ProtTrans and multi-window scanning convolutional neural networks for the prediction of protein-peptide interaction sites

This study delves into the prediction of protein-peptide interactions using advanced machine learning techniques, comparing models such as sequence-based, standard CNNs, and traditional classifiers. Leveraging pre-trained language models and multi-view window scanning CNNs, our approach yields significant improvements, with ProtTrans standing out based on 2.1 billion protein sequences and 393 billion amino acids. The integrated model demonstrates remarkable performance, achieving an AUC of 0.856 and 0.823 on the PepBCL Set_1 and Set_2 datasets, respectively. Additionally, it attains a Precision of 0.564 in PepBCL Set 1 and 0.527 in PepBCL Set 2, surpassing the performance of previous methods. Beyond this, we explore the application of this model in cancer therapy, particularly in identifying peptide interactions for selective targeting of cancer cells, and other fields. The findings of this study contribute to bioinformatics, providing valuable insights for drug discovery and therapeutic development.

Leveraging machine learning models for peptide-protein interaction prediction

Peptides play a pivotal role in a wide range of biological activities through participating in up to 40% protein-protein interactions in cellular processes. They also demonstrate remarkable specificity and efficacy, making them promising candidates for drug development. However, predicting peptide-protein complexes by traditional computational approaches, such as docking and molecular dynamics simulations, still remains a challenge due to high computational cost, flexible nature of peptides, and limited structural information of peptide-protein complexes. In recent years, the surge of available biological data has given rise to the development of an increasing number of machine learning models for predicting peptide-protein interactions. These models offer efficient solutions to address the challenges associated with traditional computational approaches. Furthermore, they offer enhanced accuracy, robustness, and interpretability in their predictive outcomes. This review presents a comprehensive overview of machine learning and deep learning models that have emerged in recent years for the prediction of peptide-protein interactions.

A comprehensive review of protein-centric predictors for biomolecular interactions: from proteins to nucleic acids and beyond

Proteins interact with diverse ligands to perform a large number of biological functions, such as gene expression and signal transduction. Accurate identification of these protein-ligand interactions is crucial to the understanding of molecular mechanisms and the development of new drugs. However, traditional biological experiments are time-consuming and expensive. With the development of high-throughput technologies, an increasing amount of protein data is available. In the past decades, many computational methods have been developed to predict protein-ligand interactions. Here, we review a comprehensive set of over 160 protein-ligand interaction predictors, which cover protein-protein, protein-nucleic acid, protein-peptide and protein-other ligands (nucleotide, heme, ion) interactions. We have carried out a comprehensive analysis of the above four types of predictors from several significant perspectives, including their inputs, feature profiles, models, availability, etc. The current methods primarily rely on protein sequences, especially utilizing evolutionary information. The significant improvement in predictions is attributed to deep learning methods. Additionally, sequence-based pretrained models and structure-based approaches are emerging as new trends.

MucLiPred: Multi-Level Contrastive Learning for Predicting Nucleic Acid Binding Residues of Proteins

Protein-molecule interactions play a crucial role in various biological functions, with their accurate prediction being pivotal for drug discovery and design processes. Traditional methods for predicting protein-molecule interactions are limited. Some can only predict interactions with a specific molecule, restricting their applicability, while others target multiple molecule types but fail to efficiently process diverse interaction information, leading to complexity and inefficiency. This study presents a novel deep learning model, MucLiPred, equipped with a dual contrastive learning mechanism aimed at improving the prediction of multiple molecule-protein interactions and the identification of potential molecule-binding residues. The residue-level paradigm focuses on differentiating binding from non-binding residues, illuminating detailed local interactions. The type-level paradigm, meanwhile, analyzes overarching contexts of molecule types, like DNA or RNA, ensuring that representations of identical molecule types gravitate closer in the representational space, bolstering the model's proficiency in discerning interaction motifs. This dual approach enables comprehensive multi-molecule predictions, elucidating the relationships among different molecule types and strengthening precise protein-molecule interaction predictions. Empirical evidence demonstrates MucLiPred's superiority over existing models in robustness and prediction accuracy. The integration of dual contrastive learning techniques amplifies its capability to detect potential molecule-binding residues with precision. Further optimization, separating representational and classification tasks, has markedly improved its performance. MucLiPred thus represents a significant advancement in protein-molecule interaction prediction, setting a new precedent for future research in this field.

DeepProSite: structure-aware protein binding site prediction using ESMFold and pretrained language model

MOTIVATION

Identifying the functional sites of a protein, such as the binding sites of proteins, peptides, or other biological components, is crucial for understanding related biological processes and drug design. However, existing sequence-based methods have limited predictive accuracy, as they only consider sequence-adjacent contextual features and lack structural information.

RESULTS

In this study, DeepProSite is presented as a new framework for identifying protein binding site that utilizes protein structure and sequence information. DeepProSite first generates protein structures from ESMFold and sequence representations from pretrained language models. It then uses Graph Transformer and formulates binding site predictions as graph node classifications. In predicting protein-protein/peptide binding sites, DeepProSite outperforms state-of-the-art sequence- and structure-based methods on most metrics. Moreover, DeepProSite maintains its performance when predicting unbound structures, in contrast to competing structure-based prediction methods. DeepProSite is also extended to the prediction of binding sites for nucleic acids and other ligands, verifying its generalization capability. Finally, an online server for predicting multiple types of residue is established as the implementation of the proposed DeepProSite.

