Junzhou Huang
University of Texas at Arlington, TX·Computer Science
Combination therapies, where two or more drugs are given together, can work far better than single drugs when the drugs are synergistic, meaning their combined effect is greater than the sum of their parts. Genes can be synergistic too, amplifying each other's effects.
- Fields
Computer Science
Pharmacology
Mathematics & Statistics
- Topics
drug synergy
combination therapy
drug combinations
- Grants
- 1 known grant, through Jun 2031
What they work on
- Develop multi-modal deep learning methods, including large language models, to predict the functions of thousands of poorly annotated genes and support analysis of gene-gene synergies.
- Design BaySyn, a Bayesian hierarchical model that predicts drug synergies with explainable mechanisms by combining screening data, multi-omics data, drug chemistry, drug-target interactions and gene-gene synergies.
- Validate the computational predictions of drug synergy through high-throughput drug screening experiments, and share the tools and results through a public web portal.
More about the research
Finding such pairs by experiment is costly and slow, and current computer methods struggle to combine many kinds of data and to explain their predictions.
Why it matters
Better prediction of which drugs work well together could speed the discovery of safer, more effective combination therapies and cut their development time and cost. Explainable predictions that link drug effects to gene interactions could also point to new therapeutic targets and support precision medicine treatments tailored to individual patients. A public web portal would give other researchers access to validated tools and data.
Known grants
From NIH and NSF research grants. Labs often have other funding we can't see.
Closest labs
Ritambhara Singh
Brown University, RI·Computer Science·Early-career
Predict gene expression by integrating histone modification profiles, 3D genome conformation, DNA sequence and single-nucleotide polymorphisms in deep learning models, including graph neural networks that treat genome folding as a network of contacts between distant DNA regions.
Paul Marjoram
University of Southern California, CA·Mathematics & Statistics
Develop a probabilistic evolutionary model using phylogenetic trees and experimental Gene Ontology annotations to automatically predict functions of uncharacterized genes.
Yunan Luo
Georgia Institute of Technology, GA·Computer Science·Early-career
Develop machine learning methods that learn protein representations from amino acid sequence and 3D structure, in order to explain how composition and shape determine protein function.
The school
University of Texas at Arlington: 11 labs on PI Pages, $154M a year on research, 177 research doctorates a year.
Reach out
A start for your email. Fill in the brackets.