Current status and challenges of artificial intelligence-enabled prediction of synergistic cancer drug combinations

Hong TAN; Shenggeng LIN; Yi XIONG

doi:10.19401/j.cnki.1007-3639.2024.09.001

您当前的位置：

首页 >

文章列表页 >

Current status and challenges of artificial intelligence-enabled prediction of synergistic cancer drug combinations

Specialists' Commentory | 更新时间：2025-12-31

- Current status and challenges of artificial intelligence-enabled prediction of synergistic cancer drug combinations
- China Oncology Vol. 34, Issue 9, Pages: 807-813(2024)
- 作者机构：
  
  1. 上海交通大学生命科学技术学院，上海 200240
  2. 上海交通大学张江高等研究院人工智能生物医药中心，上海 201203
- 作者简介：
- 基金信息：
- DOI：10.19401/j.cnki.1007-3639.2024.09.001
  CLC： TP181
- Received：07 August 2024，
  
  Revised：2024-09-13，
  
  Published：30 September 2024
- 稿件说明：
移动端阅览
Hong TAN, Shenggeng LIN, Yi XIONG. Current status and challenges of artificial intelligence-enabled prediction of synergistic cancer drug combinations[J]. China Oncology, 2024, 34(9): 807-813.
DOI：

Hong TAN, Shenggeng LIN, Yi XIONG. Current status and challenges of artificial intelligence-enabled prediction of synergistic cancer drug combinations[J]. China Oncology, 2024, 34(9): 807-813. DOI： 10.19401/j.cnki.1007-3639.2024.09.001.

摘要

近年来，癌症的发病率和死亡率不断攀升，耐药性已成为目前癌症治疗的重大挑战。传统的单一化治疗方法并不能有效地应对肿瘤细胞的异质性及其多重耐药，常导致疗效不理想。药物联合治疗作为一种重要的治疗策略，可通过多药协同作用提高疗效并延缓耐药性的发展。然而，传统的药物组合筛选方法耗时且成本高昂。随着数据的积累和计算方法的发展，人工智能特别是深度学习在癌症协同药物组合预测中展现出巨大潜力。通过人工智能技术，研究人员可以更高效地预测药物组合是否存在协同作用，降低实验成本，发现新的潜在协同药物组合。然而，人工智能模型仍存在可解释性差、特征融合不充分及标注数据缺乏等问题。本文就人工智能在癌症药物组合协同作用预测中的应用进展予以综述。首先，介绍药物耐药机制及联合治疗的挑战，指出传统方法在药物组合筛选中的局限性。然后，介绍不同深度学习模型在癌症协同药物组合预测中的优缺点，包括前馈神经网络、图神经网络、自编码器、可见神经网络、Transformer及其扩展模型等。针对现有深度学习模型普遍存在的问题，本文提出了解决方案，包括利用多模态数据增强模型的泛化能力，采用迁移学习和多任务学习应对数据不足问题，以及设计更具可解释性的模型以推动临床应用。未来，药物协同组合预测领域有望通过开发标准化的协同指标、提升模型的可解释性、整合多模态数据及应对数据稀缺问题，进一步推动模型从实验室研究走向临床应用，从而为癌症治疗提供更有效的解决方案。

Abstract

In recent years

the incidence and mortality rates of cancer have been rising steadily

with drug resistance becoming a major challenge in cancer treatment. Traditional monolithic treatment approaches have proven ineffective in addressing the heterogeneity of tumor cells and their multiple resistance mechanisms

leading to suboptimal therapeutic outcomes. Drug combination therapy

as a critical strategy

aims to enhance efficacy and delay the development of drug resistance through the synergistic action of multiple drugs. However

conventional methods for screening drug combinations are time-consuming and costly. With the accumulation of data and advances in computational methods

artificial intelligence

particularly deep learning

has demonstrated great potential in predicting synergistic drug combinations for cancer treatment. Artificial intelligence technologies allow researchers to efficiently predict whether drug combinations exhibit synergistic effects

reducing experimental costs and identifying novel potential synergistic combinations. Nevertheless

artificial intelligence models still face challenges such as poor interpretability

insufficient feature integration

and a lack of labeled data. This paper provided a comprehensive review of the advancements in artificial intelligence applications for predicting synergistic drug combinations in cancer therapy. First

it discussed the mechanisms of drug resistance and the challenges of combination therapy

highlighting the limitations of traditional drug combination screening methods. Then

it presented the advantages and disadvantages of various deep learning models used for predicting synergistic drug combinations

including feedforward neural networks

graph neural networks

autoencoders

visible neural networks

Transformer and their extended models. In response to the common issues in current deep learning models

this review proposed several solutions

such as leveraging multimodal data to enhance model generalization

employing transfer learning and multitask learning to address data scarcity

and designing more interpretable models to facilitate clinical application. In the future

the field of synergistic drug combination prediction is expected to benefit from the development of standardized synergy metrics

improvements in model interpretability

integration of multimodal data

and effective handling of data limitations

further advancing the transition of models from laboratory research to clinical practice

ultimately providing more effective solutions for cancer treatment.