AVAILABILITY AND IMPLEMENTATION

The datasets and source codes can be accessed at https://github.com/WeiLab-Biology/DeepProSite. The proposed DeepProSite can be accessed at https://inner.wei-group.net/DeepProSite/.

PepCNN deep learning tool for predicting peptide binding residues in proteins using sequence, structural, and language model features

Protein-peptide interactions play a crucial role in various cellular processes and are implicated in abnormal cellular behaviors leading to diseases such as cancer. Therefore, understanding these interactions is vital for both functional genomics and drug discovery efforts. Despite a significant increase in the availability of protein-peptide complexes, experimental methods for studying these interactions remain laborious, time-consuming, and expensive. Computational methods offer a complementary approach but often fall short in terms of prediction accuracy. To address these challenges, we introduce PepCNN, a deep learning-based prediction model that incorporates structural and sequence-based information from primary protein sequences. By utilizing a combination of half-sphere exposure, position specific scoring matrices from multiple-sequence alignment tool, and embedding from a pre-trained protein language model, PepCNN outperforms state-of-the-art methods in terms of specificity, precision, and AUC. The PepCNN software and datasets are publicly available at https://github.com/abelavit/PepCNN.git .

Machine Learning Advances in Predicting Peptide/Protein-Protein Interactions Based on Sequence Information for Lead Peptides Discovery

Peptides have shown increasing advantages and significant clinical value in drug discovery and development. With the development of high-throughput technologies and artificial intelligence (AI), machine learning (ML) methods for discovering new lead peptides have been expanded and incorporated into rational drug design. Predictions of peptide-protein interactions (PepPIs) and protein-protein interactions (PPIs) are both opportunities and challenges in computational biology, which will help to better understand the mechanisms of disease and provide the impetus for the discovery of lead peptides. This paper comprehensively reviews computational models for PepPI and PPI predictions. It begins with an introduction of various databases of peptide ligands and target proteins. Then it discusses data formats and feature representations for proteins and peptides. Furthermore, classical ML methods and emerging deep learning (DL) methods that can be used to train prediction models of PepPI and PPI are classified into four categories, and their advantages and disadvantages are analyzed. To assess the relative performance of different models, different validation protocols and evaluation indexes are discussed. The goal of this review is to help researchers quickly get started to develop computational frameworks using these integrated resources and eventually promote the discovery of lead peptides.

Docking cyclic peptides formed by a disulfide bond through a hierarchical strategy

MOTIVATION

Cyclization is a common strategy to enhance the therapeutic potential of peptides. Many cyclic peptide drugs have been approved for clinical use, in which the disulfide-driven cyclic peptide is one of the most prevalent categories. Molecular docking is a powerful computational method to predict the binding modes of molecules. For protein-cyclic peptide docking, a big challenge is considering the flexibility of peptides with conformers constrained by cyclization.

RESULTS

Integrating our efficient peptide 3D conformation sampling algorithm MODPEP2.0 and knowledge-based scoring function ITScorePP, we have proposed an extended version of our hierarchical peptide docking algorithm, named HPEPDOCK2.0, to predict the binding modes of the peptide cyclized through a disulfide against a protein. Our HPEPDOCK2.0 approach was extensively evaluated on diverse test sets and compared with the state-of-the-art cyclic peptide docking program AutoDock CrankPep (ADCP). On a benchmark dataset of 18 cyclic peptide-protein complexes, HPEPDOCK2.0 obtained a native contact fraction of above 0.5 for 61% of the cases when the top prediction was considered, compared with 39% for ADCP. On a larger test set of 25 cyclic peptide-protein complexes, HPEPDOCK2.0 yielded a success rate of 44% for the top prediction, compared with 20% for ADCP. In addition, HPEPDOCK2.0 was also validated on two other test sets of 10 and 11 complexes with apo and predicted receptor structures, respectively. HPEPDOCK2.0 is computationally efficient and the average running time for docking a cyclic peptide is about 34 min on a single CPU core, compared with 496 min for ADCP. HPEPDOCK2.0 will facilitate the study of the interaction between cyclic peptides and proteins and the development of therapeutic cyclic peptide drugs.

AVAILABILITY AND IMPLEMENTATION

http://huanglab.phys.hust.edu.cn/hpepdock/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Updated review of advances in microRNAs and complex diseases: taxonomy, trends and challenges of computational models

Since the problem proposed in late 2000s, microRNA-disease association (MDA) predictions have been implemented based on the data fusion paradigm. Integrating diverse data sources gains a more comprehensive research perspective, and brings a challenge to algorithm design for generating accurate, concise and consistent representations of the fused data. After more than a decade of research progress, a relatively simple algorithm like the score function or a single computation layer may no longer be sufficient for further improving predictive performance. Advanced model design has become more frequent in recent years, particularly in the form of reasonably combing multiple algorithms, a process known as model fusion. In the current review, we present 29 state-of-the-art models and introduce the taxonomy of computational models for MDA prediction based on model fusion and non-fusion. The new taxonomy exhibits notable changes in the algorithmic architecture of models, compared with that of earlier ones in the 2017 review by Chen et al. Moreover, we discuss the progresses that have been made towards overcoming the obstacles to effective MDA prediction since 2017 and elaborated on how future models can be designed according to a set of new schemas. Lastly, we analysed the strengths and weaknesses of each model category in the proposed taxonomy and proposed future research directions from diverse perspectives for enhancing model performance.

