In vitro systems that accurately model in vivo conditions in the gastrointestinal tract may aid the development of oral drugs with greater bioavailability. Here we show that the interaction profiles between drugs and intestinal drug transporters can be obtained by modulating transporter expression in intact porcine tissue explants via the ultrasound-mediated delivery of small interfering RNAs and that the interaction profiles can be classified via a random forest model trained on the drug–transporter relationships. For 24 drugs with well-characterized drug–transporter interactions, the model achieved 100% concordance. For 28 clinical drugs and 22 investigational drugs, the model identified 58 unknown drug–transporter interactions, 7 of which (out of 8 tested) corresponded to drug-pharmacokinetic measurements in mice. We also validated the model’s predictions for interactions between doxycycline and four drugs (warfarin, tacrolimus, digoxin and levetiracetam) through an ex vivo perfusion assay and the analysis of pharmacologic data from patients. Screening drugs for their interactions with the intestinal transportome via tissue explants and machine learning may help to expedite drug development and the evaluation of drug safety.

准确模拟胃肠道体内条件的体外系统可能有助于开发具有更高生物利用度的口服药物。在这里，我们表明，药物和肠道药物转运蛋白之间的相互作用谱可以通过超声介导的小干扰 RNA 的递送来调节完整猪组织外植体中转运蛋白的表达来获得，并且可以通过训练的随机森林模型对相互作用谱进行分类药物-转运体关系。对于 24 种具有明确药物-转运蛋白相互作用特征的药物，该模型实现了 100% 的一致性。对于 28 种临床药物和 22 种研究药物，该模型确定了 58 种未知的药物-转运蛋白相互作用，其中 7 种（测试的 8 种）对应于小鼠的药物药代动力学测量。我们还通过离体灌注测定和患者药理学数据分析，验证了模型对多西环素与四种药物（华法林、他克莫司、地高辛和左乙拉西坦）之间相互作用的预测。通过组织外植体和机器学习筛选药物与肠道转运体的相互作用可能有助于加快药物开发和药物安全性评估。