CYPstrate: A Set of Machine Learning Models for the Accurate Classification of Cytochrome P450 Enzyme Substrates and Non-Substrates

Another string to your bow: machine learning prediction of the pharmacokinetic properties of small molecules

INTRODUCTION

Prediction of pharmacokinetic (PK) properties is crucial for drug discovery and development. Machine-learning (ML) models, which use statistical pattern recognition to learn correlations between input features (such as chemical structures) and target variables (such as PK parameters), are being increasingly used for this purpose. To embed ML models for PK prediction into workflows and to guide future development, a solid understanding of their applicability, advantages, limitations, and synergies with other approaches is necessary.

AREAS COVERED

This narrative review discusses the design and application of ML models to predict PK parameters of small molecules, especially in light of established approaches including in vitro-in vivo extrapolation (IVIVE) and physiologically based pharmacokinetic (PBPK) models. The authors illustrate scenarios in which the three approaches are used and emphasize how they enhance and complement each other. In particular, they highlight achievements, the state of the art and potentials of applying machine learning for PK prediction through a comphrehensive literature review.

EXPERT OPINION

ML models, when carefully crafted, regularly updated, and appropriately used, empower users to prioritize molecules with favorable PK properties. Informed practitioners can leverage these models to improve the efficiency of drug discovery and development process.

DeepP450: Predicting Human P450 Activities of Small Molecules by Integrating Pretrained Protein Language Model and Molecular Representation

Cytochrome P450 enzymes (CYPs) play a crucial role in Phase I drug metabolism in the human body, and CYP activity toward compounds can significantly affect druggability, making early prediction of CYP activity and substrate identification essential for therapeutic development. Here, we established a deep learning model for assessing potential CYP substrates, DeepP450, by fine-tuning protein and molecule pretrained models through feature integration with cross-attention and self-attention layers. This model exhibited high prediction accuracy (0.92) on the test set, with area under the receiver operating characteristic curve (AUROC) values ranging from 0.89 to 0.98 in substrate/nonsubstrate predictions across the nine major human CYPs, surpassing current benchmarks for CYP activity prediction. Notably, DeepP450 uses only one model to predict substrates/nonsubstrates for any of the nine CYPs and exhibits certain generalizability on novel compounds and different categories of human CYPs, which could greatly facilitate early stage drug design by avoiding CYP-reactive compounds.

In vitro metabolism of the emerging contaminant 6PPD-quinone in human and rat liver microsomes: Kinetics, pathways, and mechanism

N-(1,3-dimethylbutyl)-N'-phenyl-p-phenylenediamine-quinone (6PPD-Q) is an ozonation product of the rubber antioxidant N-(1,3-dimethylbutyl)-N'-phenyl-p-phenylenediamine (6PPD). 6PPD-Q has recently been detected in various environmental media, which may enter the human body via inhalation and skin contact pathways. However, the human metabolism of 6PPD-Q has remained unknown. This study investigated the in vitro Cytochrome P450-mediated metabolism of 6PPD-Q in human and rat liver microsomes (HLMs and RLMs). 6PPD-Q was significantly metabolized at lower concentrations but slowed at high concentrations. The intrinsic clearance (CLint) of 6PPD-Q was 21.10 and 18.58 μL min-1 mg-1 protein of HLMs and RLMs, respectively, suggesting low metabolic ability compared with other reported pollutants. Seven metabolites and one intermediate were identified, and metabolites were predicted immunotoxic or mutagenic toxicity. Mono- and di-oxygenation reactions were the main phase I in vitro metabolic pathways. Enzyme inhibition experiments and molecular docking techniques were further used to reveal the metabolic mechanism. CYP1A2, 3A4, and 2C19, especially CYP1A2, play critical roles in 6PPD-Q metabolism in HLMs, whereas 6PPD-Q is extensively metabolized in RLMs. Our study is the first to demonstrate the in vitro metabolic profile of 6PPD-Q in HLMs and RLMs. The results will significantly contribute to future human health management targeting the emerging pollutant 6PPD-Q.

Machine Learning Models to Predict Cytochrome P450 2B6 Inhibitors and Substrates

Cytochrome P450 2B6 (CYP2B6) is responsible for the metabolism of ∼7% of marketed drugs. The in vitro drug interaction studies guidance for industry issued by the FDA stipulates that drug sponsors need to evaluate whether the investigated drugs interact with the major drug-metabolizing P450s including CYP2B6. Therefore, there has been greater attention to the development of predictive models for CYP2B6 inhibitors and substrates. In this study, conventional machine learning and deep learning models were developed to predict CYP2B6 inhibitors and substrates. Our results showed that the best CYP2B6 inhibitor model yielded the AUC values of 0.95 and 0.75 with the 10-fold cross-validation and the test set, respectively, and the best CYP2B6 substrate model produced the AUC values of 0.93 and 0.90 with the 10-fold cross-validation and the test set, respectively. The generalization ability of the CYP2B6 inhibitor and substrate models was assessed by using the external validation sets. Several significant substructural fragments relevant to CYP2B6 inhibitors and substrates were detected via frequency substructure analysis and information gain. In addition, the applicability domain of the models was defined by employing a nonparametric method based on the probability density distribution. We anticipate that our results would be useful for the prediction of potential CYP2B6 inhibitors and substrates in the early stage of drug discovery.