PepNN: a deep attention model for the identification of peptide binding sites

Protein-peptide interactions play a fundamental role in many cellular processes, but remain underexplored experimentally and difficult to model computationally. Here, we present PepNN-Struct and PepNN-Seq, structure and sequence-based approaches for the prediction of peptide binding sites on a protein. A main difficulty for the prediction of peptide-protein interactions is the flexibility of peptides and their tendency to undergo conformational changes upon binding. Motivated by this, we developed reciprocal attention to simultaneously update the encodings of peptide and protein residues while enforcing symmetry, allowing for information flow between the two inputs. PepNN integrates this module with modern graph neural network layers and a series of transfer learning steps are used during training to compensate for the scarcity of peptide-protein complex information. We show that PepNN-Struct achieves consistently high performance across different benchmark datasets. We also show that PepNN makes reasonable peptide-agnostic predictions, allowing for the identification of novel peptide binding proteins.

Predicting protein-peptide binding residues via interpretable deep learning

 

Identifying the protein-peptide binding residues is fundamentally important to understand the mechanisms of protein functions and explore drug discovery. Although several computational methods have been developed, they highly rely on third-party tools or information for feature design, easily resulting in low computational efficacy and suffering from low predictive performance. To address the limitations, we propose PepBCL, a novel BERT (Bidirectional Encoder Representation from Transformers)-based Contrastive Learning framework to predict the protein-Peptide binding residues based on protein sequences only. PepBCL is an end-to-end predictive model that is independent of designed features. Specifically, we introduce a well pre-trained protein language model that can automatically extract and learn high-latent representations of protein sequences relevant for protein structure and functions. Further, we design a novel contrastive learning module to optimize the feature representations of binding residues underlying the imbalanced dataset. We demonstrate that our proposed method significantly outperforms the state-of-the-art methods under benchmarking comparison, and achieves more robust performance. Moreover, we found that we further improve the performance via the integration of traditional features and our learnt features. Our results highlight the flexibility and adaptability of deep learning-based protein language model to capture both conserved and non-conserved sequential characteristics of peptide-binding residues. Interestingly, we demonstrate that peptide-binding residues in local sequential regions have more specific sequential patterns as compared with other protein-ligand binding residues, which potentially provides functional difference. Finally, to facilitate the use of our method, we establish an online predictive platform as the implementation of the proposed PepBCL, which is now available at http://server.wei-group.net/PepBCL/.

AVAILABILITY

https://github.com/Ruheng-W/PepBCL.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Efficient 3D conformer generation of cyclic peptides formed by a disulfide bond

Cyclic peptides formed by disulfide bonds have been one large group of common drug candidates in drug development. Structural information of a peptide is essential to understand its interaction with its target. However, due to the high flexibility of peptides, it is difficult to sample the near-native conformations of a peptide. Here, we have developed an extended version of our MODPEP approach, named MODPEP2.0, to fast generate the conformations of cyclic peptides formed by a disulfide bond. MODPEP2.0 builds the three-dimensional (3D) structures of a cyclic peptide from scratch by assembling amino acids one by one onto the cyclic fragment based on the constructed rotamer and cyclic backbone libraries. Being tested on a data set of 193 diverse cyclic peptides, MODPEP2.0 obtained a considerable advantage in both accuracy and computational efficiency, compared with other sampling algorithms including PEP-FOLD, ETKDG, and modified ETKDG (mETKDG). MODPEP2.0 achieved a high sampling accuracy with an average C\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\alpha$$\end{document}α RMSD of 2.20 Å and 1.66 Å when 10 and 100 conformations were considered, respectively, compared with 3.41 Å and 2.62 Å for PEP-FOLD, 3.44 Å and 3.16 Å for ETKDG, 3.09 Å and 2.72 Å for mETKDG. MODPEP2.0 also reproduced experimental peptide structures for 81.35% of the test cases when an ensemble of 100 conformations were considered, compared with 54.95%, 37.50% and 50.00% for PEP-FOLD, ETKDG, and mETKDG. MODPEP2.0 is computationally efficient and can generate 100 peptide conformations in one second. MODPEP2.0 will be useful in sampling cyclic peptide structures and modeling related protein-peptide interactions, facilitating the development of cyclic peptide drugs.

Machine learning assessment of the binding region as a tool for more efficient computational receptor-ligand docking

We present a combined computational approach to protein-ligand binding, which consists of two steps: (1) a deep neural network is used to locate a binding region on a target protein, and (2) molecular docking of a ligand is performed within the specified region to obtain the best pose using Autodock Vina. Our in-house designed neural network was trained using the PepBDB dataset. Although the training dataset consisted of protein-peptide complexes, we show that the approach is not limited to peptides, but also works remarkably well for a large class of non-peptide ligands. The results are compared with those in which the binding region (first step) was provided by Accluster. In cases where no prior experimental data on the binding region are available, our deep neural network provides a fast and effective alternative to classical software for its localization. Our code is available at https://github.com/mksmd/NNforDocking.

