Reliability measures for membrane protein topology prediction algorithms

We have developed reliability scores for five widely used membrane protein topology prediction methods, and have applied them both on a test set of 92 bacterial plasma membrane proteins with experimentally determined topologies and on all predicted helix bundle membrane proteins in three fully sequenced genomes: Escherichia coli, Saccharomyces cerevisiae and Caenorhabditis elegans. We show that the reliability scores work well for the TMHMM and MEMSAT methods, and that they allow the probability that the predicted topology is correct to be estimated for any protein. We further show that the available test set is biased towards high-scoring proteins when compared to the genome-wide data sets, and provide estimates for the expected prediction accuracy of TMHMM across the three genomes. Finally, we show that the performance of TMHMM is considerably better when limited experimental information (such as the in/out location of a protein's C terminus) is available, and estimate that at least ten percentage points in overall accuracy in whole-genome predictions can be gained in this way.     

An improved hidden Markov model for transmembrane protein detection and topology prediction and its applications to complete genomes

MOTIVATION: Knowledge of the transmembrane helical topology can help identify binding sites and infer functions for membrane proteins. However, because membrane proteins are hard to solubilize and purify, only a very small amount of membrane proteins have structure and topology experimentally determined. This has motivated various computational methods for predicting the topology of membrane proteins. RESULTS: We present an improved hidden Markov model, TMMOD, for the identification and topology prediction of transmembrane proteins. Our model uses TMHMM as a prototype, but differs from TMHMM by the architecture of the submodels for loops on both sides of the membrane and also by the model training procedure. In cross-validation experiments using a set of 83 transmembrane proteins with known topology, TMMOD outperformed TMHMM and other existing methods, with an accuracy of 89% for both topology and locations. In another experiment using a separate set of 160 transmembrane proteins, TMMOD had 84% for topology and 89% for locations. When utilized for identifying transmembrane proteins from non-transmembrane proteins, particularly signal peptides, TMMOD has consistently fewer false positives than TMHMM does. Application of TMMOD to a collection of complete genomes shows that the number of predicted membrane proteins accounts for approximately 20-30% of all genes in those genomes, and that the topology where both the N- and C-termini are in the cytoplasm is dominant in these organisms except for Caenorhabditis elegans. AVAILABILITY: http://liao.cis.udel.edu/website/servers/TMMOD/     

The use of functional domains to improve transmembrane protein topology prediction

Transmembrane proteins affect vital cellular functions and pathogenesis, and are a focus of drug design. It is difficult to obtain diffraction quality crystals to study transmembrane protein structure. Computational tools for transmembrane protein topology prediction fill in the gap between the abundance of transmembrane proteins and the scarcity of known membrane protein structures. Their prediction accuracy is still inadequate: TMHMM, the current state-of-the-art method, has less than 52% accuracy in topology prediction on one set of transmembrane proteins of known topology. Based on the observation that there are functional domains that occur preferentially internal or external to the membrane, we have extended the model of TMHMM to incorporate functional domains, using a probabilistic approach originally developed for computational gene finding. Our extension is better than TMHMM in predicting the topology of transmembrane proteins. As prediction of functional domain improves, our system's prediction accuracy will likely improve as well.     

Prediction of partial membrane protein topologies using a consensus approach

We have developed a method to reliably identify partial membrane protein topologies using the consensus of five topology prediction methods. When evaluated on a test set of experimentally characterized proteins, we find that approximately 90% of the partial consensus topologies are correctly predicted in membrane proteins from prokaryotic as well as eukaryotic organisms. Whole-genome analysis reveals that a reliable partial consensus topology can be predicted for approximately 70% of all membrane proteins in a typical bacterial genome and for approximately 55% of all membrane proteins in a typical eukaryotic genome. The average fraction of sequence length covered by a partial consensus topology is 44% for the prokaryotic proteins and 17% for the eukaryotic proteins in our test set, and similar numbers are found when the algorithm is applied to whole genomes. Reliably predicted partial topologies may simplify experimental determinations of membrane protein topology.     

