Amino Acid Encoding Methods for Protein Sequences: A Comprehensive Review and Assessment

Protein sequence analysis in the context of drug repurposing

MOTIVATION

Drug repurposing speeds up the development of new treatments, being less costly, risky, and time consuming than de novo drug discovery. There are numerous biological elements that contribute to the development of diseases and, as a result, to the repurposing of drugs.

METHODS

In this article, we analysed the potential role of protein sequences in drug repurposing scenarios. For this purpose, we embedded the protein sequences by performing four state of the art methods and validated their capacity to encapsulate essential biological information through visualization. Then, we compared the differences in sequence distance between protein-drug target pairs of drug repurposing and non - drug repurposing data. Thus, we were able to uncover patterns that define protein sequences in repurposing cases.

RESULTS

We found statistically significant sequence distance differences between protein pairs in the repurposing data and the rest of protein pairs in non-repurposing data. In this manner, we verified the potential of using numerical representations of sequences to generate repurposing hypotheses in the future.

MFA-DTI: Drug-target interaction prediction based on multi-feature fusion adopted framework

The identification of drug-target interactions (DTI) is a valuable step in the drug discovery and repositioning process. However, traditional laboratory experiments are time-consuming and expensive. Computational methods have streamlined research to determine DTIs. The application of deep learning methods has significantly improved the prediction performance for DTIs. Modern deep learning methods can leverage multiple sources of information, including sequence data that contains biological structural information, and interaction data. While useful, these methods cannot be effectively applied to each type of information individually (e.g., chemical structure and interaction network) and do not take into account the specificity of DTI data such as low- or zero-interaction biological entities. To overcome these limitations, we propose a method called MFA-DTI (Multi-feature Fusion Adopted framework for DTI). MFA-DTI consists of three modules: an interaction graph learning module that processes the interaction network to generate interaction vectors, a chemical structure learning module that extracts features from the chemical structure, and a fusion module that combines these features for the final prediction. To validate the performance of MFA-DTI, we conducted experiments on six public datasets under different settings. The results indicate that the proposed method is highly effective in various settings and outperforms state-of-the-art methods.

MehNet: a vigesimal-based model by amino acid melting points generates unique ID numbers for protein sequences

The amino acid encoding plays a pivotal role in machine learning-based methods for predicting protein structure and function, as well as in protein mapping techniques. Additionally, the classification of protein sequences presents its own challenges. The current study aims to assign a constant value to each amino acid, thereby creating distinctions among protein sequences. The datasets used in this study were obtained from the UniProt Knowledgebase. Subsequently, these datasets underwent preprocessing steps, and identical sequences were categorized under the same headings. Each amino acid was ranked based on its respective melting point and was assigned a vigesimal digit. These generated vigesimal digits were subsequently converted to decimal values. The centerpiece of this methodology was the melting point hashing table, which was given the name 'MehNet'. Ultimately, each protein sequence was assigned a unique identification number. This approach successfully digitized protein sequences. Notably, experiments involving randomly distributed vigesimal digits for amino acids did not yield results as promising as those achieved with MehNet. The model's classification phase, which utilizes a k-nearest neighbors (kNN) classifier, demonstrates exceptional performance in miscellaneous viral sequences. It achieves high accuracy rates, with an overall accuracy of 99.75%. Notably, it achieves an outstanding accuracy of 99.92% for the Influenza C class, highlighting its ability to distinguish closely related viral sequences.Communicated by Ramaswamy H. Sarma.

DeepDRP: Prediction of intrinsically disordered regions based on integrated view deep learning architecture from transformer-enhanced and protein information

Intrinsic disorder in proteins, a widely distributed phenomenon in nature, is related to many crucial biological processes and various diseases. Traditional determination methods tend to be costly and labor-intensive, therefore it is desirable to seek an accurate identification method of intrinsically disordered proteins (IDPs). In this paper, we proposed a novel Deep learning model for Intrinsically Disordered Regions in Proteins named DeepDRP. DeepDRP employed an innovative TimeDistributed strategy and Bi-LSTM architecture to predict IDPs and is driven by integrated view features of PSSM, Energy-based encoding, AAindex, and transformer-enhanced embeddings including DR-BERT, OntoProtein, Prot-T5, and ESM-2. The comparison of different feature combinations indicates that the transformer-enhanced features contribute far more than traditional features to predict IDPs and ESM-2 accounts for a larger contribution in the pre-trained fusion vectors. The ablation test verified that the TimeDistributed strategy surely increased the model performance and is an efficient approach to the IDP prediction. Compared with eight state-of-the-art methods on the DISORDER723, S1, and DisProt832 datasets, the Matthews correlation coefficient of DeepDRP significantly outperformed competing methods by 4.90 % to 36.20 %, 11.80 % to 26.33 %, and 4.82 % to 13.55 %. In brief, DeepDRP is a reliable model for IDP prediction and is freely available at https://github.com/ZX-COLA/DeepDRP.

