{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,3]],"date-time":"2026-02-03T18:35:14Z","timestamp":1770143714730,"version":"3.49.0"},"reference-count":41,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T00:00:00Z","timestamp":1736294400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:sec><jats:title>Introduction<\/jats:title><jats:p>Tumor heterogeneity significantly complicates the selection of effective cancer treatments, as patient responses to drugs can vary widely. Personalized cancer therapy has emerged as a promising strategy to enhance treatment effectiveness and precision. This study aimed to develop a personalized drug recommendation model leveraging genomic profiles to optimize therapeutic outcomes.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methods<\/jats:title><jats:p>A content-based filtering algorithm was implemented to predict drug sensitivity. Patient features were characterized by the tumor microenvironment (TME), and drug features were represented by drug fingerprints. The model was trained and validated using the Genomics of Drug Sensitivity in Cancer (GDSC) database, followed by independent validation with the Cancer Cell Line Encyclopedia (CCLE) dataset. Clinical application was assessed using The Cancer Genome Atlas (TCGA) dataset, with Best Overall Response (BOR) serving as the clinical efficacy measure. Two multilayer perceptron (MLP) models were built to predict IC<jats:sub>50<\/jats:sub> values for 542 tumor cell lines across 18 drugs.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>The model exhibited high predictive accuracy, with correlation coefficients (<jats:italic>R<\/jats:italic>) of 0.914 in the training set and 0.902 in the test set. Predictions for cytotoxic drugs, including Docetaxel (<jats:italic>R<\/jats:italic> = 0.72) and Cisplatin (<jats:italic>R<\/jats:italic> = 0.71), were particularly robust, whereas predictions for targeted therapies were less accurate (<jats:italic>R<\/jats:italic> &amp;lt; 0.3). Validation with CCLE (MFI as the endpoint) showed strong correlations (<jats:italic>R<\/jats:italic> = 0.67). Application to TCGA data successfully predicted clinical outcomes, including a significant association with 6-month progression-free survival (PFS, <jats:italic>P<\/jats:italic> = 0.007, AUC = 0.793).<\/jats:p><\/jats:sec><jats:sec><jats:title>Discussion<\/jats:title><jats:p>The model demonstrates strong performance across preclinical datasets, showing its potential for real-world application in personalized cancer therapy. By bridging preclinical IC<jats:sub>50<\/jats:sub> and clinical BOR endpoints, this approach provides a promising tool for optimizing patient-specific treatments.<\/jats:p><\/jats:sec>","DOI":"10.3389\/frai.2024.1444127","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T06:25:01Z","timestamp":1736317501000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Developing and validating a drug recommendation system based on tumor microenvironment and drug fingerprint"],"prefix":"10.3389","volume":"7","author":[{"given":"Yan","family":"Wang","sequence":"first","affiliation":[]},{"given":"Xiaoye","family":"Jin","sequence":"additional","affiliation":[]},{"given":"Rui","family":"Qiu","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Sheng","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Xuyang","family":"Song","sequence":"additional","affiliation":[]},{"given":"Jinxi","family":"He","sequence":"additional","affiliation":[]}],"member":"1965","published-online":{"date-parts":[[2025,1,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"360","DOI":"10.7150\/ijbs.66913","article-title":"Integrated machine learning and bioinformatic analyses constructed a novel stemness-related classifier to predict prognosis and immunotherapy responses for hepatocellular carcinoma patients","volume":"18","author":"Chen","year":"2022","journal-title":"Int. J. Biol. Sci"},{"key":"B2","doi-asserted-by":"publisher","first-page":"bbab378","DOI":"10.1093\/bib\/bbab378","article-title":"How