This Project Grant award of $275,956 from the National Science Foundation's (NSF) Computer and Information Science and Engineering (CISE) program aims to develop an engineered cyber-physical system that combines advanced biological models with artificial intelligence methods for predictive, automated screening of anti-cancer drugs and optimization of their dosing. The key products and services to be delivered under this award include: 1) Adoption of 3D bioprinting to generate vascularized ductal...
This Project Grant award from the National Cancer Institute (CFDA 93.398 Cancer Research Manpower) provides $147,486 to Carnegie Mellon University to develop novel computational methods for predicting kinase inhibitor off-target activity and optimizing multi-target binding during early-stage drug discovery. The key products and services to be delivered include: Novel methods to reduce the computational expense of alchemical relative binding free energy (RBFE) simulations while maintaining...
This Project Grant award from the National Institute of General Medical Sciences (NIGMS) Biomedical Research and Research Training program (CFDA 93.859) provides $350,000 to Sinopia Biosciences Inc. to develop computational methods for predicting the metabolomic profiles of unscreened chemical compounds. The goal is to enable more efficient metabolomics-based drug discovery by combining sparse experimental screening with computational inference. Key objectives include: 1) developing methods to...
This Project Grant award from the National Institute of General Medical Sciences (NIGMS) Biomedical Research and Research Training program (CFDA 93.859) provides $435,620 to The Regents of the University of California, San Francisco (UCSF) to develop and test algorithms for iteratively docking subsets of ultra-large small molecule libraries against molecular targets. The goal is to create a more efficient prioritization approach for virtual screening of trillion-scale make-on-demand small...
This Project Grant award of $665,616 from the National Institute of General Medical Sciences (NIGMS) Biomedical Research and Research Training program (CFDA 93.859) supports the development of a novel micro-capsule technology to enable high-throughput analysis of millions of live cell-cell interactions in parallel. The technology aims to address a major unmet need in screening functional antibodies and peptides, evaluating ligand-receptor specificity, and determining cell adhesion affinities....
This federal Project Grant award from the National Institute of General Medical Sciences (NIGMS) Biomedical Research and Research Training program (CFDA 93.859) provides $687,246 to the University of Florida to develop new Bayesian and machine learning methods capable of modeling genetic interactions and predicting phenotypes for complex traits. The research aims to (1) accurately predict phenotypes for novel genotypes and (2) provide biological insights into the genetic architecture of...
This $448,150 Project Grant awarded by the National Science Foundation (NSF) Biological Sciences program (CFDA 47.074) aims to develop a DNA-based toolbox for the rapid and precise modulation of cell membrane protein-protein interactions (PPIs). The goal is to establish a modular approach using antibodies and aptamers to enable targeted DNA barcoding of cell membrane proteins, particularly receptor tyrosine kinases. This will allow for the controlled stabilization of specific PPI pairs on living...
This Project Grant award of $399,483, provided by the National Institute on Drug Abuse (NIDA) under the Drug Use and Addiction Research Programs (CFDA 93.279), aims to leverage synergy between artificial intelligence (AI) and DNA-encoded library (DEL) technologies to identify novel polypharmacological therapeutics for substance use disorders (SUDs). The key objectives are to generate multivalent compounds that can simultaneously target and restore imbalances in the opioid, dopaminergic, and...
This National Science Foundation (NSF) Technology, Innovation, and Partnerships (CFDA 47.084) Project Grant award of $275,000 to Om Therapeutics Inc. will support the development of a system to enable the rapid, scalable, and cost-effective discovery of new medicines using machine learning. The project aims to encapsulate proteins and small molecules in millions of miniaturized compartments to screen for interactions that could identify novel drug candidates. The key innovations include...
This Project Grant award from the National Institute of General Medical Sciences (NIGMS) Biomedical Research and Research Training Program (CFDA 93.859) is intended to support the development and validation of a chemically induced dimerization (CID) system capable of detecting nanomolar concentrations of coenzyme A (CoA) in the presence of excess acetyl-CoA. This CID system is being created to provide a universal assay method for screening histone acetyltransferases, which are important...
