Biology subjects

Mey, A. S. J. S.

Publications and source records attributed to Mey, A. S. J. S..

7 recordsLinked to original sources

bioRxiv2026

GRASP: Graph Representation Learning with Assay Supervision for Molecular Properties

Molecular structures are abundant, while experimental bioactivity is sparse and distributed across assays. We introduce GRASP, a 93.5M-parameter graph Transformer that learns from these sources in sequence. GRASP first learns molecular structure through replaced-token detection on 1.54 billion ZINC20 molecule presentations, then adapts to sparse bioactivity across 642 ChEMBL assays. Across 23 cluster-held-out OpenADMET endpoints, GRASP achieves a mean MAE of 0.374, compared with 0.383 for CheMeleon, 0.408 for ECFP4-LightGBM, and 0.440 for Chemprop. ChEMBL adaptation reduces mean MAE from 0.407 to 0.374 and improves 21 of 23 endpoints, showing the value of intermediate bioactivity supervision. On 22 TDC ADMET tasks, GRASP gives a better point estimate than CheMeleon on 13 tasks. These results support staged molecular representation learning, where abundant molecular structure and sparse experimental measurements provide complementary supervision at different stages of training.

bioinformatics↗

bioRxiv2026

Tyrosine kinases sample unique activation ensembles

Protein kinase activation is driven by conformational changes across multiple structural components, including the conserved Asp-Phe-Gly (DFG) motif, but whether these transitions follow a universal mechanism remains unclear. Here we combine over 8.3 milliseconds of distributed unbiased molecular dynamics simulations with Markov state models (MSMs) to compare the conformational landscapes of the ABL1, EGFR and MET kinase domains. To maximize unbiased sampling of functionally relevant conformational space, we use a transfer seeding strategy that steers AlphaFold2 models derived from homologous templates to sample MET conformational states absent from available experimental databases. We find that related DFG-motif geometries separate into distinct kinetic networks. These shared structural states are connected by kinase-specific activation pathways with different regulatory elements controlling the slowest step of activation. Our findings reveal that the shared nomenclature masks distinct transition mechanisms between kinase domains, revealing new regions critical for activity and targetable conformations for inhibitor design.

biophysics↗

bioRxiv2024

Learning Binding Affinities via Fine-tuning of Protein and Ligand Language Models

Accurate in-silico prediction of protein-ligand binding affinity is essential for efficient hit identification in large molecular libraries. Commonly used structure-based methods such as docking often fail to rank compounds effectively, and free energy-based approaches, while accurate, are too computationally intensive for large-scale screening. Existing deep learning models struggle to generalize to new targets or drugs, and current evaluation methods often do not accurately reflect real-world performance. We introduce BALM, a deep learning framework that predicts binding affinity using pre-trained protein and ligand language models. We also propose improved evaluation strategies with diverse data sets and metrics to assess model performance to new targets better. Using the BindingDB dataset, BALM generalises unseen drugs, scaffolds, and targets. In few-shot scenarios for targets such as USP7 and Mpro, it outperforms traditional machine learning and docking methods, including AutoDock Vina. Adoption of our target-based evaluation methods will allow a more stringent evaluation of machine learning-based scoring tools. Our protein prediction framework shows good performance, is computationally efficient, and is highly adaptable within this evaluation setting, making it practical for early-stage drug discovery screening.

bioinformatics↗

bioRxiv2024

Comparison of Methodologies for Absolute Binding Free Energy Calculations of Ligands to Intrinsically Disordered Proteins

Modulating the function of Intrinsically Disordered Proteins (IDPs) with small molecules is of considerable importance given the crucial roles of IDPs in the patho-physiology of numerous diseases. Reported binding affinities for ligands to diverse IDPs vary broadly and little is known about the detailed molecular mechanisms that underpin ligand efficacy. Molecular simulations of IDP-ligand binding mechanisms can help us understand the mode of action of small molecule inhibitors of IDP function, but it is still unclear how binding energies can be modeled rigorously for such a flexible class of proteins. Here we compare alchemical absolute binding free energy calculation (ABFE) and Markov-State Modelling (MSM) protocols to model the binding of the small molecule 10058-F4 to a disordered peptide extracted from a segment of the oncoprotein c-Myc. The ABFE results produce binding energy estimates that are sensitive to the choice of reference structure. In contrast, the MSM results produce more reproducible binding energy estimates consistent with weak mM binding affinities and transient intermolecular contacts reported in the literature.

