Molecular Toxicity Virtual Screening Applying a Quantized Computational SNN-Based Framework

Overview

Journal Molecules

Publisher MDPI

Specialty Biology

Date 2023 Feb 11

PMID 36771009

Authors

Mauro Nascimben

Lia Rimondini

Affiliations

Soon will be listed here.

Abstract

Spiking neural networks are biologically inspired machine learning algorithms attracting researchers' attention for their applicability to alternative energy-efficient hardware other than traditional computers. In the current work, spiking neural networks have been tested in a quantitative structure-activity analysis targeting the toxicity of molecules. Multiple public-domain databases of compounds have been evaluated with spiking neural networks, achieving accuracies compatible with high-quality frameworks presented in the previous literature. The numerical experiments also included an analysis of hyperparameters and tested the spiking neural networks on molecular fingerprints of different lengths. Proposing alternatives to traditional software and hardware for time- and resource-consuming tasks, such as those found in chemoinformatics, may open the door to new research and improvements in the field.

References

Mitchell J . Machine learning methods in chemoinformatics. Wiley Interdiscip Rev Comput Mol Sci. 2014; 4(5):468-481. PMC: 4180928. DOI: 10.1002/wcms.1183. View

Polishchuk P, Muratov E, Artemenko A, Kolumbin O, Muratov N, Kuzmin V . Application of random forest approach to QSAR prediction of aquatic toxicity. J Chem Inf Model. 2009; 49(11):2481-8. DOI: 10.1021/ci900203n. View

Gerum R, Schilling A . Integration of Leaky-Integrate-and-Fire Neurons in Standard Machine Learning Architectures to Generate Hybrid Networks: A Surrogate Gradient Approach. Neural Comput. 2021; 33(10):2827-2852. DOI: 10.1162/neco_a_01424. View

Konovalov D, Coomans D, Deconinck E, Vander Heyden Y . Benchmarking of QSAR models for blood-brain barrier permeation. J Chem Inf Model. 2007; 47(4):1648-56. DOI: 10.1021/ci700100f. View

Chen D, Zheng J, Wei G, Pan F . Extracting Predictive Representations from Hundreds of Millions of Molecules. J Phys Chem Lett. 2021; 12(44):10793-10801. PMC: 9358546. DOI: 10.1021/acs.jpclett.1c03058. View

Wu Z, Ramsundar B, Feinberg E, Gomes J, Geniesse C, Pappu A . MoleculeNet: a benchmark for molecular machine learning. Chem Sci. 2018; 9(2):513-530. PMC: 5868307. DOI: 10.1039/c7sc02664a. View

Puentes P, Valderrama N, Gonzalez C, Daza L, Munoz-Camargo C, Cruz J . PharmaNet: Pharmaceutical discovery with deep recurrent neural networks. PLoS One. 2021; 16(4):e0241728. PMC: 8075191. DOI: 10.1371/journal.pone.0241728. View

Judson R, Houck K, Kavlock R, Knudsen T, Martin M, Mortensen H . In vitro screening of environmental chemicals for targeted testing prioritization: the ToxCast project. Environ Health Perspect. 2010; 118(4):485-92. PMC: 2854724. DOI: 10.1289/ehp.0901392. View

Zhang J, Mucs D, Norinder U, Svensson F . LightGBM: An Effective and Scalable Algorithm for Prediction of Chemical Toxicity-Application to the Tox21 and Mutagenicity Data Sets. J Chem Inf Model. 2019; 59(10):4150-4158. DOI: 10.1021/acs.jcim.9b00633. View

10.

Karpov P, Godin G, Tetko I . Transformer-CNN: Swiss knife for QSAR modeling and interpretation. J Cheminform. 2021; 12(1):17. PMC: 7079452. DOI: 10.1186/s13321-020-00423-w. View

11.

Guo W, Yantir H, Fouda M, Eltawil A, Salama K . Toward the Optimal Design and FPGA Implementation of Spiking Neural Networks. IEEE Trans Neural Netw Learn Syst. 2021; 33(8):3988-4002. DOI: 10.1109/TNNLS.2021.3055421. View

12.

Banerjee P, Siramshetty V, Drwal M, Preissner R . Computational methods for prediction of in vitro effects of new chemical structures. J Cheminform. 2017; 8:51. PMC: 5043617. DOI: 10.1186/s13321-016-0162-2. View

13.

Gayvert K, Madhukar N, Elemento O . A Data-Driven Approach to Predicting Successes and Failures of Clinical Trials. Cell Chem Biol. 2016; 23(10):1294-1301. PMC: 5074862. DOI: 10.1016/j.chembiol.2016.07.023. View

14.

Russell A, Orchard G, Dong Y, Mihalas S, Niebur E, Tapson J . Optimization methods for spiking neurons and networks. IEEE Trans Neural Netw. 2010; 21(12):1950-62. PMC: 3164281. DOI: 10.1109/TNN.2010.2083685. View

15.

Svetnik V, Liaw A, Tong C, Culberson J, Sheridan R, Feuston B . Random forest: a classification and regression tool for compound classification and QSAR modeling. J Chem Inf Comput Sci. 2003; 43(6):1947-58. DOI: 10.1021/ci034160g. View

16.

Durant J, Leland B, Henry D, Nourse J . Reoptimization of MDL keys for use in drug discovery. J Chem Inf Comput Sci. 2002; 42(6):1273-80. DOI: 10.1021/ci010132r. View

17.

Xu Y, Pei J, Lai L . Deep Learning Based Regression and Multiclass Models for Acute Oral Toxicity Prediction with Automatic Chemical Feature Extraction. J Chem Inf Model. 2017; 57(11):2672-2685. DOI: 10.1021/acs.jcim.7b00244. View

18.

FUKUTOME H, Tamura H, Sugata K . AN ELECTRIC ANALOGUE OF THE NEURON. Kybernetik. 1963; 2:28-32. DOI: 10.1007/BF00292107. View

19.

Ancuceanu R, Dinu M, Neaga I, Laszlo F, Boda D . Development of QSAR machine learning-based models to forecast the effect of substances on malignant melanoma cells. Oncol Lett. 2019; 17(5):4188-4196. PMC: 6466999. DOI: 10.3892/ol.2019.10068. View

20.

Motamedi F, Perez-Sanchez H, Mehridehnavi A, Fassihi A, Ghasemi F . Accelerating Big Data Analysis through LASSO-Random Forest Algorithm in QSAR Studies. Bioinformatics. 2022; 38(2):469-475. DOI: 10.1093/bioinformatics/btab659. View