Neuroepigenetic Mechanisms of Action of Ultrashort Peptides in Alzheimer's Disease

Epigenetic regulation of gene expression is necessary for maintaining higher-order cognitive functions (learning and memory). The current understanding of the role of epigenetics in the mechanism of Alzheimer’s disease (AD) is focused on DNA methylation, chromatin remodeling, histone modifications, and regulation of non-coding RNAs. The pathogenetic links of this disease are the misfolding and aggregation of tau protein and amyloid peptides, mitochondrial dysfunction, oxidative stress, impaired energy metabolism, destruction of the blood–brain barrier, and neuroinflammation, all of which lead to impaired synaptic plasticity and memory loss. Ultrashort peptides are promising neuroprotective compounds with a broad spectrum of activity and without reported side effects. The main aim of this review is to analyze the possible epigenetic mechanisms of the neuroprotective action of ultrashort peptides in AD. The review highlights the role of short peptides in the AD pathophysiology. We formulate the hypothesis that peptide regulation of gene expression can be mediated by the interaction of short peptides with histone proteins, cis- and transregulatory DNA elements and effector molecules (DNA/RNA-binding proteins and non-coding RNA). The development of therapeutic agents based on ultrashort peptides may offer a promising addition to the multifunctional treatment of AD.

Oncological drug discovery: AI meets structure-based computational research

The integration of machine learning and structure-based methods has proven valuable in the past as a way to prioritize targets and compounds in early drug discovery. In oncological research, these methods can be highly beneficial in addressing the diversity of neoplastic diseases portrayed by the different hallmarks of cancer. Here, we review six use case scenarios for integrated computational methods, namely driver prediction, computational mutagenesis, (off)-target prediction, binding site prediction, virtual screening, and allosteric modulation analysis. We address the heterogeneity of integration approaches and individual methods, while acknowledging their current limitations and highlighting their potential to bring drugs for personalized oncological therapies to the market faster.

Protein-DNA/RNA interactions: Machine intelligence tools and approaches in the era of artificial intelligence and big data

With the development of artificial intelligence technologies and the availability of large amounts of biological data, computational methods for proteomics have undergone a developmental process from traditional machine learning to deep learning. This review focuses on computational approaches and tools for the prediction of protein-DNA/RNA interactions using machine intelligence techniques. We provide an overview of the development progress of computational methods and summarize the advantages and shortcomings of these methods. We further compiled applications in tasks related to the protein-DNA/RNA interactions, and pointed out possible future application trends. Moreover, biological sequence-digitizing representation strategies used in different types of computational methods are also summarized and discussed. This article is protected by copyright. All rights reserved.

A deep-learning framework for multi-level peptide-protein interaction prediction

Peptide-protein interactions are involved in various fundamental cellular functions and their identification is crucial for designing efficacious peptide therapeutics. Recently, a number of computational methods have been developed to predict peptide-protein interactions. However, most of the existing prediction approaches heavily depend on high-resolution structure data. Here, we present a deep learning framework for multi-level peptide-protein interaction prediction, called CAMP, including binary peptide-protein interaction prediction and corresponding peptide binding residue identification. Comprehensive evaluation demonstrated that CAMP can successfully capture the binary interactions between peptides and proteins and identify the binding residues along the peptides involved in the interactions. In addition, CAMP outperformed other state-of-the-art methods on binary peptide-protein interaction prediction. CAMP can serve as a useful tool in peptide-protein interaction prediction and identification of important binding residues in the peptides, which can thus facilitate the peptide drug discovery process.

Protein-Peptide Binding Site Detection Using 3D Convolutional Neural Networks

Peptides and peptide-based molecules represent a promising therapeutic modality targeting intracellular protein-protein interactions, potentially combining the beneficial properties of biologics and small-molecule drugs. Protein-peptide complexes occupy a unique niche of interaction interfaces with respect to protein-protein and protein-small molecule complexes. Protein-peptide binding site identification resembles image object detection, a field that had been revolutionalized with computer vision techniques. We present a new protein-peptide binding site detection method called BiteNet_Pp by harnessing the power of 3D convolutional neural network. Our method employs a tensor-based representation of spatial protein structures, which is fed to 3D convolutional neural network, resulting in probability scores and coordinates of the binding "hot spots" in the input structures. We used the domain adaptation technique to fine-tune model trained on protein-small molecule complexes using a manually curated set of protein-peptide structures. BiteNet_Pp consistently outperforms existing state-of-the-art methods in the independent test benchmark. It takes less than a second to analyze a single-protein structure, making BiteNet_Pp suitable for the large-scale analysis of protein-peptide binding sites.

Computational approaches to predict protein functional families and functional sites

Understanding the mechanisms of protein function is indispensable for many biological applications, such as protein engineering and drug design. However, experimental annotations are sparse, and therefore, theoretical strategies are needed to fill the gap. Here, we present the latest developments in building functional subclassifications of protein superfamilies and using evolutionary conservation to detect functional determinants, for example, catalytic-, binding- and specificity-determining residues important for delineating the functional families. We also briefly review other features exploited for functional site detection and new machine learning strategies for combining multiple features.

