Protein Secondary Structure Prediction: A Review of Progress and Directions

AttABseq: an attention-based deep learning prediction method for antigen-antibody binding affinity changes based on protein sequences

The optimization of therapeutic antibodies through traditional techniques, such as candidate screening via hybridoma or phage display, is resource-intensive and time-consuming. In recent years, computational and artificial intelligence-based methods have been actively developed to accelerate and improve the development of therapeutic antibodies. In this study, we developed an end-to-end sequence-based deep learning model, termed AttABseq, for the predictions of the antigen-antibody binding affinity changes connected with antibody mutations. AttABseq is a highly efficient and generic attention-based model by utilizing diverse antigen-antibody complex sequences as the input to predict the binding affinity changes of residue mutations. The assessment on the three benchmark datasets illustrates that AttABseq is 120% more accurate than other sequence-based models in terms of the Pearson correlation coefficient between the predicted and experimental binding affinity changes. Moreover, AttABseq also either outperforms or competes favorably with the structure-based approaches. Furthermore, AttABseq consistently demonstrates robust predictive capabilities across a diverse array of conditions, underscoring its remarkable capacity for generalization across a wide spectrum of antigen-antibody complexes. It imposes no constraints on the quantity of altered residues, rendering it particularly applicable in scenarios where crystallographic structures remain unavailable. The attention-based interpretability analysis indicates that the causal effects of point mutations on antibody-antigen binding affinity changes can be visualized at the residue level, which might assist automated antibody sequence optimization. We believe that AttABseq provides a fiercely competitive answer to therapeutic antibody optimization.

Corner Engineering: Tailoring Enzymes for Enhanced Resistance and Thermostability in Deep Eutectic Solvents

Deep eutectic solvents (DESs), heralded for their synthesis simplicity, economic viability, and reduced volatility and flammability, have found increasing application in biocatalysis. However, challenges persist due to a frequent diminution in enzyme activity and stability. Herein, we developed a general protein engineering strategy, termed corner engineering, to acquire DES-resistant and thermostable enzymes via precise tailoring of the transition region in enzyme structure. Employing Bacillus subtilis lipase A (BSLA) as a model, we delineated the engineering process, yielding five multi-DESs resistant variants with highly improved thermostability, such as K88E/N89 K exhibited up to a 10.0-fold catalytic efficiency (kcat /KM ) increase in 30 % (v/v) choline chloride (ChCl): acetamide and 4.1-fold in 95 % (v/v) ChCl: ethylene glycol accompanying 6.7-fold thermal resistance improvement than wild type at ≈50 °C. The generality of the optimized approach was validated by two extra industrial enzymes, endo-β-1,4-glucanase PvCel5A (used for biofuel production) and esterase Bs2Est (used for plastics degradation). The molecular investigations revealed that increased water molecules at substrate binding cleft and finetuned helix formation at the corner region are two dominant determinants governing elevated resistance and thermostability. This study, coupling corner engineering with obtained molecular insights, illuminates enzyme-DES interaction patterns and fosters the rational design of more DES-resistant and thermostable enzymes in biocatalysis and biotransformation.

Assessing the fast prediction of peptide conformers and the impact of non-natural modifications

We present an assessment of different approaches to predict peptide structures using modeling tools. Several small molecule, protein, and peptide-focused methodologies were used for the fast prediction of conformers for peptides shorter than 30 amino acids. We assessed the effect of including restraints based on annotated or predicted secondary structure motifs. A number of peptides in bound conformations and in solution were collected to compare the tools. In addition, we studied the impact of changing single amino acids to non-natural residues using molecular dynamics simulations. Deep learning methods such as AlphaFold2, or the combination of physics-based approaches with secondary structure information, produce the most accurate results for natural sequences. In the case of peptides with non-natural modifications, modeling the peptide containing natural amino acids first and then modifying and simulating the peptide using benchmarked force fields is a recommended pipeline. The results can guide the modeling of oligopeptides for drug discovery projects.

