Recent advances in features generation for membrane protein sequences: From multiple sequence alignment to pre-trained language models

Membrane proteins play a crucial role in various cellular processes and are essential components of cell membranes. Computational methods have emerged as a powerful tool for studying membrane proteins due to their complex structures and properties that make them difficult to analyze experimentally. Traditional features for protein sequence analysis based on amino acid types, composition, and pair composition have limitations in capturing higher-order sequence patterns. Recently, multiple sequence alignment (MSA) and pre-trained language models (PLMs) have been used to generate features from protein sequences. However, the significant computational resources required for MSA-based features generation can be a major bottleneck for many applications. Several methods and tools have been developed to accelerate the generation of MSAs and reduce their computational cost, including heuristics and approximate algorithms. Additionally, the use of PLMs such as BERT has shown great potential in generating informative embeddings for protein sequence analysis. In this review, we provide an overview of traditional and more recent methods for generating features from protein sequences, with a particular focus on MSAs and PLMs. We highlight the advantages and limitations of these approaches and discuss the methods and tools developed to address the computational challenges associated with features generation. Overall, the advancements in computational methods and tools provide a promising avenue for gaining deeper insights into the function and properties of membrane proteins, which can have significant implications in drug discovery and personalized medicine.     

Discriminating lysosomal membrane protein types using dynamic neural network

This work presents a dynamic artificial neural network methodology, which classifies the proteins into their classes from their sequences alone: the lysosomal membrane protein classes and the various other membranes protein classes. In this paper, neural networks-based lysosomal-associated membrane protein type prediction system is proposed. Different protein sequence representations are fused to extract the features of a protein sequence, which includes seven feature sets; amino acid (AA) composition, sequence length, hydrophobic group, electronic group, sum of hydrophobicity, R-group, and dipeptide composition. To reduce the dimensionality of the large feature vector, we applied the principal component analysis. The probabilistic neural network, generalized regression neural network, and Elman regression neural network (RNN) are used as classifiers and compared with layer recurrent network (LRN), a dynamic network. The dynamic networks have memory, i.e. its output depends not only on the input but the previous outputs also. Thus, the accuracy of LRN classifier among all other artificial neural networks comes out to be the highest. The overall accuracy of jackknife cross-validation is 93.2% for the data-set. These predicted results suggest that the method can be effectively applied to discriminate lysosomal associated membrane proteins from other membrane proteins (Type-I, Outer membrane proteins, GPI-Anchored) and Globular proteins, and it also indicates that the protein sequence representation can better reflect the core feature of membrane proteins than the classical AA composition.     

Predicting membrane protein types by fusing composite protein sequence features into pseudo amino acid composition

Membrane proteins are vital type of proteins that serve as channels, receptors, and energy transducers in a cell. Prediction of membrane protein types is an important research area in bioinformatics. Knowledge of membrane protein types provides some valuable information for predicting novel example of the membrane protein types. However, classification of membrane protein types can be both time consuming and susceptible to errors due to the inherent similarity of membrane protein types. In this paper, neural networks based membrane protein type prediction system is proposed. Composite protein sequence representation (CPSR) is used to extract the features of a protein sequence, which includes seven feature sets; amino acid composition, sequence length, 2 gram exchange group frequency, hydrophobic group, electronic group, sum of hydrophobicity, and R-group. Principal component analysis is then employed to reduce the dimensionality of the feature vector. The probabilistic neural network (PNN), generalized regression neural network, and support vector machine (SVM) are used as classifiers. A high success rate of 86.01% is obtained using SVM for the jackknife test. In case of independent dataset test, PNN yields the highest accuracy of 95.73%. These classifiers exhibit improved performance using other performance measures such as sensitivity, specificity, Mathew's correlation coefficient, and F-measure. The experimental results show that the prediction performance of the proposed scheme for classifying membrane protein types is the best reported, so far. This performance improvement may largely be credited to the learning capabilities of neural networks and the composite feature extraction strategy, which exploits seven different properties of protein sequences. The proposed Mem-Predictor can be accessed at http://111.68.99.218/Mem-Predictor.     

