Ligand binding affinity prediction with fusion of graph neural networks and 3D structure-based complex graph.

Accurate protein-ligand binding affinity prediction is crucial in drug discovery. Existing methods are predominately docking-free, without explicitly considering atom-level interaction between proteins and ligands in scenarios where crystallized protein-ligand binding conformations are unavailable. Now, with breakthroughs in deep learning AI-based protein folding and binding conformation prediction, can we improve binding affinity prediction? This study introduces a framework, Folding-Docking-Affinity (FDA), which folds proteins, determines protein-ligand binding conformations, and predicts binding affinities from three-dimensional protein-ligand binding structures. Our experimental results indicate that FDA performs comparably to state-of-the-art docking-free methods. We anticipate that our proposed framework serves as a starting point for integrating binding structures for more accurate binding affinity prediction.

Accurate prediction of protein-ligand bound poses and their affinities is essential in structure-based drug discovery. Here, we present an integrated deep-learning framework that disentangles the two core tasks─affinity estimation and pose evaluation─within complementary graph neural network architectures. BA-Pred is for predicting binding affinity and RMSD-Pred is for binding pose assessment, predicting the root-mean-squared deviation of ligand poses from crystal structures. Both models employ a Gated Graph Convolutional Network with Learnable Structural Positional Encoding (GatedGCN-LSPE) architecture to capture spatial and chemical dependencies across protein-ligand graphs. BA-Pred achieved state-of-the-art scoring power on the CASF-2016 benchmark with a root-mean-squared error of 1.10 pKd, while RMSD-Pred exhibited strong docking power with a top-1 success rate of 96%, comparable to the best reported deep-learning scoring functions. The robust generalization capability of RMSD-Pred was further validated on the external Astex diverse set and PoseBusters benchmarks, where it significantly improved the pose selection success rates of AutoDock-GPU by up to 33.1%. The accuracy of our methodology was demonstrated on pharmaceutical targets in the 16th Critical Assessment of Structure Prediction, where our approach ranked second in the ligand binding affinity prediction category. By using our models, an integrated pipeline was developed for virtual screening, where pose selection was performed with RMSD-Pred and binding affinities were predicted with BA-Pred. This combined approach demonstrated robust screening performance, achieving an enrichment factor (EF) 1% of 21.1 on the CASF-2016 benchmark. Furthermore, on the LIT-PCBA benchmark, rescoring poses docked by AutoDock-GPU with our pipeline significantly improved the EF 1% from 2.18 to 3.19. These various benchmark results demonstrate that our graph-neural network models show good and balanced performance in diverse protein-ligand interaction prediction tasks. Thus, we expect that our models will serve as a promising framework to accelerate the drug discovery process.

Accurate prediction of binding affinities from protein-ligand atomic coordinates remains a major challenge in early stages of drug discovery. Using modular message passing graph neural networks describing both the ligand and the protein in their free and bound states, we unambiguously evidence that an explicit description of protein-ligand noncovalent interactions does not provide any advantage with respect to ligand or protein descriptors. Simple models, inferring binding affinities of test samples from that of the closest ligands or proteins in the training set, already exhibit good performances, suggesting that memorization largely dominates true learning in the deep neural networks. The current study suggests considering only noncovalent interactions while omitting their protein and ligand atomic environments. Removing all hidden biases probably requires much denser protein-ligand training matrices and a coordinated effort of the drug design community to solve the necessary protein-ligand structures.

Predicting protein-ligand binding affinity is a crucial and challenging task in structure-based drug discovery. With the accumulation of complex structures and binding affinity data, various machine-learning scoring functions, particularly those based on deep learning, have been developed for this task, exhibiting superiority over their traditional counterparts. A fusion model sequentially connecting a graph neural network (GNN) and a convolutional neural network (CNN) to predict protein-ligand binding affinity is proposed in this work. In this model, the intermediate outputs of the GNN layers, as supplementary descriptors of atomic chemical environments at different levels, are concatenated with the input features of CNN. The model demonstrates a noticeable improvement in performance on CASF-2016 benchmark compared to its constituent CNN models. The generalization ability of the model is evaluated by setting a series of thresholds for ligand extended-connectivity fingerprint similarity or protein sequence similarity between the training and test sets. Masking experiment reveals that model can capture key interaction regions. Furthermore, the fusion model is applied to a virtual screening task for a novel target, PI5P4Kα. The fusion strategy significantly improves the ability of the constituent CNN model to identify active compounds. This work offers a novel approach to enhancing the accuracy of deep learning models in predicting binding affinity through fusion strategies.

