Improving Protein Gamma-Turn Prediction Using Inception Capsule Networks

Evaluation of the Effectiveness of Derived Features of AlphaFold2 on Single-Sequence Protein Binding Site Prediction

Simple Summary

With the development of artificial intelligence, researchers can roughly predict the crystal structure of a protein by computer without the need for biological experiments, which provides new ideas and solutions to problems, such as protein-protein interaction and drug-target predictions. In this study, we proposed strategies to combine predicted protein structures with deep learning networks and evaluated them on different protein binding site prediction tasks. Our computational experiment results showed that all proposed strategies could effectively encode structural information for deep learning models.

Abstract

Though AlphaFold2 has attained considerably high precision on protein structure prediction, it is reported that directly inputting coordinates into deep learning networks cannot achieve desirable results on downstream tasks. Thus, how to process and encode the predicted results into effective forms that deep learning models can understand to improve the performance of downstream tasks is worth exploring. In this study, we tested the effects of five processing strategies of coordinates on two single-sequence protein binding site prediction tasks. These five strategies are spatial filtering, the singular value decomposition of a distance map, calculating the secondary structure feature, and the relative accessible surface area feature of proteins. The computational experiment results showed that all strategies were suitable and effective methods to encode structural information for deep learning models. In addition, by performing a case study of a mutated protein, we showed that the spatial filtering strategy could introduce structural changes into HHblits profiles and deep learning networks when protein mutation happens. In sum, this work provides new insight into the downstream tasks of protein-molecule interaction prediction, such as predicting the binding residues of proteins and estimating the effects of mutations.

Active disease-related compound identification based on capsule network

Pneumonia, especially corona virus disease 2019 (COVID-19), can lead to serious acute lung injury, acute respiratory distress syndrome, multiple organ failure and even death. Thus it is an urgent task for developing high-efficiency, low-toxicity and targeted drugs according to pathogenesis of coronavirus. In this paper, a novel disease-related compound identification model-based capsule network (CapsNet) is proposed. According to pneumonia-related keywords, the prescriptions and active components related to the pharmacological mechanism of disease are collected and extracted in order to construct training set. The features of each component are extracted as the input layer of capsule network. CapsNet is trained and utilized to identify the pneumonia-related compounds in Qingre Jiedu injection. The experiment results show that CapsNet can identify disease-related compounds more accurately than SVM, RF, gcForest and forgeNet.

MultiCapsNet: A General Framework for Data Integration and Interpretable Classification

The latest progresses of experimental biology have generated a large number of data with different formats and lengths. Deep learning is an ideal tool to deal with complex datasets, but its inherent “black box” nature needs more interpretability. At the same time, traditional interpretable machine learning methods, such as linear regression or random forest, could only deal with numerical features instead of modular features often encountered in the biological field. Here, we present MultiCapsNet (https://github.com/wanglf19/MultiCapsNet), a new deep learning model built on CapsNet and scCapsNet, which possesses the merits such as easy data integration and high model interpretability. To demonstrate the ability of this model as an interpretable classifier to deal with modular inputs, we test MultiCapsNet on three datasets with different data type and application scenarios. Firstly, on the labeled variant call dataset, MultiCapsNet shows a similar classification performance with neural network model, and provides importance scores for data sources directly without an extra importance determination step required by the neural network model. The importance scores generated by these two models are highly correlated. Secondly, on single cell RNA sequence (scRNA-seq) dataset, MultiCapsNet integrates information about protein-protein interaction (PPI), and protein-DNA interaction (PDI). The classification accuracy of MultiCapsNet is comparable to the neural network and random forest model. Meanwhile, MultiCapsNet reveals how each transcription factor (TF) or PPI cluster node contributes to classification of cell type. Thirdly, we made a comparison between MultiCapsNet and SCENIC. The results show several cell type relevant TFs identified by both methods, further proving the validity and interpretability of the MultiCapsNet.

Quantitative Assessment of Chirality of Protein Secondary Structures and Phenylalanine Peptide Nanotubes

In this study we consider the features of spatial-structure formation in proteins and their application in bioengineering. Methods for the quantitative assessment of the chirality of regular helical and irregular structures of proteins are presented. The features of self-assembly of phenylalanine (F) into peptide nanotubes (PNT), which form helices of different chirality, are also analyzed. A method is proposed for calculating the magnitude and sign of the chirality of helix-like peptide nanotubes using a sequence of vectors for the dipole moments of individual peptides.

Protein secondary structure assignment using pc-polyline and convolutional neural network

MOTIVATION

The assignment of protein secondary structure elements (SSEs) underpins structural analysis and prediction. The backbone of a protein could be adequately represented using a pc-polyline that passes through the centers of its peptide planes. One salient feature of pc-polyline representation is that the secondary structure of a protein becomes recognizable in a matrix whose elements are the pairwise distances between two peptide plane centers. Thus, a pc-polyline could in turn be used to assign SSEs.

RESULTS

Using convolutional neural network (CNN) here we confirm that a pc-polyline indeed contains enough information for it to be used for the accurate assignments of the six SSE types: α-helix, β-sheet, β-bulge, 310 -helix, turn and loop. The applications to three large data sets show that the assignments by our CNN-based p2psse program agree very well with those by dssp, stride and quite well with those by five other programs. The analyses of their SSE assignments raise some general questions about the characterizations of protein secondary structure. In particular the analyses illustrate the difficulty with giving a quantitative and consistent definition for each of the six SSE types especially for 310 -helix, β-bulge, turn or loop in terms of either backbone H-bond patterns, or backbone dihedral angles, or Cα -polyline or pc-polyline. The difficulty suggests that the SSE space though being dominated by the regions for the six SSE types is to a certain degree continuous.