Applications of sequence coevolution in membrane protein biochemistry

Recently, protein sequence coevolution analysis has matured into a predictive powerhouse for protein structure and function. Direct methods, which use global statistical models of sequence coevolution, have enabled the prediction of membrane and disordered protein structures, protein complex architectures, and the functional effects of mutations in proteins. The field of membrane protein biochemistry and structural biology has embraced these computational techniques, which provide functional and structural information in an otherwise experimentally-challenging field. Here we review recent applications of protein sequence coevolution analysis to membrane protein structure and function and highlight the promising directions and future obstacles in these fields. We provide insights and guidelines for membrane protein biochemists who wish to apply sequence coevolution analysis to a given experimental system.     

Geometry preserving projections algorithm for predicting membrane protein types

Given a new uncharacterized protein sequence, a biologist may want to know whether it is a membrane protein or not? If it is, which membrane protein type it belongs to? Knowing the type of an uncharacterized membrane protein often provides useful clues for finding the biological function of the query protein, developing the computational methods to address these questions can be really helpful. In this study, a sequence encoding scheme based on combing pseudo position-specific score matrix (PsePSSM) and dipeptide composition (DC) is introduced to represent protein samples. However, this sequence encoding scheme would correspond to a very high dimensional feature vector. A dimensionality reduction algorithm, the so-called geometry preserving projections (GPP) is introduced to extract the key features from the high-dimensional space and reduce the original high-dimensional vector to a lower-dimensional one. Finally, the K-nearest neighbor (K-NN) and support vector machine (SVM) classifiers are employed to identify the types of membrane proteins based on their reduced low-dimensional features. Our jackknife and independent dataset test results thus obtained are quite encouraging, which indicate that the above methods are used effectively to deal with this complicated problem of predicting the membrane protein type.     

Prediction of protein functions with gene ontology and interspecies protein homology data

Accurate computational prediction of protein functions increasingly relies on network-inspired models for the protein function transfer. This task can become challenging for proteins isolated in their own network or those with poor or uncharacterized neighborhoods. Here, we present a novel probabilistic chain-graph-based approach for predicting protein functions that builds on connecting networks of two (or more) different species by links of high interspecies sequence homology. In this way, proteins are able to "exchange" functional information with their neighbors-homologs from a different species. The knowledge of interspecies relationships, such as the sequence homology, can become crucial in cases of limited information from other sources of data, including the protein-protein interactions or cellular locations of proteins. We further enhance our model to account for the Gene Ontology dependencies by linking multiple but related functional ontology categories within and across multiple species. The resulting networks are of significantly higher complexity than most traditional protein network models. We comprehensively benchmark our method by applying it to two largest protein networks, the Yeast and the Fly. The joint Fly-Yeast network provides substantial improvements in precision, accuracy, and false positive rate over networks that consider either of the sources in isolation. At the same time, the new model retains the computational efficiency similar to that of the simpler networks.     

Membrane protein prediction methods

We survey computational approaches that tackle membrane protein structure and function prediction. While describing the main ideas that have led to the development of the most relevant and novel methods, we also discuss pitfalls, provide practical hints and highlight the challenges that remain. The methods covered include: sequence alignment, motif search, functional residue identification, transmembrane segment and protein topology predictions, homology and ab initio modeling. In general, predictions of functional and structural features of membrane proteins are improving, although progress is hampered by the limited amount of high-resolution experimental information available. While predictions of transmembrane segments and protein topology rank among the most accurate methods in computational biology, more attention and effort will be required in the future to ameliorate database search, homology and ab initio modeling.     

Fold change in evolution of protein structures

Typically, protein spatial structures are more conserved in evolution than amino acid sequences. However, the recent explosion of sequence and structure information accompanied by the development of powerful computational methods led to the accumulation of examples of homologous proteins with globally distinct structures. Significant sequence conservation, local structural resemblance, and functional similarity strongly indicate evolutionary relationships between these proteins despite pronounced structural differences at the fold level. Several mechanisms such as insertions/deletions/substitutions, circular permutations, and rearrangements in beta-sheet topologies account for the majority of detected structural irregularities. The existence of evolutionarily related proteins that possess different folds brings new challenges to the homology modeling techniques and the structure classification strategies and offers new opportunities for protein design in experimental studies.     