Predicting protein-ligand binding affinity is a central issue in drug design. Various deep learning models have been published in recent years, where many of them rely on 3D protein-ligand complex structures as input and tend to focus on the single task of reproducing binding affinity. In this study, we have developed a graph neural network model called PLANET (Protein-Ligand Affinity prediction NETwork). This model takes the graph-represented 3D structure of the binding pocket on the target protein and the 2D chemical structure of the ligand molecule as input. It was trained through a multi-objective process with three related tasks, including deriving the protein-ligand binding affinity, protein-ligand contact map, and ligand distance matrix. Besides the protein-ligand complexes with known binding affinity data retrieved from the PDBbind database, a large number of non-binder decoys were also added to the training data for deriving the final model of PLANET. When tested on the CASF-2016 benchmark, PLANET exhibited a scoring power comparable to the best result yielded by other deep learning models as well as a reasonable ranking power and docking power. In virtual screening trials conducted on the DUD-E benchmark, PLANET's performance was notably better than several deep learning and machine learning models. As on the LIT-PCBA benchmark, PLANET achieved comparable accuracy as the conventional docking program Glide, but it only spent less than 1% of Glide's computation time to finish the same job because PLANET did not need exhaustive conformational sampling. Considering the decent accuracy and efficiency of PLANET in binding affinity prediction, it may become a useful tool for conducting large-scale virtual screening.

Accurately predicting protein-ligand binding affinity is an important step in the drug discovery process. Deep learning (DL) methods have improved binding affinity prediction by using diverse categories of molecular data. However, many models rely heavily on interaction and sequence data, which impedes proper learning and limits performance in de novo applications. To address these limitations, we developed a novel graph neural network model, called StructureNet (structure-based graph neural network), to predict protein-ligand binding affinity. StructureNet improves existing DL methods by focusing entirely on structural descriptors to mitigate data memorization issues introduced by sequence and interaction data. StructureNet represents the protein and ligand structures as graphs, which are processed using a GNN-based ensemble deep learning model. StructureNet achieved a PCC of 0.68 and an AUC of 0.75 on the PDBBind v.2020 Refined Set, outperforming similar structure-based models. External validation on the DUDE-Z dataset showed that StructureNet can effectively distinguish between active and decoy ligands. Further testing on a small subset of well-known drugs indicates that StructureNet has high potential for rapid virtual screening applications. We also hybridized StructureNet with interaction- and sequence-based models to investigate their impact on testing accuracy and found minimal difference (0.01 PCC) between merged models and StructureNet as a standalone model. An ablation study found that geometric descriptors were the key drivers of model performance, with their removal leading to a PCC decrease of over 15.7%. Lastly, we tested StructureNet on ensembles of binding complex conformers generated using molecular dynamics (MD) simulations and found that incorporating multiple conformations of the same complex often improves model accuracy by capturing binding site flexibility. Overall, the results show that structural data alone are sufficient for binding affinity predictions and can address pattern recognition challenges introduced by sequence and interaction features. Additionally, structural representations of protein-ligand complexes can be considerably improved using geometric and topological descriptors. We made StructureNet GUI interface freely available online.

Inductive bias in machine learning (ML) is the set of assumptions describing how a model makes predictions. Different ML-based methods for protein-ligand binding affinity (PLA) prediction have different inductive biases, leading to different levels of generalization capability and interpretability. Intuitively, the inductive bias of an ML-based model for PLA prediction should fit in with biological mechanisms relevant for binding to achieve good predictions with meaningful reasons. To this end, we propose an interaction-based inductive bias to restrict neural networks to functions relevant for binding with two assumptions: 1) A protein-ligand complex can be naturally expressed as a heterogeneous graph with covalent and non-covalent interactions; 2) The predicted PLA is the sum of pairwise atom-atom affinities determined by non-covalent interactions. The interaction-based inductive bias is embodied by an explainable heterogeneous interaction graph neural network (EHIGN) for explicitly modeling pairwise atom-atom interactions to predict PLA from 3D structures. Extensive experiments demonstrate that EHIGN achieves better generalization capability than other state-of-the-art ML-based baselines in PLA prediction and structure-based virtual screening. More importantly, comprehensive analyses of distance-affinity, pose-affinity, and substructure-affinity relations suggest that the interaction-based inductive bias can guide the model to learn atomic interactions that are consistent with physical reality. As a case study to demonstrate practical usefulness, our method is tested for predicting the efficacy of Nirmatrelvir against SARS-CoV-2 variants. EHIGN successfully recognizes the changes in the efficacy of Nirmatrelvir for different SARS-CoV-2 variants with meaningful reasons.