关键词

Keywords

references

BRAY F , LAVERSANNE M , SUNG H , et al . Global cancer statistics 2022: GLOBOCAN estimates of incidence and mortality worldwide for 36 cancers in 185 countries [J ] . CA Cancer J Clin , 2024 , 74 ( 3 ): 229 - 263 .

MEIJER C , MULDER N H , TIMMER-BOSSCHA H , et al . Relationship of cellular glutathione to the cytotoxicity and resistance of seven platinum compounds [J ] . Cancer Res , 1992 , 52 ( 24 ): 6885 - 6889 .

HEERBOTH S , HOUSMAN G , LEARY M , et al . EMT and tumor metastasis [J ] . Clin Transl Med , 2015 , 4 : 6 . DOI: 10.1186/s40169-015-0048-3 http://doi.org/10.1186/s40169-015-0048-3

ABOLHODA A , WILSON A E , ROSS H , et al . Rapid activation of MDR 1 gene expression in human metastatic sarcoma after in vivo exposure to doxorubicin [J ] . Clin Cancer Res , 1999 , 5 ( 11 ): 3352 - 3356 .

THOMAS J , WANG L H , CLARK R E , et al . Active transport of imatinib into and out of cells: implications for drug resistance [J ] . Blood , 2004 , 104 ( 12 ): 3739 - 3745 . DOI: 10.1182/blood-2003-12-4276 http://doi.org/10.1182/blood-2003-12-4276

PAO W , MILLER V A , POLITI K A , et al . Acquired resistance of lung adenocarcinomas to gefitinib or erlotinib is associated with a second mutation in the EGFR kinase domain [J ] . PLoS Med , 2005 , 2 ( 3 ): e73 . DOI: 10.1371/journal.pmed.0020073 http://doi.org/10.1371/journal.pmed.0020073

BAO S D , WU Q L , MCLENDON R E , et al . Glioma stem cells promote radioresistance by preferential activation of the DNA damage response [J ] . Nature , 2006 , 444 ( 7120 ): 756 - 760 .

SETHI T , RINTOUL R C , MOORE S M , et al . Extracellular matrix proteins protect small cell lung cancer cells against apoptosis: a mechanism for small cell lung cancer growth and drug resistance in vivo [J ] . Nat Med , 1999 , 5 ( 6 ): 662 - 668 .

BYLER S , GOLDGAR S , HEERBOTH S , et al . Genetic and epigenetic aspects of breast cancer progression and therapy [J ] . Anticancer Res , 2014 , 34 ( 3 ): 1071 - 1077 .

BYLER S , SARKAR S . Do epigenetic drug treatments hold the key to killing cancer progenitor cells? [J ] . Epigenomics , 2014 , 6 ( 2 ): 161 - 165 . DOI: 10.2217/epi.14.4 http://doi.org/10.2217/epi.14.4

MADANI TONEKABONI S A , SOLTAN GHORAIE L , MANEM V S K , et al . Predictive approaches for drug combination discovery in cancer [J ] . Brief Bioinform , 2018 , 19 ( 2 ): 263 - 276 . DOI: 10.1093/bib/bbw104 http://doi.org/10.1093/bib/bbw104

CHOU T C . Theoretical basis, experimental design, and computerized simulation of synergism and antagonism in drug combination studies [J ] . Pharmacol Rev , 2006 , 58 ( 3 ): 621 - 681 .

SWAIN S M , BASELGA J , KIM S B , et al . Pertuzumab, trastuzumab, and docetaxel in HER2-positive metastatic breast cancer [J ] . N Engl J Med , 2015 , 372 ( 8 ): 724 - 734 .

ROTH A D , MAIBACH R , MARTINELLI G , et al . Docetaxel (Taxotere)-cisplatin (TC): an effective drug combination in gastric carcinoma. Swiss Group for Clinical Cancer Research (SAKK), and the European Institute of Oncology (EIO) [J ] . Ann Oncol , 2000 , 11 ( 3 ): 301 - 306 . DOI: 10.1023/a:1008342013224 http://doi.org/10.1023/a:1008342013224

GILLET J P , VARMA S , GOTTESMAN M M . The clinical relevance of cancer cell lines [J ] . J Natl Cancer Inst , 2013 , 105 ( 7 ): 452 - 458 .