Improved structure-related prediction for insufficient homologous proteins using MSA enhancement and pre-trained language model

In recent years, protein structure problems have become a hotspot for understanding protein folding and function mechanisms. It has been observed that most of the protein structure works rely on and benefit from co-evolutionary information obtained by multiple sequence alignment (MSA). As an example, AlphaFold2 (AF2) is a typical MSA-based protein structure tool which is famous for its high accuracy. As a consequence, these MSA-based methods are limited by the quality of the MSAs. Especially for orphan proteins that have no homologous sequence, AlphaFold2 performs unsatisfactorily as MSA depth decreases, which may pose a barrier to its widespread application in protein mutation and design problems in which there are no rich homologous sequences and rapid prediction is needed. In this paper, we constructed two standard datasets for orphan and de novo proteins which have insufficient/none homology information, called Orphan62 and Design204, respectively, to fairly evaluate the performance of the various methods in this case. Then, depending on whether or not utilizing scarce MSA information, we summarized two approaches, MSA-enhanced and MSA-free methods, to effectively solve the issue without sufficient MSAs. MSA-enhanced model aims to improve poor MSA quality from the data source by knowledge distillation and generation models. MSA-free model directly learns the relationship between residues on enormous protein sequences from pre-trained models, bypassing the step of extracting the residue pair representation from MSA. Next, we evaluated the performance of four MSA-free methods (trRosettaX-Single, TRFold, ESMFold and ProtT5) and MSA-enhanced (Bagging MSA) method compared with a traditional MSA-based method AlphaFold2, in two protein structure-related prediction tasks, respectively. Comparison analyses show that trRosettaX-Single and ESMFold which belong to MSA-free method can achieve fast prediction ($\sim\! 40$s) and comparable performance compared with AF2 in tertiary structure prediction, especially for short peptides, $\alpha $-helical segments and targets with few homologous sequences. Bagging MSA utilizing MSA enhancement improves the accuracy of our trained base model which is an MSA-based method when poor homology information exists in secondary structure prediction. Our study provides biologists an insight of how to select rapid and appropriate prediction tools for enzyme engineering and peptide drug development.

CONTACT

guofei@csu.edu.cn, jj.tang@siat.ac.cn.

TransDFL: Identification of Disordered Flexible Linkers in Proteins by Transfer Learning

Disordered flexible linkers (DFLs) are the functional disordered regions in proteins, which are the sub-regions of intrinsically disordered regions (IDRs) and play important roles in connecting domains and maintaining inter-domain interactions. Trained with the limited available DFLs, the existing DFL predictors based on the machine learning techniques tend to predict the ordered residues as DFLs, leading to a high falsepositive rate (FPR) and low prediction accuracy. Previous studies have shown that DFLs are extremely flexible disordered regions, which are usually predicted as disordered residues with high confidence [P(D) > 0.9] by an IDR predictor. Therefore, transferring an IDR predictor to an accurate DFL predictor is of great significance for understanding the functions of IDRs. In this study, we proposed a new predictor called TransDFL for identifying DFLs by transferring the RFPR-IDP predictor for IDR identification to the DFL prediction. The RFPR-IDP was pre-trained with IDR sequences to learn the general features between IDRs and DFLs, which is helpful to reduce the false positives in the ordered regions. RFPR-IDP was fine-tuned with the DFL sequences to capture the specific features of DFLs so as to be transferred into the TransDFL. Experimental results of two application scenarios (prediction of DFLs only in IDRs or prediction of DFLs in entire proteins) showed that TransDFL consistently outperformed other existing DFL predictors with higher accuracy. The corresponding web server of TransDFL can be freely accessed at http://bliulab.net/TransDFL/.

Deep learning for protein secondary structure prediction: Pre and post-AlphaFold

This paper aims to provide a comprehensive review of the trends and challenges of deep neural networks for protein secondary structure prediction (PSSP). In recent years, deep neural networks have become the primary method for protein secondary structure prediction. Previous studies showed that deep neural networks had uplifted the accuracy of three-state secondary structure prediction to more than 80%. Favored deep learning methods, such as convolutional neural networks, recurrent neural networks, inception networks, and graph neural networks, have been implemented in protein secondary structure prediction. Methods adapted from natural language processing (NLP) and computer vision are also employed, including attention mechanism, ResNet, and U-shape networks. In the post-AlphaFold era, PSSP studies focus on different objectives, such as enhancing the quality of evolutionary information and exploiting protein language models as the PSSP input. The recent trend to utilize pre-trained language models as input features for secondary structure prediction provides a new direction for PSSP studies. Moreover, the state-of-the-art accuracy achieved by previous PSSP models is still below its theoretical limit. There are still rooms for improvement to be made in the field.