The ability to accurately predict the interaction of a ligand with its receptor is a key limitation in computer-aided drug design approaches such as virtual screening and de novo design. In this article, we examine current strategies for a physics-based approach to scoring of protein-ligand affinity, as well as outlining recent developments in force fields and quantum chemical techniques. We also consider advances in the development and application of simulation-based free energy methods to study protein-ligand interactions. Fuelled by recent advances in computational algorithms and hardware, there is the opportunity for increased integration of physics-based scoring approaches at earlier stages in computationally guided drug discovery. Specifically, we envisage increased use of implicit solvent models and simulation-based scoring methods as tools for computing the affinities of large virtual ligand libraries. Approaches based on end point simulations and reference potentials allow the application of more advanced potential energy functions to prediction of protein-ligand binding affinities. Comprehensive evaluation of polarizable force fields and quantum mechanical (QM)/molecular mechanical and QM methods in scoring of protein-ligand interactions is required, particularly in their ability to address challenging targets such as metalloproteins and other proteins that make highly polar interactions. Finally, we anticipate increasingly quantitative free energy perturbation and thermodynamic integration methods that are practical for optimization of hits obtained from screened ligand libraries.

Accurate binding affinity prediction (BAP) is crucial to structure-based drug design. We present PATH+, a novel, generalizable machine learning algorithm for BAP that exploits recent advances in computational topology. Compared to current binding affinity prediction algorithms, PATH+ shows similar or better accuracy and is more generalizable across orthogonal datasets. PATH+ is not only one of the most accurate algorithms for BAP, it is also the first algorithm that is inherently interpretable. Interpretability is a key factor of trust for an algorithm and alongside generalizability, which allows PATH+ to be trusted in critical applications, such as inhibitor design. We visualized the features captured by PATH+ for two clinically relevant protein-ligand complexes and find that PATH+ captures binding-relevant structural mutations that are corroborated by biochemical data. Our work also sheds light on the features captured by current computational topology BAP algorithms that contributed to their high performance, which have been poorly understood. PATH+ also offers an improvement of 𝒪 (m + n)3 in computational complexity and is empirically over 10 times faster than the dominant (uninterpretable) computational topology algorithm for BAP. Based on insights from PATH+, we built PATH-, a scoring function for differentiating between binders and non-binders that has outstanding accuracy against 11 current algorithms for BAP. In summary, we report progress in a novel combination of interpretability, speed, and accuracy that should further empower topological screening of large virtual inhibitor libraries to protein targets, and allow binding affinity predictions to be understood and trusted. The source code for PATH+ and PATH- is released open-source as part of the OSPREY protein design software package.

Protein-ligand interactions are the molecular basis of many important cellular activities, such as gene regulation, cell metabolism, and signal transduction. Protein-ligand binding affinity is a crucial metric of the strength of the interaction between the two, and accurate prediction of its binding affinity is essential for discovering drugs' new uses. So far, although many predictive models based on machine learning and deep learning have been reported, most of the models mainly focus on one-dimensional sequence and two-dimensional structural characteristics of proteins and ligands, but fail to deeply explore the detailed interaction information between proteins and ligand atoms in the binding pocket region of three-dimensional space. In this study, we introduced a novel 4D tensor feature to capture key interactions within the binding pocket and developed a three-dimensional convolutional neural network (CNN) model based on this feature. Using ten-fold cross-validation, we identified the optimal parameter combination and pocket size. Additionally, we employed feature engineering to extract features across multiple dimensions, including one-dimensional sequences, two-dimensional structures of the ligand and protein, and three-dimensional interaction features between them. We proposed an efficient protein-ligand binding affinity prediction model MCDTA (multi-dimensional convolutional drug-target affinity), built on a multi-dimensional convolutional neural network framework. Feature ablation experiments revealed that the 4D tensor feature had the most significant impact on model performance. MCDTA performed exceptionally well on the PDBbind v.2020 dataset, achieving an RMSE of 1.231 and a PCC of 0.823. In comparative experiments, it outperformed five other mainstream binding affinity prediction models, with an RMSE of 1.349 and a PCC of 0.795. Moreover, MCDTA demonstrated strong generalization ability and practical screening performance across multiple benchmark datasets, highlighting its reliability and accuracy in predicting protein-ligand binding affinity. The code for MCDTA is available at https://github.com/dfhuang-AI/MCDTA .

