Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron

Traditional drug development is a slow and costly process that leads to the production of new drugs. Virtual screening (VS) is a computational procedure that measures the similarity of molecules as one of its primary tasks. Many techniques for capturing the biological similarity between a test compo...

Descripción completa

Guardado en:

Detalles Bibliográficos
Autores principales:	Mohammed Khaldoon Altalib, Naomie Salim
Formato:	article
Lenguaje:	EN
Publicado:	MDPI AG 2021
Materias:	drug discovery ligand-based virtual screen similarity model Siamese architecture multi-layer perceptron (MLP) Organic chemistry QD241-441
Acceso en línea:	https://doaj.org/article/4b592698a80349218e5d09472a8230fb
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

id	oai:doaj.org-article:4b592698a80349218e5d09472a8230fb
record_format	dspace
spelling	oai:doaj.org-article:4b592698a80349218e5d09472a8230fb2021-11-11T18:37:46ZSimilarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron10.3390/molecules262166691420-3049https://doaj.org/article/4b592698a80349218e5d09472a8230fb2021-11-01T00:00:00Zhttps://www.mdpi.com/1420-3049/26/21/6669https://doaj.org/toc/1420-3049Traditional drug development is a slow and costly process that leads to the production of new drugs. Virtual screening (VS) is a computational procedure that measures the similarity of molecules as one of its primary tasks. Many techniques for capturing the biological similarity between a test compound and a known target ligand have been established in ligand-based virtual screens (LBVSs). However, despite the good performances of the above methods compared to their predecessors, especially when dealing with molecules that have structurally homogenous active elements, they are not satisfied when dealing with molecules that are structurally heterogeneous. The main aim of this study is to improve the performance of similarity searching, especially with molecules that are structurally heterogeneous. The Siamese network will be used due to its capability to deal with complicated data samples in many fields. The Siamese multi-layer perceptron architecture will be enhanced by using two similarity distance layers with one fused layer, then multiple layers will be added after the fusion layer, and then the nodes of the model that contribute less or nothing during inference according to their signal-to-noise ratio values will be pruned. Several benchmark datasets will be used, which are: the MDL Drug Data Report (MDDR-DS1, MDDR-DS2, and MDDR-DS3), the Maximum Unbiased Validation (MUV), and the Directory of Useful Decoys (DUD). The results show the outperformance of the proposed method on standard Tanimoto coefficient (TAN) and other methods. Additionally, it is possible to reduce the number of nodes in the Siamese multilayer perceptron model while still keeping the effectiveness of recall on the same level.Mohammed Khaldoon AltalibNaomie SalimMDPI AGarticledrug discoveryligand-based virtual screensimilarity modelSiamese architecturemulti-layer perceptron (MLP)Organic chemistryQD241-441ENMolecules, Vol 26, Iss 6669, p 6669 (2021)
institution	DOAJ
collection	DOAJ
language	EN
topic	drug discovery ligand-based virtual screen similarity model Siamese architecture multi-layer perceptron (MLP) Organic chemistry QD241-441
spellingShingle	drug discovery ligand-based virtual screen similarity model Siamese architecture multi-layer perceptron (MLP) Organic chemistry QD241-441 Mohammed Khaldoon Altalib Naomie Salim Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron
description	Traditional drug development is a slow and costly process that leads to the production of new drugs. Virtual screening (VS) is a computational procedure that measures the similarity of molecules as one of its primary tasks. Many techniques for capturing the biological similarity between a test compound and a known target ligand have been established in ligand-based virtual screens (LBVSs). However, despite the good performances of the above methods compared to their predecessors, especially when dealing with molecules that have structurally homogenous active elements, they are not satisfied when dealing with molecules that are structurally heterogeneous. The main aim of this study is to improve the performance of similarity searching, especially with molecules that are structurally heterogeneous. The Siamese network will be used due to its capability to deal with complicated data samples in many fields. The Siamese multi-layer perceptron architecture will be enhanced by using two similarity distance layers with one fused layer, then multiple layers will be added after the fusion layer, and then the nodes of the model that contribute less or nothing during inference according to their signal-to-noise ratio values will be pruned. Several benchmark datasets will be used, which are: the MDL Drug Data Report (MDDR-DS1, MDDR-DS2, and MDDR-DS3), the Maximum Unbiased Validation (MUV), and the Directory of Useful Decoys (DUD). The results show the outperformance of the proposed method on standard Tanimoto coefficient (TAN) and other methods. Additionally, it is possible to reduce the number of nodes in the Siamese multilayer perceptron model while still keeping the effectiveness of recall on the same level.
format	article
author	Mohammed Khaldoon Altalib Naomie Salim
author_facet	Mohammed Khaldoon Altalib Naomie Salim
author_sort	Mohammed Khaldoon Altalib
title	Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron
title_short	Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron
title_full	Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron
title_fullStr	Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron
title_full_unstemmed	Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron
title_sort	similarity-based virtual screen using enhanced siamese multi-layer perceptron
publisher	MDPI AG
publishDate	2021
url	https://doaj.org/article/4b592698a80349218e5d09472a8230fb
work_keys_str_mv	AT mohammedkhaldoonaltalib similaritybasedvirtualscreenusingenhancedsiamesemultilayerperceptron AT naomiesalim similaritybasedvirtualscreenusingenhancedsiamesemultilayerperceptron
_version_	1718431759970861056

Similarity-Based Virtual Screen Using Enhanced Siamese Multi-Layer Perceptron

Ejemplares similares