The Comparison of Machine Learning and Mechanistic In Vitro–In Vivo Extrapolation Models for the Prediction of Human Intrinsic Clearance

Accurate
prediction of human pharmacokinetics (PK) remains one
of the key objectives of drug metabolism and PK (DMPK) scientists
in drug discovery projects. This is typically performed by using in
vitro–in vivo extrapolation (IVIVE) based on mechanistic PK
models. In recent years, machine learning (ML), with its ability to
harness patterns from previous outcomes to predict future events,
has gained increased popularity in application to absorption, distribution,
metabolism, and excretion (ADME) sciences. This study compares the
performance of various ML and mechanistic models for the prediction
of human IV clearance for a large (645) set of diverse compounds with
literature human IV PK data, as well as measured relevant in vitro
end points. ML models were built using multiple approaches for the
descriptors: (1) calculated physical properties and structural descriptors
based on chemical structure alone (classical QSAR/QSPR); (2) in vitro
measured inputs only with no structure-based descriptors (ML IVIVE);
and (3) in silico ML IVIVE using in silico model predictions for the
in vitro inputs. For the mechanistic models, well-stirred and parallel-tube
liver models were considered with and without the use of empirical
scaling factors and with and without renal clearance. The best ML
model for the prediction of in vivo human intrinsic clearance (CLint) was an in vitro ML IVIVE model using only six in vitro
inputs with an average absolute fold error (AAFE) of 2.5. The best
mechanistic model used the parallel-tube liver model, with empirical
scaling factors resulting in an AAFE of 2.8. The corresponding mechanistic
model with full in silico inputs achieved an AAFE of 3.3. These relative
performances of the models were confirmed with the prediction of 16
Pfizer drug candidates that were not part of the original data set.
Results show that ML IVIVE models are comparable to or superior to
their best mechanistic counterparts. We also show that ML IVIVE models
can be used to derive insights into factors for the improvement of
mechanistic PK prediction.

精准预测人类药代动力学（pharmacokinetics, PK）仍是药物发现项目中，药物代谢与药代动力学（drug metabolism and PK, DMPK）科研人员的核心目标之一。当前此类预测通常依托基于机制性药代动力学模型的体外-体内外推（in vitro–in vivo extrapolation, IVIVE）方法开展。近年来，机器学习（machine learning, ML）凭借从既往数据中挖掘规律以预测未来事件的能力，在吸收、分布、代谢、排泄（absorption, distribution, metabolism, and excretion, ADME）研究领域的应用愈发广泛。本研究针对包含645种结构多样化合物的大型数据集，结合已发表的人类静脉给药PK数据与实测关键体外终点指标，对比了多种机器学习模型与机制性模型对人类静脉清除率的预测性能。研究针对描述符构建了三类机器学习模型：（1）仅基于化学结构计算得到的理化性质与结构描述符（经典定量构效关系/定量结构性质关系，QSAR/QSPR）；（2）仅采用体外实测输入值、无需基于结构的描述符的机器学习辅助体外-体内外推（ML IVIVE）；（3）采用虚拟模型预测的体外输入值构建的虚拟ML IVIVE模型。对于机制性模型，本研究考量了充分搅拌肝脏模型与平行管肝脏模型，分别搭配或不搭配经验缩放因子，同时纳入或不纳入肾清除率。用于预测人类体内内在清除率（intrinsic clearance, CLint）的最优机器学习模型为仅采用6项体外输入值的ML IVIVE模型，其平均绝对折叠误差（average absolute fold error, AAFE）为2.5。最优机制性模型采用平行管肝脏模型搭配经验缩放因子，AAFE为2.8；若采用全虚拟输入的对应机制性模型，AAFE则为3.3。上述模型的相对性能通过16个未纳入原始数据集的辉瑞（Pfizer）候选药物的预测结果得到了验证。研究结果表明，ML IVIVE模型的性能可与最优机制性模型媲美甚至更优。此外，本研究还证实，ML IVIVE模型可用于挖掘有助于优化机制性PK预测的关键影响因素。