A Multi-label Classifier for Prediction Membrane Protein Functional Types in Animal

Membrane protein is an important composition of cell membrane. Given a membrane protein sequence, how can we identify its type(s) is very important because the type keeps a close correlation with its functions. According to previous studies, membrane protein can be divided into the following eight types: single-pass type I, single-pass type II, single-pass type III, single-pass type IV, multipass, lipid-anchor, GPI-anchor, peripheral membrane protein. With the avalanche of newly found protein sequences in the post-genomic age, it is urgent to develop an automatic and effective computational method to rapid and reliable prediction of the types of membrane proteins. At present, most of the existing methods were based on the assumption that one membrane protein only belongs to one type. Actually, a membrane protein may simultaneously exist at two or more different functional types. In this study, a new method by hybridizing the pseudo amino acid composition with multi-label algorithm called LIFT (multi-label learning with label-specific features) was proposed to predict the functional types both singleplex and multiplex animal membrane proteins. Experimental result on a stringent benchmark dataset of membrane proteins by jackknife test show that the absolute-true obtained was 0.6342, indicating that our approach is quite promising. It may become a useful high-through tool, or at least play a complementary role to the existing predictors in identifying functional types of membrane proteins.     

Prediction of leucine-rich nuclear export signal containing proteins with NESsential

The classical nuclear export signal (NES), also known as the leucine-rich NES, is a protein localization signal often involved in important processes such as signal transduction and cell cycle regulation. Although 15 years has passed since its discovery, limited structural information and high sequence diversity have hampered understanding of the NES. Several consensus sequences have been proposed to describe it, but they suffer from poor predictive power. On the other hand, the NetNES server provides the only computational method currently available. Although these two methods have been widely used to attempt to find the correct NES position within potential NES-containing proteins, their performance has not yet been evaluated on the basic task of identifying NES-containing proteins. We propose a new predictor, NESsential, which uses sequence derived meta-features, such as predicted disorder and solvent accessibility, in addition to primary sequence. We demonstrate that it can identify promising NES-containing candidate proteins (albeit at low coverage), but other methods cannot. We also quantitatively demonstrate that predicted disorder is a useful feature for prediction and investigate the different features of (predicted) ordered versus disordered NES's. Finally, we list 70 recently discovered NES-containing proteins, doubling the number available to the community.     

An ensemble of support vector machines for predicting the membrane protein type directly from the amino acid sequence

Given a particular membrane protein, it is very important to know which membrane type it belongs to because this kind of information can provide clues for better understanding its function. In this work, we propose a system for predicting the membrane protein type directly from the amino acid sequence. The feature extraction step is based on an encoding technique that combines the physicochemical amino acid properties with the residue couple model. The residue couple model is a method inspired by Chou’s quasi-sequence-order model that extracts the features by utilizing the sequence order effect indirectly. A set of support vector machines, each trained using a different physicochemical amino acid property combined with the residue couple model, are combined by vote rule. The success rate obtained by our system on a difficult dataset, where the sequences in a given membrane type have a low sequence identity to any other proteins of the same membrane type, are quite high, indicating that the proposed method, where the features are extracted directly from the amino acid sequence, is a feasible system for predicting the membrane protein type.     

Predicting metal-binding site residues in low-resolution structural models

The accurate prediction of the biochemical function of a protein is becoming increasingly important, given the unprecedented growth of both structural and sequence databanks. Consequently, computational methods are required to analyse such data in an automated manner to ensure genomes are annotated accurately. Protein structure prediction methods, for example, are capable of generating approximate structural models on a genome-wide scale. However, the detection of functionally important regions in such crude models, as well as structural genomics targets, remains an extremely important problem. The method described in the current study, MetSite, represents a fully automatic approach for the detection of metal-binding residue clusters applicable to protein models of moderate quality. The method involves using sequence profile information in combination with approximate structural data. Several neural network classifiers are shown to be able to distinguish metal sites from non-sites with a mean accuracy of 94.5%. The method was demonstrated to identify metal-binding sites correctly in LiveBench targets where no obvious metal-binding sequence motifs were detectable using InterPro. Accurate detection of metal sites was shown to be feasible for low-resolution predicted structures generated using mGenTHREADER where no side-chain information was available. High-scoring predictions were observed for a recently solved hypothetical protein from Haemophilus influenzae, indicating a putative metal-binding site.     