Reliability of transmembrane predictions in whole-genome data

Transmembrane prediction methods are generally benchmarked on a set of proteins with experimentally verified topology. We have investigated if the accuracy measured on such datasets can be expected in an unbiased genomic analysis, or if there is a bias towards 'easily predictable' proteins in the benchmark datasets. As a measurement of accuracy, the concordance of the results from five different prediction methods was used (TMHMM, PHD, HMMTOP, MEMSAT, and TOPPRED). The benchmark dataset showed significantly higher levels (up to five times) of agreement between different methods than in 10 tested genomes. We have also analyzed which programs are most prone to make mispredictions by measuring the frequency of one-out-of-five disagreeing predictions.     

Comparative analysis of amino acid distributions in integral membrane proteins from 107 genomes

We have performed a comparative analysis of amino acid distributions in predicted integral membrane proteins from a total of 107 genomes. A procedure for identification of membrane spanning helices was optimized on a homology-reduced data set of 170 multi-spanning membrane proteins with experimentally determined topologies. The optimized method was then used for extraction of highly reliable partial topologies from all predicted membrane proteins in each genome, and the average biases in amino acid distributions between loops on opposite sides of the membrane were calculated. The results strongly support the notion that a biased distribution of Lys and Arg residues between cytoplasmic and extra-cytoplasmic segments (the positive-inside rule) is present in most if not all organisms.     

Consensus predictions of membrane protein topology

We have explored the possibility that consensus predictions of membrane protein topology might provide a means to estimate the reliability of a predicted topology. Using five current topology prediction methods and a test set of 60 Escherichia coli inner membrane proteins with experimentally determined topologies, we find that prediction performance varies strongly with the number of methods that agree, and that the topology of nearly half of all E. coli inner membrane proteins can be predicted with high reliability (>90% correct predictions) by a simple majority-vote approach.     

Secreted protein prediction system combining CJ-SPHMM,TMHMM, and PSORT

To increase the coverage of secreted protein prediction, we describe a combination strategy. Instead of using a single method, we combine Hidden Markov Model (HMM)-based methods CJ-SPHMM and TMHMM with PSORT in secreted protein prediction. CJ-SPHMM is an HMM-based signal peptide prediction method, while TMHMM is an HMM-based transmembrane (TM) protein prediction algorithm. With CJ-SPHMM and TMHMM, proteins with predicted signal peptide and without predicted TM regions are taken as putative secreted proteins. This HMM-based approach predicts secreted protein with Ac (Accuracy) at 0.82 and Cc (Correlation coefficient) at 0.75, which are similar to PSORT with Ac at 0.82 and Cc at 0.76. When we further complement the HMM-based method, i.e., CJ-SPHMM + TMHMM with PSORT in secreted protein prediction, the Ac value is increased to 0.86 and the Cc value is increased to 0.81. Taking this combination strategy to search putative secreted proteins from the International Protein Index (IPI) maintained at the European Bioinformatics Institute (EBI), we constructed a putative human secretome with 5235 proteins. The prediction system described here can also be applied to predicting secreted proteins from other vertebrate proteomes. Availability: The CJ-SPHMM and predicted secreted proteins are available at: ftp://ftp.cbi.pku.edu.cn/pub/secreted-protein/     

An hierarchical artificial neural network system for the classification of transmembrane proteins.

