Transformer-Decoder GPT Models for Generating Virtual Screening Libraries of HMG-Coenzyme A Reductase Inhibitors: Effects of Temperature, Prompt Length, and Transfer-Learning Strategies

Attention-based decoder models were used to generate libraries of novel inhibitors for the HMG-Coenzyme A reductase (HMGCR) enzyme. These deep neural network models were pretrained on previously synthesized drug-like molecules from the ZINC15 database to learn the syntax of SMILES strings and then f...

Full description

Saved in:

Bibliographic Details
Main Author:	Mauricio Cafiero (2480059) (author)
Published:	2024
Subjects:	Genetics Molecular Biology Physiology Pharmacology Ecology Biological Sciences not elsewhere classified Chemical Sciences not elsewhere classified Information Systems not elsewhere classified via dockstring ), previously synthesized drug predicted ic50 values lowest ic50 values learning strategies attention desirable molecular properties dense neural network calculated quantitative estimate decoder gpt models based decoder models robust library generation ∼ 1000 molecules virtual screening libraries lowest docking scores known hmgcr inhibitors docking scores robust libraries novel inhibitors generated molecules resulting libraries generate libraries tuned models zinc15 database tanimoto similarity smiles strings several criteria prompt length optimal balance means clustering like molecules input tokens inhibit hmgcr good correlation different temperatures autodock vina also generated
Tags:	Add Tag No Tags, Be the first to tag this record!

Transformer-Decoder GPT Models for Generating Virtual Screening Libraries of HMG-Coenzyme A Reductase Inhibitors: Effects of Temperature, Prompt Length, and Transfer-Learning Strategies

Similar Items