A comprehensive framework for advanced protein classification and function prediction using synergistic approaches: Integrating bispectral analysis, machine learning, and deep learning

Proteins are fundamental components of diverse cellular systems and play crucial roles in a variety of disease processes. Consequently, it is crucial to comprehend their structure, function, and intricate interconnections. Classifying proteins into families or groups with comparable structural and functional characteristics is a crucial aspect of this comprehension. This classification is crucial for evolutionary research, predicting protein function, and identifying potential therapeutic targets. Sequence alignment and structure-based alignment are frequently ineffective techniques for identifying protein families.This study addresses the need for a more efficient and accurate technique for feature extraction and protein classification. The research proposes a novel method that integrates bispectrum characteristics, deep learning techniques, and machine learning algorithms to overcome the limitations of conventional methods. The proposed method uses numbers to represent protein sequences, utilizes bispectrum analysis, uses different topologies for convolutional neural networks to pull out features, and chooses robust features to classify protein families. The goal is to outperform existing methods for identifying protein families, thereby enhancing classification metrics. The materials consist of numerous protein datasets, whereas the methods incorporate bispectrum characteristics and deep learning strategies. The results of this study demonstrate that the proposed method for identifying protein families is superior to conventional approaches. Significantly enhanced quality metrics demonstrated the efficacy of the combined bispectrum and deep learning approaches. These findings have the potential to advance the field of protein biology and facilitate pharmaceutical innovation. In conclusion, this study presents a novel method that employs bispectrum characteristics and deep learning techniques to improve the precision and efficiency of protein family identification. The demonstrated advancements in classification metrics demonstrate this method's applicability to numerous scientific disciplines. This furthers our understanding of protein function and its implications for disease and treatment.

REC protein family expansion by the emergence of a new signaling pathway

IMPORTANCE

We explore when and why large classes of proteins expand into new sequence space. We used an unsupervised machine learning approach to observe the sequence landscape of REC domains of bacterial response regulator proteins. We find that within-gene recombination can switch effector domains and, consequently, change the regulatory context of the duplicated protein.

Comparative study of encoded and alignment-based methods for virus taxonomy classification

The emergence of viruses and their variants has made virus taxonomy more important than ever before in controlling the spread of diseases. The creation of efficient treatments and cures that target particular virus properties can be aided by understanding virus taxonomy. Alignment-based methods are commonly used for this task, but are computationally expensive and time-consuming, especially when dealing with large datasets or when detecting new virus variants is time sensitive. An alternative approach, the encoded method, has been developed that does not require prior sequence alignment and provides faster results. However, each encoded method has its own claimed accuracy. Therefore, careful evaluation and comparison of the performance of different encoded methods are essential to identify the most accurate and reliable approach for virus taxonomy classification. This study aims to address this issue by providing a comprehensive and comparative analysis of the potential of encoded methods for virus classification and phylogenetics. We compared the vectors generated for each encoded method using distance metrics to determine their similarity to alignment-based methods. The results and their validation show that K-merNV followed by CgrDft encoded methods, perform similarly to state-of-the-art multi-sequence alignment methods. This is the first study to incorporate and compare encoded methods that will facilitate future research in making more informed decisions regarding selection of a suitable method for virus taxonomy.

Finding functional motifs in protein sequences with deep learning and natural language models

Recently, prediction of structural/functional motifs in protein sequences takes advantage of powerful machine learning based approaches. Protein encoding adopts protein language models overpassing standard procedures. Different combinations of machine learning and encoding schemas are available for predicting different structural/functional motifs. Particularly interesting is the adoption of protein language models to encode proteins in addition to evolution information and physicochemical parameters. A thorough analysis of recent predictors developed for annotating transmembrane regions, sorting signals, lipidation and phosphorylation sites allows to investigate the state-of-the-art focusing on the relevance of protein language models for the different tasks. This highlights that more experimental data are necessary to exploit available powerful machine learning methods.

Machine learning-driven multifunctional peptide engineering for sustained ocular drug delivery

Sustained drug delivery strategies have many potential benefits for treating a range of diseases, particularly chronic diseases that require treatment for years. For many chronic ocular diseases, patient adherence to eye drop dosing regimens and the need for frequent intraocular injections are significant barriers to effective disease management. Here, we utilize peptide engineering to impart melanin binding properties to peptide-drug conjugates to act as a sustained-release depot in the eye. We develop a super learning-based methodology to engineer multifunctional peptides that efficiently enter cells, bind to melanin, and have low cytotoxicity. When the lead multifunctional peptide (HR97) is conjugated to brimonidine, an intraocular pressure lowering drug that is prescribed for three times per day topical dosing, intraocular pressure reduction is observed for up to 18 days after a single intracameral injection in rabbits. Further, the cumulative intraocular pressure lowering effect increases ~17-fold compared to free brimonidine injection. Engineered multifunctional peptide-drug conjugates are a promising approach for providing sustained therapeutic delivery in the eye and beyond.

