Search

Abstract 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.

Abstract 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 $$\pi $$ 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 Statement This 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.

Protein structure prediction (PSP) is a vital challenge in bioinformatics, structural biology and drug discovery. Protein secondary structure (SS) prediction is critical since three-dimensional (3D) structures are primarily made up of secondary structures. With the advancement of deep learning approaches, SS classification accuracy has been significantly improved. Many existing methods use an ensemble of complex neural networks to improve SS prediction. Because of the high dimensionality of the hyperparameter space, deep neural networks with complex architectures are typically challenging to train effectively. Also, predicting secondary structures in the boundary regions between different types of SS is challenging. This study presents Multi-S3P, which employs bidirectional Long-Short-Term-Memory (BILSTM) and Convolutional Neural Networks (CNN) with a self-attention mechanism to improve the secondary structure prediction using an effective training strategy to capture the unique characteristics of each type of secondary structure and combine them more effectively. The ensemble of CNN and BILSTM can learn both contextual information and long-range interactions between the residues. In addition, using a self-attention mechanism allows the model to focus on the most important features for improving performance. We used the SPOT-1D dataset for the training and validation of our model using a set of four input features derived from amino acid sequences. Further, the model was tested on four popular independent test datasets and compared with various state-of-the-art predictors. The presented results show that Multi-S3P outperformed the other methods in terms of Q3, Q8 accuracy and other performance metrics, achieving the highest Q3 accuracy of 87.57% and a Q8 accuracy of 77.56% on the TEST2016 test set. More importantly, Multi-S3P demonstrates high performance in SS boundary regions. Our experiment also demonstrates that the combination of different input features and a multi-network-based training strategy significantly improved the performance.

Abstract Motivation Protein backbone angle prediction has achieved significant accuracy improvement with the development of deep learning methods. Usually the same deep learning model is used in making prediction for all residues regardless of the categories of secondary structures they belong to. In this paper, we propose to train separate deep learning models for each category of secondary structures. Machine learning methods strive to achieve generality over the training examples and consequently loose accuracy. In this work, we explicitly exploit classification knowledge to restrict generalisation within the specific class of training examples. This is to compensate the loss of generalisation by exploiting specialisation knowledge in an informed way. Results The new method named SAP4SS obtains mean absolute error (MAE) values of 15.59, 18.87, 6.03, and 21.71 respectively for four types of backbone angles $$\phi$$ ϕ , $$\psi$$ ψ , $$\theta$$ θ , and $$\tau$$ τ . Consequently, SAP4SS significantly outperforms existing state-of-the-art methods SAP, OPUS-TASS, and SPOT-1D: the differences in MAE for all four types of angles are from 1.5 to 4.1% compared to the best known results. Availability SAP4SS along with its data is available from https://gitlab.com/mahnewton/sap4ss .

Abstract Protein structure prediction (PSP) has achieved significant progress lately via prediction of inter-residue distances using deep learning models and exploitation of the predictions during conformational search. In this context, prediction of large inter-residue distances and also prediction of distances between residues separated largely in the protein sequence remain challenging. To deal with these challenges, state-of-the-art inter-residue distance prediction algorithms have used large sets of coevolutionary and non-coevolutionary features. In this paper, we argue that the more the types of features used, the more the kinds of noises introduced and then the deep learning model has to overcome the noises to improve the accuracy of the predictions. Also, multiple features capturing similar underlying characteristics might not necessarily have significantly better cumulative effect. So we scrutinise the feature space to reduce the types of features to be used, but at the same time, we strive to improve the prediction accuracy. Consequently, for inter-residue real distance prediction, in this paper, we propose a deep learning model named scrutinised distance predictor (SDP), which uses only 2 coevolutionary and 3 non-coevolutionary features. On several sets of benchmark proteins, our proposed SDP method improves mean Local Distance Different Test (LDDT) scores at least by 10% over existing state-of-the-art methods. The SDP program along with its data is available from the website https://gitlab.com/mahnewton/sdp .

Protein structure prediction (PSP) is essential for drug discovery. PSP involves minimising an unknown scoring function over an astronomical search space. PSP has achieved significant progress recently via end-to-end deep learning models that require enormous computational resources and almost all known proteins as training data. In this paper, we develop a conformational search method for PSP based on scoring functions involving geometric constraints learnt by deep learning models. When machine learning models achieve generality and thus obviously loose accuracy, conformational search methods could perform protein-specific fine tuning of the predicted conformations. However, effective conformational sampling in PSP remains a key challenge. Existing conformational search algorithms adopt random selection approaches for neighbor generation and thus greatly depend on luck. We propose a new approach to analyse geometric constraint-based scores, to identify the regions of the current conformations causing inferior scores, and to alter the identified regions to generate neighbour conformations. Our approach prefers informed decisions to random selections from an artificial intelligence perspective. The proposed method also provides promising search guidance as it obtains significant improvements from given initial conformations. On a set of 35 benchmark proteins of varying types and sizes, our algorithm significantly outperforms state-of-the-art PSP search algorithms that use random sampling with a similar scoring function: the improvement is about 1Å better average in root mean square deviation (RMSD) values. Our sample generation approach could be used in other bioinformatics research areas requiring search.