PLAGCA: Predicting protein-ligand binding affinity with the graph cross-attention mechanism.

Pharmaceutical Applications of the Polarizable Amoeba Potential, Including Protein-Ligand Binding Affinity and Drug Solubility, using the Force Field X Software

In the drug discovery process and repurposing of existing drugs, accurately identifying ligands with high binding affinity to proteins is a very critical step. However, it sinks a lot of time and resources to detect the protein-ligand binding affinity through biological experiments. Therefore, it is very necessary to develop an accurate and reliable computational method to predict the binding affinity between protein and ligand. At present, some computational methods have been proposed to predict the protein-ligand binding affinity, but the absence of protein-ligand complexes structures restricts some predictive methods that require input the complexes structures. In this paper, a novel deep-learning-based method is proposed, named DPLA, to predict binding affinity by integrating multilevel information of protein and ligand. More specifically, our model extracted some important information, such as sequence representation, structural property representation of amino acids in protein and protein binding pocket, MACCS key ligand molecular fingerprint and ligand molecular network features. This method was tested on the PDBbind core set, and we compared it with some recent state-of-art protein-ligand affinity prediction methods. The excellent performance shows that DPLA is an accurate and reliable method for affinity prediction.

The field of computational protein design has experienced important recent success. However, the de novo computational design of high-affinity protein-ligand interfaces is still largely an open challenge. Using the Rosetta program, we attempted the in silico design of a high-affinity protein interface to a small peptide ligand. We chose the thermophilic endo-1,4-β-xylanase from Nonomuraea flexuosa as the protein scaffold on which to perform our designs. Over the course of the study, 12 proteins derived from this scaffold were produced and assayed for binding to the target ligand. Unfortunately, none of the designed proteins displayed evidence of high-affinity binding. Structural characterization of four designed proteins revealed that although the predicted structure of the protein model was highly accurate, this structural accuracy did not translate into accurate prediction of binding affinity. Crystallographic analyses indicate that the lack of binding affinity is possibly due to unaccounted for protein dynamics in the 'thumb' region of our design scaffold intrinsic to the family 11 β-xylanase fold. Further computational analysis revealed two specific, single amino acid substitutions responsible for an observed change in backbone conformation, and decreased dynamic stability of the catalytic cleft. These findings offer new insight into the dynamic and structural determinants of the β-xylanase proteins.

Structure-guided drug design efforts stand to benefit greatly from insights provided by accurate predictive models of binding affinity. Here we use Delaunay tessellation to analyze atomic four-body interactions in a diverse set of high-resolution crystal structures for three hundred protein-ligand complexes, each with an experimentally determined dissociation constant. Two hundred of these complexes are randomly selected to derive an empirical function for predicting the standard Gibbs free energy of binding (ΔG). In each case, structural atomic coordinates are used to generate tessellations for the protein-ligand complex as well as for the isolated protein without the bound ligand. An all-atom four-body knowledge-based statistical potential is used to generate a topological score based on each tessellation, and binding affinity is calculated as an empirical linear function of the difference between the topological scores of the complex and the isolated protein. Experimental and calculated ΔG values are in good agreement, with a correlation coefficient (r) of 0.79 and a standard error of 1.98 kcal/mol. To evaluate the method, tessellation-based topological score differences are calculated for the remaining one hundred complexes, and the linear transformation derived from the training data is used to predict their binding affinities. Again, the correlation coefficient is 0.79 between experimental and calculated binding energies for the test set, with a standard error of 1.93 kcal/mol.