Biology subjects

Gaetz, J.

Publications and source records attributed to Gaetz, J..

3 recordsLinked to original sources

bioRxiv2024

A Framework for Autonomous AI-Driven Drug Discovery

The exponential increase in biomedical data offers unprecedented opportunities for drug discovery, yet overwhelms traditional data analysis methods, limiting the pace of new drug development. Here we introduce a framework for autonomous artificial intelligence (AI)-driven drug discovery that integrates knowledge graphs with large language models (LLMs). It is capable of planning and carrying out automated drug discovery programs at a massive scale while providing details of its research strategy, progress, and all supporting data. At the heart of this framework lies the focal graph - a novel construct that harnesses centrality algorithms to distill vast, noisy datasets into concise, transparent, data-driven hypotheses. We demonstrate that even small-scale applications of this highly scalable approach can yield novel, transparent insights relevant to multiple stages of the drug discovery process, including chemical structure-based target prediction, and present the implementation of a system which autonomously plans and executes a multi-step target discovery workflow. Graphical Abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=65 SRC="FIGDIR/small/629024v3_ufig1.gif" ALT="Figure 1"> View larger version (18K): org.highwire.dtl.DTLVardef@9d7d7dorg.highwire.dtl.DTLVardef@199d768org.highwire.dtl.DTLVardef@10d0335org.highwire.dtl.DTLVardef@14d8d1c_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2024

Morphological map of under- and over-expression of genes in human cells

Cell Painting images offer valuable insights into a cells state and enable many biological applications, but publicly available arrayed datasets only include hundreds of genes perturbed. The JUMP (Joint Undertaking in Morphological Profiling) Cell Painting Consortium perturbed roughly 75% of the protein-coding genome in human U-2 OS cells, generating a rich resource of single-cell images and extracted features. These profiles capture the phenotypic impacts of perturbing 15,243 human genes, including overexpressing 12,609 genes (using open reading frames, ORFs) and knocking out 7,975 genes (using CRISPR-Cas9). We mitigated technical artifacts by rigorously evaluating data processing options and validated the datasets robustness and biological relevance. Analysis of phenotypic profiles revealed novel gene clusters and functional relationships, including those associated with mitochondrial function, cancer, and neural processes. The JUMP Cell Painting genetic dataset is a valuable resource for exploring gene relationships and uncovering novel functions.

bioinformatics↗

bioRxiv2021

Capacity to erase gene occlusion is a defining feature distinguishing naive from primed pluripotency

Pluripotent stem cells can exist in either the naive state representing a developmental blank slate or the downstream primed state poised for differentiation. Currently, known differences between these two states are mostly phenomenological, and none can adequately explain why the two states should differ in developmental priming. Gene occlusion is a mode of epigenetic inactivation that renders genes unresponsive to their cognate transcriptional activators. It plays a crucial role in lineage restriction. Here, we report that a defining feature distinguishing the two pluripotent states lies in the ability of naive but not primed cells to erase occlusion. This "deocclusion" capacity requires Esrrb, a gene expressed only in the naive but not primed state. Notably, Esrrb silencing in the primed state is itself due to occlusion. Collectively, our data argue that the Esrrb-dependent deocclusion capacity in naive cells is key for sustaining naive pluripotency, and the loss of this capacity in the primed state via the occlusion of Esrrb poises cells for differentiation.

molecular biology↗