Natively unstructured regions in proteins identified from contact predictions

Artificial Intelligence Learns Protein Prediction

From AlphaGO over StableDiffusion to ChatGPT, the recent decade of exponential advances in artificial intelligence (AI) has been altering life. In parallel, advances in computational biology are beginning to decode the language of life: AlphaFold2 leaped forward in protein structure prediction, and protein language models (pLMs) replaced expertise and evolutionary information from multiple sequence alignments with information learned from reoccurring patterns in databases of billions of proteins without experimental annotations other than the amino acid sequences. None of those tools could have been developed 10 years ago; all will increase the wealth of experimental data and speed up the cycle from idea to proof. AI is affecting molecular and medical biology at giant steps, and the most important might be the leap toward more powerful protein design.

Prediction of folding patterns for intrinsic disordered protein

The conformation flexibility of natural protein causes both complexity and difficulty to understand the relationship between structure and function. The prediction of intrinsically disordered protein primarily is focusing on to disclose the regions with structural flexibility involving relevant biological functions and various diseases. The order of amino acids in protein sequence determines possible conformations, folding flexibility and biological function. Although many methods provided the information of intrinsically disordered protein (IDP), but the results are mainly limited to determine the locations of regions without knowledge of possible folding conformations. Here, the developed protein folding fingerprint adopted the protein folding variation matrix (PFVM) to reveal all possible folding patterns for the intrinsically disordered protein along its sequence. The PFVM integrally exhibited the intrinsically disordered protein with disordering regions, degree of disorder as well as folding pattern. The advantage of PFVM will not only provide rich information for IDP, but also may promote the study of protein folding problem.

Concentration and time-dependent amyloidogenic characteristics of intrinsically disordered N-terminal region of Saccharomyces cerevisiae Stm1

Saccharomyces cerevisiae Stm1 protein is a ribosomal association factor, which plays an important role in preserving ribosomes in a nutrition-deprived environment. It is also shown to take part in apoptosis-like cell death. Stm1 N-terminal region (Stm1_N1-113) is shown to recognize purine motif DNA triplex and G-quadruplex. Circular dichroism (CD) spectra of Stm1_N1-113 (enriched in positively-charged Lysine and Arginine; negatively-charged Aspartate; polar-uncharged Threonine, Asparagine, Proline and Serine; hydrophobic Alanine, Valine, and Glycine) collected after 0 and 24 h indicate that the protein assumes beta-sheet conformation at the higher concentrations in contrast to intrinsically disordered conformation seen for its monomeric form found in the crystal structure. Thioflavin-T kinetics experiments indicate that the lag phase is influenced by the salt concentration. Atomic force microscopy (AFM) images collected for a variety of Stm1_N1-113 concentrations (in the range of 1-400 μM) in the presence of 150 mM NaCl at 0, 24, and 48 h indicate a threshold concentration requirement to observe the time-dependent amyloid formation. This is prominent seen at the physiological salt concentration of 150 mM NaCl with the fibrillation observed for 400 μM concentration at 48 h, whereas oligomerization or proto-fibrillation is seen for the other concentrations. Such concentration-dependent fibrillation of Stm1_N1-113 explains that amyloid fibrils formed during the overexpression of Stm1_N1-113 may act as a molecular device to trigger apoptosis-like cell death.

Protein intrinsically disordered region prediction by combining neural architecture search and multi-objective genetic algorithm

BACKGROUND

Intrinsically disordered regions (IDRs) are widely distributed in proteins and related to many important biological functions. Accurately identifying IDRs is of great significance for protein structure and function analysis. Because the long disordered regions (LDRs) and short disordered regions (SDRs) share different characteristics, the existing predictors fail to achieve better and more stable performance on datasets with different ratios between LDRs and SDRs. There are two main reasons. First, the existing predictors construct network structures based on their own experiences such as convolutional neural network (CNN) which is used to extract the feature of neighboring residues in protein, and long short-term memory (LSTM) is used to extract the long-distance dependencies feature of protein residues. But these networks cannot capture the hidden feature associated with the length-dependent between residues. Second, many algorithms based on deep learning have been proposed but the complementarity of the existing predictors is not fully explored and used.

RESULTS

In this study, the neural architecture search (NAS) algorithm was employed to automatically construct the network structures so as to capture the hidden features in protein sequences. In order to stably predict both the LDRs and SDRs, the model constructed by NAS was combined with length-dependent models for capturing the unique features of SDRs or LDRs and general models for capturing the common features between LDRs and SDRs. A new predictor called IDP-Fusion was proposed.

