Jeremy L. Jenkins

Single Cell Foundation Models Evaluation (scFME) for In-Silico Perturbation

The paper introduces scFME, a framework to evaluate fine-tuned foundation models for in-silico perturbation, showing its effectiveness in characterizing model performance.

Evaluating Foundation Models for In-Silico Perturbation

This paper evaluates foundation models for in-silico perturbation using a novel framework, revealing differences in their performance across biological contexts and gene categories.

Compound activity prediction with dose-dependent transcriptomic profiles and deep learning

The paper introduces TAT models to predict compound activity using dose-dependent transcriptomic profiles, achieving 51% assay prediction success and validating malaria inhibitor identification.

DRUG-seq Provides Unbiased Biological Activity Readouts for Drug Discovery

DRUG-seq provides high-throughput, unbiased transcriptomic data for drug discovery, demonstrating reproducibility and mechanism-of-action resolution for diverse compounds.

Learning epistatic gene interactions from perturbation screens

The paper develops a model to infer pairwise epistatic gene interactions from siRNA perturbation screens, showing that glinternet outperforms xyz in accuracy for high-dimensional data.

Systematic Chemogenetic Library Assembly

The paper describes the assembly of a chemogenetic library through data mining and crowdsourcing, sharing 4186 compounds with annotated gene targets.

Cheminformatics tools for analyzing and designing optimized small molecule libraries

The paper develops tools to compare and design optimized small molecule libraries using chemical and biological data, resulting in a more effective kinase inhibitor library.