Roman Stratiichuk

In this work we performed a critical assessment of the benchmarking procedures used in Therapeutics Data Commons (TDC) ADMET leaderboards, focusing on reproducibility, robustness against data leakage, and signs of test-set overfitting across all 22 TDC ADMET endpoints. For each endpoint, the top 3 leaderboard models were screened with a unified protocol: execution environment reproducibility check, data leakage assessment, verification of hyperparameter optimisation practices, and final re-evaluation of results and TDC ranking. Only 3 methods (CaliciBoost, MapLight, MapLight+GNN) passed all checks and showed overall reproducible performance, whereas most of top-ranked models exhibited unavailable code, non-reproducible execution environments, runtime incompatibilities, or various methodological flaws. In particular, we identified direct or indirect data leakages in MiniMol, GradientBoost and XGBoost models. We also used our in-house models based on the Mol2Vec architecture to investigate the consequences of deliberately overfitting on the TDC test set. It is shown that deliberate or accidental tuning on the public test set may lead to significant inflation of the model metrics and leaderboard position. Our results emphasize the urgent need for better public ADMET benchmarks with the hidden test sets, strict dataset versioning and model submission with standardized inference environments.

Background. Canonical transient receptor potential channel 4 (TRPC4) in intestinal smooth muscle is activated via interaction with M2/M3 muscarinic receptors and activated by these receptors G-proteins and represents an important component of calcium signaling. Blockade of these channels by highly potent inhibitors such as Pico145 is of considerable interest for the development of new pharmacological approaches. The aim of this study was to investigate the effect of Pico145 on muscarinic receptor–induced cation current (mICAT) in mouse ileal smooth muscle cells and to elucidate the molecular mechanism of Pico145 binding to the TRPC4 channel. Methods. Electrophysiological experiments were performed using the patch-clamp technique on isolated smooth muscle cells from mouse ileum. Molecular modeling was conducted by docking Pico145 into the cryo-EM structure of TRPC4 (PDB: 5Z96) following validation on the reference TRPC1/TRPC4:Pico145 complex (PDB: 8WPM). Binding energies and spatial correspondence of the ligand pose relative to the experimentally determined Pico145 position in the TRPC1/TRPC4 channel were evaluated. Results. Pico145 was shown to markedly suppress the amplitude of mICAT in intestinal smooth muscle cells. et a concentration of 100 pM, the inhibitor reduced the current by more than 80 % (p < 0.05) compared with control, consistent with the established contribution of TRPC4 to the generation of mICAT. Molecular docking confirmed that Pico145 binds within a conserved intersubunit hydrophobic pocket of the TRPC4 transmembrane domain, which corresponds to the binding site previously identified in the structurally related TRPC5 protein. The modeled conformation of Pico145 almost completely reproduces the experimentally determined ligand pose in the TRPC4 channel. Minor differences in the amino acid composition of the pocket (Thr599 in mouse TRPC4 versus Val624 in human TRPC4) do not affect the binding mode, confirming the conserved nature of the inhibition mechanism. Conclusions. Pico145 effectively blocks receptor-operated TRPC4 channels in smooth muscle, leading to a pronounced inhibition of mICAT. Molecular modeling revealed that Pico145 binds to a conserved intramembrane site in the TRPC4 channel that coincides with the binding site in structurally related TRPC1/4/5 channels. These results support the common inhibitory mechanism of the TRPC4 by Pico145 and may facilitate the rational design of new selective TRPC channel blockers.

Rigid docking remains the most popular method of predicting protein-protein interactions in cases when experimental 3D structures of the complexes are not available. The docking often relies on known unbound (Apo) protein structures, which may differ significantly from their bound (Holo) forms. Modern machine learning (ML) based conformational sampling techniques allow generating ensembles of functionally relevant protein structures, which may be closer to their Holo forms and thus could improve the outcomes of the classical rigid protein-protein docking. Here, we sampled conformations of the protein subunits in 30 complexes from the novel PINDER data set with two state-of-the-art ML-based techniques and evaluated their docking performance using several physics-based, data-based, and ML-based scoring functions. We showed that such conformational sampling rarely produces structures that are closer to the Holo conformations than the corresponding Apo ones. Moreover, even when such conformations are generated, none of the tested scoring functions were able to prioritize and rank them correctly. Our work highlights critical limitations in the current ML-enhanced rigid protein-protein docking workflows and emphasizes the need for new approaches that can better utilize the potential of modern techniques for conformational generation and scoring.