This work presents a simple artificial neural network which classifies proteins into two classes from their sequences alone: the membrane protein class and the non-membrane protein class. This may be important in the functional assignment and analysis of open reading frames (ORF's) identified in complete genomes and, especially, those ORF's that correspond to proteins with unknown function. The network described here has a simple hierarchical feed-forward topology and a limited number of neurons which makes it very fast. By using only information contained in 11 protein sequences, the method was able to identify, with 100% accuracy, all membrane proteins with reliable topologies collected from several papers in the literature. Applied to a test set of 995 globular, water-soluble proteins, the neural network classified falsely 23 of them in the membrane protein class (97.7% of correct assignment). The method was also applied to the complete SWISS-PROT database with considerable success and on ORF's of several complete genomes. The neural network developed was associated with the PRED-TMR algorithm (Pasquier,C., Promponas,V.J., Palaios,G.A., Hamodrakas,J.S. and Hamodrakas,S.J., 1999) in a new application package called PRED-TMR2. A WWW server running the PRED-TMR2 software is available at http://o2.db.uoa.gr/PRED-TMR2     

Estimation of membrane proteins in the human proteome

Genomics and proteomics have added valuable information to our knowledgebase of the human biological system including the discovery of therapeutic targets and disease biomarkers. However, molecular profiling studies commonly result in the identification of novel proteins of unknown localization. A class of proteins of special interest is membrane proteins, in particular plasma membrane proteins. Despite their biological and medical significance, the 3-dimensional structures of less than 1% of plasma membrane proteins have been determined. In order to aid in identification of membrane proteins, a number of computational methods have been developed. These tools operate by predicting the presence of transmembrane segments. Here, we utilized five topology prediction methods (TMHMM, SOSUI, waveTM, HMMTOP, and TopPred II) in order to estimate the ratio of integral membrane proteins in the human proteome. These methods employ different algorithms and include a newly-developed method (waveTM) that has yet to be tested on a large proteome database. Since these tools are prone for error mainly as a result of falsely predicting signal peptides as transmembrane segments, we have utilized an additional method, SignalP. Based on our analyses, the ratio of human proteins with transmembrane segments is estimated to fall between 15% and 39% with a consensus of 13%. Agreement among the programs is reduced further when both a positive identification of a membrane protein and the number of transmembrane segments per protein are considered. Such a broad range of prediction depends on the selectivity of the individual method in predicting integral membrane proteins. These methods can play a critical role in determining protein structure and, hence, identifying suitable drug targets in humans.     

A predictor of membrane class: Discriminating alpha-helical and beta-barrel membrane proteins from non-membranous proteins

Accurate protein structure prediction remains an active objective of research in bioinformatics. Membrane proteins comprise approximately 20% of most genomes. They are, however, poorly tractable targets of experimental structure determination. Their analysis using bioinformatics thus makes an important contribution to their on-going study. Using a method based on Bayesian Networks, which provides a flexible and powerful framework for statistical inference, we have addressed the alignment-free discrimination of membrane from non-membrane proteins. The method successfully identifies prokaryotic and eukaryotic alpha-helical membrane proteins at 94.4% accuracy, beta-barrel proteins at 72.4% accuracy, and distinguishes assorted non-membranous proteins with 85.9% accuracy. The method here is an important potential advance in the computational analysis of membrane protein structure. It represents a useful tool for the characterisation of membrane proteins with a wide variety of potential applications.     

使用多特征联合变量的支持向量机方法预测外膜蛋白

外膜蛋白(Outer Membrane Proteins, OMPs)是一类具有重要生物功能的蛋白质, 通过生物信息学方法来预测OMPs能够为预测OMPs的二级和三级结构以及在基因组发现新的OMPs提供帮助。文中提出计算蛋白质序列的氨基酸含量特征、二肽含量特征和加权多阶氨基酸残基指数相关系数特征, 将三类特征组合, 采用支持向量机(Support Vector Machine, SVM)算法来识别OMPs。计算了包括四种残基指数的多种组合特征的识别结果, 并且讨论了相关系数的阶次和权值对预测性能的影响。在数据集上的十倍交叉验证测试和独立性测试结果显示, 组合特征识别方法对OMPs和非OMPs的识别精度最高分别达到96.96%和97.33%, 优于现有的多种方法。在五种细菌基因组内识别OMPs的结果显示, 组合特征方法具有很高的特异性, 并且对PDB数据库中已知结构的OMPs识别准确度超过99%。表明该方法能够作为基因组内筛选OMPs的有效工具。     