Glycoinformatics in the Artificial Intelligence Era

Artificial intelligence (AI) methods have been and are now being increasingly integrated in prediction software implemented in bioinformatics and its glycoscience branch known as glycoinformatics. AI techniques have evolved in the past decades, and their applications in glycoscience are not yet widespread. This limited use is partly explained by the peculiarities of glyco-data that are notoriously hard to produce and analyze. Nonetheless, as time goes, the accumulation of glycomics, glycoproteomics, and glycan-binding data has reached a point where even the most recent deep learning methods can provide predictors with good performance. We discuss the historical development of the application of various AI methods in the broader field of glycoinformatics. A particular focus is placed on shining a light on challenges in glyco-data handling, contextualized by lessons learnt from related disciplines. Ending on the discussion of state-of-the-art deep learning approaches in glycoinformatics, we also envision the future of glycoinformatics, including development that need to occur in order to truly unleash the capabilities of glycoscience in the systems biology era.

Different methods, techniques and their limitations in protein structure prediction: A review

Because of the increase in different types of diseases in human habitats, demands for designing various types of drugs are also increasing. Protein and its structure play a very important role in drug design. Therefore researchers from different areas like mathematics, medicines, and computer science are teaming up for getting better solutions in the said field. In this paper, we have discussed different methods of secondary and tertiary protein structure prediction (PSP), along with the limitations of different approaches. Different types of datasets used in PSP are also discussed here. This paper also tells about different performance measures to evaluate the prediction accuracy of PSP methods. Different software's/servers are available for download, which are used to find the protein structures for the input protein sequence. These softwares will also help to compare the performance of any new algorithm with other available methods. Details of those softwares are also mentioned in this paper.

Wide-Line NMR Melting Diagrams, Their Thermodynamic Interpretation, and Secondary Structure Predictions for A30P and E46K α-Synuclein

Parkinson's disease is thought to be caused by aggregation of the intrinsically disordered protein, α-synuclein. Two amyloidogenic variants, A30P, and E46K familial mutants were investigated by wide-line ¹H NMR spectrometry as a completion of our earlier work on wild-type and A53T α-synuclein (Bokor M. et al. WT and A53T α-synuclein systems: melting diagram and its new interpretation. Int. J. Mol. Sci.2020, 21, 3997.). A monolayer of mobile water molecules hydrates A30P α-synuclein at the lowest potential barriers (temperatures), while E46K α-synuclein has here third as much mobile hydration, insufficient for functionality. According to wide-line ¹H NMR results and secondary structure predictions, E46K α-synuclein is more compact than the A30P variant and they are more compact than the wild type (WT) and A53T variants. Linear hydration vs potential barrier sections of A30P α-synuclein shows one and E46K shows two slopes. The different slopes of the latter between potential barriers E _a,1 and E _a,2 reflect a change in water-protein interactions. The 31-32% homogeneous potential barrier distribution of the protein-water bonds refers to a non-negligible amount of secondary structures in all four α-synuclein variants. The secondary structures detected by wide-line ¹H NMR are solvent-exposed α-helices, which are predicted by secondary structure models. β-sheets are only minor components of the protein structures as three- and eight-state predicted secondary structures are dominated by α-helices and coils.

Deep Ensemble Learning with Atrous Spatial Pyramid Networks for Protein Secondary Structure Prediction

The secondary structure of proteins is significant for studying the three-dimensional structure and functions of proteins. Several models from image understanding and natural language modeling have been successfully adapted in the protein sequence study area, such as Long Short-term Memory (LSTM) network and Convolutional Neural Network (CNN). Recently, Gated Convolutional Neural Network (GCNN) has been proposed for natural language processing. It has achieved high levels of sentence scoring, as well as reduced the latency. Conditionally Parameterized Convolution (CondConv) is another novel study which has gained great success in the image processing area. Compared with vanilla CNN, CondConv uses extra sample-dependant modules to conditionally adjust the convolutional network. In this paper, we propose a novel Conditionally Parameterized Convolutional network (CondGCNN) which utilizes the power of both CondConv and GCNN. CondGCNN leverages an ensemble encoder to combine the capabilities of both LSTM and CondGCNN to encode protein sequences by better capturing protein sequential features. In addition, we explore the similarity between the secondary structure prediction problem and the image segmentation problem, and propose an ASP network (Atrous Spatial Pyramid Pooling (ASPP) based network) to capture fine boundary details in secondary structure. Extensive experiments show that the proposed method can achieve higher performance on protein secondary structure prediction task than existing methods on CB513, Casp11, CASP12, CASP13, and CASP14 datasets. We also conducted ablation studies over each component to verify the effectiveness. Our method is expected to be useful for any protein related prediction tasks, which is not limited to protein secondary structure prediction.

