A Simple Representation of Three-Dimensional Molecular Structure

  • J Med Chem. 2017 Sep 14;60(17):7393-7409. doi: 10.1021/acs.jmedchem.7b00696.
Seth D Axen  1 ,  Xi-Ping Huang  2  3 ,  Elena L Cáceres  1  4 ,  Leo Gendelev  1  4 ,  Bryan L Roth  2  3  5 ,  Michael J Keiser  1  4
Affiliations
  • 1. Department of Bioengineering and Therapeutic Sciences, University of California, San Francisco , 675 Nelson Rising Lane NS 416A, San Francisco, California 94143, United States.
  • 2. Department of Pharmacology, University of North Carolina School of Medicine , Chapel Hill, North Carolina 27599, United States.
  • 3. National Institute of Mental Health Psychoactive Drug Screening Program (NIMH PDSP), University of North Carolina , Chapel Hill, North Carolina 27599, United States.
  • 4. Department of Pharmaceutical Chemistry, Institute for Neurodegenerative Diseases, and Institute for Computational Health Sciences, University of California, San Francisco , 675 Nelson Rising Lane NS 416A, San Francisco, California 94143, United States.
  • 5. Division of Chemical Biology and Medicinal Chemistry, Eshelman School of Pharmacy, University of North Carolina at Chapel Hill , Chapel Hill, North Carolina 27599, United States.
PMID: 28731335 DOI: 10.1021/acs.jmedchem.7b00696
Abstract

Statistical and machine learning approaches predict drug-to-target relationships from 2D small-molecule topology patterns. One might expect 3D information to improve these calculations. Here we apply the logic of the extended connectivity fingerprint (ECFP) to develop a rapid, alignment-invariant 3D representation of molecular conformers, the extended three-dimensional fingerprint (E3FP). By integrating E3FP with the similarity ensemble approach (SEA), we achieve higher precision-recall performance relative to SEA with ECFP on ChEMBL20 and equivalent receiver operating characteristic performance. We identify classes of molecules for which E3FP is a better predictor of similarity in bioactivity than is ECFP. Finally, we report novel drug-to-target binding predictions inaccessible by 2D fingerprints and confirm three of them experimentally with ligand efficiencies from 0.442-0.637 kcal/mol/heavy atom.

Products