flâneur

Widespread false negatives in DNA-encoded library data: how linker effects impair machine learning-based lead prediction - Chemical Science (RSC Publishing) DOI:10.1039/D5SC00844A

pubs.rsc.org · 7,041 words · saved by 1 readers

Alba L. Montoya‡ a, Adam S. Hogendorf‡ a, Steven Tingey b, Aadarsh Kuberan c, Lik Hang Yuen a, Herwig Schüler d and Raphael M. Franzini *ae aDepartment of Medicinal Chemistry, College of Pharmacy, University of Utah, 30 S 2000 E, Salt Lake City, UT 84112, USA. E-mail: raphael.franzini@utah.edu bWaterford School, 1480 E 9400 S, Sandy, UT 84093, USA cWest High School, 241 N 300 W, Salt Lake City, UT 84103, USA dCenter for Molecular Protein Science, Department of Chemistry, Lund University, Lund, 22100, Sweden eHuntsman Cancer Institute, University of Utah, 2000 Circle of Hope, Salt Lake City, UT 84054, USA First published on 9th May 2025 DNA-encoded chemical libraries (DECLs) have become integral to early-stage drug discovery, yielding active compounds and extensive labeled datasets for machine learning (ML)-based prediction of bioactive molecules. However, the information content of DECL selection data remains scarcely explored. This study systematically investigates for the first time

Widespread false negatives in DNA-encoded library data: how linker effects impair machine learning-based lead prediction - Chemical Science (RSC Publishing) DOI:10.1039/D5SC00844A View PDF Version Previous Article Next Article Open Access Article This Open Access Article is licensed under a Creative Commons Attribution-Non Commercial 3.0 Unported Licence DOI: 10.1039/D5SC00844A (Edge Article) Chem. Sci. , 2025, 16 , 10918-10927 Widespread false negatives in DNA-encoded library data: how linker effects impair machine learning-based lead prediction † Alba L. Montoya ‡ a , Adam S. Hogendorf ‡ a ,

saved by

related reading