Isaac S. Kohane

The paper identifies domain-specific phenotypic effects of MACF1 variants outside the GAR domain, revealing broader neurodevelopmental and craniofacial anomalies.

This paper demonstrates that ensilication preserves DNA integrity at ambient temperature, enabling diagnostic-quality long-read sequencing without cold-chain infrastructure.

This study identifies rare germline variants in immune and drug target genes that are enriched in cancer exceptional responders compared to typical patients, suggesting potential biomarkers for improved treatment outcomes.

The paper presents a joint genomic analysis of UDN patients using whole genome sequencing and new statistical methods to prioritize disease genes, revealing new disease associations and releasing a software tool for cohort analysis.

SHEPHERD uses few-shot learning and a knowledge graph to improve diagnosis of rare genetic diseases using simulated data and real-world patient cohorts.

This paper simulates patients with novel genetic conditions to evaluate gene prioritization methods in diagnosing rare disorders.

This paper presents a deep convolutional neural network to predict antibiotic resistance in M. tuberculosis isolates, achieving state-of-the-art accuracy and enabling interpretable feature analysis.

The paper examines how changes in control population definitions affect statistical results in a case-control study linking depression and Type 2 Diabetes Mellitus using real-world evidence.

This study identifies traits associated with polygenic risk for depression using UK Biobank data and finds causal links between depression risk and brain structure, as well as environmental interactions.

This study evaluates the efficacy of obesity polygenic risk scores in autistic versus non-autistic populations, finding that genetic variants associated with obesity in non-autistic populations are less representative in autistic individuals.

The paper examines how genetic and environmental factors influence DNA methylation at variably methylated regions in neonatal blood, finding that combined effects best explain methylation variability.

This study uses a multitask deep learning model to predict tuberculosis drug resistance from genomic data, achieving high accuracy in both first-line and second-line drug resistance prediction.

This paper develops an automated high-throughput phenotyping method (MAP) that improves phenotype accuracy and scalability for PheWAS studies.

The paper applies polygenic risk scoring to a large family with bipolar and depressive disorders to study genetic risk patterns and anticipation.

The paper analyzes C. elegans single-cell developmental data to show coordinated oscillations in gene activation and introduces a novel method for identifying gene expression patterns linked to developmental timing.

Genome-wide association meta-analysis of 130,664 major depression cases and 330,470 controls identifies 44 independent risk loci enriched in cortical neurons, conserved mammalian regions, splicing networks, and antidepressant targets.

The paper identifies sex-specific differences in immune-related pathways, particularly complement-dependent microglial synaptic pruning, during brain development and suggests their role in sex differences in neurological disorder vulnerability.