ADMET Scoring Models for Real-World Drug Design

Zihan Wang, Junren Li, Yuzhe Wang, Luhua Lai

Submission Type: I want my submission to be considered for poster only

Keywords: ADMET; pairwise learning; meta-learning

TL;DR: To solve ADMET bottlenecks in drug discovery, our pipeline uses LLMs to mine real-world literature data, meta/pairwise learning to mitigate batch effects, and a novel aNDCG metric for robust, practical evaluation of predictive models.

Confirmation Of Submission Requirements: I submit an abstract. It uses the template provided on the submission page and is no longer than 2 pages.

Submission Number: 367