n") apoe = results['apoe_status'] f.write(f"APOE Genotype: {apoe['apoe_status']}\n") f.write(f" rs429358: {apoe['rs429358_genotype']}\n") f.write(f" rs7412: {apoe['rs7412_genotype']}\n") f.write(f"Interpretation: {apoe['interpretation']}\n\n") # By category for category in sorted(results['summary_by_category'].keys()): snps = results['summary_by_category'][category] f.write("\n" + "=" * 100 + "\n") f.write(f"{category.upper()}\n") f.write("=" * 100 + "\n\n") for snp in snps: f.write(f"SNP: {snp['rsid']}\n") f.write(f"Gene: {snp['gene']} ({snp['variant']})\n") f.write(f"Location: Chromosome {snp['chromosome']}:{snp['position']}\n") f.write(f"Affects: {snp['affects']}\n") f.write(f"Your Genotype: {snp['user_genotype']}\n") f.write(f"Risk Allele: {snp['risk_allele']}\n") f.write(f"Clinical Significance: {snp['clinical_significance'].upper()}\n") f.write(f"\nMeaning: {snp['interpretation']}\n") f.write(f"Notes: {snp['notes']}\n") f.write("-" * 100 + "\n\n") if __name__ == '__main__': genomes_file = '/sessions/lucid-sleepy-lamport/23andme/genome_Vasilios_Syrros_v4_Full_20260402081234.txt' # Run analysis results = analyze_genome(genomes_file) # Save JSON results json_output = '/sessions/lucid-sleepy-lamport/23andme/genome_analysis.json' with open(json_output, 'w') as f: # Convert defaultdict to regular dict for JSON serialization results['summary_by_category'] = dict(results['summary_by_category']) json.dump(results, f, indent=2) print(f"\nJSON results saved to: {json_output}") # Generate and save text summary txt_output = '/sessions/lucid-sleepy-lamport/23andme/genome_summary.txt' generate_summary_report(results, txt_output) print(f"Summary report saved to: {txt_output}") # Print to console print("\n" + "=" * 100) print("DETAILED FINDINGS BY CATEGORY") print("=" * 100) for category in sorted(results['summary_by_category'].keys()): snps = results['summary_by_category'][category] print(f"\n{category.upper()} ({len(snps)} SNPs)") print("-" * 100) for snp in snps: print(f"\n {snp['rsid']} - {snp['gene']} ({snp['variant']})") print(f" Genotype: {snp['user_genotype']} | Significance: {snp['clinical_significance'].upper()}") print(f" {snp['interpretation']}")