MutCov: A pipeline for evaluating the effect of mutations in spike protein on infectivity and antigenicity of SARS-CoV-2

Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), causing an outbreak of coronavirus disease 2019 (COVID-19), is a major threat to public health worldwide. Previous studies have shown that the spike protein of SARS-CoV-2 determines viral infectivity and major antigenicity. However, the spike protein has been undergoing various mutations, which bring a great challenge to the prevention and treatment of COVID-19. Here we present the MutCov, a pipeline for evaluating the effect of mutations in spike protein on infectivity and antigenicity of SARS-CoV-2 by calculating the binding free energy between spike protein and angiotensin-converting enzyme 2 (ACE2) or neutralizing monoclonal antibody (mAb). The predicted infectivity and antigenicity were highly consistent with biologically experimental results, and demonstrated that the MutCov achieved good prediction performance. In conclusion, the MutCov is of high importance for systematically evaluating the effect of novel mutations and improving the prevention and treatment of COVID-19. The source code and installation instruction of MutCov are freely available at http://jianglab.org.cn/MutCov.

Lightweight ProteinUnet2 network for protein secondary structure prediction: a step towards proper evaluation

Background

The prediction of protein secondary structures is a crucial and significant step for ab initio tertiary structure prediction which delivers the information about proteins activity and functions. As the experimental methods are expensive and sometimes impossible, many SS predictors, mainly based on different machine learning methods have been proposed for many years. Currently, most of the top methods use evolutionary-based input features produced by PSSM and HHblits software, although quite recently the embeddings—the new description of protein sequences generated by language models (LM) have appeared that could be leveraged as input features. Apart from input features calculation, the top models usually need extensive computational resources for training and prediction and are barely possible to run on a regular PC. SS prediction as the imbalanced classification problem should not be judged by the commonly used Q3/Q8 metrics. Moreover, as the benchmark datasets are not random samples, the classical statistical null hypothesis testing based on the Neyman–Pearson approach is not appropriate.

Results

We present a lightweight deep network ProteinUnet2 for SS prediction which is based on U-Net convolutional architecture and evolutionary-based input features (from PSSM and HHblits) as well as SPOT-Contact features. Through an extensive evaluation study, we report the performance of ProteinUnet2 in comparison with top SS prediction methods based on evolutionary information (SAINT and SPOT-1D). We also propose a new statistical methodology for prediction performance assessment based on the significance from Fisher–Pitman permutation tests accompanied by practical significance measured by Cohen’s effect size.

Conclusions

Our results suggest that ProteinUnet2 architecture has much shorter training and inference times while maintaining results similar to SAINT and SPOT-1D predictors. Taking into account the relatively long times of calculating evolutionary-based features (from PSSM in particular), it would be worth conducting the predictive ability tests on embeddings as input features in the future. We strongly believe that our proposed here statistical methodology for the evaluation of SS prediction results will be adopted and used (and even expanded) by the research community.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-022-04623-z.

i6mA-Vote: Cross-Species Identification of DNA N6-Methyladenine Sites in Plant Genomes Based on Ensemble Learning With Voting

DNA N6-Methyladenine (6mA) is a common epigenetic modification, which plays some significant roles in the growth and development of plants. It is crucial to identify 6mA sites for elucidating the functions of 6mA. In this article, a novel model named i6mA-vote is developed to predict 6mA sites of plants. Firstly, DNA sequences were coded into six feature vectors with diverse strategies based on density, physicochemical properties, and position of nucleotides, respectively. To find the best coding strategy, the feature vectors were compared on several machine learning classifiers. The results suggested that the position of nucleotides has a significant positive effect on 6mA sites identification. Thus, the dinucleotide one-hot strategy which can describe position characteristics of nucleotides well was employed to extract DNA features in our method. Secondly, DNA sequences of Rosaceae were divided into a training dataset and a test dataset randomly. Finally, i6mA-vote was constructed by combining five different base-classifiers under a majority voting strategy and trained on the Rosaceae training dataset. The i6mA-vote was evaluated on the task of predicting 6mA sites from the genome of the Rosaceae, Rice, and Arabidopsis separately. In Rosaceae, the performances of i6mA-vote were 0.955 on accuracy (ACC), 0.909 on Matthew correlation coefficients (MCC), 0.955 on sensitivity (SN), and 0.954 on specificity (SP). Those indicators, in the order of ACC, MCC, SN, SP, were 0.882, 0.774, 0.961, and 0.803 on Rice while they were 0.798, 0.617, 0.666, and 0.929 on Arabidopsis. According to the indicators, our method was effectiveness and better than other concerned methods. The results also illustrated that i6mA-vote does not only well in 6mA sites prediction of intraspecies but also interspecies plants. Moreover, it can be seen that the specificity is distinctly lower than the sensitivity in Rice while it is just the opposite in Arabidopsis. It may be resulted from sequence similarity among Rosaceae, Rice and Arabidopsis.