Green alga Chlamydomonas reinhardtii can effectively remove diclofenac from the water environment - A new perspective on biotransformation

The use of unicellular algae to remove xenobiotics (including drugs) from wastewaters is one of the rapidly developing areas of environmental protection. Numerous data indicate that for efficient phycoremediation three processes are important, i.e. biosorption, bioaccumulation, and biotransformation. Although biosorption and bioaccumulation do not raise any serious doubts, biotransformation is more problematic since its products can be potentially more toxic than the parent compounds posing a threat to organisms living in a given environment, including organisms that made this transformation. Thus, two questions need to be answered before the proper algae strain is chosen for phycoremediation, namely what metabolites are produced during biotransformation, and how resistant is the analyzed strain to a mixture of parent compound and metabolites that appear over the course of culture? In this work, we evaluated the remediation potential of the model green alga Chlamydomonas reinhardtii in relation to non-steroidal anti-inflammatory drugs (NSAIDs), as exemplified by diclofenac. To achieve this, we analysed the susceptibility of C. reinhardtii to diclofenac as well as its capability to biosorption, bioaccumulation, and biotransformation of the drug. We have found that even at a relatively high concentration of diclofenac the algae maintained their vitality and were able to remove (37.7%) DCF from the environment. A wide range of phase I and II metabolites of diclofenac (38 transformation products) was discovered, with many of them characteristic rather for animal and bacterial biochemical pathways than for plant metabolism. Due to such a large number of detected products, 18 of which were not previously reported, the proposed scheme of diclofenac transformation by C. reinhardtii not only significantly contributes to broadening the knowledge in this field, but also allows to suggest possible pathways of degradation of xenobiotics with a similar structure. It is worth pointing out that a decrease in the level of diclofenac in the media observed in this study cannot be fully explained by biotransformation (8.4%). The mass balance analysis indicates that other processes (total 22%), such as biosorption, a non-extractable residue formation, or complete decomposition in metabolic cycles can be involved in the diclofenac disappearance, and those findings open the prospects of further research.

Machine Learning in Drug Metabolism Study

Metabolic reactions in the body transform the administered drug into metabolites. These metabolites exhibit diverse biological activities. Drug metabolism is the major underlying cause of drug overdose-related toxicity, adversative drug effects and the drug's reduced efficacy. Though metabolic reactions deactivate a drug, drug metabolites are often considered pivotal agents for off-target effects or toxicity. On the other side, in combination drug therapy, one drug may influence another drug's metabolism and clearance and is thus considered one of the primary causes of drug-drug interactions. Today with the advancement of machine learning, the metabolic fate of a drug candidate can be comprehensively studied throughout the drug development procedure. Naïve Bayes, Logistic Regression, k-Nearest Neighbours, Decision Trees, different Boosting and Ensemble methods, Support Vector Machines and Artificial Neural Network boosted Deep Learning are some machine learning algorithms which are being extensively used in such studies. Such tools are covering several attributes of drug metabolism, with an emphasis on the prediction of drug-drug interactions, drug-target-interactions, clinical drug responses, metabolite predictions, sites of metabolism, etc. These reports are crucial for evaluating metabolic stability and predicting prospective drug-drug interactions, and can help pharmaceutical companies accelerate the drug development process in a less resource-demanding manner than what in vitro studies offer. It could also help medical practitioners to use combinatorial drug therapy in a more resourceful manner. Also, with the help of the enormous growth of deep learning, traditional fields of computational drug development like molecular interaction fields, molecular docking, quantitative structure-to-activity relationship (QSAR) studies and quantum mechanical simulations are producing results which were unimaginable couple of years back. This review provides a glimpse of a few contextually relevant machine learning algorithms and then focuses on their outcomes in different studies.

Considerations for Improving Metabolism Predictions for In Vitro to In Vivo Extrapolation

High-throughput (HT) in vitro to in vivo extrapolation (IVIVE) is an integral component in new approach method (NAM)-based risk assessment paradigms, for rapidly translating in vitro toxicity assay results into the context of in vivo exposure. When coupled with rapid exposure predictions, HT-IVIVE supports the use of HT in vitro assays for risk-based chemical prioritization. However, the reliability of prioritization based on HT bioactivity data and HT-IVIVE can be limited as the domain of applicability of current HT-IVIVE is generally restricted to intrinsic clearance measured primarily in pharmaceutical compounds. Further, current approaches only consider parent chemical toxicity. These limitations occur because current state-of-the-art HT prediction tools for clearance and metabolite kinetics do not provide reliable data to support HT-IVIVE. This paper discusses current challenges in implementation of IVIVE for prioritization and risk assessment and recommends a path forward for addressing the most pressing needs and expanding the utility of IVIVE.