A disentangled generative model for improved drug response prediction in patients via sample synthesis

Personalized drug response prediction from molecular data is an important challenge in precision medicine for treating cancer. Computational methods have been widely explored and have become increasingly accurate in recent years. However, the clinical application of prediction methods is still in it...

Full description

Saved in:
Bibliographic Details
Main Authors: Kunshi Li, Bihan Shen, Fangyoumin Feng, Xueliang Li, Yue Wang, Na Feng, Zhixuan Tang, Liangxiao Ma, Hong Li
Format: Article
Language:English
Published: Elsevier 2025-06-01
Series:Journal of Pharmaceutical Analysis
Subjects:
Online Access:http://www.sciencedirect.com/science/article/pii/S2095177924002259
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849318367309070336
author Kunshi Li
Bihan Shen
Fangyoumin Feng
Xueliang Li
Yue Wang
Na Feng
Zhixuan Tang
Liangxiao Ma
Hong Li
author_facet Kunshi Li
Bihan Shen
Fangyoumin Feng
Xueliang Li
Yue Wang
Na Feng
Zhixuan Tang
Liangxiao Ma
Hong Li
author_sort Kunshi Li
collection DOAJ
description Personalized drug response prediction from molecular data is an important challenge in precision medicine for treating cancer. Computational methods have been widely explored and have become increasingly accurate in recent years. However, the clinical application of prediction methods is still in its infancy due to large discrepancies between preclinial models and patients. We present a novel disentangled synthesis transfer network (DiSyn) for drug response prediction specifically designed for transfer learning from preclinical models to clinical patients. DiSyn uses a domain separation network (DSN) to disentangle drug response related features, employs data synthesis technology to increase the sample size and iteratively trains for better feature disentanglement. DiSyn is pretrained on large-scale unlabeled cancer samples and validated by three datasets, The Cancer Genome Atlas (TCGA), Investigation of Serial Studies to Predict Your Therapeutic Response With Imaging And moLecular Analysis 2 (I-SPY2) and Novartis Institutes for Biomedical Research Patient-Derived Xenograft Encyclopedia (NIBR PDXE), achieving competitive performance with the state-of-the-art methods on cancer patients and mice. Furthermore, the application of DiSyn to thousands of breast cancer patients show the heterogeneity in drug responses and demonstrate its potential value in biomarker discovery and drug combination prediction.
format Article
id doaj-art-03db1d5a7a2f4dc4ba3005cdf563a0a6
institution Kabale University
issn 2095-1779
language English
publishDate 2025-06-01
publisher Elsevier
record_format Article
series Journal of Pharmaceutical Analysis
spelling doaj-art-03db1d5a7a2f4dc4ba3005cdf563a0a62025-08-20T03:50:50ZengElsevierJournal of Pharmaceutical Analysis2095-17792025-06-0115610112810.1016/j.jpha.2024.101128A disentangled generative model for improved drug response prediction in patients via sample synthesisKunshi Li0Bihan Shen1Fangyoumin Feng2Xueliang Li3Yue Wang4Na Feng5Zhixuan Tang6Liangxiao Ma7Hong Li8CAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, ChinaCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, ChinaCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, ChinaCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, ChinaMolecular Pathology Laboratory, National Center for Liver Cancer, Eastern Hepatobiliary Surgery Hospital, Shanghai, 201800, ChinaMolecular Pathology Laboratory, National Center for Liver Cancer, Eastern Hepatobiliary Surgery Hospital, Shanghai, 201800, ChinaCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, ChinaCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, ChinaCAS Key Laboratory of Computational Biology, Shanghai Institute of Nutrition and Health, University of Chinese Academy of Sciences, Chinese Academy of Sciences, Shanghai, 200031, China; Corresponding author.Personalized drug response prediction from molecular data is an important challenge in precision medicine for treating cancer. Computational methods have been widely explored and have become increasingly accurate in recent years. However, the clinical application of prediction methods is still in its infancy due to large discrepancies between preclinial models and patients. We present a novel disentangled synthesis transfer network (DiSyn) for drug response prediction specifically designed for transfer learning from preclinical models to clinical patients. DiSyn uses a domain separation network (DSN) to disentangle drug response related features, employs data synthesis technology to increase the sample size and iteratively trains for better feature disentanglement. DiSyn is pretrained on large-scale unlabeled cancer samples and validated by three datasets, The Cancer Genome Atlas (TCGA), Investigation of Serial Studies to Predict Your Therapeutic Response With Imaging And moLecular Analysis 2 (I-SPY2) and Novartis Institutes for Biomedical Research Patient-Derived Xenograft Encyclopedia (NIBR PDXE), achieving competitive performance with the state-of-the-art methods on cancer patients and mice. Furthermore, the application of DiSyn to thousands of breast cancer patients show the heterogeneity in drug responses and demonstrate its potential value in biomarker discovery and drug combination prediction.http://www.sciencedirect.com/science/article/pii/S2095177924002259Precision medicineTransfer learningDrug response prediction
spellingShingle Kunshi Li
Bihan Shen
Fangyoumin Feng
Xueliang Li
Yue Wang
Na Feng
Zhixuan Tang
Liangxiao Ma
Hong Li
A disentangled generative model for improved drug response prediction in patients via sample synthesis
Journal of Pharmaceutical Analysis
Precision medicine
Transfer learning
Drug response prediction
title A disentangled generative model for improved drug response prediction in patients via sample synthesis
title_full A disentangled generative model for improved drug response prediction in patients via sample synthesis
title_fullStr A disentangled generative model for improved drug response prediction in patients via sample synthesis
title_full_unstemmed A disentangled generative model for improved drug response prediction in patients via sample synthesis
title_short A disentangled generative model for improved drug response prediction in patients via sample synthesis
title_sort disentangled generative model for improved drug response prediction in patients via sample synthesis
topic Precision medicine
Transfer learning
Drug response prediction
url http://www.sciencedirect.com/science/article/pii/S2095177924002259
work_keys_str_mv AT kunshili adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT bihanshen adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT fangyouminfeng adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT xueliangli adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT yuewang adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT nafeng adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT zhixuantang adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT liangxiaoma adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT hongli adisentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT kunshili disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT bihanshen disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT fangyouminfeng disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT xueliangli disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT yuewang disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT nafeng disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT zhixuantang disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT liangxiaoma disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis
AT hongli disentangledgenerativemodelforimproveddrugresponsepredictioninpatientsviasamplesynthesis