AVAILABILITY

The program is available at https://github.com/wlincong/p2pSSE.

TMP- SSurface2: A Novel Deep Learning-Based Surface Accessibility Predictor for Transmembrane Protein Sequence

Transmembrane protein (TMP) is an important type of membrane protein that is involved in various biological membranes related biological processes. As major drug targets, TMPs’ surfaces are highly concerned to form the structural biases of their material-bindings for drugs or other biological molecules. However, the quantity of determinate TMP structures is still far less than the requirements, while artificial intelligence technologies provide a promising approach to accurately identify the TMP surfaces, merely depending on their sequences without any feature-engineering. For this purpose, we present an updated TMP surface residue predictor TMP-SSurface2 which achieved an even higher prediction accuracy compared to our previous version. The method uses an attention-enhanced Bidirectional Long Short Term Memory (BiLSTM) network, benefiting from its efficient learning capability, some useful latent information is abstracted from protein sequences, thus improving the Pearson correlation coefficients (CC) value performance of the old version from 0.58 to 0.66 on an independent test dataset. The results demonstrate that TMP-SSurface2 is efficient in predicting the surface of transmembrane proteins, representing new progress in transmembrane protein structure modeling based on primary sequences. TMP-SSurface2 is freely accessible at https://github.com/NENUBioCompute/TMP-SSurface-2.0.

TMPSS: A Deep Learning-Based Predictor for Secondary Structure and Topology Structure Prediction of Alpha-Helical Transmembrane Proteins

Alpha transmembrane proteins (αTMPs) profoundly affect many critical biological processes and are major drug targets due to their pivotal protein functions. At present, even though the non-transmembrane secondary structures are highly relevant to the biological functions of αTMPs along with their transmembrane structures, they have not been unified to be studied yet. In this study, we present a novel computational method, TMPSS, to predict the secondary structures in non-transmembrane parts and the topology structures in transmembrane parts of αTMPs. TMPSS applied a Convolutional Neural Network (CNN), combined with an attention-enhanced Bidirectional Long Short-Term Memory (BiLSTM) network, to extract the local contexts and long-distance interdependencies from primary sequences. In addition, a multi-task learning strategy was used to predict the secondary structures and the transmembrane helixes. TMPSS was thoroughly trained and tested against a non-redundant independent dataset, where the Q3 secondary structure prediction accuracy achieved 78% in the non-transmembrane region, and the accuracy of the transmembrane region prediction achieved 90%. In sum, our method showcased a unified model for predicting the secondary structure and topology structure of αTMPs by only utilizing features generated from primary sequences and provided a steady and fast prediction, which promisingly improves the structural studies on αTMPs.

Deep learning for mining protein data

The recent emergence of deep learning to characterize complex patterns of protein big data reveals its potential to address the classic challenges in the field of protein data mining. Much research has revealed the promise of deep learning as a powerful tool to transform protein big data into valuable knowledge, leading to scientific discoveries and practical solutions. In this review, we summarize recent publications on deep learning predictive approaches in the field of mining protein data. The application architectures of these methods include multilayer perceptrons, stacked autoencoders, deep belief networks, two- or three-dimensional convolutional neural networks, recurrent neural networks, graph neural networks, and complex neural networks and are described from five perspectives: residue-level prediction, sequence-level prediction, three-dimensional structural analysis, interaction prediction, and mass spectrometry data mining. The advantages and deficiencies of these architectures are presented in relation to various tasks in protein data mining. Additionally, some practical issues and their future directions are discussed, such as robust deep learning for protein noisy data, architecture optimization for specific tasks, efficient deep learning for limited protein data, multimodal deep learning for heterogeneous protein data, and interpretable deep learning for protein understanding. This review provides comprehensive perspectives on general deep learning techniques for protein data analysis.

MUFold-SSW: a new web server for predicting protein secondary structures, torsion angles and turns

MOTIVATION

Protein secondary structure and backbone torsion angle prediction can provide important information for predicting protein 3D structures and protein functions. Our new methods MUFold-SS, MUFold-Angle, MUFold-BetaTurn and MUFold-GammaTurn, developed based on advanced deep neural networks, achieved state-of-the-art performance for predicting secondary structures, backbone torsion angles, beta-turns and gamma-turns, respectively. An easy-to-use web service will provide the community a convenient way to use these methods for research and development.

RESULTS

MUFold-SSW, a new web server, is presented. It provides predictions of protein secondary structures, torsion angles, beta-turns and gamma-turns for a given protein sequence. This server implements MUFold-SS, MUFold-Angle, MUFold-BetaTurn and MUFold-GammaTurn, which performed well for both easy targets (proteins with weak sequence similarity in PDB) and hard targets (proteins without detectable similarity in PDB) in various experimental tests, achieving results better than or comparable with those of existing methods.

AVAILABILITY AND IMPLEMENTATION

MUFold-SSW is accessible at http://mufold.org/mufold-ss-angle.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.