Natural Peptides Inducing Cancer Cell Death: Mechanisms and Properties of Specific Candidates for Cancer Therapeutics

Nowadays, cancer has become the second highest leading cause of death, and it is expected to continue to affect the population in forthcoming years. Additionally, treatment options will become less accessible to the public as cases continue to grow and disease mechanisms expand. Hence, specific candidates with confirmed anticancer effects are required to develop new drugs. Among the novel therapeutic options, proteins are considered a relevant source, given that they have bioactive peptides encrypted within their sequences. These bioactive peptides, which are molecules consisting of 2–50 amino acids, have specific activities when administered, producing anticancer effects. Current databases report the effects of peptides. However, uncertainty is found when their molecular mechanisms are investigated. Furthermore, analyses addressing their interaction networks or their directly implicated mechanisms are needed to elucidate their effects on cancer cells entirely. Therefore, relevant peptides considered as candidates for cancer therapeutics with specific sequences and known anticancer mechanisms were accurately reviewed. Likewise, those features which turn certain peptides into candidates and the mechanisms by which peptides mediate tumor cell death were highlighted. This information will make robust the knowledge of these candidate peptides with recognized mechanisms and enhance their non-toxic capacity in relation to healthy cells and further avoid cell resistance.

Natural Peptides Inducing Cancer Cell Death: Mechanisms and Properties of Specific Candidates for Cancer Therapeutics

Nowadays, cancer has become the second highest leading cause of death, and it is expected to continue to affect the population in forthcoming years. Additionally, treatment options will become less accessible to the public as cases continue to grow and disease mechanisms expand. Hence, specific candidates with confirmed anticancer effects are required to develop new drugs. Among the novel therapeutic options, proteins are considered a relevant source, given that they have bioactive peptides encrypted within their sequences. These bioactive peptides, which are molecules consisting of 2–50 amino acids, have specific activities when administered, producing anticancer effects. Current databases report the effects of peptides. However, uncertainty is found when their molecular mechanisms are investigated. Furthermore, analyses addressing their interaction networks or their directly implicated mechanisms are needed to elucidate their effects on cancer cells entirely. Therefore, relevant peptides considered as candidates for cancer therapeutics with specific sequences and known anticancer mechanisms were accurately reviewed. Likewise, those features which turn certain peptides into candidates and the mechanisms by which peptides mediate tumor cell death were highlighted. This information will make robust the knowledge of these candidate peptides with recognized mechanisms and enhance their non-toxic capacity in relation to healthy cells and further avoid cell resistance.

CSI-LSTM: a web server to predict protein secondary structure using bidirectional long short term memory and NMR chemical shifts

Protein secondary structure provides rich structural information, hence the description and understanding of protein structure relies heavily on it. Identification or prediction of secondary structures therefore plays an important role in protein research. In protein NMR studies, it is more convenient to predict secondary structures from chemical shifts as compared to the traditional determination methods based on inter-nuclear distances provided by NOESY experiment. In recent years, there was a significant improvement observed in deep neural networks, which had been applied in many research fields. Here we proposed a deep neural network based on bidirectional long short term memory (biLSTM) to predict protein 3-state secondary structure using NMR chemical shifts of backbone nuclei. While comparing with the existing methods the proposed method showed better prediction accuracy. Based on the proposed method, a web server has been built to provide protein secondary structure prediction service.

SYNBIP: synthetic binding proteins for research, diagnosis and therapy

The success of protein engineering and design has extensively expanded the protein space, which presents a promising strategy for creating next-generation proteins of diverse functions. Among these proteins, the synthetic binding proteins (SBPs) are smaller, more stable, less immunogenic, and better of tissue penetration than others, which make the SBP-related data attracting extensive interest from worldwide scientists. However, no database has been developed to systematically provide the valuable information of SBPs yet. In this study, a database named ‘Synthetic Binding Proteins for Research, Diagnosis, and Therapy (SYNBIP)’ was thus introduced. This database is unique in (a) comprehensively describing thousands of SBPs from the perspectives of scaffolds, biophysical & functional properties, etc.; (b) panoramically illustrating the binding targets & the broad application of each SBP and (c) enabling a similarity search against the sequences of all SBPs and their binding targets. Since SBP is a human-made protein that has not been found in nature, the discovery of novel SBPs relied heavily on experimental protein engineering and could be greatly facilitated by in-silico studies (such as AI and computational modeling). Thus, the data provided in SYNBIP could lay a solid foundation for the future development of novel SBPs. The SYNBIP is accessible without login requirement at both official (https://idrblab.org/synbip/) and mirror (http://synbip.idrblab.net/) sites.