CHOI S Y , LIN D , GOUT P W , et al . Lessons from patient-derived xenografts for better in vitro modeling of human cancer [J ] . Adv Drug Deliv Rev , 2014 , 79/80 : 222 - 237 .

LEHÁR J , KRUEGER A S , AVERY W , et al . Synergistic drug combinations tend to improve therapeutically relevant selectivity [J ] . Nat Biotechnol , 2009 , 27 ( 7 ): 659 - 666 . DOI: 10.1038/nbt.1549 http://doi.org/10.1038/nbt.1549

TAN X , HU L , LUQUETTE L J 3rd , et al . Systematic identification of synergistic drug pairs targeting HIV [J ] . Nat Biotechnol , 2012 , 30 ( 11 ): 1125 - 1130 . DOI: 10.1038/nbt.2391 http://doi.org/10.1038/nbt.2391

ZHENG S Y , ALDAHDOOH J , SHADBAHR T , et al . DrugComb update: a more comprehensive drug sensitivity data repository and analysis portal [J ] . Nucleic Acids Res , 2021 , 49 ( W1 ): W174-W184 .

GHANDI M , HUANG F W , JANÉ-VALBUENA J , et al . Next-generation characterization of the cancer cell line encyclopedia [J ] . Nature , 2019 , 569 ( 7757 ): 503 - 508 .

WISHART D S , FEUNANG Y D , GUO A C , et al . DrugBank 5.0: a major update to the DrugBank database for 2018 [J ] . Nucleic Acids Res , 2018 , 46 ( D1 ): D1074-D1082 .

YANG K , BAI H J , OUYANG Q , et al . Finding multiple target optimal intervention in disease-related molecular network [J ] . Mol Syst Biol , 2008 , 4 : 228 . DOI: 10.1038/msb.2008.60 http://doi.org/10.1038/msb.2008.60

SUN X Q , BAO J G , YOU Z H , et al . Modeling of signaling crosstalk-mediated drug resistance and its implications on drug combination [J ] . Oncotarget , 2016 , 7 ( 39 ): 63995 - 64006 . DOI: 10.18632/oncotarget.11745 http://doi.org/10.18632/oncotarget.11745

ZINNER R G , BARRETT B L , POPOVA E , et al . Algorithmic guided screening of drug combinations of arbitrary size for activity against cancer cells [J ] . Mol Cancer Ther , 2009 , 8 ( 3 ): 521 - 532 . DOI: 10.1158/1535-7163.MCT-08-0937 http://doi.org/10.1158/1535-7163.MCT-08-0937

WU L L , WEN Y Q , LENG D J , et al . Machine learning methods, databases and tools for drug combination prediction [J ] . Brief Bioinform , 2022 , 23 ( 1 ): bbab355 .

SIDOROV P , NAULAERTS S , ARIEY-BONNET J , et al . Predicting synergism of cancer drug combinations using NCI-ALMANAC data [J ] . Front Chem , 2019 , 7 : 509 . DOI: 10.3389/fchem.2019.00509 http://doi.org/10.3389/fchem.2019.00509

XU Q , XIONG Y , DAI H , et al . PDC-SGB: Prediction of effective drug combinations using a stochastic gradient boosting algorithm [J ] . J Theor Biol , 2017 , 417 : 1 - 7 . DOI: S0022-5193(17)30019-X http://doi.org/S0022-5193(17)30019-X

HUANG H , ZHANG P , QU X A , et al . Systematic prediction of drug combinations based on clinical side-effects [J ] . Sci Rep , 2014 , 4 : 7160 . DOI: 10.1038/srep07160 http://doi.org/10.1038/srep07160

PREUER K , LEWIS R P I , HOCHREITER S , et al . DeepSynergy: predicting anti-cancer drug synergy with deep learning [J ] . Bioinformatics , 2018 , 34 ( 9 ): 1538 - 1546 . DOI: 10.1093/bioinformatics/btx806 http://doi.org/10.1093/bioinformatics/btx806

WANG J X , LIU X J , SHEN S Y , et al . DeepDDS: deep graph neural network with attention mechanism to predict synergistic drug combinations [J ] . Brief Bioinform , 2022 , 23 ( 1 ): bbab390 .

ZHANG T Y , ZHANG L W , PAYNE P R O , et al . Synergistic drug combination prediction by integrating multiomics data in deep learning models [J ] . Methods Mol Biol , 2021 , 2194 : 223 - 238 . DOI: 10.1007/978-1-0716-0849-4_12 http://doi.org/10.1007/978-1-0716-0849-4_12

KUENZI B M , PARK J , FONG S H , et al . Predicting drug response and synergy using a deep learning model of human cancer cells [J ] . Cancer Cell , 2020 , 38 ( 5 ): 672 - 684 .e6. DOI: 10.1016/j.ccell.2020.09.014 http://doi.org/10.1016/j.ccell.2020.09.014

LI T H , SHETTY S , KAMATH A , et al . CancerGPT for few shot drug pair synergy prediction using large pretrained language models [J ] . NPJ Digit Med , 2024 , 7 ( 1 ): 40 . DOI: 10.1038/s41746-024-01024-9 http://doi.org/10.1038/s41746-024-01024-9

KURU H I , TASTAN O , CICEK A E . MatchMaker: a deep learning framework for drug synergy prediction [J ] . IEEE/ACM Trans Comput Biol Bioinform , 2022 , 19 ( 4 ): 2334 - 2344 .

