TransCDR: a deep learning model for enhancing the generalizability of drug activity prediction through transfer learning and multimodal data fusion.

IF 4.4 1区 生物学 Q1 BIOLOGY BMC Biology Pub Date : 2024-10-09 DOI:10.1186/s12915-024-02023-8
Xiaoqiong Xia, Chaoyu Zhu, Fan Zhong, Lei Liu
{"title":"TransCDR: a deep learning model for enhancing the generalizability of drug activity prediction through transfer learning and multimodal data fusion.","authors":"Xiaoqiong Xia, Chaoyu Zhu, Fan Zhong, Lei Liu","doi":"10.1186/s12915-024-02023-8","DOIUrl":null,"url":null,"abstract":"<p><strong>Background: </strong>Accurate and robust drug response prediction is of utmost importance in precision medicine. Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR), their performances can be improved by addressing issues such as insufficient data modality, suboptimal fusion algorithms, and poor generalizability for novel drugs or cell lines.</p><p><strong>Results: </strong>We introduce TransCDR, which uses transfer learning to learn drug representations and fuses multi-modality features of drugs and cell lines by a self-attention mechanism, to predict the IC<sub>50</sub> values or sensitive states of drugs on cell lines. We are the first to systematically evaluate the generalization of the CDR prediction model to novel (i.e., never-before-seen) compound scaffolds and cell line clusters. TransCDR shows better generalizability than 8 state-of-the-art models. TransCDR outperforms its 5 variants that train drug encoders (i.e., RNN and AttentiveFP) from scratch under various scenarios. The most critical contributors among multiple drug notations and omics profiles are Extended Connectivity Fingerprint and genetic mutation. Additionally, the attention-based fusion module further enhances the predictive performance of TransCDR. TransCDR, trained on the GDSC dataset, demonstrates strong predictive performance on the external testing set CCLE. It is also utilized to predict missing CDRs on GDSC. Moreover, we investigate the biological mechanisms underlying drug response by classifying 7675 patients from TCGA into drug-sensitive or drug-resistant groups, followed by a Gene Set Enrichment Analysis.</p><p><strong>Conclusions: </strong>TransCDR emerges as a potent tool with significant potential in drug response prediction.</p>","PeriodicalId":9339,"journal":{"name":"BMC Biology","volume":null,"pages":null},"PeriodicalIF":4.4000,"publicationDate":"2024-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11462810/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"BMC Biology","FirstCategoryId":"99","ListUrlMain":"https://doi.org/10.1186/s12915-024-02023-8","RegionNum":1,"RegionCategory":"生物学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"BIOLOGY","Score":null,"Total":0}
引用次数: 0

Abstract

Background: Accurate and robust drug response prediction is of utmost importance in precision medicine. Although many models have been developed to utilize the representations of drugs and cancer cell lines for predicting cancer drug responses (CDR), their performances can be improved by addressing issues such as insufficient data modality, suboptimal fusion algorithms, and poor generalizability for novel drugs or cell lines.

Results: We introduce TransCDR, which uses transfer learning to learn drug representations and fuses multi-modality features of drugs and cell lines by a self-attention mechanism, to predict the IC50 values or sensitive states of drugs on cell lines. We are the first to systematically evaluate the generalization of the CDR prediction model to novel (i.e., never-before-seen) compound scaffolds and cell line clusters. TransCDR shows better generalizability than 8 state-of-the-art models. TransCDR outperforms its 5 variants that train drug encoders (i.e., RNN and AttentiveFP) from scratch under various scenarios. The most critical contributors among multiple drug notations and omics profiles are Extended Connectivity Fingerprint and genetic mutation. Additionally, the attention-based fusion module further enhances the predictive performance of TransCDR. TransCDR, trained on the GDSC dataset, demonstrates strong predictive performance on the external testing set CCLE. It is also utilized to predict missing CDRs on GDSC. Moreover, we investigate the biological mechanisms underlying drug response by classifying 7675 patients from TCGA into drug-sensitive or drug-resistant groups, followed by a Gene Set Enrichment Analysis.

Conclusions: TransCDR emerges as a potent tool with significant potential in drug response prediction.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
TransCDR:通过迁移学习和多模态数据融合提高药物活性预测通用性的深度学习模型。
背景:准确而稳健的药物反应预测在精准医疗中至关重要。尽管已经开发了许多模型来利用药物和癌细胞系的表征预测癌症药物反应(CDR),但通过解决数据模态不足、次优融合算法以及对新型药物或细胞系的普适性差等问题,这些模型的性能还可以得到改善:我们介绍了TransCDR,它利用迁移学习来学习药物表征,并通过自注意机制融合药物和细胞系的多模态特征,从而预测药物在细胞系上的IC50值或敏感状态。我们首次系统地评估了 CDR 预测模型对新型(即从未见过的)化合物支架和细胞系群的普适性。与 8 个最先进的模型相比,TransCDR 显示出更好的通用性。在各种情况下,TransCDR 都优于其 5 个从头开始训练药物编码器(即 RNN 和 AttentiveFP)的变体。在多种药物符号和 omics 资料中,最重要的贡献者是扩展连接指纹和基因突变。此外,基于注意力的融合模块进一步提高了 TransCDR 的预测性能。在 GDSC 数据集上训练的 TransCDR 在外部测试集 CCLE 上表现出很强的预测性能。它还被用于预测 GDSC 上缺失的 CDR。此外,我们还通过将来自 TCGA 的 7675 名患者分为药物敏感组和药物耐受组,然后进行基因组富集分析,研究了药物反应的生物机制:TransCDR是一种有效的工具,在药物反应预测方面具有巨大潜力。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
BMC Biology
BMC Biology 生物-生物学
CiteScore
7.80
自引率
1.90%
发文量
260
审稿时长
3 months
期刊介绍: BMC Biology is a broad scope journal covering all areas of biology. Our content includes research articles, new methods and tools. BMC Biology also publishes reviews, Q&A, and commentaries.
期刊最新文献
Novel function of single-target regulator NorR involved in swarming motility and biofilm formation revealed in Vibrio alginolyticus. Hibernation reduces GABA signaling in the brainstem to enhance motor activity of breathing at cool temperatures. A powerful and versatile new fixation protocol for immunostaining and in situ hybridization that preserves delicate tissues. Bridging chemical structure and conceptual knowledge enables accurate prediction of compound-protein interaction. Evolutionary divergent clusters of transcribed extinct truncated retroposons drive low mRNA expression and developmental regulation in the protozoan Leishmania.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1