ACCURATE INTERACTION DETECTION IN COMBINATORIAL SCREENS WITH COMPLEX PHENOTYPES - PROJECT SUMMARY COMBINATORIAL SCREENS CHARACTERIZE THE MOLECULAR PATHWAYS OF THE CELL BY IDENTIFYING INTERACTIONS BETWEEN PERTURBATIONS. QUANTIFYING INTERACTIONS REQUIRES A NOTION OF NON-INTERACTION (I.E., A NULL INTERACTION MODEL), WHICH IS WELL-ESTABLISHED FOR COMBINATORIAL SCREENS MEASURING CELL SURVIVAL AND OTHER SIMPLE PHENOTYPES. HOWEVER, RECENT ADVANCES IN SINGLE-CELL OMICS AND AUTOMATED MICROSCOPY HAVE ENABLED COMBINATORIAL SCREENS WITH HIGH- DIMENSIONAL PHENOTYPIC PROFILES. THESE PHENOTYPIC PROFILES CONSIST OF FEATURES WITH UNKNOWN, NON-LINEAR BEHAVIOR, SUCH AS GENE EXPRESSION OR IMAGE FEATURES. AS A RESULT, THERE IS NO WELL-DEFINED NULL INTERACTION MODEL FOR COMBINATORIAL SCREENS WITH HIGH-DIMENSIONAL PHENOTYPES. THE GOAL OF MY PROPOSAL IS TO ESTABLISH A NULL INTERACTION MODEL FOR HIGH-DIMENSIONAL PHENOTYPES. MY APPROACH, TERMED DENIM (DATA-DRIVEN ESTIMATION OF NULL INTERACTION MODELS), AIMS TO USE ROBUST ESTIMATION MODELS TO LEARN AN ADDITIVE REPRESENTATION FOR NULL PERTURBATIONS AND IMPROVE QUANTIFICATION OF INTERACTIONS ACROSS COMBINATORIAL SCREEN DATASETS. IN ADDITION, THIS FRAMEWORK HAS A KEY APPLICATION IN DRUG TARGET IDENTIFICATION BY ENABLING ACCURATE PRIORITIZATION OF CHEMICAL-GENETIC INTERACTIONS FROM MICROSCOPY-BASED PHENOTYPIC PROFILES. MY CENTRAL HYPOTHESIS IS THAT NULL INTERACTION MODELS WHICH ACCURATELY MODEL THE DIVERSE BEHAVIOR OF HIGH- DIMENSIONAL FEATURES CAN SUBSTANTIALLY IMPROVE INTERACTION DETECTION. IN AIM 1, I WILL DEVELOP AND CRITICALLY ASSESS DENIM USING BOTH SIMULATED AND REAL-WORLD COMBINATORIAL DATASETS WITH GENE EXPRESSION OR HIGH-CONTENT IMAGING READOUTS. I WILL EVALUATE DENIM AGAINST EXISTING BASELINES ON THE ABILITY TO ACCURATELY INTERACTION STRENGTH IN SIMULATION, AS WELL AS RECAPITULATE KNOWN INTERACTIONS BETWEEN GENE PAIRS OR DRUG PAIRS. PRELIMINARY DATA FROM SIMULATION DEMONSTRATES THAT DENIM CAN ACCURATELY IDENTIFY AND LEARN NON-LINEAR PERTURBATION TRAJECTORIES, WHICH LEADS TO IMPROVEMENT IN PERFORMANCE RELATIVE TO THE STANDARD BASELINE (I.E., VECTOR ADDITION). IN AIM 2, I WILL LEVERAGE THE IMPROVED PRIORITIZATION OF INTERACTIONS PROVIDED BY DENIM TO PERFORM DRUG TARGET IDENTIFICATION. THIS TARGET IDENTIFICATION PLATFORM REQUIRES LARGE-SCALE GENETIC PERTURBATIONS AND THE STUDY OF CHEMICAL-GENETIC INTERACTIONS. TO THIS END, PRELIMINARY RESULTS SHOW THAT LARGE-SCALE GENETIC PERTURBATIONS CAN BE ACCURATELY CONDUCTED USING POOLED GENETIC SCREENING FOLLOWED BY IN SITU SEQUENCING FOR GUIDE DEMULTIPLEXING. MOREOVER, I ANALYZED A PILOT SCREEN ON A WELL-ESTABLISHED MEK1/2 INHIBITOR, WHERE I ACCURATELY RECOVERED TARGET PATHWAY COMPONENTS, WITH SIMILAR PERFORMANCE USING DRUG-RELEVANT OR DRUG-AGNOSTIC BIOMARKERS. TOGETHER, COMPLETION OF THIS PROPOSAL WILL RESULT IN A RIGOROUS FRAMEWORK FOR HIGH-DIMENSIONAL INTERACTIONS, BENCHMARKING OF NULL INTERACTION MODELS, AND A NOVEL PLATFORM FOR CHEMICAL-GENETIC TARGET IDENTIFICATION USING MICROSCOPY-BASED PHENOTYPIC PROFILES.