Cargando…

DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning

Synergistic drug combinations have demonstrated effective therapeutic effects in cancer treatment. Deep learning methods accelerate identification of novel drug combinations by reducing the search space. However, potential adverse drug–drug interactions (DDIs), which may increase the risks for combi...

Descripción completa

Detalles Bibliográficos
Autores principales: Wang, Zhongming, Dong, Jiahui, Wu, Lianlian, Dai, Chong, Wang, Jing, Wen, Yuqi, Zhang, Yixin, Yang, Xiaoxi, He, Song, Bo, Xiaochen
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2023
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9861702/
https://www.ncbi.nlm.nih.gov/pubmed/36677903
http://dx.doi.org/10.3390/molecules28020844
_version_ 1784874907684831232
author Wang, Zhongming
Dong, Jiahui
Wu, Lianlian
Dai, Chong
Wang, Jing
Wen, Yuqi
Zhang, Yixin
Yang, Xiaoxi
He, Song
Bo, Xiaochen
author_facet Wang, Zhongming
Dong, Jiahui
Wu, Lianlian
Dai, Chong
Wang, Jing
Wen, Yuqi
Zhang, Yixin
Yang, Xiaoxi
He, Song
Bo, Xiaochen
author_sort Wang, Zhongming
collection PubMed
description Synergistic drug combinations have demonstrated effective therapeutic effects in cancer treatment. Deep learning methods accelerate identification of novel drug combinations by reducing the search space. However, potential adverse drug–drug interactions (DDIs), which may increase the risks for combination therapy, cannot be detected by existing computational synergy prediction methods. We propose DEML, an ensemble-based multi-task neural network, for the simultaneous optimization of five synergy regression prediction tasks, synergy classification, and DDI classification tasks. DEML uses chemical and transcriptomics information as inputs. DEML adapts the novel hybrid ensemble layer structure to construct higher order representation using different perspectives. The task-specific fusion layer of DEML joins representations for each task using a gating mechanism. For the Loewe synergy prediction task, DEML overperforms the state-of-the-art synergy prediction method with an improvement of 7.8% and 13.2% for the root mean squared error and the R2 correlation coefficient. Owing to soft parameter sharing and ensemble learning, DEML alleviates the multi-task learning ‘seesaw effect’ problem and shows no performance loss on other tasks. DEML has a superior ability to predict drug pairs with high confidence and less adverse DDIs. DEML provides a promising way to guideline novel combination therapy strategies for cancer treatment.
format Online
Article
Text
id pubmed-9861702
institution National Center for Biotechnology Information
language English
publishDate 2023
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-98617022023-01-22 DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning Wang, Zhongming Dong, Jiahui Wu, Lianlian Dai, Chong Wang, Jing Wen, Yuqi Zhang, Yixin Yang, Xiaoxi He, Song Bo, Xiaochen Molecules Article Synergistic drug combinations have demonstrated effective therapeutic effects in cancer treatment. Deep learning methods accelerate identification of novel drug combinations by reducing the search space. However, potential adverse drug–drug interactions (DDIs), which may increase the risks for combination therapy, cannot be detected by existing computational synergy prediction methods. We propose DEML, an ensemble-based multi-task neural network, for the simultaneous optimization of five synergy regression prediction tasks, synergy classification, and DDI classification tasks. DEML uses chemical and transcriptomics information as inputs. DEML adapts the novel hybrid ensemble layer structure to construct higher order representation using different perspectives. The task-specific fusion layer of DEML joins representations for each task using a gating mechanism. For the Loewe synergy prediction task, DEML overperforms the state-of-the-art synergy prediction method with an improvement of 7.8% and 13.2% for the root mean squared error and the R2 correlation coefficient. Owing to soft parameter sharing and ensemble learning, DEML alleviates the multi-task learning ‘seesaw effect’ problem and shows no performance loss on other tasks. DEML has a superior ability to predict drug pairs with high confidence and less adverse DDIs. DEML provides a promising way to guideline novel combination therapy strategies for cancer treatment. MDPI 2023-01-14 /pmc/articles/PMC9861702/ /pubmed/36677903 http://dx.doi.org/10.3390/molecules28020844 Text en © 2023 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
Wang, Zhongming
Dong, Jiahui
Wu, Lianlian
Dai, Chong
Wang, Jing
Wen, Yuqi
Zhang, Yixin
Yang, Xiaoxi
He, Song
Bo, Xiaochen
DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning
title DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning
title_full DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning
title_fullStr DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning
title_full_unstemmed DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning
title_short DEML: Drug Synergy and Interaction Prediction Using Ensemble-Based Multi-Task Learning
title_sort deml: drug synergy and interaction prediction using ensemble-based multi-task learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9861702/
https://www.ncbi.nlm.nih.gov/pubmed/36677903
http://dx.doi.org/10.3390/molecules28020844
work_keys_str_mv AT wangzhongming demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT dongjiahui demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT wulianlian demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT daichong demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT wangjing demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT wenyuqi demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT zhangyixin demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT yangxiaoxi demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT hesong demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning
AT boxiaochen demldrugsynergyandinteractionpredictionusingensemblebasedmultitasklearning