Deepro-Glu: combination of convolutional neural network and Bi-LSTM models using ProtBert and handcrafted features to identify lysine glutarylation sites

Lysine glutarylation (Kglu) is a newly discovered post-translational modification of proteins with important roles in mitochondrial functions, oxidative damage, etc. The established biological experimental methods to identify glutarylation sites are often time-consuming and costly. Therefore, there is an urgent need to develop computational methods for efficient and accurate identification of glutarylation sites. Most of the existing computational methods only utilize handcrafted features to construct the prediction model and do not consider the positive impact of the pre-trained protein language model on the prediction performance. Based on this, we develop an ensemble deep-learning predictor Deepro-Glu that combines convolutional neural network and bidirectional long short-term memory network using the deep learning features and traditional handcrafted features to predict lysine glutaryation sites. The deep learning features are generated from the pre-trained protein language model called ProtBert, and the handcrafted features consist of sequence-based features, physicochemical property-based features and evolution information-based features. Furthermore, the attention mechanism is used to efficiently integrate the deep learning features and the handcrafted features by learning the appropriate attention weights. 10-fold cross-validation and independent tests demonstrate that Deepro-Glu achieves competitive or superior performance than the state-of-the-art methods. The source codes and data are publicly available at https://github.com/xwanggroup/Deepro-Glu.

A systematic review on the state-of-the-art strategies for protein representation

The study of drug-target protein interaction is a key step in drug research. In recent years, machine learning techniques have become attractive for research, including drug research, due to their automated nature, predictive power, and expected efficiency. Protein representation is a key step in the study of drug-target protein interaction by machine learning, which plays a fundamental role in the ultimate accomplishment of accurate research. With the progress of machine learning, protein representation methods have gradually attracted attention and have consequently developed rapidly. Therefore, in this review, we systematically classify current protein representation methods, comprehensively review them, and discuss the latest advances of interest. According to the information extraction methods and information sources, these representation methods are generally divided into structure and sequence-based representation methods. Each primary class can be further divided into specific subcategories. As for the particular representation methods involve both traditional and the latest approaches. This review contains a comprehensive assessment of the various methods which researchers can use as a reference for their specific protein-related research requirements, including drug research.

A Novel Capsule Network with Attention Routing to Identify Prokaryote Phosphorylation Sites

By denaturing proteins and promoting the formation of multiprotein complexes, protein phosphorylation has important effects on the activity of protein functional molecules and cell signaling. The regulation of protein phosphorylation allows microbes to respond rapidly and reversibly to specific environmental stimuli or niches, which is closely related to the molecular mechanisms of bacterial drug resistance. Accurate prediction of phosphorylation sites (p-site) of prokaryotes can contribute to addressing bacterial resistance and providing new perspectives for developing novel antibacterial drugs. Most existing studies focus on human phosphorylation sites, while tools targeting phosphorylation site identification of prokaryotic proteins are still relatively scarce. This study designs a capsule network-based prediction technique for p-site in prokaryotes. To address the poor scalability and unreliability of dynamic routing processes in the output space of capsule networks, a more reliable way is introduced to learn the consistency between capsules. We incorporate a self-attention mechanism into the routing algorithm to capture the global information of the capsule, reducing the computational effort while enriching the representation capability of the capsule. Aiming at the weak robustness of the model, EcapsP improves the prediction accuracy and stability by introducing shortcuts and unconditional reconfiguration. In addition, the study compares and analyzes the prediction performance based on word vectors, physicochemical properties, and mixing characteristics in predicting serine (Ser/S), threonine (Thr/T), and tyrosine (Tyr/Y) p-site. The comprehensive experimental results show that the accuracy of the developed technique is close to 70% for the identification of the three phosphorylation sites in prokaryotes. Importantly, in side-by-side comparisons with other state-of-the-art predictors, our method improves the Matthews correlation coefficient (MCC) by approximately 7%. The results demonstrate the superiority of EcapsP in terms of high performance and reliability.

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.

DeepASmRNA: Reference-free prediction of alternative splicing events with a scalable and interpretable deep learning model

Alternative splicing is crucial for a wide range of biological processes. However, limited by the availability of reference genomes, genome-wide patterns of alternative splicing remain unknown in most nonmodel organisms. We present an attention-based convolutional neural network model, DeepASmRNA, for predicting alternative splicing events using only transcriptomic data. DeepASmRNA consists of two parts: identification of alternatively spliced transcripts and classification of alternative splicing events, which outperformed the state-of-the-art method, AStrap, and other deep learning models. Then, we utilize transfer learning to increase the performance in species with limited training data and use an interpretation method to decipher splicing codes. Finally, applying Amborella, DeepASmRNA can identify more AS events than AStrap while maintaining the same level of precision, suggesting that DeepASmRNA has superior sensitivity to identify alternative splicing events. In summary, DeepASmRNA is scalable and interpretable for detecting genome-wide patterns of alternative splicing in species without a reference genome.

