In the last decades three-dimensional (3D) in vitro cancer models have been proposed as a bridge between bidimensional (2D) cell cultures and in vivo animal models, the gold standards in the preclinical assessment of anticancer drug efficacy. 3D in vitro cancer models can be generated through a multitude of techniques, from both immortalized cancer cell lines and primary patient-derived tumor tissue. Among them, spheroids and organoids represent the most versatile and promising models, as they faithfully recapitulate the complexity and heterogeneity of human cancers. Although their recent applications include drug screening programs and personalized medicine, 3D in vitro cancer models have not yet been established as preclinical tools for studying anticancer drug efficacy and supporting preclinical-to-clinical translation, which remains mainly based on animal experimentation. In this review, we describe the state-of-the-art of 3D in vitro cancer models for the efficacy evaluation of anticancer agents, focusing on their potential contribution to replace, reduce and refine animal experimentations, highlighting their strength and weakness, and discussing possible perspectives to overcome current challenges.

Precision dosing, the tailoring of drug doses to optimize therapeutic benefits and minimize risks in each patient, is essential for drugs with a narrow therapeutic window and severe adverse effects. Adaptive dosing strategies extend the precision dosing concept to time‐varying treatments which require sequential dose adjustments based on evolving patient conditions. Reinforcement learning (RL) naturally fits this paradigm: it perfectly mimics the sequential decision‐making process where clinicians adapt dose administration based on patient response and evolution monitoring. This paper aims to investigate the potentiality of coupling RL with population PK/PD models to develop precision dosing algorithms, reviewing the most relevant works in the field. Case studies in which PK/PD models were integrated within RL algorithms as simulation engine to predict consequences of any dosing action have been considered and discussed. They mainly concern propofol‐induced anesthesia, anticoagulant therapy with warfarin and a variety of anticancer treatments differing for administered agents and/or monitored biomarkers. The resulted picture highlights a certain heterogeneity in terms of precision dosing approaches, applied methodologies, and degree of adherence to the clinical domain. In addition, a tutorial on how a precision dosing problem should be formulated in terms of the key elements composing the RL framework (i.e., system state, agent actions and reward function), and on how PK/PD models could enhance RL approaches is proposed for readers interested in delving in this field. Overall, the integration of PK/PD models into a RL‐framework holds great promise for precision dosing, but further investigations and advancements are still needed to address current limitations and extend the applicability of this methodology to drugs requiring adaptive dosing strategies.

Machine learning (ML) approaches are receiving increasing attention from pharmaceutical companies and regulatory agencies, given their ability to mine knowledge from available data. In drug discovery, for example, they are employed in quantitative structure–property relationship (QSPR) models to predict biological properties from the chemical structure of a drug molecule. In this paper, following the Second Solubility Challenge (SC-2), a QSPR model based on artificial neural networks (ANNs) was built to predict the intrinsic solubility (logS₀) of the 100-compound low-variance tight set and the 32-compound high-variance loose set provided by SC-2 as test datasets. First, a training dataset of 270 drug-like molecules with logS₀ value experimentally determined was gathered from the literature. Then, a standard three-layer feed-forward neural network was defined by using 10 ChemGPS physico-chemical descriptors as input features. The developed ANN showed adequate predictive performances on both of the SC-2 test datasets. Benefits and limitations of ML approaches have been highlighted and discussed, starting from this case-study. The main findings confirmed that ML approaches are an attractive and promising tool to predict logS₀; however, many aspects, such as data quality, molecular descriptor computation and selection, and assessment of applicability domain, are crucial but often neglected, and should be carefully considered to improve predictions based on ML.

Understanding the pharmacokinetics, safety and efficacy of candidate drugs is crucial for their success. One key aspect is the characterization of absorption, distribution, metabolism, excretion and toxicity (ADMET) properties, which require early assessment in the drug discovery and development process. This study aims to present an innovative approach for predicting ADMET properties using attention-based graph neural networks (GNNs). The model utilizes a graph-based representation of molecules directly derived from Simplified Molecular Input Line Entry System (SMILE) notation. Information is processed sequentially, from substructures to the whole molecule, employing a bottom-up approach. The developed GNN is tested and compared with existing approaches using six benchmark datasets and by encompassing regression (lipophilicity and aqueous solubility) and classification (CYP2C9, CYP2C19, CYP2D6 and CYP3A4 inhibition) tasks. Results show the effectiveness of our model, which bypasses the computationally expensive retrieval and selection of molecular descriptors. This approach provides a valuable tool for high-throughput screening, facilitating early assessment of ADMET properties and enhancing the likelihood of drug success in the development pipeline.

The integration of pharmacokinetic‐pharmacodynamic (PK‐PD) modeling and simulations with artificial intelligence/machine learning algorithms is one of the most attractive areas of the pharmacometric research. These hybrid techniques are currently under investigation to perform several tasks, among which precision dosing. In this scenario, this paper presents and evaluates a new framework embedding PK‐PD models into a reinforcement learning (RL) algorithm, Q‐learning (QL), to personalize pharmacological treatment. Each patient is represented with a set of PK‐PD parameters and has a personal QL agent which optimizes the individual treatment. In the training phase, leveraging PK‐PD simulations, the QL agent assesses different actions, defined consistently with the clinical knowledge to consider only plausible dose‐adjustments, in order to find the optimal rules. The proposed framework was evaluated to optimize the erdafitinib treatment in patients with metastatic urothelial carcinoma. This drug was approved by the US Food and Drug Administration (FDA) with a dose‐adaptive protocol based on monitoring the levels of serum phosphate, which represent a biomarker of both treatment efficacy and toxicity. To evaluate the flexibility of the methodology, a heterogeneous virtual population of 141 patients was generated using an erdafitinib population PK (PopPK)‐PD literature model. For each patient, treatment response was simulated by using both QL‐optimized protocol and the clinical one. QL agents outperform the approved dose‐adaptive rules, increasing more than 10% the efficacy and the safety of treatment at each end point. Results confirm the great potentialities of the integration of PopPK‐PD models and RL algorithms to optimize precision dosing tasks.

Health authorities carefully evaluate any change in the batch manufacturing process of a drug before and after regulatory approval. In the absence of an adequate in vitro–in vivo correlation (Level A IVIVC), an in vivo bioequivalence (BE) study is frequently required, increasing the cost and time of drug development. This study focused on developing a Level A IVIVC for progesterone vaginal rings (PVRs), a dosage form designed for the continuous delivery in vivo. The pharmacokinetics (PK) of four batches of rings charged with 125, 375, 750 and 1500 mg of progesterone and characterized by different in vitro release rates were evaluated in two clinical studies. In vivo serum concentrations and in vitro release profiles were used to develop a population IVIVC progesterone ring (P-ring) model through a direct differential-equation-based method and a nonlinear-mixed-effect approach. The in vivo release, ${\mathrm{R}}_{\mathrm{vivo}}\left(\mathrm{t}\right)$, was predicted from the in vitro profile through a nonlinear relationship. ${\mathrm{R}}_{\mathrm{vivo}}\left(\mathrm{t}\right)$ was used as the input of a compartmental PK model describing the in vivo serum concentration dynamics of progesterone. The proposed IVIVC P-ring model was able to correctly predict the in vivo concentration–time profiles of progesterone starting from the in vitro PVR release profiles. Its internal and external predictability was carefully evaluated considering the FDA acceptance criteria for IVIVC assessment of extended-release oral drugs. Obtained results justified the use of the in vitro release testing in lieu of clinical studies for the BE assessment of any new PVRs batches. Finally, the possible use of the developed population IVIVC model as a simulator of virtual BE trials was explored through a case study.