Molecular Graph-Based Deep Learning Algorithm Facilitates an Imaging-Based Strategy for Rapid Discovery of Small Molecules Modulating Biomolecular Condensates

Overview

Journal J Med Chem

Publisher American Chemical Society

Specialty Chemistry

Date 2023 Nov 8

PMID 37937963

Authors

Peng Gao

Qi Zhang

Devin Keely

Don W Cleveland

Yihong Ye

Wei Zheng

Min Shen

Haiyang Yu

Affiliations

Soon will be listed here.

Abstract

Biomolecular condensates are proposed to cause diseases, such as cancer and neurodegeneration, by concentrating proteins at abnormal subcellular loci. Imaging-based compound screens have been used to identify small molecules that reverse or promote biomolecular condensates. However, limitations of conventional imaging-based methods restrict the screening scale. Here, we used a graph convolutional network (GCN)-based computational approach and identified small molecule candidates that reduce the nuclear liquid-liquid phase separation of TAR DNA-binding protein 43 (TDP-43), an essential protein that undergoes phase transition in neurodegenerative diseases. We demonstrated that the GCN-based deep learning algorithm is suitable for spatial information extraction from the molecular graph. Thus, this is a promising method to identify small molecule candidates with novel scaffolds. Furthermore, we validated that these candidates do not affect the normal splicing function of TDP-43. Taken together, a combination of an imaging-based screen and a GCN-based deep learning method dramatically improves the speed and accuracy of the compound screen for biomolecular condensates.

References

Ling S, Polymenidou M, Cleveland D . Converging mechanisms in ALS and FTD: disrupted RNA and protein homeostasis. Neuron. 2013; 79(3):416-38. PMC: 4411085. DOI: 10.1016/j.neuron.2013.07.033. View

Wexler R, Martirez J, Rappe A . Chemical Pressure-Driven Enhancement of the Hydrogen Evolving Activity of NiP from Nonmetal Surface Doping Interpreted via Machine Learning. J Am Chem Soc. 2018; 140(13):4678-4683. DOI: 10.1021/jacs.8b00947. View

Behler J . Perspective: Machine learning potentials for atomistic simulations. J Chem Phys. 2016; 145(17):170901. DOI: 10.1063/1.4966192. View

Schmidt H, Barreau A, Rohatgi R . Phase separation-deficient TDP43 remains functional in splicing. Nat Commun. 2019; 10(1):4890. PMC: 6814767. DOI: 10.1038/s41467-019-12740-2. View

Gao P, Zhang J, Qiu H, Zhao S . A general QSPR protocol for the prediction of atomic/inter-atomic properties: a fragment based graph convolutional neural network (F-GCN). Phys Chem Chem Phys. 2021; 23(23):13242-13249. DOI: 10.1039/d1cp00677k. View

Sorensen K, Jorgensen M, Bruix A, Hammer B . Accelerating atomic structure search with cluster regularization. J Chem Phys. 2018; 148(24):241734. DOI: 10.1063/1.5023671. View

Meagher K, Redman L, Carlson H . Development of polyphosphate parameters for use with the AMBER force field. J Comput Chem. 2003; 24(9):1016-25. DOI: 10.1002/jcc.10262. View

Behler J . First Principles Neural Network Potentials for Reactive Simulations of Large Molecular and Condensed Systems. Angew Chem Int Ed Engl. 2017; 56(42):12828-12840. DOI: 10.1002/anie.201703114. View

Patel A, Lee H, Jawerth L, Maharana S, Jahnel M, Hein M . A Liquid-to-Solid Phase Transition of the ALS Protein FUS Accelerated by Disease Mutation. Cell. 2015; 162(5):1066-77. DOI: 10.1016/j.cell.2015.07.047. View

10.

Gao P, Zhang J, Sun Y, Yu J . Accurate predictions of aqueous solubility of drug molecules via the multilevel graph convolutional network (MGCN) and SchNet architectures. Phys Chem Chem Phys. 2020; 22(41):23766-23772. DOI: 10.1039/d0cp03596c. View

11.

Melamed Z, Lopez-Erauskin J, Baughn M, Zhang O, Drenner K, Sun Y . Premature polyadenylation-mediated loss of stathmin-2 is a hallmark of TDP-43-dependent neurodegeneration. Nat Neurosci. 2019; 22(2):180-190. PMC: 6348009. DOI: 10.1038/s41593-018-0293-z. View

12.

Wang J, Olsson S, Wehmeyer C, Perez A, Charron N, De Fabritiis G . Machine Learning of Coarse-Grained Molecular Dynamics Force Fields. ACS Cent Sci. 2019; 5(5):755-767. PMC: 6535777. DOI: 10.1021/acscentsci.8b00913. View

13.

Bai Y, Wilbraham L, Slater B, Zwijnenburg M, Sprick R, Cooper A . Accelerated Discovery of Organic Polymer Photocatalysts for Hydrogen Evolution from Water through the Integration of Experiment and Theory. J Am Chem Soc. 2019; 141(22):9063-9071. PMC: 7007211. DOI: 10.1021/jacs.9b03591. View

14.

Huang R, Zhu H, Shinn P, Ngan D, Ye L, Thakur A . The NCATS Pharmaceutical Collection: a 10-year update. Drug Discov Today. 2019; 24(12):2341-2349. DOI: 10.1016/j.drudis.2019.09.019. View

15.

Boulay G, Sandoval G, Riggi N, Iyer S, Buisson R, Naigles B . Cancer-Specific Retargeting of BAF Complexes by a Prion-like Domain. Cell. 2017; 171(1):163-178.e19. PMC: 6791823. DOI: 10.1016/j.cell.2017.07.036. View

16.

Panapitiya G, Avendano-Franco G, Ren P, Wen X, Li Y, Lewis J . Machine-Learning Prediction of CO Adsorption in Thiolated, Ag-Alloyed Au Nanoclusters. J Am Chem Soc. 2018; 140(50):17508-17514. DOI: 10.1021/jacs.8b08800. View

17.

Kwon Y, Lee D, Choi Y, Kang M, Kang S . Neural Message Passing for NMR Chemical Shift Prediction. J Chem Inf Model. 2020; 60(4):2024-2030. DOI: 10.1021/acs.jcim.0c00195. View

18.

Mitrea D, Mittasch M, Ferreira Gomes B, Klein I, Murcko M . Modulating biomolecular condensates: a novel approach to drug discovery. Nat Rev Drug Discov. 2022; 21(11):841-862. PMC: 9380678. DOI: 10.1038/s41573-022-00505-4. View

19.

Gao P, Zhang J, Peng Q, Zhang J, Glezakou V . General Protocol for the Accurate Prediction of Molecular C/H NMR Chemical Shifts via Machine Learning Augmented DFT. J Chem Inf Model. 2020; 60(8):3746-3754. DOI: 10.1021/acs.jcim.0c00388. View

20.

Mater A, Coote M . Deep Learning in Chemistry. J Chem Inf Model. 2019; 59(6):2545-2559. DOI: 10.1021/acs.jcim.9b00266. View