much can deep learning improve prediction of the responses to drugs in cancer cell lines?","volume":"23","author":"Chen","year":"2022","journal-title":"Brief. Bioinf"},{"key":"B3","doi-asserted-by":"publisher","first-page":"235","DOI":"10.1038\/s43018-019-0018-6","article-title":"Discovering the anticancer potential of non-oncology drugs by systematic viability profiling","volume":"1","author":"Corsello","year":"2020","journal-title":"Nat. Cancer"},{"key":"B4","doi-asserted-by":"publisher","first-page":"104683","DOI":"10.1016\/j.phrs.2020.104683","article-title":"Tumor microenvironment: challenges and opportunities in targeting metastasis of triple negative breast cancer","volume":"153","author":"Deepak","year":"2020","journal-title":"Pharmacol. Res."},{"key":"B5","doi-asserted-by":"publisher","first-page":"103715","DOI":"10.1016\/j.drudis.2023.103715","article-title":"Machine-learning-based adverse drug event prediction from observational health data: a review","volume":"28","author":"Denck","year":"2023","journal-title":"Drug Discov. Today"},{"key":"B6","doi-asserted-by":"publisher","first-page":"2891","DOI":"10.1093\/bioinformatics\/btw344","article-title":"Evaluating the molecule-based prediction of clinical drug responses in cancer","volume":"32","author":"Ding","year":"2016","journal-title":"Bioinformatics"},{"key":"B7","doi-asserted-by":"publisher","first-page":"106537","DOI":"10.1016\/j.bioorg.2023.106537","article-title":"Ginsenoside Rh4 inhibits breast cancer growth through targeting histone deacetylase 2 to regulate immune microenvironment and apoptosis","volume":"135","author":"Dong","year":"2023","journal-title":"Bioorg. Chem"},{"key":"B8","doi-asserted-by":"publisher","first-page":"btad390","DOI":"10.1016\/j.gpb.2023.01.006","article-title":"Preclinical-to-clinical anti-cancer drug response prediction and biomarker identification using TINDL","volume":"39","author":"Earl Hostallero","year":"2023","journal-title":"Genom. Proteom. Bioinf."},{"key":"B9","doi-asserted-by":"publisher","first-page":"149","DOI":"10.2174\/18715206MTA1uNjQp3","article-title":"A review of of chemotherapy and photodynamic therapy for lung cancer treatment","volume":"21","author":"El-Hussein","year":"2021","journal-title":"Anticancer. Agents Med. Chem"},{"key":"B10","doi-asserted-by":"publisher","first-page":"3837","DOI":"10.7150\/ijbs.64077","article-title":"Immunotherapy in colorectal cancer: current achievements and future perspective","volume":"17","author":"Fan","year":"2021","journal-title":"Int. J. Biol. Sci"},{"key":"B11","doi-asserted-by":"publisher","first-page":"540","DOI":"10.1016\/j.jgg.2021.03.007","article-title":"Large-scale pharmacogenomic studies and drug response prediction for personalized cancer medicine","volume":"48","author":"Feng","year":"2021","journal-title":"J. Genet. Genom"},{"key":"B12","doi-asserted-by":"publisher","first-page":"1714","DOI":"10.1038\/s41467-022-29358-6","article-title":"A single-cell analysis of breast cancer cell lines to study tumour heterogeneity and drug response","volume":"13","author":"Gambardella","year":"2022","journal-title":"Nat. Commun"},{"key":"B13","doi-asserted-by":"publisher","first-page":"879","DOI":"10.1038\/s42256-022-00541-0","article-title":"A context-aware deconfounding autoencoder for robust prediction of personalized clinical drug response from cell-line compound screening","volume":"4","author":"He","year":"2022","journal-title":"Nat. Mach. Intell"},{"key":"B14","doi-asserted-by":"publisher","first-page":"497","DOI":"10.1016\/j.tibtech.2019.12.021","article-title":"Enabling technologies for personalized and precision medicine","volume":"38","author":"Ho","year":"2020","journal-title":"Trends Biotechnol"},{"key":"B15","doi-asserted-by":"publisher","first-page":"1069353","DOI":"10.3389\/frai.2023.1069353","article-title":"Development and evaluation of a java-based deep neural network