This work proposes a method to compute accurate kinetics for general ligand-unbinding problems at modest computational expense and minimal fine tuning, building on the AIMMD path sampling framework and opting for modelling the committor with a single descriptor-free, equivariant graph neural network shared across all systems.
Abstract
The kinetics of protein-ligand binding systems are increasingly recognized as a key determinant of drug efficacy, yet remain far harder to compute than binding affinities. Existing kinetics methods either bias the dynamics along a collective variable (CV), demanding careful system-specific CV design, or use path sampling, which keeps the dynamics unbiased but can struggle to converge rates out of deep free-energy wells and often relies on hand-engineered descriptors. By combining the `best of both worlds', we propose a method to compute accurate kinetics for general ligand-unbinding problems at modest computational expense and minimal fine tuning, building on the AI for Molecular Mechanism Discovery (AIMMD) path sampling framework. To avoid the need for feature engineering, we opt for modelling the committor with a single descriptor-free, equivariant graph neural network shared across all systems. We also partially flatten deep bound-state wells with a static, basin-restricted bias potential. This improves convergence by lifting the path sampling state boundary out of regions, where the committor is hard to learn, while leaving the reactive region strictly unbiased. Across host-guest and protein-ligand systems spanning roughly 17 orders of magnitude in residence time, the method robustly recovers rates in line with reference and experimental values. Simultaneously, and without further sampling, it also reconstructs the underlying unbinding mechanisms. We additionally find that accurate rates do not require globally accurate committor models, allowing for efficient kinetics estimation even in a low-data training regime. Requiring little system-specific setup, our approach offers an efficient and broadly generalizable route to binding kinetics, and its shared committor architecture lays crucial groundwork for probing structure-kinetics relationships across ligand series in drug discovery.
This study presents a method to derive optimized CV from transition state region (TS) via an interpretable machine learning (ML) model, Elastic Net, which greatly accelerate ligand binding-unbinding transitions and achieves rapid free energy surface (FES) convergence across diverse systems.
The resulting model, HydrAffinity, is an interaction-free, dynamic sparse model that uses pre-trained encoders and MoE for parameter-efficient learning and outperforms all interaction-free methods and matches state-of-the-art interaction-based methods on CASF-2016.
A category-stratified, statistically powered benchmark comparing pose prediction from receptor conformational ensembles against AlphaFold2, used as a matched static-structure baseline, across 29 protein–ligand systems spanning cryptic-pocket, induced-fit, water-mediated, and autoimmune-indication target classes is presented.
Ryan Varghese, Pooja Tiwary, Krishil Oswal· bioRxiv· 0 citations
Cryptic binding sites (CBSs) are crucial functional sites that become accessible following conformational changes by ligand binding. They play a significant role in expanding the scope of druggable targets and revealing the dynamic regulatory mechanisms of proteins. Most existing computational methods rely on holo (ligand-bound) structures and struggle to effectively identify CBSs in the apo (ligand-free) state. Furthermore, these methods fail to account for protein three-dimensional conformational changes and spatial geometric information, often making it difficult to explain the dynamic characteristics of CBS formation.To address these challenges, we present CrypKANet, an innovative multimodal predictive framework for cryptic binding site identification that integrates EGNN, gated attention mechanisms, and Kolmogorov-Arnold Network (KAN). Our framework employs a two-branch design to independently encode geometric and biochemical features: the EGNN branch is dedicated to explicitly capturing three-dimensional spatial restraints and conformational dynamics, whereas the GINE branch strengthens the representation of residue-level chemical interactions and topological connectivity. Finally, the model predicts cryptic binding sites through the KAN classifier. Experimental results on the CBS benchmark dataset demonstrate that CrypKANet outperforms the existing state-of-the-art methods, and exhibits excellent generalization performance on protein-protein interaction sites and ligand binding site tasks.
Yongxian Fan, Xianchen Zheng, Yangfeng Zhu et al.· IEEE journal of biomedical a...· 0 citations
BACKGROUND AND PURPOSE
Binding kinetics are essentially based on rate constants. Yet, this view has been challenged by the idea that 'binding fluxes' are dynamic and therefore more relevant. Those fluxes refer to the rate at which a target/receptor changes from one state into another through ligand/drug binding or a conformational change. Besides acting as building blocks for many algebraic expressions, they also determine how the concentration of each individual target state evolves over time. Here we show that such fluxes offer additional opportunities for understanding and predicting ligand binding.
EXPERIMENTAL APPROACH
Simulated binding data are obtained by solving the relevant set of flux-based differential equations for increasingly complex ligand binding models over very small time intervals by Euler's method. As input, they require only ligand concentration(s) and rate constants.
KEY RESULTS
Compared to often-complex algebraic expressions, binding fluxes allow more intuitive/inductive insight into different aspects of ligand binding such as the occurrence of transient binding overshoots and the effect of a closing lid over the ligand's binding pocket on ligand dissociation. These examples disclose fundamental principles that govern ligand binding and, above all, they highlight the essential role of rate constants in all the examined binding models.
CONCLUSIONS AND IMPLICATIONS
Binding fluxes and rate constants complement each other: They respectively indicate how and why binding processes evolve in a certain fashion. The presented flux-based approaches have the advantage to address pre-equilibrium as well as equilibrium conditions and can be applied to any ligand-binding model.
G. Vauquelin, Terry Kenakin, D. Maes· British Journal of Pharmacol...· 0 citations
Boltz-Perturb is presented, a framework for addressing small molecule binding poses through perturbing model conditioning signals during model inference, and it is demonstrated that inference-time perturbations can unlock latent structural diversity in generative co-folding models and improve protein-ligand predictions without costly retraining.
Hyeyun Jung, BoRam Lee, Alan C. Cheng· bioRxiv· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