Evaluating machine learning methodologies for identification of cancer driver genes

Cancer is driven by distinctive sorts of changes and basic variations in genes. Recognizing cancer driver genes is basic for accurate oncological analysis. Numerous methodologies to distinguish and identify drivers presently exist, but efficient tools to combine and optimize them on huge datasets are few. Most strategies for prioritizing transformations depend basically on frequency-based criteria. Strategies are required to dependably prioritize organically dynamic driver changes over inert passengers in high-throughput sequencing cancer information sets. This study proposes a model namely PCDG-Pred which works as a utility capable of distinguishing cancer driver and passenger attributes of genes based on sequencing data. Keeping in view the significance of the cancer driver genes an efficient method is proposed to identify the cancer driver genes. Further, various validation techniques are applied at different levels to establish the effectiveness of the model and to obtain metrics like accuracy, Mathew's correlation coefficient, sensitivity, and specificity. The results of the study strongly indicate that the proposed strategy provides a fundamental functional advantage over other existing strategies for cancer driver genes identification. Subsequently, careful experiments exhibit that the accuracy metrics obtained for self-consistency, independent set, and cross-validation tests are 91.08%., 87.26%, and 92.48% respectively.

De novo Prediction of Moonlighting Proteins Using Multimodal Deep Ensemble Learning

Moonlighting proteins (MPs) are a special type of protein with multiple independent functions. MPs play vital roles in cellular regulation, diseases, and biological pathways. At present, very few MPs have been discovered by biological experiments. Due to the lack of data sample, computation-based methods to identify MPs are limited. Currently, there is no de-novo prediction method for MPs. Therefore, systematic research and identification of MPs are urgently required. In this paper, we propose a multimodal deep ensemble learning architecture, named MEL-MP, which is the first de novo computation model for predicting MPs. First, we extract four sequence-based features: primary protein sequence information, evolutionary information, physical and chemical properties, and secondary protein structure information. Second, we select specific classifiers for each kind of feature. Finally, we apply the stacked ensemble to integrate the output of each classifier. Through comprehensive model selection and cross-validation experiments, it is shown that specific classifiers for specific feature types can achieve superior performance. For validating the effectiveness of the fusion-based stacked ensemble, different feature fusion strategies including direct combination and a multimodal deep auto-encoder are used for comparative purposes. MEL-MP is shown to exhibit superior prediction performance (F-score = 0.891), surpassing the existing machine learning model, MPFit (F-score = 0.784). In addition, MEL-MP is leveraged to predict the potential MPs among all human proteins. Furthermore, the distribution of predicted MPs on different chromosomes, the evolution of MPs, the association of MPs with diseases, and the functional enrichment of MPs are also explored. Finally, for maximum convenience, a user-friendly web server is available at: http://ml.csbg-jlu.site/mel-mp/.

A Novel Machine Learning Strategy for the Prediction of Antihypertensive Peptides Derived from Food with High Efficiency

Strategies to screen antihypertensive peptides with high throughput and rapid speed will doubtlessly contribute to the treatment of hypertension. Food-derived antihypertensive peptides can reduce blood pressure without side effects. In the present study, a novel model based on the eXtreme Gradient Boosting (XGBoost) algorithm was developed and compared with the dominating machine learning models. To further reflect on the reliability of the method in a real situation, the optimized XGBoost model was utilized to predict the antihypertensive degree of the k-mer peptides cutting from six key proteins in bovine milk, and the peptide-protein docking technology was introduced to verify the findings. The results showed that the XGBoost model achieved outstanding performance, with an accuracy of 86.50% and area under the receiver operating characteristic curve of 94.11%, which were better than the other models. Using the XGBoost model, the prediction of antihypertensive peptides derived from milk protein was consistent with the peptide-protein docking results, and was more efficient. Our results indicate that using the XGBoost algorithm as a novel auxiliary tool is feasible to screen for antihypertensive peptides derived from food, with high throughput and high efficiency.

Methods for Molecular Modelling of Protein Complexes

Biological processes are often mediated by complexes formed between proteins and various biomolecules. The 3D structures of such protein-biomolecule complexes provide insights into the molecular mechanism of their action. The structure of these complexes can be predicted by various computational methods. Choosing an appropriate method for modelling depends on the category of biomolecule that a protein interacts with and the availability of structural information about the protein and its interacting partner. We intend for the contents of this chapter to serve as a guide as to what software would be the most appropriate for the type of data at hand and the kind of 3D complex structure required. Particularly, we have dealt with protein-small molecule ligand, protein-peptide, protein-protein, and protein-nucleic acid interactions.Most, if not all, model building protocols perform some sampling and scoring. Typically, several alternate conformations and configurations of the interactors are sampled. Each such sample is then scored for optimization. To boost the confidence in these predicted models, their assessment using other independent scoring schemes besides the inbuilt/default ones would prove to be helpful. This chapter also lists such software and serves as a guide to gauge the fidelity of modelled structures of biomolecular complexes.

SPRINT-Gly: predicting N- and O-linked glycosylation sites of human and mouse proteins by using sequence and predicted structural properties

MOTIVATION

Protein glycosylation is one of the most abundant post-translational modifications that plays an important role in immune responses, intercellular signaling, inflammation and host-pathogen interactions. However, due to the poor ionization efficiency and microheterogeneity of glycopeptides identifying glycosylation sites is a challenging task, and there is a demand for computational methods. Here, we constructed the largest dataset of human and mouse glycosylation sites to train deep learning neural networks and support vector machine classifiers to predict N-/O-linked glycosylation sites, respectively.

