Stephen V. Faraone

The paper introduces an adversarial neural network to identify genetic resilience markers in Alzheimer's disease, finding five SNPs associated with resilience independent of polygenic risk scores.

This study develops an explainable deep learning model to predict ADHD using genetic, environmental, cognitive, and temperament data, finding that temperament features significantly improve classification performance.

This paper develops a multi-stage graph attention network to improve Alzheimer's disease classification from genome-wide association data by capturing epistatic interactions and enhancing interpretability.

This paper develops a framework using genomic context and genotype data in convolutional neural networks to predict type 2 diabetes risk, showing improved performance over polygenic risk scores.

The paper identifies novel CNV loci and dose-dependent gene effects across six psychiatric disorders using genome-wide analysis.

The paper identifies shared and divergent genetic mechanisms across psychiatric disorders using gene-set burden analysis of copy number variants.

This review identifies a multifactorial etiology and neurobiology of IED, highlighting the amygdala and orbitofrontal cortex, serotonergic signaling, and childhood trauma as key factors.

The paper identifies five genomic factors explaining most genetic variance across 14 psychiatric disorders and finds shared and disorder-specific genetic signals with distinct biological functions.

This study identifies factors affecting model performance in genomic machine learning by analyzing associations between study features and reported results.

This study identifies genetic resilience factors for Alzheimer's disease by constructing polygenic resilience scores that reduce genetic risk penetrance and correlate with polygenic risk scores in unaffected individuals.

A genome-wide association study of 69,369 schizophrenia cases and 236,642 controls identifies 270 risk loci, prioritizes 130 genes, and links common and rare risk variants to neuronal synaptic biology.

Exomes of 24,248 schizophrenia cases and 97,322 controls implicate ultra-rare damaging variants in 10 genes, including GRIN2A and GRIA3, with odds ratios of 3 to 50.

This study identifies genetic variants associated with antisocial behavior through a genome-wide association meta-analysis, finding significant links to FOXP2 and correlations with multiple health and behavioral traits.

This study analyzes structural brain asymmetries in ADHD using 39 datasets, finding small effects that do not meet study-wide significance thresholds.

The paper examines genetic correlations between neuropsychiatric disorders using structural MRI data from the ENIGMA consortium, finding significant overlaps in brain structure and genetic architecture.

The paper examines sex-differentiated genetic effects across neuropsychiatric and behavioral traits using GWAS summary statistics and finds small, polygenic sex differences with enriched neuron-related genes.

BrainGENIE predicts brain-tissue gene expression from peripheral blood transcriptomes, outperforming existing methods in accuracy and biological relevance.

This study identifies nine new genetic loci associated with ADHD and shows shared genetic architecture between childhood and adult ADHD.

This study uses Swedish registry data to predict substance use disorders in ADHD youth with machine learning models, achieving moderate accuracy even without prior SUD diagnosis.

This study identifies schizophrenia genetic associations in East Asian and European populations, finding similar genetic effects across ancestries but highlighting challenges in polygenic risk prediction across groups.

The paper investigates how genetic variation in DRD4 interacts with seasonal daylight changes to influence inattention, finding support for the Spring-focus hypothesis and seasonal patterns in ADHD-related symptoms.

This study identifies risk variants and characterizes the polygenic architecture of ADHD comorbid with disruptive behavior disorders through a large GWAS meta-analysis.

This study identifies three novel genes associated with ADHD by linking genetic variants to differential DNA methylation and gene expression in brain tissues.

This study performs a cross-disorder GWAS meta-analysis of ADHD, ASD, OCD, and TS, identifying 297 genome-wide significant variants and 21 genes associated with shared genetic risk.

This study compares structural brain differences across ADHD, ASD, and OCD using MRI data from multiple cohorts, finding disorder-specific alterations in brain volume and cortical thickness.

The paper investigates selective brain region vulnerability in ADHD by analyzing gene expression, cell abundance, and brain size changes using imaging and postmortem data.

The paper identifies genetic correlations between ADHD and brain volumes, finding negative associations with intracranial volume and specific brain regions.

Cross-disorder meta-analysis of eight psychiatric GWAS (232,964 cases, 494,162 controls) reports 109 loci shared by two or more disorders and three groups of correlated disorders.

The paper investigates polygenic associations between ADHD and literacy/language abilities, finding that genetic confounding with educational attainment masks ADHD-specific reading impairments.