Bioptic B1: A Target-Agnostic Potency-Based Small Molecules Search Engine

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Vinogradov, Vlad, Izmailov, Ivan, Steshin, Simon, Nguyen, Kong T.
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916782536654848
author Vinogradov, Vlad
Izmailov, Ivan
Steshin, Simon
Nguyen, Kong T.
author_facet Vinogradov, Vlad
Izmailov, Ivan
Steshin, Simon
Nguyen, Kong T.
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2406_14572
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Bioptic B1: A Target-Agnostic Potency-Based Small Molecules Search Engine
Vinogradov, Vlad
Izmailov, Ivan
Steshin, Simon
Nguyen, Kong T.
Quantitative Methods
Artificial Intelligence
Information Retrieval
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.
title Bioptic B1: A Target-Agnostic Potency-Based Small Molecules Search Engine
topic Quantitative Methods
Artificial Intelligence
Information Retrieval
url https://arxiv.org/abs/2406.14572