•

DeepASmRNA uses only the transcriptome to predict alternative splicing events

•

DeepASmRNA identifies adjacent HSPs to greatly improve the recall

•

DeepASmRNA uses attention-based convolutional neural network to classify AS events

•

Transfer learning is used to increase the predictive power of a target species

FFP: joint Fast Fourier transform and fractal dimension in amino acid property-aware phylogenetic analysis

Background

Amino acid property-aware phylogenetic analysis (APPA) refers to the phylogenetic analysis method based on amino acid property encoding, which is used for understanding and inferring evolutionary relationships between species from the molecular perspective. Fast Fourier transform (FFT) and Higuchi’s fractal dimension (HFD) have excellent performance in describing sequences’ structural and complexity information for APPA. However, with the exponential growth of protein sequence data, it is very important to develop a reliable APPA method for protein sequence analysis.

Results

Consequently, we propose a new method named FFP, it joints FFT and HFD. Firstly, FFP is used to encode protein sequences on the basis of the important physicochemical properties of amino acids, the dissociation constant, which determines acidity and basicity of protein molecules. Secondly, FFT and HFD are used to generate the feature vectors of encoded sequences, whereafter, the distance matrix is calculated from the cosine function, which describes the degree of similarity between species. The smaller the distance between them, the more similar they are. Finally, the phylogenetic tree is constructed. When FFP is tested for phylogenetic analysis on four groups of protein sequences, the results are obviously better than other comparisons, with the highest accuracy up to more than 97%.

Conclusion

FFP has higher accuracy in APPA and multi-sequence alignment. It also can measure the protein sequence similarity effectively. And it is hoped to play a role in APPA’s related research.

Predicting aggregate morphology of sequence-defined macromolecules with recurrent neural networks

Self-assembly of dilute sequence-defined macromolecules is a complex phenomenon in which the local arrangement of chemical moieties can lead to the formation of long-range structure. The dependence of this structure on the sequence necessarily implies that a mapping between the two exists, yet it has been difficult to model so far. Predicting the aggregation behavior of these macromolecules is challenging due to the lack of effective order parameters, a vast design space, inherent variability, and high computational costs associated with currently available simulation techniques. Here, we accurately predict the morphology of aggregates self-assembled from sequence-defined macromolecules using supervised machine learning. We find that regression models with implicit representation learning perform significantly better than those based on engineered features such as k-mer counting, and a recurrent-neural-network-based regressor performs the best out of nine model architectures we tested. Furthermore, we demonstrate the high-throughput screening of monomer sequences using the regression model to identify candidates for self-assembly into selected morphologies. Our strategy is shown to successfully identify multiple suitable sequences in every test we performed, so we hope the insights gained here can be extended to other increasingly complex design scenarios in the future, such as the design of sequences under polydispersity and at varying environmental conditions.

KinasePhos 3.0: Redesign and Expansion of the Prediction on Kinase-specific Phosphorylation Sites

The purpose of this work is to enhance KinasePhos, a machine learning-based kinase-specific phosphorylation site prediction tool. Experimentally verified kinase-specific phosphorylation data were collected from PhosphoSitePlus, UniProtKB, the Group-based Prediction System 5.0, and Phospho.ELM. In total, 41,421 experimentally verified kinase-specific phosphorylation sites were identified. A total of 1380 unique kinases were identified, including 753 with existing classification information from KinBase and the remaining 627 annotated by building a phylogenetic tree. Based on this kinase classification, a total of 771 predictive models were built at the individual, family, and group levels, using at least 15 experimentally verified substrate sites in positive training datasets. The improved models demonstrated their effectiveness compared with other prediction tools. For example, the prediction of sites phosphorylated by the protein kinase B, casein kinase 2, and protein kinase A families had accuracies of 94.5%, 92.5%, and 90.0%, respectively. The average prediction accuracy for all 771 models was 87.2%. For enhancing interpretability, the SHapley Additive exPlanations (SHAP) method was employed to assess feature importance. The web interface of KinasePhos 3.0 has been redesigned to provide comprehensive annotations of kinase-specific phosphorylation sites on multiple proteins. Additionally, considering the large scale of phosphoproteomic data, a downloadable prediction tool is available at https://awi.cuhk.edu.cn/KinasePhos/download.html or https://github.com/tom-209/KinasePhos-3.0-executable-file.

i2APP: A Two-Step Machine Learning Framework For Antiparasitic Peptides Identification

Parasites can cause enormous damage to their hosts. Studies have shown that antiparasitic peptides can inhibit the growth and development of parasites and even kill them. Because traditional biological methods to determine the activity of antiparasitic peptides are time-consuming and costly, a method for large-scale prediction of antiparasitic peptides is urgently needed. We propose a computational approach called i2APP that can efficiently identify APPs using a two-step machine learning (ML) framework. First, in order to solve the imbalance of positive and negative samples in the training set, a random under sampling method is used to generate a balanced training data set. Then, the physical and chemical features and terminus-based features are extracted, and the first classification is performed by Light Gradient Boosting Machine (LGBM) and Support Vector Machine (SVM) to obtain 264-dimensional higher level features. These features are selected by Maximal Information Coefficient (MIC) and the features with the big MIC values are retained. Finally, the SVM algorithm is used for the second classification in the optimized feature space. Thus the prediction model i2APP is fully constructed. On independent datasets, the accuracy and AUC of i2APP are 0.913 and 0.935, respectively, which are better than the state-of-arts methods. The key idea of the proposed method is that multi-level features are extracted from peptide sequences and the higher-level features can distinguish well the APPs and non-APPs.

