Deep-learning platform GPS enables de novo drug discovery by predicting transcriptomic perturbations from chemical structures
By
Xiaopeng Li1,10 Send email to [email protected]
Summary
This paper presents GPS (gene expression profile predictor on chemical structures), a deep-learning-based drug discovery platform that screens large compound libraries and optimizes lead molecules by matching disease transcriptomic profiles with compound-induced transcriptomic features predicted from chemical structures. The approach enables de novo drug discovery guided by transcriptomic features, moving beyond traditional drug repurposing to discover novel therapeutics that reverse disease-associated transcriptional phenotypes.
Source
bskyDeep-learning platform GPS enables de novo drug discovery by predicting transcriptomic perturbations from chemical structurescell.comKey quotes
· 3 pulledIdentifying drugs that reverse disease-associated transcriptomic features has been widely explored for drug repurposing, but its potential for de novo drug discovery remains underexplored.
Here, we present gene expression profile predictor on chemical structures (GPS), a deep-learning-based drug discovery platform, guided by transcriptomic features, that screens large compound libraries and optimizes lead molecules.
We first develop a model that captures transcriptomic perturbation signatures solely from chemical structures and deploy it to library compounds.
You might also wanna read
Nature research paper: Zero-shot design of drug-binding proteins via neural iterative selection−expansion
Nature research paper: Zero-shot design of drug-binding proteins via neural iterative selection−expansion
Harmonic Discovery: AI-powered platform for precision drug design launches on Product Hunt
Harmonic Discovery is a biotech platform that uses machine learning and generative chemistry to design safer, more effective medicines. The
Product Hunt·1mo ago
How LLMs Are Transforming Preclinical Drug Discovery Data Access
The article discusses how Large Language Models (LLMs) are being applied to preclinical drug discovery to help researchers efficiently acces
AI Advances in Drug Discovery: From Data Integration to Dual-Action Cancer Drug Design
The article discusses recent advancements in AI-driven drug discovery, highlighting two key developments: 1) Analytica 2026, an event focuse
drugtargetreview.com·5mo ago
Network-driven discovery of repurposable drugs targeting hallmarks of aging
OpenAI and Molecule.one demonstrate GPT-5.4-powered AI chemist improving medicinal chemistry reactions
OpenAI and Molecule.one demonstrate a near-autonomous AI chemist using GPT-5.4 that successfully improved a challenging reaction in medicina
openai.com·17d ago
Comments
Sign in to join the conversation.
No comments yet. Be the first.