biophysics↗

bioRxiv2023

From Proteins to Ligands: Decoding Deep Learning Methods for Binding Affinity Prediction

Accurate in silico prediction of protein-ligand binding affinity is important in the early stages of drug discovery. Deep learning-based methods exist but have yet to overtake more conventional methods such as giga-docking largely due to their lack of generalisability. To improve generalizability we need to understand what these models learn from input protein and ligand data. We systematically investigated a sequence-based deep learning framework to assess the impact of protein and ligand encodings on predicting binding affinities for commonly used kinase data sets. The role of proteins is studied using convolutional neural network-based encodings obtained from sequences and graph neural network-based encodings enriched with structural information from contact maps. Ligand-based encodings are generated from graph-neural networks. We test different ligand perturbations by randomizing node and edge properties. For proteins we make use of 3 different protein contact generation methods (AlphaFold2, Pconsc4, and ESM-1b) and compare these with a random control. Our investigation shows that protein encodings do not substantially impact the binding predictions, with no statistically significant difference in binding affinity for KIBA in the investigated metrics (concordance index, Pearsons R Spearmans Rank, and RMSE). Significant differences are seen for ligand encodings with random ligands and random ligand node properties, suggesting a much bigger reliance on ligand data for the learning tasks. Using different ways to combine protein and ligand encodings, did not show a significant change in performance. TOC Graphic O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=111 SRC="FIGDIR/small/551483v1_ufig1.gif" ALT="Figure 1"> View larger version (25K): org.highwire.dtl.DTLVardef@117f37forg.highwire.dtl.DTLVardef@173427eorg.highwire.dtl.DTLVardef@126a39org.highwire.dtl.DTLVardef@fbcc6d_HPS_FORMAT_FIGEXP M_FIG C_FIG

bioinformatics↗

bioRxiv2018

Effect of automation on the accuracy of alchemical free energy calculation protocols

Hit-to-lead virtual screening frequently relies on a cascade of computational methods that starts with rapid calculations applied to a large number of compounds and ends with more expensive computations restricted to a subset of compounds that passed initial filters. This work focuses on set up protocols for alchemical free energy (AFE) scoring in the context of a Docking - MM/PBSA - AFE cascade. A dataset of 15 congeneric inhibitors of the ACK1 protein was used to evaluate the performance of AFE set up protocols that varied in the steps taken to prepare input files (using previously docked and best scored poses, manual selection of poses, manual placement of binding site water molecules). The main finding is that use of knowledge derived from X-ray structures to model binding modes, together with the manual placement of a bridging water molecule, improves the R2 from 0.45 {+/-} 0.06 to 0.76 {+/-} 0.02 and decreases the mean unsigned error from 2.11 {+/-} 0.08 to 1.24 {+/-} 0.04 kcal mol-1. By contrast a brute force automated protocol that increased the sampling time ten-fold lead to little improvements in accuracy. Besides, it is shown that for the present dataset hysteresis can be used to flag poses that need further attention even without prior knowledge of experimental binding affinities.

molecular biology↗

bioRxiv2017

Impact of domain knowledge on blinded predictions of binding energies by alchemical free energy calculations

The drug design data resource (D3R) consortium organises blinded challenges to address the latest advances in computational methods for ligand pose prediction, affinity ranking, and free energy calculations. Within the context of the second D3R Grand Challenge several blinded binding free energies predictions were made for two congeneric series of FXR inhibitors with a semi-automated alchemical free energy calculations workflow featuring the FESetup and SOMD tools. Reasonable performance was observed in retrospective analyses of literature datasets. Nevertheless blinded predictions on the full D3R datasets were poor due to difficulties encountered with the ranking of compounds that vary in their net-charge. Performance increased for predictions that were restricted to subsets of compounds carrying the same net-charge. Disclosure of X-ray crystallography derived binding modes maintained or improved the correlation with experiment in a subsequent rounds of predictions. The best performing protocols on D3R set1 and set2 were comparable or superior to predictions made on the basis of analysis of literature SARs only, and comparable or slightly inferior, to the best submissions from other groups.

biophysics↗