Prediction of lysine formylation sites using support vector machine based on the sample selection from majority classes and synthetic minority over-sampling techniques

Lysine formylation is a newly discovered and mostly interested type of post-translational modification (PTM) that is generally found on core and linker histone proteins of prokaryote and eukaryote and plays various important roles on the regulation of various cellular mechanisms. Hence, it is very urgent to properly identify formylation site in protein for understanding the molecular mechanism of formylation deeply and defining drug for relevant diseases. As experimentally identification of formylation site using traditional processes are expensive and time consuming, a simple and high speedy mathematical model for predicting accurately lysine formylation sites is highly desired. A useful computational model named PLF_SVM is deigned and proposed in this study by using binary encoding (BE), amino acid composition (AAC), reverse position relative incidence matrix (RPRIM), position relative incidence matrix (PRIM), and position specific amino acid propensity (PSAAP) feature generation methods for predicting formylated and non-formylated lysine sites. Besides, the Synthetic Minority Oversampling Technique (SMOTE) and a proposed sample selection strategy named EnSVM are applied to handle the imbalance training dataset problem. Thereafter, the optimal number of features are selected by F-score method to train the model. Finally, it has been seen that PLF_SVM outperforms the state-of-the-art approaches in validation and independent test with an accuracy of 98.61% and 98.77% respectively. At https://plf-svm.herokuapp.com/, a user-friendly web tool is also created for identifying formylation sites. Therefore, the proposed method may be helpful guideline for the analysis and prediction of formylated lysine and knowing the process of cellular regulation.

Testing machine learning techniques for general application by using protein secondary structure prediction. A brief survey with studies of pitfalls and benefits using a simple progressive learning approach

Many researchers have recently used the prediction of protein secondary structure (local conformational states of amino acid residues) to test advances in predictive and machine learning technology such as Neural Net Deep Learning. Protein secondary structure prediction continues to be a helpful tool in research in biomedicine and the life sciences, but it is also extremely enticing for testing predictive methods such as neural nets that are intended for different or more general purposes. A complication is highlighted here for researchers testing their methods for other applications. Modern protein databases inevitably contain important clues to the answer, so-called "strong buried clues", though often obscurely; they are hard to avoid. This is because most proteins or parts of proteins in a modern protein data base are related to others by biological evolution. For researchers developing machine learning and predictive methods, this can overstate and so confuse understanding of the true quality of a predictive method. However, for researchers using the algorithms as tools, understanding strong buried clues is of great value, because they need to make maximum use of all information available. A simple method related to the GOR methods but with some features of neural nets in the sense of progressive learning of large numbers of weights, is used to explore this. It can acquire tens of millions and hence gigabytes of weights, but they are learned stably by exhaustive sampling. The significance of the findings is discussed in the light of promising recent results from AlphaFold using Google's DeepMind.

ProtRe-CN: Protein Remote Homology Detection by Combining Classification Methods and Network Methods via Learning to Rank

Protein remote homology detection is one of fundamental research tasks for downstream analysis (i.e., protein structure and function prediction). Many advanced methods are proposed from different views with complementary detection ability, such as the classification method, the network method, and the ranking method. A framework integrating these heterogeneous methods is urgently desired to reduce the false positive rate and predictive bias. We propose a novel ranking method called ProtRe-CN by fusing the classification methods and network methods via Learning to Rank. Experimental results on the benchmark dataset and the independent dataset show that ProtRe-CN outperforms other existing state-of-the-art predictors. ProtRe-CN improves the detective performance via correcting the false positives in the ranking list by combining the heterogeneous methods. The web server of ProtRe-CN can be accessed at http://bliulab.net/ProtRe-CN.

