Leveraging scaffold information to predict protein-ligand binding affinity with an empirical graph neural network

T-ALPHA: A Hierarchical Transformer-Based Deep Neural Network for Protein-Ligand Binding Affinity Prediction with Uncertainty-Aware Self-Learning for Protein-Specific Alignment

There is significant interest in targeting disease-causing proteins with small molecule inhibitors to restore healthy cellular states. The ability to accurately predict the binding affinity of small molecules to a protein target in silico enables the rapid identification of candidate inhibitors and facilitates the optimization of on-target potency. In this work, we present T-ALPHA, a novel deep learning model that enhances protein-ligand binding affinity prediction by integrating multimodal feature representations within a hierarchical transformer framework to capture information critical to accurately predicting binding affinity. T-ALPHA outperforms all existing models reported in the literature on multiple benchmarks designed to evaluate protein-ligand binding affinity scoring functions. Remarkably, T-ALPHA maintains state-of-the-art performance when utilizing predicted structures rather than crystal structures, a powerful capability in real-world drug discovery applications where experimentally determined structures are often unavailable or incomplete. Additionally, we present an uncertainty-aware self-learning method for protein-specific alignment that does not require additional experimental data and demonstrate that it improves T-ALPHA's ability to rank compounds by binding affinity to biologically significant targets such as the SARS-CoV-2 main protease and the epidermal growth factor receptor. To facilitate implementation of T-ALPHA and reproducibility of all results presented in this paper, we made all of our software available at https://github.com/gregory-kyro/T-ALPHA.

Improving drug-target affinity prediction by adaptive self-supervised learning

Computational drug-target affinity prediction is important for drug screening and discovery. Currently, self-supervised learning methods face two major challenges in drug-target affinity prediction. The first difficulty lies in the phenomenon of sample mismatch: self-supervised learning processes drug and target samples independently, while actual prediction requires the integration of drug-target pairs. Another challenge is the mismatch between the broadness of self-supervised learning objectives and the precision of biological mechanisms of drug-target affinity (i.e., the induced-fit principle). The former focuses on global feature extraction, while the latter emphasizes the importance of local precise matching. To address these issues, an adaptive self-supervised learning-based drug-target affinity prediction (ASSLDTA) was designed. ASSLDTA integrates a novel adaptive self-supervised learning (ASSL) module with a high-level feature learning network to extract the feature. The ASSL leverages a large amount of unlabeled training data to effectively capture low-level features of drugs and targets. Its goal is to maximize the retention of original feature information, thereby bridging the objective gap between self-supervised learning and drug-target affinity prediction and alleviating the sample mismatch problem. The high-level feature learning network, on the other hand, focuses on extracting effective high-level features for affinity prediction through a small amount of labeled data. Through this two-stage feature extraction design, each stage undertakes specific tasks, fully leveraging the advantages of each model while efficiently integrating information from different data sources, providing a more accurate and comprehensive solution for drug-target affinity prediction. In our experiments, ASSLDTA is much better than other deep methods, and the result of ASSLDTA is significantly increased by learning adaptive self-supervised learning-based features, which validates the effectiveness of our ASSLDTA.

Protein representations: Encoding biological information for machine learning in biocatalysis

Enzymes offer a more environmentally friendly and low-impact solution to conventional chemistry, but they often require additional engineering for their application in industrial settings, an endeavour that is challenging and laborious. To address this issue, the power of machine learning can be harnessed to produce predictive models that enable the in silico study and engineering of improved enzymatic properties. Such machine learning models, however, require the conversion of the complex biological information to a numerical input, also called protein representations. These inputs demand special attention to ensure the training of accurate and precise models, and, in this review, we therefore examine the critical step of encoding protein information to numeric representations for use in machine learning. We selected the most important approaches for encoding the three distinct biological protein representations - primary sequence, 3D structure, and dynamics - to explore their requirements for employment and inductive biases. Combined representations of proteins and substrates are also introduced as emergent tools in biocatalysis. We propose the division of fixed representations, a collection of rule-based encoding strategies, and learned representations extracted from the latent spaces of large neural networks. To select the most suitable protein representation, we propose two main factors to consider. The first one is the model setup, which is influenced by the size of the training dataset and the choice of architecture. The second factor is the model objectives such as consideration about the assayed property, the difference between wild-type models and mutant predictors, and requirements for explainability. This review is aimed at serving as a source of information and guidance for properly representing enzymes in future machine learning models for biocatalysis.

