Sequential Contrastive and Deep Learning Models to Identify Selective Butyrylcholinesterase Inhibitors

Overview

Journal J Chem Inf Model

Publisher American Chemical Society

Specialties Chemistry
Medical Informatics

Date 2024 Mar 27

PMID 38532612

Authors

Mustafa Kemal Ozalp

Patricia A Vignaux

Ana C Puhl

Thomas R Lane

Fabio Urbina

Sean Ekins

Affiliations

Soon will be listed here.

Abstract

Butyrylcholinesterase (BChE) is a target of interest in late-stage Alzheimer's Disease (AD) where selective BChE inhibitors (BIs) may offer symptomatic treatment without the harsh side effects of acetylcholinesterase (AChE) inhibitors. In this study, we explore multiple machine learning strategies to identify BIs , optimizing for precision over all other metrics. We compare state-of-the-art supervised contrastive learning (CL) with deep learning (DL) and Random Forest (RF) machine learning, across single and sequential modeling configurations, to identify the best models for BChE selectivity. We used these models to virtually screen a vendor library of 5 million compounds for BIs and tested 20 of these compounds . Seven of the 20 compounds displayed selectivity for BChE over AChE, reflecting a hit rate of 35% for our model predictions, suggesting a highly efficient strategy for modeling selective inhibition.

References

Jiang C, Ge Y, Cheng Z, Wang Y, Tao H, Zhu K . Discovery of New Selective Butyrylcholinesterase (BChE) Inhibitors with Anti-Aβ Aggregation Activity: Structure-Based Virtual Screening, Hit Optimization and Biological Evaluation. Molecules. 2019; 24(14). PMC: 6680840. DOI: 10.3390/molecules24142568. View

Dighe S, Deora G, De La Mora E, Nachon F, Chan S, Parat M . Discovery and Structure-Activity Relationships of a Highly Selective Butyrylcholinesterase Inhibitor by Structure-Based Virtual Screening. J Med Chem. 2016; 59(16):7683-9. DOI: 10.1021/acs.jmedchem.6b00356. View

Tayeb H, Yang H, Price B, Tarazi F . Pharmacotherapies for Alzheimer's disease: beyond cholinesterase inhibitors. Pharmacol Ther. 2011; 134(1):8-25. DOI: 10.1016/j.pharmthera.2011.12.002. View

Arendt T, Bigl V, Walther F, Sonntag M . Decreased ratio of CSF acetylcholinesterase to butyrylcholinesterase activity in Alzheimer's disease. Lancet. 1984; 1(8369):173. DOI: 10.1016/s0140-6736(84)90116-8. View

Millard C, Broomfield C . A computer model of glycosylated human butyrylcholinesterase. Biochem Biophys Res Commun. 1992; 189(3):1280-6. DOI: 10.1016/0006-291x(92)90212-4. View

Bartels C, Wiersema B, van der Spek A, Innis J, La Du B . Characterization of 12 silent alleles of the human butyrylcholinesterase (BCHE) gene. Am J Hum Genet. 1996; 58(1):52-64. PMC: 1914969. View

Shrivastava A, Kell D . FragNet, a Contrastive Learning-Based Transformer Model for Clustering, Interpreting, Visualizing, and Navigating Chemical Space. Molecules. 2021; 26(7). PMC: 8038408. DOI: 10.3390/molecules26072065. View

Wang Y, Magar R, Liang C, Barati Farimani A . Improving Molecular Contrastive Learning via Faulty Negative Mitigation and Decomposed Fragment Contrast. J Chem Inf Model. 2022; 62(11):2713-2725. DOI: 10.1021/acs.jcim.2c00495. View

Gers F, Schmidhuber J, Cummins F . Learning to forget: continual prediction with LSTM. Neural Comput. 2000; 12(10):2451-71. DOI: 10.1162/089976600300015015. View

10.

Soreq H, Seidman S . Acetylcholinesterase--new roles for an old actor. Nat Rev Neurosci. 2001; 2(4):294-302. DOI: 10.1038/35067589. View

11.

Miles J, Kapure J, Deora G, Courageux C, Igert A, Dias J . Rapid discovery of a selective butyrylcholinesterase inhibitor using structure-based virtual screening. Bioorg Med Chem Lett. 2020; 30(24):127609. DOI: 10.1016/j.bmcl.2020.127609. View

12.

Yao K, Wang X, Li W, Zhu H, Jiang Y, Li Y . Semi-supervised heterogeneous graph contrastive learning for drug-target interaction prediction. Comput Biol Med. 2023; 163:107199. DOI: 10.1016/j.compbiomed.2023.107199. View

13.

Maelicke A, Hoeffle-Maas A, Ludwig J, Maus A, Samochocki M, Jordis U . Memogain is a galantamine pro-drug having dramatically reduced adverse effects and enhanced efficacy. J Mol Neurosci. 2009; 40(1-2):135-7. DOI: 10.1007/s12031-009-9269-5. View

14.

Lv W, Xue Y . Prediction of acetylcholinesterase inhibitors and characterization of correlative molecular descriptors by machine learning methods. Eur J Med Chem. 2010; 45(3):1167-72. DOI: 10.1016/j.ejmech.2009.12.038. View

15.

Zheng Z, Tan Y, Wang H, Yu S, Liu T, Liang C . CasANGCL: pre-training and fine-tuning model based on cascaded attention network and graph contrastive learning for molecular property prediction. Brief Bioinform. 2023; 24(1). DOI: 10.1093/bib/bbac566. View

16.

Watkins P, ZIMMERMAN H, KNAPP M, Gracon S, Lewis K . Hepatotoxic effects of tacrine administration in patients with Alzheimer's disease. JAMA. 1994; 271(13):992-8. View

17.

Vignaux P, Lane T, Urbina F, Gerlach J, Puhl A, Snyder S . Validation of Acetylcholinesterase Inhibition Machine Learning Models for Multiple Species. Chem Res Toxicol. 2023; 36(2):188-201. PMC: 9945174. DOI: 10.1021/acs.chemrestox.2c00283. View

18.

Darvesh S, Hopkins D, Geula C . Neurobiology of butyrylcholinesterase. Nat Rev Neurosci. 2003; 4(2):131-8. DOI: 10.1038/nrn1035. View

19.

Lane T, Urbina F, Rank L, Gerlach J, Riabova O, Lepioshkin A . Machine Learning Models for Activity: Prediction and Target Visualization. Mol Pharm. 2021; 19(2):674-689. PMC: 9121329. DOI: 10.1021/acs.molpharmaceut.1c00791. View

20.

Saxena A, Redman A, Jiang X, Lockridge O, Doctor B . Differences in active site gorge dimensions of cholinesterases revealed by binding of inhibitors to human butyrylcholinesterase. Biochemistry. 1997; 36(48):14642-51. DOI: 10.1021/bi971425+. View