Table 1_Developing and validating a drug recommendation system based on tumor microenvironment and drug fingerprint.xlsx

IntroductionTumor 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.
MethodsA 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 IC50 values for 542 tumor cell lines across 18 drugs.
ResultsThe model exhibited high predictive accuracy, with correlation coefficients (R) of 0.914 in the training set and 0.902 in the test set. Predictions for cytotoxic drugs, including Docetaxel (R = 0.72) and Cisplatin (R = 0.71), were particularly robust, whereas predictions for targeted therapies were less accurate (R < 0.3). Validation with CCLE (MFI as the endpoint) showed strong correlations (R = 0.67). Application to TCGA data successfully predicted clinical outcomes, including a significant association with 6-month progression-free survival (PFS, P = 0.007, AUC = 0.793).
DiscussionThe model demonstrates strong performance across preclinical datasets, showing its potential for real-world application in personalized cancer therapy. By bridging preclinical IC50 and clinical BOR endpoints, this approach provides a promising tool for optimizing patient-specific treatments.

引言
肿瘤异质性显著增加了遴选有效癌症治疗方案的难度，因不同患者对药物的响应差异悬殊。个性化癌症治疗已成为提升治疗有效性与精准性的极具前景的策略。本研究旨在开发一款基于基因组特征的个性化药物推荐模型，以优化治疗结局。

方法
本研究采用基于内容的过滤算法预测药物敏感性。患者特征以肿瘤微环境（tumor microenvironment, TME）进行表征，药物特征则通过药物指纹（drug fingerprints）进行描述。模型以癌症药物敏感性基因组学（Genomics of Drug Sensitivity in Cancer, GDSC）数据库进行训练与验证，随后利用癌症细胞系百科全书（Cancer Cell Line Encyclopedia, CCLE）数据集开展独立验证。本研究采用癌症基因组图谱（The Cancer Genome Atlas, TCGA）数据集评估模型的临床应用价值，以最佳总体疗效（Best Overall Response, BOR）作为临床疗效评价指标。此外，本研究构建了两个多层感知机（multilayer perceptron, MLP）模型，用于预测18种药物对542株肿瘤细胞系的半数抑制浓度（IC50）值。

结果
本模型展现出较高的预测精度，训练集与测试集的相关系数（R）分别为0.914与0.902。包括多西他赛（Docetaxel，R=0.72）和顺铂（Cisplatin，R=0.71）在内的细胞毒性药物预测结果尤为稳健，而靶向治疗药物的预测精度相对偏低（R<0.3）。利用CCLE数据集（以平均荧光强度（Mean Fluorescence Intensity, MFI）作为终点指标）进行验证时，模型展现出较强的相关性（R=0.67）。将模型应用于TCGA数据可成功预测临床结局，其中与6个月无进展生存期（progression-free survival, PFS）存在显著关联（P=0.007，曲线下面积AUC=0.793）。

讨论
本模型在多个临床前数据集中均展现出优异性能，表明其在个性化癌症治疗的实际临床应用中具有潜力。该方法通过衔接临床前IC50与临床BOR两类终点指标，为优化患者个体化治疗方案提供了极具前景的工具。