Motivation: Accurately identifying and prioritizing protein binding pockets is a foundational element of small-molecule drug discovery. Defining these known pockets currently relies on a laborious manual process of extracting key residue data from selected publications, reconciling inconsistent terminology, and independently computing volumetric representations. This manual curation to ensure biological relevance is time-consuming, error-prone, and represents a major bottleneck for efficient, high-throughput drug discovery. Results: We present a novel approach for the identification and prioritization of protein binding pockets for small molecules by combining geometric pocket detection with large language models (LLMs). Our method leverages Fpocket to generate candidate pockets, which are then validated against published experimental data extracted from research articles using LLM with a series of prompts fine-tuned to identify and extract residue-level information associated with experimentally confirmed binding sites. We developed a curated benchmark dataset of diverse proteins and associated literature to train and evaluate the LLM’s performance in paper relevance assessment and pocket extraction. Availability and implementation: The developed benchmark dataset and methodology are freely available at the GitHub repository (https://github.com/receptor-ai/LLM-benchmark-dataset) and Zenodo (DOI: 10.5281/zenodo.15798647).

The accurate prediction of ADMET (Absorption, Distribution, Metabolism, Excretion, and Toxicity) properties is crucial for early-stage drug development, enabling the reduction of late-stage attrition and guiding compound prioritization. In recent years, machine learning models have emerged as powerful tools for ADMET prediction, leveraging diverse molecular representations ranging from handcrafted descriptors to graph neural networks and language model embeddings. Despite these advances, balancing predictive performance with computational efficiency remains a key challenge, particularly for high-throughput screening scenarios. Among unsupervised embedding methods, Mol2Vec has shown promise by capturing chemical substructure context analogously to word embeddings in natural language processing. However, its performance on comprehensive ADMET benchmarks has not been systematically assessed. In this work, we reimplement Mol2Vec with an expanded training corpus and higher embedding dimensionality, and evaluate its utility across 16 ADMET prediction tasks from the Therapeutics Data Commons (TDC). We show that while Mol2Vec embeddings alone are competitive, combining them with classical molecular descriptors and applying feature selection significantly improves performance. Our final MLP models with enhanced Mol2Vec embeddings achieved top-1 results in 10 of 16 benchmarks, outperforming all previously reported models on the TDC leaderboard in this regard, demonstrating that descriptor-enriched representations, paired even with relatively simple MLPs, can rival or exceed the performance of more complex models.

Rigid docking remains the most popular method of predicting protein-protein interactions in cases when experimental 3D structures of the complexes are not available. The docking often relies on known unbound (Apo) protein structures, which may differ significantly from their bound (Holo) forms. Modern machine learning (ML) based conformational sampling techniques allow generating ensembles of functionally relevant protein structures, which may be closer to their Holo forms and thus could improve the outcomes of the classical rigid protein-protein docking. Here, we sampled conformations of the protein subunits in 30 complexes from the novel PINDER dataset with two state-of-the-art ML-based techniques and evaluated their docking performance using several physics-based, data-based, and ML-based scoring functions. We showed that such conformational sampling rarely produces structures that are closer to the Holo conformations than the corresponding Apo ones. Moreover, even when such conformations are generated, none of the tested scoring functions were able to prioritize and rank them correctly. Our work highlights critical limitations in the current ML-enhanced rigid protein-protein docking workflows and emphasizes the need for new approaches that can better utilize the potential of modern techniques for conformational generation and scoring.

We present a novel approach for the identification and prioritization of protein binding pockets for small molecules by combining geometric pocket detection with Large Language Models (LLMs). Our method leverages Fpocket to generate candidate pockets, which are then validated against published experimental data extracted from research articles using LLM with a series of prompts fine-tuned to identify and extract residue-level information associated with experimentally confirmed binding sites. We developed a curated benchmark dataset of diverse proteins and associated literature to train and evaluate the LLM’s performance in paper relevance assessment and pocket extraction. The extracted information is then mapped onto protein structures and used to filter and merge the geometry-based predictions, generating a refined volumetric representation of biologically relevant pockets. This hybrid pipeline offers an efficient, accurate and automated method for identifying functional binding pockets, addressing a significant bottleneck in the high-throughput drug discovery workflows. The developed benchmark dataset and methodology are freely available at https://github.com/MelnychenkoM/LLM-benchmark-dataset .

Classical protein-ligand docking has been a cornerstone technique in computational drug discovery for decades, but has reached an accuracy and performance plateau. Recently introduced Machine Learning (ML) based docking methods offer a promising paradigm shift, but their practical adoption is hampered by accuracy-to-speed trade-offs, inadequate benchmarking standards, and questionable chemical validity of predicted poses. In this study, we introduce ArtiDock - an ML-based docking technique optimized for high-throughput virtual screening applications. To evaluate ArtiDock, we developed a dedicated performance and accuracy benchmark for pocket-specific rigid protein-ligand docking, which mimics realistic industrial drug discovery scenarios and is based on the novel PLINDER dataset. We demonstrate that ArtiDock is 29-38% more accurate in comparison to leading open-source and commercial classical docking techniques such as AutoDock, Vina, and Glide, while providing a low computational cost. ArtiDock notably excels in challenging docking scenarios involving unbound protein structures and binding sites containing ions and structured water molecules. Our results show that ArtiDock could be considered as a method of choice in high-throughput virtual screening scenarios.