Predicting protein subcellular location with network embedding and enrichment features

The subcellular location of a protein is highly related to its function. Identifying the location of a given protein is an essential step for investigating its related problems. Traditional experimental methods can produce solid determination. However, their limitations, such as high cost and low efficiency, are evident. Computational methods provide an alternative means to address these problems. Most previous methods constantly extract features from protein sequences or structures for building prediction models. In this study, we use two types of features and combine them to construct the model. The first feature type is extracted from a protein–protein interaction network to abstract the relationship between the encoded protein and other proteins. The second type is obtained from gene ontology and biological pathways to indicate the existing functions of the encoded protein. These features are analyzed using some feature selection methods. The final optimum features are adopted to build the model with recurrent neural network as the classification algorithm. Such model yields good performance with Matthews correlation coefficient of 0.844. A decision tree is used as a rule learning classifier to extract decision rules. Although the performance of decision rules is poor, they are valuable in revealing the molecular mechanism of proteins with different subcellular locations. The final analysis confirms the reliability of the extracted rules. The source code of the propose method is freely available at https://github.com/xypan1232/rnnloc     

Prediction of protein kinase-specific phosphorylation sites in hierarchical structure using functional information and random forest

Reversible protein phosphorylation is one of the most important post-translational modifications, which regulates various biological cellular processes. Identification of the kinase-specific phosphorylation sites is helpful for understanding the phosphorylation mechanism and regulation processes. Although a number of computational approaches have been developed, currently few studies are concerned about hierarchical structures of kinases, and most of the existing tools use only local sequence information to construct predictive models. In this work, we conduct a systematic and hierarchy-specific investigation of protein phosphorylation site prediction in which protein kinases are clustered into hierarchical structures with four levels including kinase, subfamily, family and group. To enhance phosphorylation site prediction at all hierarchical levels, functional information of proteins, including gene ontology (GO) and protein–protein interaction (PPI), is adopted in addition to primary sequence to construct prediction models based on random forest. Analysis of selected GO and PPI features shows that functional information is critical in determining protein phosphorylation sites for every hierarchical level. Furthermore, the prediction results of Phospho.ELM and additional testing dataset demonstrate that the proposed method remarkably outperforms existing phosphorylation prediction methods at all hierarchical levels. The proposed method is freely available at http://bioinformatics.ustc.edu.cn/phos_pred/.     

Molecular dynamics simulations of membrane proteins

Membrane proteins control the traffic across cell membranes and thereby play an essential role in cell function from transport of various solutes to immune response via molecular recognition. Because it is very difficult to determine the structures of membrane proteins experimentally, computational methods have been increasingly used to study their structure and function. Here we focus on two classes of membrane proteins—ion channels and transporters—which are responsible for the generation of action potentials in nerves, muscles, and other excitable cells. We describe how computational methods have been used to construct models for these proteins and to study the transport mechanism. The main computational tool is the molecular dynamics (MD) simulation, which can be used for everything from refinement of protein structures to free energy calculations of transport processes. We illustrate with specific examples from gramicidin and potassium channels and aspartate transporters how the function of these membrane proteins can be investigated using MD simulations.     

A New Method for the Discovery of Essential Proteins

Background

Experimental methods for the identification of essential proteins are always costly, time-consuming, and laborious. It is a challenging task to find protein essentiality only through experiments. With the development of high throughput technologies, a vast amount of protein-protein interactions are available, which enable the identification of essential proteins from the network level. Many computational methods for such task have been proposed based on the topological properties of protein-protein interaction (PPI) networks. However, the currently available PPI networks for each species are not complete, i.e. false negatives, and very noisy, i.e. high false positives, network topology-based centrality measures are often very sensitive to such noise. Therefore, exploring robust methods for identifying essential proteins would be of great value.