method for drug response predictions","volume":"6","author":"Huang","year":"2023","journal-title":"Front. Artif. Intell"},{"key":"B16","doi-asserted-by":"publisher","first-page":"876100","DOI":"10.3389\/frai.2022.876100","article-title":"Application of artificial intelligence to plasma metabolomics profiles to predict response to neoadjuvant chemotherapy in triple-negative breast cancer","volume":"5","author":"Irajizad","year":"2022","journal-title":"Front Artif Intell"},{"key":"B17","doi-asserted-by":"publisher","first-page":"3858","DOI":"10.1021\/acs.jcim.1c00706","article-title":"HiDRA: hierarchical network for drug response prediction with attention","volume":"61","author":"Jin","year":"2021","journal-title":"J. Chem. Inf. Model"},{"key":"B18","doi-asserted-by":"publisher","first-page":"2784","DOI":"10.3390\/tomography8060232","article-title":"Deep learning prediction of pathologic complete response in breast cancer using MRI and other clinical data: a systematic review","volume":"8","author":"Khan","year":"2022","journal-title":"Tomography"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1227091","DOI":"10.3389\/frai.2023.1227091","article-title":"Artificial intelligence in clinical medicine: catalyzing a sustainable global healthcare paradigm","volume":"6","author":"Krishnan","year":"2023","journal-title":"Front. Artif. Intell"},{"key":"B20","doi-asserted-by":"publisher","first-page":"bbab460","DOI":"10.1093\/bib\/bbab460","article-title":"Machine learning meets omics: applications and perspectives","volume":"23","author":"Li","year":"2022","journal-title":"Brief. Bioinf"},{"key":"B21","doi-asserted-by":"publisher","first-page":"850","DOI":"10.1016\/j.gpb.2022.11.003","article-title":"Machine learning for lung cancer diagnosis, treatment, and prognosis","volume":"20","author":"Li","year":"2022","journal-title":"Genom. Proteom. Bioinf"},{"key":"B22","doi-asserted-by":"publisher","first-page":"759","DOI":"10.1016\/j.cels.2021.06.006","article-title":"Artificial intelligence for proteomics and biomarker discovery","volume":"12","author":"Mann","year":"2021","journal-title":"Cell Syst."},{"key":"B23","doi-asserted-by":"publisher","first-page":"1164808","DOI":"10.3389\/fonc.2023.1164808","article-title":"An era of personalized medicine in breast cancer: integrating artificial intelligence into practice","volume":"13","author":"Masood","year":"2023","journal-title":"Front. Oncol"},{"key":"B24","doi-asserted-by":"publisher","first-page":"730","DOI":"10.1124\/pharmrev.120.000206","article-title":"Sex- and gender-based pharmacological response to drugs","volume":"73","author":"Mauvais-Jarvis","year":"2021","journal-title":"Pharmacol. Rev"},{"key":"B25","doi-asserted-by":"publisher","first-page":"1171907","DOI":"10.3389\/fonc.2023.1171907","article-title":"Personalized immunotherapy for cancer","volume":"13","author":"Pasetto","year":"2023","journal-title":"Front. Oncol"},{"key":"B26","doi-asserted-by":"publisher","first-page":"404","DOI":"10.1097\/MOU.0000000000000882","article-title":"Artificial intelligence in bladder cancer prognosis: a pathway for personalized medicine","volume":"31","author":"Pinar","year":"2021","journal-title":"Curr. Opin. Urol"},{"key":"B27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.34133\/research.0050","article-title":"Trends and potential of machine learning and deep learning in drug study at single-cell level","volume":"6","author":"Qi","year":"2023","journal-title":"Research"},{"key":"B28","doi-asserted-by":"publisher","first-page":"4003","DOI":"10.1016\/j.csbj.2021.07.003","article-title":"Machine learning in the prediction of cancer therapy","volume":"19","author":"Rafique","year":"2021","journal-title":"Comput. Struct. Biotechnol. J"},{"key":"B29","doi-asserted-by":"publisher","first-page":"3650","DOI":"10.1016\/j.csbj.2021.06.026","article-title":"DDRS: detection of drug response SNPs specifically in patients receiving drug