使用多特征联合变量的支持向量机方法预测外膜蛋白

外膜蛋白(Outer Membrane Proteins, OMPs)是一类具有重要生物功能的蛋白质, 通过生物信息学方法来预测OMPs能够为预测OMPs的二级和三级结构以及在基因组发现新的OMPs提供帮助。文中提出计算蛋白质序列的氨基酸含量特征、二肽含量特征和加权多阶氨基酸残基指数相关系数特征, 将三类特征组合, 采用支持向量机(Support Vector Machine, SVM)算法来识别OMPs。计算了包括四种残基指数的多种组合特征的识别结果, 并且讨论了相关系数的阶次和权值对预测性能的影响。在数据集上的十倍交叉验证测试和独立性测试结果显示, 组合特征识别方法对OMPs和非OMPs的识别精度最高分别达到96.96%和97.33%, 优于现有的多种方法。在五种细菌基因组内识别OMPs的结果显示, 组合特征方法具有很高的特异性, 并且对PDB数据库中已知结构的OMPs识别准确度超过99%。表明该方法能够作为基因组内筛选OMPs的有效工具。     

Membrane topology of three Xcp proteins involved in exoprotein transport by Pseudomonas aeruginosa.

Xcp proteins constitute the secretory apparatus of Pseudomonas aeruginosa. Deduced amino acid sequence of xcp genes, expression, and subcellular localization revealed unexpected features. Indeed, most Xcp proteins are found in the cytoplasmic membrane although xcp mutations lead to periplasmic accumulation of exoproteins, indicating that the limiting step is translocation across the outer membrane. To understand the mechanism by which the machinery functions and the interactions between its components, it is valuable to know their membrane organization. We report data demonstrating the N(in)-C(out) topologies of three general secretion pathway components, the XcpP, -Y, and -Z proteins.     

Proportion of membrane proteins in proteomes of 15 single-cell organisms analyzed by the SOSUI prediction system

A software system, SOSUI, was previously developed for discriminating between soluble and membrane proteins and predicting transmembrane regions (Hirokawa et al., Bioinformatics, 14 (1998) 378-379). The performance of the system was 99% for the discrimination between two types of proteins and 96% for the prediction of transmembrane helices. When all of the amino acid sequences from 15 single-cell organisms were analyzed by SOSUI, the proportion of predicted polytopic membrane proteins showed an almost constant value of 15-20%, irrespective of the total genome size. However, single-cell organisms appeared to be categorized in terms of the preference of the number of transmembrane segments: species with small genomes were characterized by a significant peak at a helix number of approximately six or seven; species with large genomes showed a peak at 10 or 11 helices; and species with intermediate genome sizes showed a monotonous decrease of the population of membrane proteins against the number of transmembrane helices.     

A combined transmembrane topology and signal peptide prediction method

An inherent problem in transmembrane protein topology prediction and signal peptide prediction is the high similarity between the hydrophobic regions of a transmembrane helix and that of a signal peptide, leading to cross-reaction between the two types of predictions. To improve predictions further, it is therefore important to make a predictor that aims to discriminate between the two classes. In addition, topology information can be gained when successfully predicting a signal peptide leading a transmembrane protein since it dictates that the N terminus of the mature protein must be on the non-cytoplasmic side of the membrane. Here, we present Phobius, a combined transmembrane protein topology and signal peptide predictor. The predictor is based on a hidden Markov model (HMM) that models the different sequence regions of a signal peptide and the different regions of a transmembrane protein in a series of interconnected states. Training was done on a newly assembled and curated dataset. Compared to TMHMM and SignalP, errors coming from cross-prediction between transmembrane segments and signal peptides were reduced substantially by Phobius. False classifications of signal peptides were reduced from 26.1% to 3.9% and false classifications of transmembrane helices were reduced from 19.0% to 7.7%. Phobius was applied to the proteomes of Homo sapiens and Escherichia coli. Here we also noted a drastic reduction of false classifications compared to TMHMM/SignalP, suggesting that Phobius is well suited for whole-genome annotation of signal peptides and transmembrane regions. The method is available at as well as at     

Evaluation of methods for the prediction of membrane spanning regions.

