Joshua F. McMichael

Searching the Druggable Genome using Large Language Models

The paper develops a server enabling large language models to access drug-gene interaction data through natural language queries.

CompBio and MIRaS : A Multi-omic Analysis Platform Built on a Memory-Based Intelligence Engine

The paper introduces CompBio, a multi-omic analysis platform using MIRaS, a memory-based intelligence engine, to analyze omics data without relying on human-curated knowledgebases, producing traceable and statistically significant results.

dgiLIT: A Method for Prioritization and AI Curation of Drug-Gene Interactions

The paper introduces dgiLIT, an AI-driven method to prioritize and curate drug-gene interactions from biomedical literature for inclusion in DGIdb, achieving high validation rates.

CIViC MCP: Integrating Large Language Models with the Clinical Interpretations of Variants in Cancer

The paper introduces CIViC MCP, a system that uses large language models to interface with the CIViC knowledgebase, enabling natural language queries for cancer variant interpretations.

CIViC-Fact: a proof-of-concept framework for AI-assisted verification of cancer variant interpretations

CIViC-Fact evaluates AI models for verifying cancer variant interpretations using full-text evidence, showing abstracts are insufficient for accurate validation.

Ultra Deep Sequencing Reveals the Mutational Landscape of Classical Hodgkin Lymphoma

This study uses ultra-deep exome sequencing to identify recurrent mutations in classical Hodgkin lymphoma HRS cells, demonstrating its utility for analyzing genomic variants in large patient cohorts.

Computational prediction of MHC anchor locations guide neoantigen identification and prioritization

The paper predicts MHC anchor positions for 328 HLA alleles and shows that incorporating these improves neoantigen identification by correcting misclassified candidates in tumor samples.

RegTools: Integrated analysis of genomic and transcriptomic data for the discovery of splice-associated variants in cancer

RegTools identifies splice-associated variants in cancer by integrating genomic and transcriptomic data across 9,000 tumor samples, discovering 235,778 splicing events.

Evolution of the open-access CIViC knowledgebase is driven by the needsof the cancer variant interpretation community

The paper describes the evolution of the CIViC knowledgebase to meet the needs of the cancer variant interpretation community by expanding its functionality and data types.

Integration of the Drug-Gene Interaction Database (DGIdb) with open crowdsource efforts

DGIdb 4.0 aggregates drug-gene interaction and druggability claims from 41 sources, adding crowd-sourced Drug Target Commons, Wikidata-based drug normalization, search-relative query scores, and NDEx export.

CIViCpy: a Python software development and analysis toolkit for the CIViC knowledgebase

CIViCpy is a Python SDK for accessing and analyzing the CIViC knowledgebase, enabling efficient variant annotation in cancer genomics.

pVACtools: a computational toolkit to identify and visualize cancer neoantigens

pVACtools provides a suite of tools for neoantigen prediction, prioritization, and vaccine design in cancer immunotherapy.

The CIViC knowledge model and standard operating procedures for curation and clinical interpretation of variants in cancer

The paper describes the CIViC knowledge model and curation procedures for systematically organizing and interpreting cancer-related genetic variants.