Author Archives: Vera

While the cytochrome P450 enzymes have long been studied, there is a growing need to better understand the role of non-CYP enzymes in drug metabolism. To facilitate this, we developed MetaSite 7 to provide the prediction of drug metabolism using 23 non-CYP Phase I enzymes including eight families and their related isoforms. Twenty enzymes, including 12 different families, responsible for Phase II reactions were also considered.

The prediction determines the probability of a molecule to be a substrate for each enzyme by identifying reactive atoms in the molecule structure. In MetaSite 7, we used the enzyme’s 3D structure to identify reactive atoms of the molecule which may be exposed to the cofactor or active binding site of the enzyme. The GRID force field is used to calculate flexible interaction fields between the catalytic residues of the enzyme and the molecule.

Multiple docking poses are considered, and the energy contributions are summed. The poses are ranked, and the lowest energy pose is used to generate a [1,2,3]This prediction can be repeated for each of the enzymes in MetaSite 7, resulting in a more comprehensive view of the site of metabolism (SOM) for both Phase I and Phase II enzymes.

Furthermore, the predictions may be combined by subjecting the potential first-generation metabolites to further predictions, allowing for a more complete view of second-generation metabolites.

In conclusion, we utilized the 3D structures of the different CYP isoforms and 43 non-CYP enzymes to predict both Phase I and Phase II metabolism, along with the probability of a drug molecule to be a substrate for each enzyme. These predictions provide an increased understanding of the potential metabolic pathway in the human body.

Peptides represent a promising class of therapeutic agents due to their high target specificity, favorable safety profiles, and efficient tissue penetration. However, their clinical development remains limited by poor in vivo stability, rapid enzymatic degradation, and short plasma half-lives. Structural flexibility and high solvent accessibility further increase susceptibility to proteolysis, resulting in rapid clearance and reduced therapeutic efficacy. While chemical strategies such as cyclization and incorporation of non-natural amino acids can improve peptide stability, it remains challenging prior to synthesis to identify peptides that would benefit from such modifications based on metabolic stability and pharmacokinetic properties.

Here, we present a Graphormer-based machine learning framework for predicting key properties relevant to peptide metabolic stability, including proteolytic cleavage sites and peptide blood stability, as well as pharmacokinetic properties such as permeability. In addition, we demonstrate the ability of the approach to predict other peptide properties, including solvent accessibility, secondary structure, and post-translational modifications, which are included to assess the model’s capacity to capture structural information relevant for predicting metabolism- and pharmacokinetics-related properties.

The models employ transformer architecture with added mechanisms to encode graph structural information. Importantly, unlike most existing state-of-the-art tools, our approach is not restricted to natural amino acids and supports cyclic peptides. Depending on the target property, the Graphormer architecture was adapted for different downstream tasks, including binary or multiclass classification, ranking, and regression.

The Graphormer site of cleavage ranking model was evaluated under 28 datasets collected from MEROPS, which compiled experimentally verified cleavage sites from proteases involved in peptide-drug degradation. The site-of-cleavage ranking model was evaluated on 28 MEROPS datasets of experimentally verified protease cleavage sites involved in peptide-drug degradation, achieving an average MAP of 0.59 and Precision@1 of 0.47, outperforming ProsperousPlus.¹

The peptide blood stability model, trained on 635 peptides up to 50 amino acids including cyclic and modified peptides, achieved comparable performance to PepMSND², with accuracy 0.84, precision 0.85, recall 0.81, F1 score 0.81, and MCC 0.70.

For permeability, trained and tested on 6,888 cyclic peptides from the CycPeptMP database³, the model achieved R² = 0.77, MAE = 0.36, and MSE = 0.26, showing good generalization to structurally diverse peptides.

For solvent accessibility, formulated as buried versus exposed residues and validated on protein sequences up to 1,000 amino acids, the model achieved recall 0.81 and F1 score 0.78, comparable to existing methods.⁴

For secondary structure prediction evaluated using Jensen-Shannon distance across helix, strand, and coil states, the model achieved the lowest JSD for coil (0.207), outperforming all compared methods⁵, and improved over JPred4 and PSIPRED for helix and strand while narrowing the gap with PEP2D.

Finally, in predicting post-translational modifications across seven PTM types, the binary model outperformed state-of-the-art method⁶ for lysine acetylation, SUMOylation, ubiquitination, and arginine methylation, and achieved comparable performance for the remaining classes, demonstrating robustness across diverse biochemical modifications.