John A. Bachman

This paper introduces INDRA, a system that uses NLP and probability models to assemble high-quality molecular mechanisms from text and databases, improving accuracy over machine reading alone.

The paper presents a computational framework for analyzing SARS-CoV-2-host interactions to identify drug targets and model disease mechanisms.

The paper develops ProtMapper to normalize phosphosite positions from databases and text mining, creating a comprehensive corpus of regulatory annotations.

The paper introduces STonKGs, a Transformer model trained on biomedical text and knowledge graphs, which outperforms single-modality models in classification tasks.

The paper introduces Biofactoid, a tool that crowdsources structured biological knowledge from authors, enabling efficient human-computer interaction and expanding existing pathway databases.

The paper describes the development of a computational knowledge repository, the COVID-19 Disease Map, which curates SARS-CoV-2 virus-host interaction mechanisms and provides tools for their analysis and application.

GeneWalk identifies gene functions relevant to a biological context using network representation learning and validates it on RNA-seq and NET-seq data from human and mouse samples.

This paper refines the definition of the human kinome, identifies understudied kinases, and highlights their potential as drug targets through differential expression, essentiality, and mutation data.

The paper develops workflows to re-curate and enrich knowledge graphs encoded in Biological Expression Language using automated and manual methods.

FamPlex improves named entity recognition and grounding for protein families and complexes in biomedical text by providing a manually curated resource with hierarchical organization and curated patterns.

The paper introduces INDRA, a tool that converts natural language descriptions of molecular mechanisms into executable computational models of biological networks.