RESULTS

The method, called SPRINT-Gly, achieved consistent results between ten-fold cross validation and independent test for predicting human and mouse glycosylation sites. For N-glycosylation, a mouse-trained model performs equally well in human glycoproteins and vice versa, however, due to significant differences in O-linked sites separate models were generated. Overall, SPRINT-Gly is 18% and 50% higher in Matthews correlation coefficient than the next best method compared in N-linked and O-linked sites, respectively. This improved performance is due to the inclusion of novel structure and sequence-based features.

AVAILABILITY AND IMPLEMENTATION

http://sparks-lab.org/server/SPRINT-Gly/.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

FRnet-DTI: Deep convolutional neural network for drug-target interaction prediction

The task of drug-target interaction prediction holds significant importance in pharmacology and therapeutic drug design. In this paper, we present FRnet-DTI, an auto-encoder based feature manipulation and a convolutional neural network based classifier for drug target interaction prediction. Two convolutional neural networks are proposed: FRnet-Encode and FRnet-Predict. Here, one model is used for feature manipulation and the other one for classification. Using the first method FRnet-Encode, we generate 4096 features for each of the instances in each of the datasets and use the second method, FRnet-Predict, to identify interaction probability employing those features. We have tested our method on four gold standard datasets extensively used by other researchers. Experimental results shows that our method significantly improves over the state-of-the-art method on three out of four drug-target interaction gold standard datasets on both area under curve for Receiver Operating Characteristic (auROC) and area under Precision Recall curve (auPR) metric. We also introduce twenty new potential drug-target pairs for interaction based on high prediction scores. The source codes and implementation details of our methods are available from https://github.com/farshidrayhanuiu/FRnet-DTI/ and also readily available to use as an web application from http://farshidrayhan.pythonanywhere.com/FRnet-DTI/.

To Improve Protein Sequence Profile Prediction through Image Captioning on Pairwise Residue Distance Map

Protein sequence profile prediction aims to generate multiple sequences from structural information to advance the protein design. Protein sequence profile can be computationally predicted by energy-based or fragment-based methods. By integrating these methods with neural networks, our previous method, SPIN2, has achieved a sequence recovery rate of 34%. However, SPIN2 employed only one-dimensional (1D) structural properties that are not sufficient to represent three-dimensional (3D) structures. In this study, we represented 3D structures by 2D maps of pairwise residue distances and developed a new method (SPROF) to predict protein sequence profiles based on an image captioning learning frame. To our best knowledge, this is the first method to employ a 2D distance map for predicting protein properties. SPROF achieved 39.8% in sequence recovery of residues on the independent test set, representing a 5.2% improvement over SPIN2. We also found the sequence recovery increased with the number of their neighbored residues in 3D structural space, indicating that our method can effectively learn long-range information from the 2D distance map. Thus, such network architecture using a 2D distance map is expected to be useful for other 3D structure-based applications, such as binding site prediction, protein function prediction, and protein interaction prediction. The online server and the source code is available at http://biomed.nscc-gz.cn and https://github.com/biomed-AI/SPROF , respectively.

SubMito-XGBoost: predicting protein submitochondrial localization by fusing multiple feature information and eXtreme gradient boosting

Motivation

Mitochondria are an essential organelle in most eukaryotes. They not only play an important role in energy metabolism but also take part in many critical cytopathological processes. Abnormal mitochondria can trigger a series of human diseases, such as Parkinson's disease, multifactor disorder and Type-II diabetes. Protein submitochondrial localization enables the understanding of protein function in studying disease pathogenesis and drug design.

Results

We proposed a new method, SubMito-XGBoost, for protein submitochondrial localization prediction. Three steps are included: (i) the g-gap dipeptide composition (g-gap DC), pseudo-amino acid composition (PseAAC), auto-correlation function (ACF) and Bi-gram position-specific scoring matrix (Bi-gram PSSM) are employed to extract protein sequence features, (ii) Synthetic Minority Oversampling Technique (SMOTE) is used to balance samples, and the ReliefF algorithm is applied for feature selection and (iii) the obtained feature vectors are fed into XGBoost to predict protein submitochondrial locations. SubMito-XGBoost has obtained satisfactory prediction results by the leave-one-out-cross-validation (LOOCV) compared with existing methods. The prediction accuracies of the SubMito-XGBoost method on the two training datasets M317 and M983 were 97.7% and 98.9%, which are 2.8–12.5% and 3.8–9.9% higher than other methods, respectively. The prediction accuracy of the independent test set M495 was 94.8%, which is significantly better than the existing studies. The proposed method also achieves satisfactory predictive performance on plant and non-plant protein submitochondrial datasets. SubMito-XGBoost also plays an important role in new drug design for the treatment of related diseases.

Availability and implementation

The source codes and data are publicly available at https://github.com/QUST-AIBBDRC/SubMito-XGBoost/.

Supplementary information

Supplementary data are available at Bioinformatics online.

A network embedding-based multiple information integration method for the MiRNA-disease association prediction

BACKGROUND

MiRNAs play significant roles in many fundamental and important biological processes, and predicting potential miRNA-disease associations makes contributions to understanding the molecular mechanism of human diseases. Existing state-of-the-art methods make use of miRNA-target associations, miRNA-family associations, miRNA functional similarity, disease semantic similarity and known miRNA-disease associations, but the known miRNA-disease associations are not well exploited.

