https://arxiv.org/abs/2406.14572
Vlad Vinogradov, Ivan Izmailov, Simon Steshin, Kong T. Nguyen
Abstract
Recent successes in virtual screening have been made possible by large models and extensive chemical libraries. However, combining these elements is challenging: the larger the model, the more expensive it is to run, making ultra-large libraries unfeasible. To address this, we developed a target-agnostic, efficacy-based molecule search model, which allows us to find structurally dissimilar molecules with similar biological activities. We used the best practices to design fast retrieval system, based on processor-optimized SIMD instructions, enabling us to screen the ultra-large 40B Enamine REAL library with 100\% recall rate. We extensively benchmarked our model and several state-of-the-art models for both speed performance and retrieval quality of novel molecules.
Subjects: Quantitative Methods (q-bio.QM); Artificial Intelligence (cs.AI); Information Retrieval (cs.IR)
Cite as: arXiv:2406.14572 [q-bio.QM] (or arXiv:2406.14572v3 [q-bio.QM] for this version)