treatment","volume":"19","author":"Rong","year":"2021","journal-title":"Comput. Struct. Biotechnol. J"},{"key":"B30","doi-asserted-by":"publisher","first-page":"1353","DOI":"10.1158\/2159-8290.CD-20-1312","article-title":"Paradigms on Immunotherapy Combinations with Chemotherapy","volume":"11","author":"Salas-Benito","year":"2021","journal-title":"Cancer Discov"},{"key":"B31","doi-asserted-by":"publisher","first-page":"104258","DOI":"10.1016\/j.phrs.2019.104258","article-title":"Understanding and overcoming the resistance of cancer to PD-1\/PD-L1 blockade","volume":"145","author":"Shergold","year":"2019","journal-title":"Pharmacol. Res"},{"key":"B32","doi-asserted-by":"publisher","first-page":"e0082122","DOI":"10.1128\/aac.00821-22","article-title":"A Plasmodium falciparum RING finger E3 ubiquitin ligase modifies the roles of PfMDR1 and PfCRT in parasite drug responses","volume":"67","author":"Singh","year":"2023","journal-title":"Antimicrob. Agents Chemother"},{"key":"B33","doi-asserted-by":"publisher","first-page":"1427","DOI":"10.1002\/med.21764","article-title":"Artificial intelligence and machine learning-aided drug discovery in central nervous system diseases: State-of-the-arts and future directions","volume":"41","author":"Vatansever","year":"2021","journal-title":"Med. Res. Rev"},{"key":"B34","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/s10456-017-9562-9","article-title":"Tumor angiogenesis and vascular normalization: alternative therapeutic targets","volume":"20","author":"Viallard","year":"2017","journal-title":"Angiogenesis"},{"key":"B35","doi-asserted-by":"publisher","first-page":"14639","DOI":"10.1007\/s10489-022-03294-w","article-title":"A multi-view multi-omics model for cancer drug response prediction","volume":"52","author":"Wang","year":"2022","journal-title":"Appl. Intell"},{"key":"B36","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1186\/s12859-022-05080-4","article-title":"Drug response prediction using graph representation learning and Laplacian feature selection","volume":"23","author":"Xie","year":"2022","journal-title":"BMC Bioinf"},{"key":"B37","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1186\/s12916-020-01613-x","article-title":"The challenges of colposcopy for cervical cancer screening in LMICs and solutions by artificial intelligence","volume":"18","author":"Xue","year":"2020","journal-title":"BMC Med."},{"key":"B38","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.ymeth.2020.08.006","article-title":"Prediction of drug response in multilayer networks based on fusion of multiomics data","volume":"192","author":"Yu","year":"2021","journal-title":"Methods"},{"key":"B39","doi-asserted-by":"publisher","first-page":"104767","DOI":"10.1016\/j.isci.2022.104767","article-title":"Tissue-specific identification of multi-omics features for pan-cancer drug response prediction","volume":"25","author":"Zhao","year":"2022","journal-title":"Iscience"},{"key":"B40","doi-asserted-by":"publisher","first-page":"3760","DOI":"10.7150\/ijbs.61717","article-title":"Single-cell RNA sequencing reveals spatiotemporal heterogeneity and malignant progression in pancreatic neuroendocrine tumor","volume":"17","author":"Zhou","year":"2021","journal-title":"Int. J. Biol. Sci"},{"key":"B41","doi-asserted-by":"publisher","first-page":"214","DOI":"10.1186\/s12916-018-1215-3","article-title":"Pancreatic cancer: challenges and opportunities","volume":"16","author":"Zhu","year":"2018","journal-title":"BMC Med"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1444127\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,23]],"date-time":"2025-01-23T11:42:47Z","timestamp":1737632567000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2024.1444127\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1,8]]},"references-count":41,"alternative-id":["10.3389\/frai.2024.1444127"],"URL":"https:\/\/doi.org\/10.3389\/frai.2024.1444127","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1,8]]},"article-number":"1444127"}}