Method

In this paper, a new essential protein discovery method, named CoEWC (Co-Expression Weighted by Clustering coefficient), has been proposed. CoEWC is based on the integration of the topological properties of PPI network and the co-expression of interacting proteins. The aim of CoEWC is to capture the common features of essential proteins in both date hubs and party hubs. The performance of CoEWC is validated based on the PPI network of Saccharomyces cerevisiae. Experimental results show that CoEWC significantly outperforms the classical centrality measures, and that it also outperforms PeC, a newly proposed essential protein discovery method which outperforms 15 other centrality measures on the PPI network of Saccharomyces cerevisiae. Especially, when predicting no more than 500 proteins, even more than 50% improvements are obtained by CoEWC over degree centrality (DC), a better centrality measure for identifying protein essentiality.

Conclusions

We demonstrate that more robust essential protein discovery method can be developed by integrating the topological properties of PPI network and the co-expression of interacting proteins. The proposed centrality measure, CoEWC, is effective for the discovery of essential proteins.     

Predicting protein folding rate from amino acid sequence

Predicting protein folding rate from amino acid sequence is an important challenge in computational and molecular biology. Over the past few years, many methods have been developed to reflect the correlation between the folding rates and protein structures and sequences. In this paper, we present an effective method, a combined neural network--genetic algorithm approach, to predict protein folding rates only from amino acid sequences, without any explicit structural information. The originality of this paper is that, for the first time, it tackles the effect of sequence order. The proposed method provides a good correlation between the predicted and experimental folding rates. The correlation coefficient is 0.80 and the standard error is 2.65 for 93 proteins, the largest such databases of proteins yet studied, when evaluated with leave-one-out jackknife test. The comparative results demonstrate that this correlation is better than most of other methods, and suggest the important contribution of sequence order information to the determination of protein folding rates.     

金黄色葡萄球菌蛋白质相互作用网络及功能

【目的】金黄色葡萄球菌是一种革兰氏阳性菌,是目前最难以对付的病菌之一。它能引起多种感染,特别是在医院环境中。近年来,抗药性金黄色葡萄球菌传染更加严重,已成为公共卫生威胁。由于以前对于金黄色葡萄球菌的实验性研究大都是基于单个基因或者蛋白进行的,为了更好的研究这个物种,有必要从整体上把握金黄色葡萄球菌的蛋白作用机理。【方法】采用系统发生谱、操纵子法、基因融合法、基因邻近法、同源映射法等五种计算方法预测金黄色葡萄球菌蛋白质相互作用网络。【结果】从蛋白组的角度构建了金黄色葡萄球菌蛋白相互作用网络,并对网络进行功能分析。【结论】网络的分析表明金黄色葡萄球菌的蛋白质相互作用网络也服从scale-free属性,发现了SA0939、SA0868、rplD等重要的蛋白。通过对金黄色葡萄球菌的重要的细胞壁合成和信号转导调控蛋白局部网络分析,发现了一些对这两个系统十分重要的蛋白分子,这些信息将为更好的了解金黄色葡萄球菌的致病机理和开发新的药物靶点提供指导。     

Some remarks on protein attribute prediction and pseudo amino acid composition

With the accomplishment of human genome sequencing, the number of sequence-known proteins has increased explosively. In contrast, the pace is much slower in determining their biological attributes. As a consequence, the gap between sequence-known proteins and attribute-known proteins has become increasingly large. The unbalanced situation, which has critically limited our ability to timely utilize the newly discovered proteins for basic research and drug development, has called for developing computational methods or high-throughput automated tools for fast and reliably identifying various attributes of uncharacterized proteins based on their sequence information alone. Actually, during the last two decades or so, many methods in this regard have been established in hope to bridge such a gap. In the course of developing these methods, the following things were often needed to consider: (1) benchmark dataset construction, (2) protein sample formulation, (3) operating algorithm (or engine), (4) anticipated accuracy, and (5) web-server establishment. In this review, we are to discuss each of the five procedures, with a special focus on the introduction of pseudo amino acid composition (PseAAC), its different modes and applications as well as its recent development, particularly in how to use the general formulation of PseAAC to reflect the core and essential features that are deeply hidden in complicated protein sequences.