Ensembling methods for protein-ligand binding affinity prediction

Protein-ligand binding affinity prediction is a key element of computer-aided drug discovery. Most of the existing deep learning methods for protein-ligand binding affinity prediction utilize single models and suffer from low accuracy and generalization capability. In this paper, we train 13 deep learning models from combinations of 5 input features. Then, we explore all possible ensembles of the trained models to find the best ensembles. Our deep learning models use cross-attention and self-attention layers to extract short and long-range interactions. Our method is named Ensemble Binding Affinity (EBA). EBA extracts information from various models using different combinations of input features, such as simple 1D sequential and structural features of the protein-ligand complexes rather than 3D complex features. EBA is implemented to accurately predict the binding affinity of a protein-ligand complex. One of our ensembles achieves the highest Pearson correlation coefficient (R) value of 0.914 and the lowest root mean square error (RMSE) value of 0.957 on the well-known benchmark test set CASF2016. Our ensembles show significant improvements of more than 15% in R-value and 19% in RMSE on both well-known benchmark CSAR-HiQ test sets over the second-best predictor named CAPLA. Furthermore, the superior performance of the ensembles across all metrics compared to existing state-of-the-art protein-ligand binding affinity prediction methods on all five benchmark test datasets demonstrates the effectiveness and robustness of our approach. Therefore, our approach to improving binding affinity prediction between proteins and ligands can contribute to improving the success rate of potential drugs and accelerate the drug development process.

Distance plus attention for binding affinity prediction

Protein-ligand binding affinity plays a pivotal role in drug development, particularly in identifying potential ligands for target disease-related proteins. Accurate affinity predictions can significantly reduce both the time and cost involved in drug development. However, highly precise affinity prediction remains a research challenge. A key to improve affinity prediction is to capture interactions between proteins and ligands effectively. Existing deep-learning-based computational approaches use 3D grids, 4D tensors, molecular graphs, or proximity-based adjacency matrices, which are either resource-intensive or do not directly represent potential interactions. In this paper, we propose atomic-level distance features and attention mechanisms to capture better specific protein-ligand interactions based on donor-acceptor relations, hydrophobicity, and π -stacking atoms. We argue that distances encompass both short-range direct and long-range indirect interaction effects while attention mechanisms capture levels of interaction effects. On the very well-known CASF-2016 dataset, our proposed method, named Distance plus Attention for Affinity Prediction (DAAP), significantly outperforms existing methods by achieving Correlation Coefficient (R) 0.909, Root Mean Squared Error (RMSE) 0.987, Mean Absolute Error (MAE) 0.745, Standard Deviation (SD) 0.988, and Concordance Index (CI) 0.876. The proposed method also shows substantial improvement, around 2% to 37%, on five other benchmark datasets. The program and data are publicly available on the website https://gitlab.com/mahnewton/daap. Scientific Contribution StatementThis study innovatively introduces distance-based features to predict protein-ligand binding affinity, capitalizing on unique molecular interactions. Furthermore, the incorporation of protein sequence features of specific residues enhances the model's proficiency in capturing intricate binding patterns. The predictive capabilities are further strengthened through the use of a deep learning architecture with attention mechanisms, and an ensemble approach, averaging the outputs of five models, is implemented to ensure robust and reliable predictions.