PAN Y C , REN H T , LAN L , et al . Review of predicting synergistic drug combinations [J ] . Life , 2023 , 13 ( 9 ): 1878 .

LIU X , SONG C Z , LIU S C , et al . Multi-way relation-enhanced hypergraph representation learning for anti-cancer drug synergy prediction [J ] . Bioinformatics , 2022 , 38 ( 20 ): 4782 - 4789 .

HU J , GAO J , FANG X M , et al . DTSyn: a dual-transformer-based neural network to predict synergistic drug combinations [J ] . Brief Bioinform , 2022 , 23 ( 5 ): bbac302 .

EDWARDS C , NAIK A , KHOT T , et al . SynerGPT: in-context learning for personalized drug synergy prediction and drug design [EB/OL ] . ( 2023 - 10 - 24 ) [ 2024 - 08 - 06 ] . http://arxiv.org/abs/2307.11694 http://arxiv.org/abs/2307.11694 http://arxiv.org/abs/2307.11694 .

XU Y J , DONG Q , LI F , et al . Identifying subpathway signatures for individualized anticancer drug response by integrating multi-omics data [J ] . J Transl Med , 2019 , 17 ( 1 ): 255 . DOI: 10.1186/s12967-019-2010-4 http://doi.org/10.1186/s12967-019-2010-4

HE H H , CHEN G X , CHEN C Y C . 3DGT-DDI: 3D graph and text based neural network for drug-drug interaction prediction [J ] . Brief Bioinform , 2022 , 23 ( 3 ): bbac134 .

WANG X W , ZHU H M , CHEN D Y , et al . A complete graph-based approach with multi-task learning for predicting synergistic drug combinations [J ] . Bioinformatics , 2023 , 39 ( 6 ): btad351 .

ZHANG P , TU S K . MGAE-DC: predicting the synergistic effects of drug combinations through multi-channel graph autoencoders [J ] . PLoS Comput Biol , 2023 , 19 ( 3 ): e1010951 .

PRETO A J , MATOS-FILIPE P , MOURÃO J , et al . SYNPRED: prediction of drug combination effects in cancer using different synergy metrics and ensemble learning [J ] . Gigascience , 2022 , 11 : giac087 .

WANG Y , WANG J J , LIU Y . Deep learning for predicting synergistic drug combinations: state-of-the-arts and future directions [J ] . Clin Transl Discov , 2024 , 4 ( 3 ): e317 .

LIU S C , WANG H C , LIU W Y , et al . Pre-training molecular graph representation with 3D geometry [EB/OL ] . ( 2022 - 05 - 29 ) [ 2024 - 08 - 06 ] . 2110.07728. http://arxiv.org/abs/2110.07728 http://arxiv.org/abs/2110.07728 http://arxiv.org/abs/2110.07728 .

Views

1937

下载量

CSCD

Alert me when the article has been cited

提交

Tools

Publicity Resources

Artificial intelligence in gastric cancer diagnosis, treatment and prognostic prediction: current application and future perspective

Deep learning-based lymphocyte infiltration detection on pathological images

Research progress and prospects of MRI in predicting lymph node status in breast cancer

MRI-based radiomics and deep learning model construction: non-invasive differentiation of molecular subtypes in primary intracranial diffuse large B-cell lymphoma

Related Author

Dongge PENG

Ziye WAN

Ning LU

Han ZHUANG

Weigang HU

Zhen ZHANG

Jiazhou WANG

杨　鑫

Related Institution

Graduate School of Xinjiang Medical university, Urumqi 830000, Xinjiang Uygur Autonomous Region

Department of Oncology, Xinjiang Military Region General Hospital of the Chinese People’s Liberation Army, Urumqi 830000, Xinjiang Uygur Autonomous Region

Department of Radiation Oncology, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University, Shanghai Key Laboratory of Radiation Oncology, Shanghai Clinical Research Center for Radiation Oncology

复旦大学附属肿瘤医院放射治疗中心，复旦大学上海医学院肿瘤学系

Department of Breast Surgery, Fudan University Shanghai Cancer Center, Department of Oncology, Shanghai Medical College, Fudan University

AI问答

⁰