A brief review of protein-ligand interaction prediction

Quantum-level machine learning calculations of Levodopa

Many drug molecules contain functional groups, resulting in a torsional barrier corresponding to rotation around the bond linking the fragments. In medicinal chemistry and pharmaceutical sciences, inclusive of drug design studies, the exact calculation of the potential energy surface (PES) of these molecular torsions is extremely important and precious. Machine learning (ML), including deep learning (DL), is currently one of the most rapidly evolving tools in computer-aided drug discovery and molecular simulations. In this work, we used ANI-1x neural network potential as a quantum-level ML to predict the PESs of the L-3,4-dihydroxyphenylalanine (Levodopa) antiparkinsonian drug molecule. The electronic energies and structural parameters calculated by density functional theory (DFT) using the wB97X method and all possible Pople's basis sets indicated the 6-31G(d) basis set, when used with the wB97X functional, exhibits behavior similar to that of the ANI-1x model. The vibrational frequencies investigation showed a linear correlation between DFT and ML data. All ANI-1x calculations were completed quickly in a very short computing time. From this perspective, we expect the ANI-1x dataset applied in this work to be appreciably efficient and effective in computational structure-based drug design studies.

Interplay of PROTAC Complex Dynamics for Undruggable Targets: Insights into Ternary Complex Behavior and Linker Design

Protein degraders, such as bifunctional proteolysis-targeting chimeras (PROTACs), selectively eliminate target proteins by leveraging the natural protein degradation machinery. PROTACs bridge the target protein with an E3 ligase, which induces ubiquitination and degradation. Investigating ternary complex structures elucidates the molecular mechanisms of their formation and degradation. This study examines the binding dynamics of E3 ligases (VHL, CRBN, and cIAP) with proteins of interest, focusing on dynamics, cooperativity, selectivity, linker length, and PROTAC conformations. The influence of interface residues and linker lengths on specific conformations for target proteins and E3 ligases is highlighted. Utilizing molecular dynamics and steered molecular dynamics simulations, the study provides comprehensive parameters on the behavior and stability of diverse ternary complexes. These insights are crucial for designing PROTACs targeting disease-causing proteins and advancing the development of degradable ternary complexes for therapeutic applications.

The effect of chrysin binding on the conformational dynamics and unfolding pathway of human serum albumin

Studies on the interactions between ligands and proteins provide insights into how a possible medication alters the structures and activities of the target or carrier proteins. The natural flavonoid aglycone Chrysin (CHR) has demonstrated anti-inflammatory, antioxidant, antiapoptotic, neuroprotective, and antineoplastic effects, both in vitro and in vivo. In this work, we investigated the impact of CHR binding on the as-yet-unexplored conformation, dynamics, and unfolding mechanism of human serum albumin (HSA). We determined CHR binding to HSA domain-II with the association constant (Ka) of 2.70 ± 0.21 × 105 M-1. The urea-induced sequential unfolding mechanism of HSA was used to elucidate the debatable binding location of CHR. CHR binding induced both secondary and tertiary structural alterations in the protein as studied by far-UV circular dichroism and intrinsic fluorescence spectroscopy. Red edge excitation shift (REES) indicated a decrease in conformational dynamics of the protein on the complex formation. This suggested an ordered compact and spatial arrangement of the CHR-boundmolecule. The binding of CHR was found to significantly modulate the urea-induced unfolding pathway of HSA. Urea-induced unfolding pathway of HSA became a two-state process (N-U) from a three-state process (N-I-U). The interaction of CHR is found to increase the thermal stability of the protein by ∼4 °C. This study focuses on the fundamental sciences and demonstrates how prospective medication compounds can alter the dynamics and stability of protein structure.

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 generalizability. 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, Pearson's R Spearman's 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.

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.

Predicting Drug-Protein Interactions through Branch-Chain Mining and multi-dimensional attention network