Phylogenetic Analysis: A Novel Method of Protein Sequence Similarity Analysis

Protein sequence similarity analysis (PSSA) is a significant task in bioinformatics, which can obtain information about unknown sequences such as protein structures and homology relationships. Protein sequence refers to the series of amino acids with rich physical and chemical properties, namely the basic structure of proteins. However, sequence similarity analysis and phylogenetic analysis between different species which have complex amino acid sequences is a challenging problem. In this paper, nine properties of amino acids were considered and the sequence was converted into numerical values by principal component analysis (PCA); with Haar Wavelet Transform, and Higuchi fractal dimension (HFD), a new feature vector is constructed to represent the sequence; Spearman distance was selected to calculate the distance matrix and the phylogenetic tree was constructed. In this paper, two representative protein sequences (9 ND5 (NADH dehydrogenase 5) and 8 ND6 (NADH dehydrogenase 6)) were selected for similarity analysis and phylogenetic analysis, and compared with MEGA software and other existing methods. The extensive results show that our method is outperforming and results consistent with the known facts.

Recognition of Protein Network for Bioinformatics Knowledge Analysis Using Support Vector Machine

Protein is the material foundation of living things, and it directly takes part in and runs the process of living things itself. Predicting protein complexes helps us understand the structure and function of complexes, and it is an important foundation for studying how cells work. Genome-wide protein interaction (PPI) data is growing as high-throughput experiments become more common. The aim of this research is that it provides a dual-tree complex wavelet transform which is used to find out about the structure of proteins. It also identifies the secondary structure of protein network. Many computer-based methods for predicting protein complexes have also been developed in the field. Identifying the secondary structure of a protein is very important when you are studying protein characteristics and properties. This is how the protein sequence is added to the distance matrix. The scope of this research is that it can confidently predict certain protein complexes rapidly, which compensates for shortcomings in biological research. The three-dimensional coordinates of C atom are used to do this. According to the texture information in the distance matrix, the matrix is broken down into four levels by the double-tree complex wavelet transform because it has four levels. The subband energy and standard deviation in different directions are taken, and then, the two-dimensional feature vector is used to show the secondary structure features of the protein in a way that is easy to understand. Then, the KNN and SVM classifiers are used to classify the features that were found. Experiments show that a new feature called a dual-tree complex wavelet can improve the texture granularity and directionality of the traditional feature extraction method, which is called secondary structure.

An analysis of protein language model embeddings for fold prediction

The identification of the protein fold class is a challenging problem in structural biology. Recent computational methods for fold prediction leverage deep learning techniques to extract protein fold-representative embeddings mainly using evolutionary information in the form of multiple sequence alignment (MSA) as input source. In contrast, protein language models (LM) have reshaped the field thanks to their ability to learn efficient protein representations (protein-LM embeddings) from purely sequential information in a self-supervised manner. In this paper, we analyze a framework for protein fold prediction using pre-trained protein-LM embeddings as input to several fine-tuning neural network models, which are supervisedly trained with fold labels. In particular, we compare the performance of six protein-LM embeddings: the long short-term memory-based UniRep and SeqVec, and the transformer-based ESM-1b, ESM-MSA, ProtBERT and ProtT5; as well as three neural networks: Multi-Layer Perceptron, ResCNN-BGRU (RBG) and Light-Attention (LAT). We separately evaluated the pairwise fold recognition (PFR) and direct fold classification (DFC) tasks on well-known benchmark datasets. The results indicate that the combination of transformer-based embeddings, particularly those obtained at amino acid level, with the RBG and LAT fine-tuning models performs remarkably well in both tasks. To further increase prediction accuracy, we propose several ensemble strategies for PFR and DFC, which provide a significant performance boost over the current state-of-the-art results. All this suggests that moving from traditional protein representations to protein-LM embeddings is a very promising approach to protein fold-related tasks.