RESULTS

In this paper, a network embedding-based multiple information integration method (NEMII) is proposed for the miRNA-disease association prediction. First, known miRNA-disease associations are formulated as a bipartite network, and the network embedding method Structural Deep Network Embedding (SDNE) is adopted to learn embeddings of nodes in the bipartite network. Second, the embedding representations of miRNAs and diseases are combined with biological features about miRNAs and diseases (miRNA-family associations and disease semantic similarities) to represent miRNA-disease pairs. Third, the prediction models are constructed based on the miRNA-disease pairs by using the random forest. In computational experiments, NEMII achieves high-accuracy performances and outperforms other state-of-the-art methods: GRNMF, NTSMDA and PBMDA. The usefulness of NEMII is further validated by case studies. The studies demonstrate the great potential of network embedding method for the miRNA-disease association prediction, and SDNE outperforms other popular network embedding methods: DeepWalk, High-Order Proximity preserved Embedding (HOPE) and Laplacian Eigenmaps (LE).

CONCLUSION

We propose a new method, named NEMII, for predicting miRNA-disease associations, which has great potential to benefit the field of miRNA-disease association prediction.

Discovery of receptor-ligand interfaces in the immunoglobulin superfamily

Cell-surface-anchored immunoglobulin superfamily (IgSF) proteins are widespread throughout the human proteome, forming crucial components of diverse biological processes including immunity, cell-cell adhesion, and carcinogenesis. IgSF proteins generally function through protein-protein interactions carried out between extracellular, membrane-bound proteins on adjacent cells, known as trans-binding interfaces. These protein-protein interactions constitute a class of pharmaceutical targets important in the treatment of autoimmune diseases, chronic infections, and cancer. A molecular-level understanding of IgSF protein-protein interactions would greatly benefit further drug development. A critical step toward this goal is the reliable identification of IgSF trans-binding interfaces. We propose a novel combination of structure and sequence information to identify trans-binding interfaces in IgSF proteins. We developed a structure-based binding interface prediction approach that can identify broad regions of the protein surface that encompass the binding interfaces and suggests that IgSF proteins possess binding supersites. These interfaces could theoretically be pinpointed using sequence-based conservation analysis, with performance approaching the theoretical upper limit of binding interface prediction accuracy, but achieving this in practice is limited by the current ability to identify an appropriate multiple sequence alignment for conservation analysis. However, an important contribution of combining the two orthogonal methods is that agreement between these approaches can estimate the reliability of the predictions. This approach was benchmarked on the set of 22 IgSF proteins with experimentally solved structures in complex with their ligands. Additionally, we provide structure-based predictions and reliability scores for the 62 IgSF proteins with known structure but yet uncharacterized binding interfaces.

Predicting prognosis of endometrioid endometrial adenocarcinoma on the basis of gene expression and clinical features using Random Forest

Traditional clinical features are not sufficient to accurately judge the prognosis of endometrioid endometrial adenocarcinoma (EEA). Molecular biological characteristics and traditional clinical features are particularly important in the prognosis of EEA. The aim of the present study was to establish a predictive model that considers genes and clinical features for the prognosis of EEA. The clinical and RNA sequencing expression data of EEA were derived from samples from The Cancer Genome Atlas (TCGA) and Peking University People's Hospital (PKUPH; Beijing, China). Samples from TCGA were used as the training set, and samples from the PKUPH were used as the testing set. Variable selection using Random Forests (VSURF) was used to select the genes and clinical features on the basis of TCGA samples. The RF classification method was used to establish the prediction model. Kaplan-Meier curves were tested with the log-rank test. The results from this study demonstrated that on the basis of TCGA samples, 11 genes and the grade were selected as the input features. In the training set, the out-of-bag (OOB) error of RF model-1, which was established using the '11 genes', was 0.15; the OOB error of RF model-2, which was established using the 'grade', was 0.39; and the OOB error of RF model-3, established using the '11 genes and grade', was 0.15. In the testing set, the classification accuracy of RF model-1, model-2 and model-3 was 71.43, 66.67 and 80.95%, respectively. In conclusion, to the best of our knowledge, the VSURF was used to select features relevant to EEA prognosis, and an EEA predictive model combining genes and traditional features was established for the first time in the present study. The prediction accuracy of the RF model on the basis of the 11 genes and grade was markedly higher than that of the RF models established by either the 11 genes or grade alone.

A Comprehensive Review on Current Advances in Peptide Drug Development and Design

Protein-protein interactions (PPIs) execute many fundamental cellular functions and have served as prime drug targets over the last two decades. Interfering intracellular PPIs with small molecules has been extremely difficult for larger or flat binding sites, as antibodies cannot cross the cell membrane to reach such target sites. In recent years, peptides smaller size and balance of conformational rigidity and flexibility have made them promising candidates for targeting challenging binding interfaces with satisfactory binding affinity and specificity. Deciphering and characterizing peptide-protein recognition mechanisms is thus central for the invention of peptide-based strategies to interfere with endogenous protein interactions, or improvement of the binding affinity and specificity of existing approaches. Importantly, a variety of computation-aided rational designs for peptide therapeutics have been developed, which aim to deliver comprehensive docking for peptide-protein interaction interfaces. Over 60 peptides have been approved and administrated globally in clinics. Despite this, advances in various docking models are only on the merge of making their contribution to peptide drug development. In this review, we provide (i) a holistic overview of peptide drug development and the fundamental technologies utilized to date, and (ii) an updated review on key developments of computational modeling of peptide-protein interactions (PepPIs) with an aim to assist experimental biologists exploit suitable docking methods to advance peptide interfering strategies against PPIs.

