Abstract Medical research results show that the effectiveness of an antitumor drug is highly dependent on the genomic characteristics of patients. How to customize an optimal medical treatment for each tumor patient is an extremely important and challenging research topic. Aiming at this subject, a set of methods to predict the efficacy response of various antitumor drugs is proposed by machine learning technology for data processing, feature extraction and modeling of the tumor gene sequences of patients. Firstly, a data mining algorithm based on multiscale association rules is proposed for feature selection at different scales of genomics data. Then, the selected genomics data are locally accumulated by the cumulative window function to further compress the data and extract the gene feature information with stronger overall expression. Based on the above, a fully connected multi-layer neural network is designed and the extracted multiscale cumulative gene features are treated as input samples to train the network. Finally, two fusion methods, including feature fusion and decision fusion, are utilized to predict the responses of a tumor gene sequence to different antitumor drugs, respectively. Results of simulation experiments show that the proposed approach is superior in key performance indexes, such as sensitivity, specificity, accuracy and the area under characteristic curve.
Corresponding Authors:
GUO Chengan, Ph.D., professor. His research interests include signal and information processing, intelligent computation, biomedical signal processing and medical intelligence.
About author:: HAN Rui, Ph.D. candidate. Her research interests include biological information processing and medical intelligence.
HAN Rui,GUO Cheng'an. Prediction of Antitumor Drug Response Based on Multiscale Local Cumulative Features and Neural Networks[J]. Pattern Recognition and Artificial Intelligence, 2022, 35(4): 323-332.
[1] AGUR Z, ELISHMERENI M, KHEIFETZ Y. Personalizing Oncology Treatments by Predicting Drug Efficacy, Side-Effects, and Improved Therapy: Mathematics, Statistics, and Their Integration. Wiley Interdisciplinary Reviews Systems Biology and Medicine, 2014, 6(3): 239-253. [2] FORBES S A, BEARE D, GUNASEKARAN P, et al. COSMIC: Exploring the World's Knowledge of Somatic Mutations in Human Cancer. Nucleic Acids Research, 2015, 43(D1): D805-D811. [3] YANG W J, SOARES J, GRENINGER P, et al. Genomics of Drug Sensitivity in Cancer(GDSC): A Resource for Therapeutic Biomarker Discovery in Cancer Cells. Nucleic Acids Research, 2012, 41(D1): D955-D961. [4] CHANG Y, PARK H, YANG H J, et al. Cancer Drug Response Profile Scan(CDRscan): A Deep Learning Model That Predicts Drug Effectiveness from Cancer Genomic Signature. Scientific Reports, 2018, 8(1). DOI: 10.1038/s41598-018-27214-6. [5] XU X L, GU H, WANG Y, et al. Autoencoder Based Feature Selection Method for Classification of Anticancer Drug Response. Frontiers in Genetics, 2019, 10. DOI: 10.3389/fgene.2019.00233. [6] VOUGAS K, KROCHMAL M, JACKSON T, et al. Deep Learning and Association Rule Mining for Predicting Drug Response in Cancer [C/OL].[2021-08-11]. https://www.biorxiv.org/content/biorxiv/early/2017/05/09/070490.full.pdf. [7] SHARIFI-NOGHABI H, ZOLOTAREVA O, COLLINS C C, et al. MOLI: Multi-omics Late Integration with Deep Neural Networks for Drug Response Prediction. Bioinformatics, 2019, 35(14): i501-i509. [8] BAPTISTA D, FERREIRA P G, ROCHA M. Deep Learning for Drug Response Prediction in Cancer. Briefings in Bioinformatics, 2021, 22(1): 360-379. [9] LI M, WANG Y K, ZHENG R Q, et al. DeepDSC: A Deep Lear-ning Method to Predict Drug Sensitivity of Cancer Cell Lines. IEEE/ACM Transactions on Computational Biology and Bioinformatics, 2019, 18(2): 575-582. [10] ZHU Y T, BRETTIN T, EVRARD Y A, et al. Ensemble Transfer Learning for the Prediction of Anti Cancer Drug Response. Scienti-fic Reports, 2020, 10(1). DOI: 10.1038/s41598-020-74921-0. [11] BAI J, HAN R, GUO C A. A Hybrid Convolutional Network for Prediction of Anti-Cancer Drug Response // Proc of the 11th International Conference on Information Science and Technology. Wa-shington, USA: IEEE, 2021: 636-645. [12] AZUAJE F, KAOMA T, JEANTY C, et al. Drug Response Prediction and Analysis System for Oncology Research[C/OL].[2021-08-11]. https://www.biorxiv.org/content/biorxiv/early/2017/12/21/237727.full.pdf. [13] VOUGAS K, SAKELLAROPOULOS T, KOTSINAS A, et al. Machine Learning and Data Mining Frameworks for Predicting Drug Response in Cancer: An Overview and a Novel in Silico Screening Process Based on Association Rule Mining. Pharmacology & Therapeutics, 2019, 203. DOI: 10.1016/j.pharmthera.2019.107395. [14] AGRAWAL R, SRIKANT R. Fast Algorithms for Mining Associa-tion Rules in Large Databases // Proc of the 20th International Conference on Very Large Data Bases. San Francisco, USA: Morgan Kaufmann Publishers, 1994: 487-499. [15] LIN T Y, GOYAL P, GIRSHICK R, et al. Focal Loss for Dense Object Detection. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2018, 42(2): 318-327. [16] CARMONA-SAEZ P, CHAGOYEN M, RODRIGUEZ A, et al. Integrated Analysis of Gene Expression by Association Rules Disco-very. BMC Bioinformatics, 2006, 7. DOI: 10.1186/1471-2105-7-54. [17] BIN Y N, WANG X J, ZHAO L, et al. An Analysis of Mutational Signatures of Synonymous Mutations Across 15 Cancer Types. BMC Medical Genetics, 2019, 20. DOI: 10.1186/s12881-019-0926-4.
2022, Vol. 35 