MOTIVATION: A variety of tools are available to predict the topology of transmembrane proteins. To date no independent evaluation of the performance of these tools has been published. A better understanding of the strengths and weaknesses of the different tools would guide both the biologist and the bioinformatician to make better predictions of membrane protein topology. RESULTS: Here we present an evaluation of the performance of the currently best known and most widely used methods for the prediction of transmembrane regions in proteins. Our results show that TMHMM is currently the best performing transmembrane prediction program.     

Outer membrane β-barrel structure prediction through the lens of AlphaFold2

Most proteins found in the outer membrane of gram-negative bacteria share a common domain: the transmembrane β-barrel. These outer membrane β-barrels (OMBBs) occur in multiple sizes and different families with a wide range of functions evolved independently by amplification from a pool of homologous ancestral ββ-hairpins. This is part of the reason why predicting their three-dimensional (3D) structure, especially by homology modeling, is a major challenge. Recently, DeepMind's AlphaFold v2 (AF2) became the first structure prediction method to reach close-to-experimental atomic accuracy in CASP even for difficult targets. However, membrane proteins, especially OMBBs, were not abundant during their training, raising the question of how accurate the predictions are for these families. In this study, we assessed the performance of AF2 in the prediction of OMBBs and OMBB-like folds of various topologies using an in-house-developed tool for the analysis of OMBB 3D structures, and barrOs. In agreement with previous studies on other membrane protein classes, our results indicate that AF2 predicts transmembrane β-barrel structures at high accuracy independently of the use of templates, even for novel topologies absent from the training set. These results provide confidence on the models generated by AF2 and open the door to the structural elucidation of novel transmembrane β-barrel topologies identified in high-throughput OMBB annotation studies or designed de novo.     

Prediction of helix-helix contacts and interacting helices in polytopic membrane proteins using neural networks

Despite rapidly increasing numbers of available 3D structures, membrane proteins still account for less than 1% of all structures in the Protein Data Bank. Recent high-resolution structures indicate a clearly broader structural diversity of membrane proteins than initially anticipated, motivating the development of reliable structure prediction methods specifically tailored for this class of molecules. One important prediction target capturing all major aspects of a protein's 3D structure is its contact map. Our analysis shows that computational methods trained to predict residue contacts in globular proteins perform poorly when applied to membrane proteins. We have recently published a method to identify interacting alpha-helices in membrane proteins based on the analysis of coevolving residues in predicted transmembrane regions. Here, we present a substantially improved algorithm for the same problem, which uses a newly developed neural network approach to predict helix-helix contacts. In addition to the input features commonly used for contact prediction of soluble proteins, such as windowed residue profiles and residue distance in the sequence, our network also incorporates features that apply to membrane proteins only, such as residue position within the transmembrane segment and its orientation toward the lipophilic environment. The obtained neural network can predict contacts between residues in transmembrane segments with nearly 26% accuracy. It is therefore the first published contact predictor developed specifically for membrane proteins performing with equal accuracy to state-of-the-art contact predictors available for soluble proteins. The predicted helix-helix contacts were employed in a second step to identify interacting helices. For our dataset consisting of 62 membrane proteins of solved structure, we gained an accuracy of 78.1%. Because the reliable prediction of helix interaction patterns is an important step in the classification and prediction of membrane protein folds, our method will be a helpful tool in compiling a structural census of membrane proteins.