Identifying drug-protein interactions (DPIs) is crucial in drug discovery and repurposing. Computational methods for precise DPI identification can expedite development timelines and reduce expenses compared with conventional experimental methods. Lately, deep learning techniques have been employed for predicting DPIs, enhancing these processes. Nevertheless, the limitations observed in prior studies, where many extract features from complete drug and protein entities, overlooking the crucial theoretical foundation that pharmacological responses are often correlated with specific substructures, can lead to poor predictive performance. Furthermore, certain substructure-focused research confines its exploration to a solitary fragment category, such as a functional group. In this study, addressing these constraints, we present an end-to-end framework termed BCMMDA for predicting DPIs. The framework considers various substructure types, including branch chains, common substructures, and specific fragments. We designed a specific feature learning module by combining our proposed multi-dimensional attention mechanism with convolutional neural networks (CNNs). Deep CNNs assist in capturing the synergistic effects among these fragment sets, enabling the extraction of relevant features of drugs and proteins. Meanwhile, the multi-dimensional attention mechanism refines the relationship between drug and protein features by assigning attention vectors to each drug compound and amino acid. This mechanism empowers the model to further concentrate on pivotal substructures and elements, thereby improving its ability to identify essential interactions in DPI prediction. We evaluated the performance of BCMMDA on four well-known benchmark datasets. The results indicated that BCMMDA outperformed state-of-the-art baseline models, demonstrating significant improvement in performance.

Intelligent Protein Design and Molecular Characterization Techniques: A Comprehensive Review

In recent years, the widespread application of artificial intelligence algorithms in protein structure, function prediction, and de novo protein design has significantly accelerated the process of intelligent protein design and led to many noteworthy achievements. This advancement in protein intelligent design holds great potential to accelerate the development of new drugs, enhance the efficiency of biocatalysts, and even create entirely new biomaterials. Protein characterization is the key to the performance of intelligent protein design. However, there is no consensus on the most suitable characterization method for intelligent protein design tasks. This review describes the methods, characteristics, and representative applications of traditional descriptors, sequence-based and structure-based protein characterization. It discusses their advantages, disadvantages, and scope of application. It is hoped that this could help researchers to better understand the limitations and application scenarios of these methods, and provide valuable references for choosing appropriate protein characterization techniques for related research in the field, so as to better carry out protein research.

Understanding the Role of Activation Loop Mutants in Drug Efficacy for FLT3-ITD

The type III receptor tyrosine kinase FLT3 is a pivotal kinase for hematopoietic progenitor cell regulation, with significant implications in acute myeloid leukemia (AML) through mutations like internal tandem duplication (ITD). This study delves into the structural intricacies of FLT3, the roles of activation loop mutants, and their interaction with tyrosine kinase inhibitors. Coupled with this, the research leverages molecular contrastive learning and protein language modeling to examine interactions between small molecule inhibitors and FLT3 activation loop mutants. Utilizing the ConPLex platform, over 5.7 million unique FLT3 activation loop mutants-small molecule pairs were analyzed. The binding free energies of three inhibitors were assessed, and cellular apoptotic responses were evaluated under drug treatments. Notably, the introduction of the Xepto50 scoring system provides a nuanced metric for drug efficacy. The findings underscore the modulation of molecular interactions and cellular responses by Y842 mutations in FLT3-KD, highlighting the need for tailored therapeutic approaches in FLT3-ITD-related malignancies.

Expanding Training Data for Structure-Based Receptor-Ligand Binding Affinity Regression through Imputation of Missing Labels

The success of machine learning is, in part, due to a large volume of data available to train models. However, the amount of training data for structure-based molecular property prediction remains limited. The previously described CrossDocked2020 data set expanded the available training data for binding pose classification in a molecular docking setting but did not address expanding the amount of receptor-ligand binding affinity data. We present experiments demonstrating that imputing binding affinity labels for complexes without experimentally determined binding affinities is a viable approach to expanding training data for structure-based models of receptor-ligand binding affinity. In particular, we demonstrate that utilizing imputed labels from a convolutional neural network trained only on the affinity data present in CrossDocked2020 results in a small improvement in the binding affinity regression performance, despite the additional sources of noise that such imputed labels add to the training data. The code, data splits, and imputation labels utilized in this paper are freely available at https://github.com/francoep/ImputationPaper.

Prediction of metabolite-protein interactions based on integration of machine learning and constraint-based modeling

Motivation

Metabolite-protein interactions play an important role in regulating protein functions and metabolism. Yet, predictions of metabolite-protein interactions using genome-scale metabolic networks are lacking. Here, we fill this gap by presenting a computational framework, termed SARTRE, that employs features corresponding to shadow prices determined in the context of flux variability analysis to predict metabolite-protein interactions using supervised machine learning.

Results

By using gold standards for metabolite-protein interactomes and well-curated genome-scale metabolic models of Escherichia coli and Saccharomyces cerevisiae, we found that the implementation of SARTRE with random forest classifiers accurately predicts metabolite-protein interactions, supported by an average area under the receiver operating curve of 0.86 and 0.85, respectively. Ranking of features based on their importance for classification demonstrated the key role of shadow prices in predicting metabolite-protein interactions. The quality of predictions is further supported by the excellent agreement of the organism-specific classifiers on unseen interactions shared between the two model organisms. Further, predictions from SARTRE are highly competitive against those obtained from a recent deep-learning approach relying on a variety of protein and metabolite features. Together, these findings show that features extracted from constraint-based analyses of metabolic networks pave the way for understanding the functional roles of the interactions between proteins and small molecules.

