Molecule Auto-correction to Facilitate Molecular Design

Overview

Journal J Comput Aided Mol Des

Publisher Springer

Specialties Biomedical Engineering
Molecular Biology

Date 2024 Feb 16

PMID 38363377

Authors

Alan Kerstjens

Hans De Winter

Affiliations

Soon will be listed here.

Abstract

Ensuring that computationally designed molecules are chemically reasonable is at best cumbersome. We present a molecule correction algorithm that morphs invalid molecular graphs into structurally related valid analogs. The algorithm is implemented as a tree search, guided by a set of policies to minimize its cost. We showcase how the algorithm can be applied to molecular design, either as a post-processing step or as an integral part of molecule generators.

References

Winter R, Montanari F, Steffen A, Briem H, Noe F, Clevert D . Efficient multi-objective molecular optimization in a continuous latent space. Chem Sci. 2019; 10(34):8016-8024. PMC: 6836962. DOI: 10.1039/c9sc01928f. View

Segler M, Waller M . Neural-Symbolic Machine Learning for Retrosynthesis and Reaction Prediction. Chemistry. 2017; 23(25):5966-5971. DOI: 10.1002/chem.201605499. View

Kerstjens A, De Winter H . LEADD: Lamarckian evolutionary algorithm for de novo drug design. J Cheminform. 2022; 14(1):3. PMC: 8760751. DOI: 10.1186/s13321-022-00582-y. View

Tukey J . Comparing individual means in the analysis of variance. Biometrics. 1949; 5(2):99-114. View

OBoyle N, Sayle R . Comparing structural fingerprints using a literature-based similarity benchmark. J Cheminform. 2016; 8:36. PMC: 4932683. DOI: 10.1186/s13321-016-0148-0. View

Gomez L . Decision Making in Medicinal Chemistry: The Power of Our Intuition. ACS Med Chem Lett. 2018; 9(10):956-958. PMC: 6187401. DOI: 10.1021/acsmedchemlett.8b00359. View

Sattarov B, Baskin I, Horvath D, Marcou G, Bjerrum E, Varnek A . De Novo Molecular Design by Combining Deep Autoencoder Recurrent Neural Networks with Generative Topographic Mapping. J Chem Inf Model. 2019; 59(3):1182-1196. DOI: 10.1021/acs.jcim.8b00751. View

Gaulton A, Bellis L, Bento A, Chambers J, Davies M, Hersey A . ChEMBL: a large-scale bioactivity database for drug discovery. Nucleic Acids Res. 2011; 40(Database issue):D1100-7. PMC: 3245175. DOI: 10.1093/nar/gkr777. View

Bajorath J . Representation and identification of activity cliffs. Expert Opin Drug Discov. 2017; 12(9):879-883. DOI: 10.1080/17460441.2017.1353494. View

10.

Riniker S, Landrum G . Open-source platform to benchmark fingerprints for ligand-based virtual screening. J Cheminform. 2013; 5(1):26. PMC: 3686626. DOI: 10.1186/1758-2946-5-26. View

11.

Hartenfeller M, Zettl H, Walter M, Rupp M, Reisen F, Proschak E . DOGS: reaction-driven de novo design of bioactive compounds. PLoS Comput Biol. 2012; 8(2):e1002380. PMC: 3280956. DOI: 10.1371/journal.pcbi.1002380. View

12.

Nicolaou C, Brown N . Multi-objective optimization methods in drug design. Drug Discov Today Technol. 2013; 10(3):e427-35. DOI: 10.1016/j.ddtec.2013.02.001. View

13.

Maggiora G . On outliers and activity cliffs--why QSAR often disappoints. J Chem Inf Model. 2006; 46(4):1535. DOI: 10.1021/ci060117s. View

14.

Irwin J, Tang K, Young J, Dandarchuluun C, Wong B, Khurelbaatar M . ZINC20-A Free Ultralarge-Scale Chemical Database for Ligand Discovery. J Chem Inf Model. 2020; 60(12):6065-6073. PMC: 8284596. DOI: 10.1021/acs.jcim.0c00675. View

15.

Brown N, Fiscato M, Segler M, Vaucher A . GuacaMol: Benchmarking Models for de Novo Molecular Design. J Chem Inf Model. 2019; 59(3):1096-1108. DOI: 10.1021/acs.jcim.8b00839. View

16.

Gao W, Coley C . The Synthesizability of Molecules Proposed by Generative Models. J Chem Inf Model. 2020; 60(12):5714-5723. DOI: 10.1021/acs.jcim.0c00174. View

17.

Olivecrona M, Blaschke T, Engkvist O, Chen H . Molecular de-novo design through deep reinforcement learning. J Cheminform. 2017; 9(1):48. PMC: 5583141. DOI: 10.1186/s13321-017-0235-x. View

18.

Kerstjens A, De Winter H . A molecule perturbation software library and its application to study the effects of molecular design constraints. J Cheminform. 2023; 15(1):89. PMC: 10523775. DOI: 10.1186/s13321-023-00761-5. View

19.

Fromer J, Coley C . Computer-aided multi-objective optimization in small molecule discovery. Patterns (N Y). 2023; 4(2):100678. PMC: 9982302. DOI: 10.1016/j.patter.2023.100678. View

20.

Skoraczynski G, Kitlas M, Miasojedow B, Gambin A . Critical assessment of synthetic accessibility scores in computer-assisted synthesis planning. J Cheminform. 2023; 15(1):6. PMC: 9840255. DOI: 10.1186/s13321-023-00678-z. View