Protein-protein binding supersites

The lack of a deep understanding of how proteins interact remains an important roadblock in advancing efforts to identify binding partners and uncover the corresponding regulatory mechanisms of the functions they mediate. Understanding protein-protein interactions is also essential for designing specific chemical modifications to develop new reagents and therapeutics. We explored the hypothesis of whether protein interaction sites serve as generic biding sites for non-cognate protein ligands, just as it has been observed for small-molecule-binding sites in the past. Using extensive computational docking experiments on a test set of 241 protein complexes, we found that indeed there is a strong preference for non-cognate ligands to bind to the cognate binding site of a receptor. This observation appears to be robust to variations in docking programs, types of non-cognate protein probes, sizes of binding patches, relative sizes of binding patches and full-length proteins, and the exploration of obligate and non-obligate complexes. The accuracy of the docking scoring function appears to play a role in defining the correct site. The frequency of interaction of unrelated probes recognizing the binding interface was utilized in a simple prediction algorithm that showed accuracy competitive with other state of the art methods.

The choice of sequence homologs included in multiple sequence alignments has a dramatic impact on evolutionary conservation analysis

Motivation

The analysis of sequence conservation patterns has been widely utilized to identify functionally important (catalytic and ligand-binding) protein residues for over a half-century. Despite decades of development, on average state-of-the-art non-template-based functional residue prediction methods must predict ∼25% of a protein's total residues to correctly identify half of the protein's functional site residues. The overwhelming proportion of false positives results in reported 'F-Scores' of ∼0.3. We investigated the limits of current approaches, focusing on the so-far neglected impact of the specific choice of homologs included in multiple sequence alignments (MSAs).

Results

The limits of conservation-based functional residue prediction were explored by surveying the binding sites of 1023 proteins. A straightforward conservation analysis of MSAs composed of randomly selected homologs sampled from a PSI-BLAST search achieves average F-Scores of ∼0.3, a performance matching that reported by state-of-the-art methods, which often consider additional features for the prediction in a machine learning setting. Interestingly, we found that a simple combinatorial MSA sampling algorithm will in almost every case produce an MSA with an optimal set of homologs whose conservation analysis reaches average F-Scores of ∼0.6, doubling state-of-the-art performance. We also show that this is nearly at the theoretical limit of possible performance given the agreement between different binding site definitions. Additionally, we showcase the progress in this direction made by Selection of Alignment by Maximal Mutual Information (SAMMI), an information-theory-based approach to identifying biologically informative MSAs. This work highlights the importance and the unused potential of optimally composed MSAs for conservation analysis.

Supplementary information

Supplementary data are available at Bioinformatics online.

Hierarchical Flexible Peptide Docking by Conformer Generation and Ensemble Docking of Peptides

Given the importance of peptide-mediated protein interactions in cellular processes, protein-peptide docking has received increasing attention. Here, we have developed a Hierarchical flexible Peptide Docking approach through fast generation and ensemble docking of peptide conformations, which is referred to as HPepDock. Tested on the LEADS-PEP benchmark data set of 53 diverse complexes with peptides of 3-12 residues, HPepDock performed significantly better than the 11 docking protocols of five small-molecule docking programs (DOCK, AutoDock, AutoDock Vina, Surflex, and GOLD) in predicting near-native binding conformations. HPepDock was also evaluated on the 19 bound/unbound and 10 unbound/unbound protein-peptide complexes of the Glide SP-PEP benchmark and showed an overall better performance than Glide SP-PEP+MM-GBSA and FlexPepDock in both bound and unbound docking. HPepDock is computationally efficient, and the average running time for docking a peptide is ∼15 min with the range from about 1 min for short peptides to around 40 min for long peptides.

iDTI-ESBoost: Identification of Drug Target Interaction Using Evolutionary and Structural Features with Boosting

Prediction of new drug-target interactions is critically important as it can lead the researchers to find new uses for old drugs and to disclose their therapeutic profiles or side effects. However, experimental prediction of drug-target interactions is expensive and time-consuming. As a result, computational methods for predictioning new drug-target interactions have gained a tremendous interest in recent times. Here we present iDTI-ESBoost, a prediction model for identification of drug-target interactions using evolutionary and structural features. Our proposed method uses a novel data balancing and boosting technique to predict drug-target interaction. On four benchmark datasets taken from a gold standard data, iDTI-ESBoost outperforms the state-of-the-art methods in terms of area under receiver operating characteristic (auROC) curve. iDTI-ESBoost also outperforms the latest and the best-performing method found in the literature in terms of area under precision recall (auPR) curve. This is significant as auPR curves are argued as suitable metric for comparison for imbalanced datasets similar to the one studied here. Our reported results show the effectiveness of the classifier, balancing methods and the novel features incorporated in iDTI-ESBoost. iDTI-ESBoost is a novel prediction method that has for the first time exploited the structural features along with the evolutionary features to predict drug-protein interactions. We believe the excellent performance of iDTI-ESBoost both in terms of auROC and auPR would motivate the researchers and practitioners to use it to predict drug-target interactions. To facilitate that, iDTI-ESBoost is implemented and made publicly available at: http://farshidrayhan.pythonanywhere.com/iDTI-ESBoost/.