Machine Learning for Sequence and Structure-Based Protein-Ligand Interaction Prediction

Developing new drugs is too expensive and time -consuming. Accurately predicting the interaction between drugs and targets will likely change how the drug is discovered. Machine learning-based protein-ligand interaction prediction has demonstrated significant potential. In this paper, computational methods, focusing on sequence and structure to study protein-ligand interactions, are examined. Therefore, this paper starts by presenting an overview of the data sets applied in this area, as well as the various approaches applied for representing proteins and ligands. Then, sequence-based and structure-based classification criteria are subsequently utilized to categorize and summarize both the classical machine learning models and deep learning models employed in protein-ligand interaction studies. Moreover, the evaluation methods and interpretability of these models are proposed. Furthermore, delving into the diverse applications of protein-ligand interaction models in drug research is presented. Lastly, the current challenges and future directions in this field are addressed.

Prediction of protein-ligand binding affinity via deep learning models

Accurately predicting the binding affinity between proteins and ligands is crucial in drug screening and optimization, but it is still a challenge in computer-aided drug design. The recent success of AlphaFold2 in predicting protein structures has brought new hope for deep learning (DL) models to accurately predict protein-ligand binding affinity. However, the current DL models still face limitations due to the low-quality database, inaccurate input representation and inappropriate model architecture. In this work, we review the computational methods, specifically DL-based models, used to predict protein-ligand binding affinity. We start with a brief introduction to protein-ligand binding affinity and the traditional computational methods used to calculate them. We then introduce the basic principles of DL models for predicting protein-ligand binding affinity. Next, we review the commonly used databases, input representations and DL models in this field. Finally, we discuss the potential challenges and future work in accurately predicting protein-ligand binding affinity via DL models.

Iterative Knowledge-Based Scoring Function for Protein-Ligand Interactions by Considering Binding Affinity Information

Scoring functions for protein-ligand interactions play a critical role in structure-based drug design. Owing to the good balance between general applicability and computational efficiency, knowledge-based scoring functions have obtained significant advancements and achieved many successes. Nevertheless, knowledge-based scoring functions face a challenge in utilizing the experimental affinity data and thus may not perform well in binding affinity prediction. Addressing the challenge, we have proposed an improved version of the iterative knowledge-based scoring function ITScore by considering binding affinity information, which is referred to as ITScoreAff, based on a large training set of 6216 protein-ligand complexes with both structures and affinity data. ITScoreAff was extensively evaluated and compared with ITScore, 33 traditional, and 6 machine learning scoring functions in terms of docking power, ranking power, and screening power on the independent CASF-2016 benchmark. It was shown that ITScoreAff obtained an overall better performance than the other 40 scoring functions and gave an average success rate of 85.3% in docking power, a correlation coefficient of 0.723 in scoring power, and an average rank correlation coefficient of 0.668 in ranking power. In addition, ITScoreAff also achieved the overall best screening power when the top 10% of the ranked database were considered. These results demonstrated the robustness of ITScoreAff and its improvement over existing scoring functions.

Geometric graph learning with extended atom-types features for protein-ligand binding affinity prediction

Understanding and accurately predicting protein-ligand binding affinity are essential in the drug design and discovery process. At present, machine learning-based methodologies are gaining popularity as a means of predicting binding affinity due to their efficiency and accuracy, as well as the increasing availability of structural and binding affinity data for protein-ligand complexes. In biomolecular studies, graph theory has been widely applied since graphs can be used to model molecules or molecular complexes in a natural manner. In the present work, we upgrade the graph-based learners for the study of protein-ligand interactions by integrating extensive atom types such as SYBYL and extended connectivity interactive features (ECIF) into multiscale weighted colored graphs (MWCG). By pairing with the gradient boosting decision tree (GBDT) machine learning algorithm, our approach results in two different methods, namely sybylGGL-Score and ecifGGL-Score. Both of our models are extensively validated in their scoring power using three commonly used benchmark datasets in the drug design area, namely CASF-2007, CASF-2013, and CASF-2016. The performance of our best model sybylGGL-Score is compared with other state-of-the-art models in the binding affinity prediction for each benchmark. While both of our models achieve state-of-the-art results, the SYBYL atom-type model sybylGGL-Score outperforms other methods by a wide margin in all benchmarks. Finally, the best-performing SYBYL atom-type model is evaluated on two test sets that are independent of CASF benchmarks.