Cargando…
Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction
Determining and modeling the possible behaviour and actions of molecules requires investigating the basic structural features and physicochemical properties that determine their behaviour during chemical, physical, biological, and environmental processes. Computational approaches such as machine lea...
Autores principales: | , , , , , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
MDPI
2022
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9657591/ https://www.ncbi.nlm.nih.gov/pubmed/36362018 http://dx.doi.org/10.3390/ijms232113230 |
_version_ | 1784829735901069312 |
---|---|
author | Hentabli, Hamza Bengherbia, Billel Saeed, Faisal Salim, Naomie Nafea, Ibtehal Toubal, Abdelmoughni Nasser, Maged |
author_facet | Hentabli, Hamza Bengherbia, Billel Saeed, Faisal Salim, Naomie Nafea, Ibtehal Toubal, Abdelmoughni Nasser, Maged |
author_sort | Hentabli, Hamza |
collection | PubMed |
description | Determining and modeling the possible behaviour and actions of molecules requires investigating the basic structural features and physicochemical properties that determine their behaviour during chemical, physical, biological, and environmental processes. Computational approaches such as machine learning methods are alternatives to predicting the physiochemical properties of molecules based on their structures. However, the limited accuracy and high error rates of such predictions restrict their use. In this paper, a novel technique based on a deep learning convolutional neural network (CNN) for the prediction of chemical compounds’ bioactivity is proposed and developed. The molecules are represented in the new matrix format Mol2mat, a molecular matrix representation adapted from the well-known 2D-fingerprint descriptors. To evaluate the performance of the proposed methods, a series of experiments were conducted using two standard datasets, namely the MDL Drug Data Report (MDDR) and Sutherland, datasets comprising 10 homogeneous and 14 heterogeneous activity classes. After analysing the eight fingerprints, all the probable combinations were investigated using the five best descriptors. The results showed that a combination of three fingerprints, ECFP4, EPFP4, and ECFC4, along with a CNN activity prediction process, achieved the highest performance of 98% AUC when compared to the state-of-the-art ML algorithms NaiveB, LSVM, and RBFN. |
format | Online Article Text |
id | pubmed-9657591 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2022 |
publisher | MDPI |
record_format | MEDLINE/PubMed |
spelling | pubmed-96575912022-11-15 Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction Hentabli, Hamza Bengherbia, Billel Saeed, Faisal Salim, Naomie Nafea, Ibtehal Toubal, Abdelmoughni Nasser, Maged Int J Mol Sci Article Determining and modeling the possible behaviour and actions of molecules requires investigating the basic structural features and physicochemical properties that determine their behaviour during chemical, physical, biological, and environmental processes. Computational approaches such as machine learning methods are alternatives to predicting the physiochemical properties of molecules based on their structures. However, the limited accuracy and high error rates of such predictions restrict their use. In this paper, a novel technique based on a deep learning convolutional neural network (CNN) for the prediction of chemical compounds’ bioactivity is proposed and developed. The molecules are represented in the new matrix format Mol2mat, a molecular matrix representation adapted from the well-known 2D-fingerprint descriptors. To evaluate the performance of the proposed methods, a series of experiments were conducted using two standard datasets, namely the MDL Drug Data Report (MDDR) and Sutherland, datasets comprising 10 homogeneous and 14 heterogeneous activity classes. After analysing the eight fingerprints, all the probable combinations were investigated using the five best descriptors. The results showed that a combination of three fingerprints, ECFP4, EPFP4, and ECFC4, along with a CNN activity prediction process, achieved the highest performance of 98% AUC when compared to the state-of-the-art ML algorithms NaiveB, LSVM, and RBFN. MDPI 2022-10-30 /pmc/articles/PMC9657591/ /pubmed/36362018 http://dx.doi.org/10.3390/ijms232113230 Text en © 2022 by the authors. https://creativecommons.org/licenses/by/4.0/Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). |
spellingShingle | Article Hentabli, Hamza Bengherbia, Billel Saeed, Faisal Salim, Naomie Nafea, Ibtehal Toubal, Abdelmoughni Nasser, Maged Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction |
title | Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction |
title_full | Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction |
title_fullStr | Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction |
title_full_unstemmed | Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction |
title_short | Convolutional Neural Network Model Based on 2D Fingerprint for Bioactivity Prediction |
title_sort | convolutional neural network model based on 2d fingerprint for bioactivity prediction |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9657591/ https://www.ncbi.nlm.nih.gov/pubmed/36362018 http://dx.doi.org/10.3390/ijms232113230 |
work_keys_str_mv | AT hentablihamza convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction AT bengherbiabillel convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction AT saeedfaisal convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction AT salimnaomie convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction AT nafeaibtehal convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction AT toubalabdelmoughni convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction AT nassermaged convolutionalneuralnetworkmodelbasedon2dfingerprintforbioactivityprediction |