Single-Molecule Classification of Aspartic Acid and Leucine by Molecular Recognition through Hydrogen Bonding and Time-Series Analysis

Amino acid detection/identification methods are important for understanding biological systems. In this study, we developed the single-molecule measurement for investigated quantum tunneling enhancement by chemical modification and machine learning based time series analysis for develop accurate amino acid discrimination. We performed single-molecule measurement of L-aspartic Acid (Asp) and L-leucine (Leu) with mercaptoacetic acid (MAA) chemical modified nano-gap. The measured current was investigated by machine learning based time series analysis method for accurate amino acid discrimination. Compared to measurements using bare nano-gap, it is found that MAA modification improves the difference in the conductance-time profiles between Asp and Leu through the hydrogen bonding facilitated tunneling phenomena. It is also found that this method enables determination of relative concentration. even in the mixture of Asp and Leu. It improves selective analysis for amino acids, and therefore would be applicable in medicine, diagnosis, and single-molecule peptide sequencing.

GLTM: A Global-Local Attention LSTM Model to Locate Dimer Motif of Single-Pass Membrane Proteins

Single-pass membrane proteins, which constitute up to 50% of all transmembrane proteins, are typically active in significant conformational changes, such as a dimer or other oligomers, which is essential for understanding the function of transmembrane proteins. Finding the key motifs of oligomers through experimental observation is a routine method used in the field to infer the potential conformations of other members of the transmembrane protein family. However, approaches based on experimental observation need to consume a lot of time and manpower costs; moreover, they are hard to reveal the potential motifs. A proposed approach is to build an accurate and efficient transmembrane protein oligomer prediction model to screen the key motifs. In this paper, an attention-based Global-Local structure LSTM model named GLTM is proposed to predict dimers and screen potential dimer motifs. Different from traditional motifs screening based on highly conserved sequence search frame, a self-attention mechanism has been employed in GLTM to locate the highest dimerization score of subsequence fragments and has been proven to locate most known dimer motifs well. The proposed GLTM can reach 97.5% accuracy on the benchmark dataset collected from Membranome2.0. The three characteristics of GLTM can be summarized as follows: First, the original sequence fragment was converted to a set of subsequences which having the similar length of known motifs, and this additional step can greatly enhance the capability of capturing motif pattern; Second, to solve the problem of sample imbalance, a novel data enhancement approach combining improved one-hot encoding with random subsequence windows has been proposed to improve the generalization capability of GLTM; Third, position penalization has been taken into account, which makes a self-attention mechanism focused on special TM fragments. The experimental results in this paper fully demonstrated that the proposed GLTM has a broad application perspective on the location of potential oligomer motifs, and is helpful for preliminary and rapid research on the conformational change of mutants.

Using Chou's 5-steps rule to identify N6-methyladenine sites by ensemble learning combined with multiple feature extraction methods

N⁶-methyladenine (m6A), a type of modification mostly affecting the downstream biological functions and determining the levels of gene expression, is mediated by the methylation of adenine in nucleic acids. It is also a key factor for influencing biological processes and has attracted attention as a target for treating diseases. Here, an ensemble predictor named as TL-Methy, was developed to identify m6A sites across the genome. TL-Methy is a 2-level machine learning method developed by combining the support vector machine model and multiple features extraction methods, including nucleic acid composition, di-nucleotide composition, tri-nucleotide composition, position-specific trinucleotide propensity, Bi-profile Bayes, binary encoding, and accumulated nucleotide frequency. For Homo sapiens, TL-Methy method reached the accuracy of 91.68% on jackknife test and of 92.23% on 10-fold cross validation test; For Mus musculus, TL-Methy method achieved the accuracy of 93.66% on jackknife test and of 97.07% on 10-fold cross validation test; For Saccharomyces cerevisiae, TL-Methy method obtained the accuracy of 81.57% on jackknife test and of 82.54% on 10-fold cross validation test; For rice genome, TL-Methy method achieved the accuracy of 91.87% on jackknife test and of 93.04% on 10-fold cross validation test. The results via these two test approaches demonstrated the robustness and practicality of our TL-Methy model. The TL-Methy model may be as a potential method for m6A site identification.Communicated by Ramaswamy H. Sarma.

A Review of Sensors and Biosensors Modified with Conducting Polymers and Molecularly Imprinted Polymers Used in Electrochemical Detection of Amino Acids: Phenylalanine, Tyrosine, and Tryptophan

Recently, the studies on developing sensors and biosensors-with an obvious interdisciplinary character-have drawn the attention of many researchers specializing in various fundamental, but also complex domains such as chemistry, biochemistry, physics, biophysics, biology, bio-pharma-medicine, and bioengineering. Along these lines, the present paper is structured into three parts, and is aimed at synthesizing the most relevant studies on the construction and functioning of versatile devices, of electrochemical sensors and biosensors, respectively. The first part presents examples of the most representative scientific research focusing on the role and the importance of the phenylalanine, tyrosine, and tryptophan amino acids, selected depending on their chemical structure and their impact on the central nervous system. The second part is dedicated to presenting and exemplifying conductor polymers and molecularly imprinted polymers used as sensitive materials in achieving electrochemical sensors and biosensors. The last part of the review analyzes the sensors and biosensors developed so far to detect amino acids with the aid of conductor polymers and molecularly imprinted polymers from the point of view of the performances obtained, with emphasis on the detection methods, on the electrochemical reactions that take place upon detection, and on the electroanalytical performances. The present study was carried out with a view to highlighting, for the benefit of specialists in medicine and pharmacy, the possibility of achieving and purchasing efficient devices that might be used in the quality control of medicines, as well as in studying and monitoring diseases associated with these amino acids.