Protein Secondary Structure Prediction With a Reductive Deep Learning Method

Protein secondary structures have been identified as the links in the physical processes of primary sequences, typically random coils, folding into functional tertiary structures that enable proteins to involve a variety of biological events in life science. Therefore, an efficient protein secondary structure predictor is of importance especially when the structure of an amino acid sequence fragment is not solved by high-resolution experiments, such as X-ray crystallography, cryo-electron microscopy, and nuclear magnetic resonance spectroscopy, which are usually time consuming and expensive. In this paper, a reductive deep learning model MLPRNN has been proposed to predict either 3-state or 8-state protein secondary structures. The prediction accuracy by the MLPRNN on the publicly available benchmark CB513 data set is comparable with those by other state-of-the-art models. More importantly, taking into account the reductive architecture, MLPRNN could be a baseline for future developments.

i4mC-EL: Identifying DNA N4-Methylcytosine Sites in the Mouse Genome Using Ensemble Learning

As one of important epigenetic modifications, DNA N4-methylcytosine (4mC) plays a crucial role in controlling gene replication, expression, cell cycle, DNA replication, and differentiation. The accurate identification of 4mC sites is necessary to understand biological functions. In the paper, we use ensemble learning to develop a model named i4mC-EL to identify 4mC sites in the mouse genome. Firstly, a multifeature encoding scheme consisting of Kmer and EIIP was adopted to describe the DNA sequences. Secondly, on the basis of the multifeature encoding scheme, we developed a stacked ensemble model, in which four machine learning algorithms, namely, BayesNet, NaiveBayes, LibSVM, and Voted Perceptron, were utilized to implement an ensemble of base classifiers that produce intermediate results as input of the metaclassifier, Logistic. The experimental results on the independent test dataset demonstrate that the overall rate of predictive accurate of i4mC-EL is 82.19%, which is better than the existing methods. The user-friendly website implementing i4mC-EL can be accessed freely at the following.

Amino Acid Reduction Can Help to Improve the Identification of Antimicrobial Peptides and Their Functional Activities

Antimicrobial peptides (AMPs) are considered as potential substitutes of antibiotics in the field of new anti-infective drug design. There have been several machine learning algorithms and web servers in identifying AMPs and their functional activities. However, there is still room for improvement in prediction algorithms and feature extraction methods. The reduced amino acid (RAA) alphabet effectively solved the problems of simplifying protein complexity and recognizing the structure conservative region. This article goes into details about evaluating the performances of more than 5,000 amino acid reduced descriptors generated from 74 types of amino acid reduced alphabet in the first stage and the second stage to construct an excellent two-stage classifier, Identification of Antimicrobial Peptides by Reduced Amino Acid Cluster (iAMP-RAAC), for identifying AMPs and their functional activities, respectively. The results show that the first stage AMP classifier is able to achieve the accuracy of 97.21 and 97.11% for the training data set and independent test dataset. In the second stage, our classifier still shows good performance. At least three of the four metrics, sensitivity (SN), specificity (SP), accuracy (ACC), and Matthews correlation coefficient (MCC), exceed the calculation results in the literature. Further, the ANOVA with incremental feature selection (IFS) is used for feature selection to further improve prediction performance. The prediction performance is further improved after the feature selection of each stage. At last, a user-friendly web server, iAMP-RAAC, is established at http://bioinfor.imu.edu. cn/iampraac.

Comprehensive predictions of secondary structures for comparative analysis in different species

Protein structures are directly linked to biological functions. However, there is a gap of knowledge between the decoded genome and the structure. To bridge the gap, we focused on the secondary structure (SS). From a comprehensive analysis of predicted SS of proteins in different types of organisms, we have arrived at the following findings: The proportions of SS in genomes were different among phylogenic domains. The distributions of strand lengths indicated structural limitations in all of the species. Different from bacteria and archaea, eukaryotes have an abundance of α-helical and random coil proteins. Interestingly, there was a relationship between SS and post-translational modifications. By calculating hydrophobicity moments of helices and strands, highly amphipathic fragments of SS were found, which might be related to the biological functions. In conclusion, comprehensive predictions of SS will provide valuable perspectives to understand the entire protein structures in genomes and will help one to discover or design functional proteins.

ATSE: a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural network and attention mechanism

MOTIVATION

Peptides have recently emerged as promising therapeutic agents against various diseases. For both research and safety regulation purposes, it is of high importance to develop computational methods to accurately predict the potential toxicity of peptides within the vast number of candidate peptides.

RESULTS

In this study, we proposed ATSE, a peptide toxicity predictor by exploiting structural and evolutionary information based on graph neural networks and attention mechanism. More specifically, it consists of four modules: (i) a sequence processing module for converting peptide sequences to molecular graphs and evolutionary profiles, (ii) a feature extraction module designed to learn discriminative features from graph structural information and evolutionary information, (iii) an attention module employed to optimize the features and (iv) an output module determining a peptide as toxic or non-toxic, using optimized features from the attention module.