Availability and implementation

https://github.com/fayazsoleymani/SARTRE.

Self- and cross-attention accurately predicts metabolite-protein interactions

Metabolites regulate activity of proteins and thereby affect cellular processes in all organisms. Despite extensive efforts to catalogue the metabolite-protein interactome in different organisms by employing experimental and computational approaches, the coverage of such interactions remains fragmented, particularly for eukaryotes. Here, we make use of two most comprehensive collections, BioSnap and STITCH, of metabolite-protein interactions from seven eukaryotes as gold standards to train a deep learning model that relies on self- and cross-attention over protein sequences. This innovative protein-centric approach results in interaction-specific features derived from protein sequence alone. In addition, we designed and assessed a first double-blind evaluation protocol for metabolite-protein interactions, demonstrating the generalizability of the model. Our results indicated that the excellent performance of the proposed model over simpler alternatives and randomized baselines is due to the local and global features generated by the attention mechanisms. As a results, the predictions from the deep learning model provide a valuable resource for studying metabolite-protein interactions in eukaryotes.

Application of machine learning on understanding biomolecule interactions in cellular machinery

Machine learning (ML) applications have become ubiquitous in all fields of research including protein science and engineering. Apart from protein structure and mutation prediction, scientists are focusing on knowledge gaps with respect to the molecular mechanisms involved in protein binding and interactions with other components in the experimental setups or the human body. Researchers are working on several wet-lab techniques and generating data for a better understanding of concepts and mechanics involved. The information like biomolecular structure, binding affinities, structure fluctuations and movements are enormous which can be handled and analyzed by ML. Therefore, this review highlights the significance of ML in understanding the biomolecular interactions while assisting in various fields of research such as drug discovery, nanomedicine, nanotoxicity and material science. Hence, the way ahead would be to force hand-in hand of laboratory work and computational techniques.

Modeling DTA by Combining Multiple-Instance Learning with a Private-Public Mechanism

The prediction of the strengths of drug–target interactions, also called drug–target binding affinities (DTA), plays a fundamental role in facilitating drug discovery, where the goal is to find prospective drug candidates. With the increase in the number of drug–protein interactions, machine learning techniques, especially deep learning methods, have become applicable for drug–target interaction discovery because they significantly reduce the required experimental workload. In this paper, we present a spontaneous formulation of the DTA prediction problem as an instance of multi-instance learning. We address the problem in three stages, first organizing given drug and target sequences into instances via a private-public mechanism, then identifying the predicted scores of all instances in the same bag, and finally combining all the predicted scores as the output prediction. A comprehensive evaluation demonstrates that the proposed method outperforms other state-of-the-art methods on three benchmark datasets.

Application of Mathematical Modeling and Computational Tools in the Modern Drug Design and Development Process

The conventional drug discovery approach is an expensive and time-consuming process, but its limitations have been overcome with the help of mathematical modeling and computational drug design approaches. Previously, finding a small molecular candidate as a drug against a disease was very costly and required a long time to screen a compound against a specific target. The development of novel targets and small molecular candidates against different diseases including emerging and reemerging diseases remains a major concern and necessitates the development of novel therapeutic targets as well as drug candidates as early as possible. In this regard, computational and mathematical modeling approaches for drug development are advantageous due to their fastest predictive ability and cost-effectiveness features. Computer-aided drug design (CADD) techniques utilize different computer programs as well as mathematics formulas to comprehend the interaction of a target and drugs. Traditional methods to determine small-molecule candidates as a drug have several limitations, but CADD utilizes novel methods that require little time and accurately predict a compound against a specific disease with minimal cost. Therefore, this review aims to provide a brief insight into the mathematical modeling and computational approaches for identifying a novel target and small molecular candidates for curing a specific disease. The comprehensive review mainly focuses on biological target prediction, structure-based and ligand-based drug design methods, molecular docking, virtual screening, pharmacophore modeling, quantitative structure-activity relationship (QSAR) models, molecular dynamics simulation, and MM-GBSA/MM-PBSA approaches along with valuable database resources and tools for identifying novel targets and therapeutics against a disease. This review will help researchers in a way that may open the road for the development of effective drugs and preventative measures against a disease in the future as early as possible.