Deep learning program to predict protein functions based on sequence information

•

A new deep learning program to predict protein functions in silico.

•

Requirement of nothing more than the protein sequence information.

•

A sequence segmentation to improve the efficiency of prediction.

•

Prediction of the clinical impact of mutations or polymorphisms.

Deep learning technologies have been adopted to predict the functions of newly identified proteins in silico. However, most current models are not suitable for poorly characterized proteins because they require diverse information on target proteins. We designed a binary classification deep learning program requiring only sequence information. This program was named ‘FUTUSA’ (function teller using sequence alone). It applied sequence segmentation during the sequence feature extraction process, by a convolution neural network, to train the regional sequence patterns and their relationship. This segmentation process improved the predictive performance by 49% than the full-length process. Compared with a baseline method, our approach achieved higher performance in predicting oxidoreductase activity. In addition, FUTUSA also showed dramatic performance in predicting acetyltransferase and demethylase activities. Next, we tested the possibility that FUTUSA can predict the functional consequence of point mutation. After trained for monooxygenase activity, FUTUSA successfully predicted the impact of point mutations on phenylalanine hydroxylase, which is responsible for an inherited metabolic disease PKU. This deep-learning program can be used as the first-step tool for characterizing newly identified or poorly studied proteins.•

We proposed new deep learning program to predict protein functions in silico that requires nothing more than the protein sequence information.

•

Due to application of sequence segmentation, the efficiency of prediction is improved.

•

This method makes prediction of the clinical impact of mutations or polymorphisms possible.

Artificial intelligence based methods for hot spot prediction

Proteins interact through their interfaces to fulfill essential functions in the cell. They bind to their partners in a highly specific manner and form complexes that have a profound effect on understanding the biological pathways they are involved in. Any abnormal interactions may cause diseases. Therefore, the identification of small molecules which modulate protein interactions through their interfaces has high therapeutic potential. However, discovering such molecules is challenging. Most protein-protein binding affinity is attributed to a small set of amino acids found in protein interfaces known as hot spots. Recent studies demonstrate that drug-like small molecules specifically may bind to hot spots. Therefore, hot spot prediction is crucial. As experimental data accumulates, artificial intelligence begins to be used for computational hot spot prediction. First, we review machine learning and deep learning for computational hot spot prediction and then explain the significance of hot spots toward drug design.

Augmented sequence features and subcellular localization for functional characterization of unknown protein sequences

Advances in high-throughput techniques lead to evolving a large number of unknown protein sequences (UPS). Functional characterization of UPS is significant for the investigation of disease symptoms and drug repositioning. Protein subcellular localization is imperative for the functional characterization of protein sequences. Diverse techniques are used on protein sequences for feature extraction. However, many times a single feature extraction technique leads to poor prediction performance. In this paper, two feature augmentations are described through sequence induced, physicochemical, and evolutionary information of the amino acid residues. While augmented features preserve the sequence-order-information and protein-residue-properties. Two bacterial protein datasets Gram-Positive (G +) and Gram-Negative (G-) are utilized for the experimental work. After performing essential preprocessing on protein datasets, two sets of feature vectors are obtained. These feature vectors are used separately to train the different individual and ensembles such as decision tree (C 4.5), k-nearest neighbor (k-NN), multi-layer perceptron (MLP), Naïve Bayes (NB), support vector machine (SVM), AdaBoost, gradient boosting machine (GBM), and random forest (RF) with fivefold cross-validation. Prediction results of the model demonstrate that overall accuracy reported by C4.5 is highest 99.57% on G + and 97.47% on G- datasets with known protein sequences. Similarly, for the UPS overall accuracy of G + is 85.17% with SVM and 82.45% with G- dataset using MLP.

In-Pero: Exploiting Deep Learning Embeddings of Protein Sequences to Predict the Localisation of Peroxisomal Proteins

Peroxisomes are ubiquitous membrane-bound organelles, and aberrant localisation of peroxisomal proteins contributes to the pathogenesis of several disorders. Many computational methods focus on assigning protein sequences to subcellular compartments, but there are no specific tools tailored for the sub-localisation (matrix vs. membrane) of peroxisome proteins. We present here In-Pero, a new method for predicting protein sub-peroxisomal cellular localisation. In-Pero combines standard machine learning approaches with recently proposed multi-dimensional deep-learning representations of the protein amino-acid sequence. It showed a classification accuracy above 0.9 in predicting peroxisomal matrix and membrane proteins. The method is trained and tested using a double cross-validation approach on a curated data set comprising 160 peroxisomal proteins with experimental evidence for sub-peroxisomal localisation. We further show that the proposed approach can be easily adapted (In-Mito) to the prediction of mitochondrial protein localisation obtaining performances for certain classes of proteins (matrix and inner-membrane) superior to existing tools.