CONCLUSION

Comparative studies demonstrate that the proposed ATSE significantly outperforms all other competing methods. We found that structural information is complementary to the evolutionary information, effectively improving the predictive performance. Importantly, the data-driven features learned by ATSE can be interpreted and visualized, providing additional information for further analysis. Moreover, we present a user-friendly online computational platform that implements the proposed ATSE, which is now available at http://server.malab.cn/ATSE. We expect that it can be a powerful and useful tool for researchers of interest.

Applications of Protein Secondary Structure Algorithms in SARS-CoV-2 Research

Since the outset of COVID-19, the pandemic has prompted immediate global efforts to sequence SARS-CoV-2, and over 450 000 complete genomes have been publicly deposited over the course of 12 months. Despite this, comparative nucleotide and amino acid sequence analyses often fall short in answering key questions in vaccine design. For example, the binding affinity between different ACE2 receptors and SARS-COV-2 spike protein cannot be fully explained by amino acid similarity at ACE2 contact sites because protein structure similarities are not fully reflected by amino acid sequence similarities. To comprehensively compare protein homology, secondary structure (SS) analysis is required. While protein structure is slow and difficult to obtain, SS predictions can be made rapidly, and a well-predicted SS structure may serve as a viable proxy to gain biological insight. Here we review algorithms and information used in predicting protein SS to highlight its potential application in pandemics research. We also showed examples of how SS predictions can be used to compare ACE2 proteins and to evaluate the zoonotic origins of viruses. As computational tools are much faster than wet-lab experiments, these applications can be important for research especially in times when quickly obtained biological insights can help in speeding up response to pandemics.

ApoPred: Identification of Apolipoproteins and Their Subfamilies With Multifarious Features

Apolipoprotein is a group of plasma proteins that are associated with a variety of diseases, such as hyperlipidemia, atherosclerosis, Alzheimer’s disease, and diabetes. In order to investigate the function of apolipoproteins and to develop effective targets for related diseases, it is necessary to accurately identify and classify apolipoproteins. Although it is possible to identify apolipoproteins accurately through biochemical experiments, they are expensive and time-consuming. This work aims to establish a high-efficiency and high-accuracy prediction model for recognition of apolipoproteins and their subfamilies. We firstly constructed a high-quality benchmark dataset including 270 apolipoproteins and 535 non-apolipoproteins. Based on the dataset, pseudo-amino acid composition (PseAAC) and composition of k-spaced amino acid pairs (CKSAAP) were used as input vectors. To improve the prediction accuracy and eliminate redundant information, analysis of variance (ANOVA) was used to rank the features. And the incremental feature selection was utilized to obtain the best feature subset. Support vector machine (SVM) was proposed to construct the classification model, which could produce the accuracy of 97.27%, sensitivity of 96.30%, and specificity of 97.76% for discriminating apolipoprotein from non-apolipoprotein in 10-fold cross-validation. In addition, the same process was repeated to generate a new model for predicting apolipoprotein subfamilies. The new model could achieve an overall accuracy of 95.93% in 10-fold cross-validation. According to our proposed model, a convenient webserver called ApoPred was established, which can be freely accessed at http://tang-biolab.com/server/ApoPred/service.html. We expect that this work will contribute to apolipoprotein function research and drug development in relevant diseases.

ProteinUnet-An efficient alternative to SPIDER3-single for sequence-based prediction of protein secondary structures

Predicting protein function and structure from sequence remains an unsolved problem in bioinformatics. The best performing methods rely heavily on evolutionary information from multiple sequence alignments, which means their accuracy deteriorates for sequences with a few homologs, and given the increasing sequence database sizes requires long computation times. Here, a single‐sequence‐based prediction method is presented, called ProteinUnet, leveraging an U‐Net convolutional network architecture. It is compared to SPIDER3‐Single model, based on long short‐term memory‐bidirectional recurrent neural networks architecture. Both methods achieve similar results for prediction of secondary structures (both three‐ and eight‐state), half‐sphere exposure, and contact number, but ProteinUnet has two times fewer parameters, 17 times shorter inference time, and can be trained 11 times faster. Moreover, ProteinUnet tends to be better for short sequences and residues with a low number of local contacts. Additionally, the method of loss weighting is presented as an effective way of increasing accuracy for rare secondary structures.