The heterogeneity of the Caco-2 cell line and differences in experimental protocols for permeability assessment using this cell-based method have resulted in the high variability of Caco-2 permeability measurements. These problems have limited the generation of large datasets to develop accurate and applicable regression models. This study presents a QSPR approach developed on the KNIME analytical platform and based on a structurally diverse dataset of over 4900 molecules. Interpretable models were obtained using random forest supervised recursive algorithms for data cleaning and feature selection. The development of a conditional consensus model based on regional and global regression random forest produced models with RMSE values between 0.43–0.51 for all validation sets. The potential applicability of the model as a surrogate for the in vitro Caco-2 assay was demonstrated through blind prediction of 32 drugs recommended by the International Council for the Harmonization of Technical Requirements for Pharmaceuticals (ICH) for validation of in vitro permeability methods. The model was validated for the preliminary estimation of the BCS/BDDCS class. The KNIME workflow developed to automate new drug prediction is freely available. The results suggest that this automated prediction platform is a reliable tool for identifying the most promising compounds with high intestinal permeability during the early stages of drug discovery.

Background/Objectives: The rapid expansion of New Approach Methodologies (NAMs) is transforming oral biopharmaceutics by offering mechanistically rich, human-relevant tools that can reduce reliance on animal testing while improving translational confidence. Regulatory agencies, including the Food and Drug Administration (FDA) and the European Medicines Agency (EMA), are increasingly open to NAM-generated evidence, provided that methods are fit-for-purpose and scientifically justified. This review synthesizes current advances and evaluates how NAMs can be integrated across drug-development stages to enhance the prediction of oral absorption, formulation performance, and regulatory decision-making. Methods: A comprehensive literature review was conducted across classical and emerging methodologies, including in vitro permeability and solubility models, organoids, organ-on-a-chip (OoC) systems, machine learning frameworks, and mechanistic approaches such as the physiologically based pharmacokinetic (PBPK) and biopharmaceutics (PBBM) models. Emphasis was placed on physiological relevance, predictive performance, validation status, and regulatory applicability. Results: Classical tools remain essential for the Biopharmaceutics Classification System (BCS)-based biowaivers and risk-based assessments, yet they often lack physiological fidelity. NAMs provide enhanced representation of intestinal architecture, hydrodynamics, transporter activity, and metabolism. Organoids and microphysiological systems generate high-quality permeability and metabolic data, while computational NAMs enable scalable prediction of ADME properties and formulation behavior. When integrated into PBPK/PBBM models, these methods have great potential in predicting in vivo performance in humans. Evidence demonstrates that NAMs can refine, reduce, and, in specific contexts, replace animal studies without compromising scientific rigor. Conclusions: NAMs complement, rather than displace, classical biopharmaceutic tools, enabling a more mechanistic, human-centered, and ethically responsible framework for drug development. Their effective implementation will depend on continued validation, standardization, and regulatory harmonization as the field transitions toward fully NAM-supported biopharmaceutical assessment.