A Novel Protein Mapping Method for Predicting the Protein Interactions in COVID-19 Disease by Deep Learning

The new type of corona virus (SARS-COV-2) emerging in Wuhan, China has spread rapidly to the world and has become a pandemic. In addition to having a significant impact on daily life, it also shows its effect in different areas, including public health and economy. Currently, there is no vaccine or antiviral drug available to prevent the COVID-19 disease. Therefore, determination of protein interactions of new types of corona virus is vital in clinical studies, drug therapy, identification of preclinical compounds and protein functions. Protein–protein interactions are important to examine protein functions and pathways involved in various biological processes and to determine the cause and progression of diseases. Various high-throughput experimental methods have been used to identify protein–protein interactions in organisms, yet, there is still a huge gap in specifying all possible protein interactions in an organism. In addition, since the experimental methods used include cloning, labeling, affinity purification mass spectrometry, the processes take a long time. Determining these interactions with artificial intelligence-based methods rather than experimental approaches may help to identify protein functions faster. Thus, protein–protein interaction prediction using deep-learning algorithms has been employed in conjunction with experimental method to explore new protein interactions. However, to predict protein interactions with artificial intelligence techniques, protein sequences need to be mapped. There are various types and numbers of protein-mapping methods in the literature. In this study, we wanted to contribute to the literature by proposing a novel protein-mapping method based on the AVL tree. The proposed method was inspired by the fast search performance on the dictionary structure of AVL tree and was used to verify the protein interactions between SARS-COV-2 virus and human. First, protein sequences were mapped by both the proposed method and various protein-mapping methods. Then, the mapped protein sequences were normalized and classified by bidirectional recurrent neural networks. The performance of the proposed method was evaluated with accuracy, f1-score, precision, recall, and AUC scores. Our results indicated that our mapping method predicts the protein interactions between SARS-COV-2 virus proteins and human proteins at an accuracy of 97.76%, precision of 97.60%, recall of 98.33%, f1-score of 79.42%, and with AUC 89% in average.

Effect of sequence padding on the performance of deep learning models in archaeal protein functional prediction

The use of raw amino acid sequences as input for deep learning models for protein functional prediction has gained popularity in recent years. This scheme obliges to manage proteins with different lengths, while deep learning models require same-shape input. To accomplish this, zeros are usually added to each sequence up to a established common length in a process called zero-padding. However, the effect of different padding strategies on model performance and data structure is yet unknown. We propose and implement four novel types of padding the amino acid sequences. Then, we analysed the impact of different ways of padding the amino acid sequences in a hierarchical Enzyme Commission number prediction problem. Results show that padding has an effect on model performance even when there are convolutional layers implied. Contrastingly to most of deep learning works which focus mainly on architectures, this study highlights the relevance of the deemed-of-low-importance process of padding and raises awareness of the need to refine it for better performance. The code of this analysis is publicly available at https://github.com/b2slab/padding_benchmark .

EnACP: An Ensemble Learning Model for Identification of Anticancer Peptides

As cancer remains one of the main threats of human life, developing efficient cancer treatments is urgent. Anticancer peptides, which could overcome the significant side effects and poor results of traditional cancer treatments, have become a new potential alternative these years. However, identifying anticancer peptides by experimental methods is time consuming and resource consuming, it is of great significance to develop effective computational tools to quickly and accurately identify potential anticancer peptides from amino acid sequences. For most current computational methods, feature representation plays a key role in their final successes. This study proposes a novel fast and accurate approach to identify anticancer peptides using diversified feature representations and ensemble learning method. For the feature representations, the information is encoded from multidimensional feature spaces, including sequence composition, sequence-order, physicochemical properties, etc. In order to better model the potential relationships of peptides, multiple ensemble classifiers, LightGBMs, are applied to detect the different feature sets at first. Then the obtained multiple outputs are used as inputs of the support vector machine classifier, which effectively identifies anticancer peptides. Experimental results on cross validation and independent test sets demonstrate that our method can achieve better or comparable performances compared with other state-of-the-art methods.

Prediction of Protein-Protein Interaction Sites Using Convolutional Neural Network and Improved Data Sets

Protein-protein interaction (PPI) sites play a key role in the formation of protein complexes, which is the basis of a variety of biological processes. Experimental methods to solve PPI sites are expensive and time-consuming, which has led to the development of different kinds of prediction algorithms. We propose a convolutional neural network for PPI site prediction and use residue binding propensity to improve the positive samples. Our method obtains a remarkable result of the area under the curve (AUC) = 0.912 on the improved data set. In addition, it yields much better results on samples with high binding propensity than on randomly selected samples. This suggests that there are considerable false-positive PPI sites in the positive samples defined by the distance between residue atoms.