PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma
Stability of compounds in the human plasma is crucial for maintaining sufficient systemic drug exposure and considered an essential factor in the early stages of drug discovery and development. The rapid degradation of compounds in the plasma can result in poor in vivo efficacy. Currently, there are...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Elsevier
2023-01-01
|
Series: | Computational and Structural Biotechnology Journal |
Subjects: | |
Online Access: | http://www.sciencedirect.com/science/article/pii/S2001037023002416 |
_version_ | 1797384087403495424 |
---|---|
author | Woo Dae Jang Jidon Jang Jin Sook Song Sunjoo Ahn Kwang-Seok Oh |
author_facet | Woo Dae Jang Jidon Jang Jin Sook Song Sunjoo Ahn Kwang-Seok Oh |
author_sort | Woo Dae Jang |
collection | DOAJ |
description | Stability of compounds in the human plasma is crucial for maintaining sufficient systemic drug exposure and considered an essential factor in the early stages of drug discovery and development. The rapid degradation of compounds in the plasma can result in poor in vivo efficacy. Currently, there are no open-source software programs for predicting human plasma stability. In this study, we developed an attention-based graph neural network, PredPS to predict the plasma stability of compounds in human plasma using in-house and open-source datasets. The PredPS outperformed the two machine learning and two deep learning algorithms that were used for comparison indicating its stability-predicting efficiency. PredPS achieved an area under the receiver operating characteristic curve of 90.1%, accuracy of 83.5%, sensitivity of 82.3%, and specificity of 84.6% when evaluated using 5-fold cross-validation. In the early stages of drug discovery, PredPS could be a helpful method for predicting the human plasma stability of compounds. Saving time and money can be accomplished by adopting an in silico-based plasma stability prediction model at the high-throughput screening stage. The source code for PredPS is available at https://bitbucket.org/krict-ai/predps and the PredPS web server is available at https://predps.netlify.app. |
first_indexed | 2024-03-08T21:30:26Z |
format | Article |
id | doaj.art-bd4d78c3b6b540fa9bbc02740bd52450 |
institution | Directory Open Access Journal |
issn | 2001-0370 |
language | English |
last_indexed | 2024-03-08T21:30:26Z |
publishDate | 2023-01-01 |
publisher | Elsevier |
record_format | Article |
series | Computational and Structural Biotechnology Journal |
spelling | doaj.art-bd4d78c3b6b540fa9bbc02740bd524502023-12-21T07:31:45ZengElsevierComputational and Structural Biotechnology Journal2001-03702023-01-012135323539PredPS: Attention-based graph neural network for predicting stability of compounds in human plasmaWoo Dae Jang0Jidon Jang1Jin Sook Song2Sunjoo Ahn3Kwang-Seok Oh4Data Convergence Drug Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, Republic of Korea; Corresponding author.Data Convergence Drug Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, Republic of KoreaData Convergence Drug Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, Republic of KoreaData Convergence Drug Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, Republic of Korea; Department of Medicinal and Pharmaceutical Chemistry, University of Science and Technology, Daejeon 34129, Republic of KoreaData Convergence Drug Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, Republic of Korea; Department of Medicinal and Pharmaceutical Chemistry, University of Science and Technology, Daejeon 34129, Republic of Korea; Corresponding author at: Data Convergence Drug Research Center, Korea Research Institute of Chemical Technology, Daejeon 34114, Republic of Korea.Stability of compounds in the human plasma is crucial for maintaining sufficient systemic drug exposure and considered an essential factor in the early stages of drug discovery and development. The rapid degradation of compounds in the plasma can result in poor in vivo efficacy. Currently, there are no open-source software programs for predicting human plasma stability. In this study, we developed an attention-based graph neural network, PredPS to predict the plasma stability of compounds in human plasma using in-house and open-source datasets. The PredPS outperformed the two machine learning and two deep learning algorithms that were used for comparison indicating its stability-predicting efficiency. PredPS achieved an area under the receiver operating characteristic curve of 90.1%, accuracy of 83.5%, sensitivity of 82.3%, and specificity of 84.6% when evaluated using 5-fold cross-validation. In the early stages of drug discovery, PredPS could be a helpful method for predicting the human plasma stability of compounds. Saving time and money can be accomplished by adopting an in silico-based plasma stability prediction model at the high-throughput screening stage. The source code for PredPS is available at https://bitbucket.org/krict-ai/predps and the PredPS web server is available at https://predps.netlify.app.http://www.sciencedirect.com/science/article/pii/S2001037023002416Plasma stabilityDrug discoveryADMEGraph neural networkAttention analysisMachine learning |
spellingShingle | Woo Dae Jang Jidon Jang Jin Sook Song Sunjoo Ahn Kwang-Seok Oh PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma Computational and Structural Biotechnology Journal Plasma stability Drug discovery ADME Graph neural network Attention analysis Machine learning |
title | PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma |
title_full | PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma |
title_fullStr | PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma |
title_full_unstemmed | PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma |
title_short | PredPS: Attention-based graph neural network for predicting stability of compounds in human plasma |
title_sort | predps attention based graph neural network for predicting stability of compounds in human plasma |
topic | Plasma stability Drug discovery ADME Graph neural network Attention analysis Machine learning |
url | http://www.sciencedirect.com/science/article/pii/S2001037023002416 |
work_keys_str_mv | AT woodaejang predpsattentionbasedgraphneuralnetworkforpredictingstabilityofcompoundsinhumanplasma AT jidonjang predpsattentionbasedgraphneuralnetworkforpredictingstabilityofcompoundsinhumanplasma AT jinsooksong predpsattentionbasedgraphneuralnetworkforpredictingstabilityofcompoundsinhumanplasma AT sunjooahn predpsattentionbasedgraphneuralnetworkforpredictingstabilityofcompoundsinhumanplasma AT kwangseokoh predpsattentionbasedgraphneuralnetworkforpredictingstabilityofcompoundsinhumanplasma |