CONCLUSIONS

Experimental results showed that IDP-Fusion can achieve more stable performance than the other existing predictors on independent test sets with different ratios between SDRs and LDRs.

Data-Driven Models for Predicting Intrinsically Disordered Protein Polymer Physics Directly from Composition or Sequence

The molecular-level understanding of intrinsically disordered proteins is challenging due to experimental characterization difficulties. Computational understanding of IDPs also requires fundamental advances, as the leading tools for predicting protein folding (e.g., AlphaFold), typically fail to describe the structural ensembles of IDPs. The focus of this paper is to 1) develop new representations for intrinsically disordered proteins and 2) pair these representations with classical machine learning and deep learning models to predict the radius of gyration and derived scaling exponent of IDPs. Here, we build a new physically-motivated feature called the bag of amino acid interactions representation, which encodes pairwise interactions explicitly into the representation. This feature essentially counts and weights all possible non-bonded interactions in a sequence and thus is, in principle, compatible with arbitrary sequence lengths. To see how well this new feature performs, both categorical and physically-motivated featurization techniques are tested on a computational dataset containing 10,000 sequences simulated at the coarse-grained level. The results indicate that this new feature outperforms the other purely categorical and physically-motivated features and possesses solid extrapolation capabilities. For future use, this feature can potentially provide physical insights into amino acid interactions, including their temperature dependence, and be applied to other protein spaces.

ADOPT: intrinsic protein disorder prediction through deep bidirectional transformers

Intrinsically disordered proteins (IDPs) are important for a broad range of biological functions and are involved in many diseases. An understanding of intrinsic disorder is key to develop compounds that target IDPs. Experimental characterization of IDPs is hindered by the very fact that they are highly dynamic. Computational methods that predict disorder from the amino acid sequence have been proposed. Here, we present ADOPT (Attention DisOrder PredicTor), a new predictor of protein disorder. ADOPT is composed of a self-supervised encoder and a supervised disorder predictor. The former is based on a deep bidirectional transformer, which extracts dense residue-level representations from Facebook's Evolutionary Scale Modeling library. The latter uses a database of nuclear magnetic resonance chemical shifts, constructed to ensure balanced amounts of disordered and ordered residues, as a training and a test dataset for protein disorder. ADOPT predicts whether a protein or a specific region is disordered with better performance than the best existing predictors and faster than most other proposed methods (a few seconds per sequence). We identify the features that are relevant for the prediction performance and show that good performance can already be gained with <100 features. ADOPT is available as a stand-alone package at https://github.com/PeptoneLtd/ADOPT and as a web server at https://adopt.peptone.io/.

Intrinsically Disordered Proteins: An Overview

Many proteins and protein segments cannot attain a single stable three-dimensional structure under physiological conditions; instead, they adopt multiple interconverting conformational states. Such intrinsically disordered proteins or protein segments are highly abundant across proteomes, and are involved in various effector functions. This review focuses on different aspects of disordered proteins and disordered protein regions, which form the basis of the so-called "Disorder-function paradigm" of proteins. Additionally, various experimental approaches and computational tools used for characterizing disordered regions in proteins are discussed. Finally, the role of disordered proteins in diseases and their utility as potential drug targets are explored.

SETH predicts nuances of residue disorder from protein embeddings

Predictions for millions of protein three-dimensional structures are only a few clicks away since the release of AlphaFold2 results for UniProt. However, many proteins have so-called intrinsically disordered regions (IDRs) that do not adopt unique structures in isolation. These IDRs are associated with several diseases, including Alzheimer's Disease. We showed that three recent disorder measures of AlphaFold2 predictions (pLDDT, "experimentally resolved" prediction and "relative solvent accessibility") correlated to some extent with IDRs. However, expert methods predict IDRs more reliably by combining complex machine learning models with expert-crafted input features and evolutionary information from multiple sequence alignments (MSAs). MSAs are not always available, especially for IDRs, and are computationally expensive to generate, limiting the scalability of the associated tools. Here, we present the novel method SETH that predicts residue disorder from embeddings generated by the protein Language Model ProtT5, which explicitly only uses single sequences as input. Thereby, our method, relying on a relatively shallow convolutional neural network, outperformed much more complex solutions while being much faster, allowing to create predictions for the human proteome in about 1 hour on a consumer-grade PC with one NVIDIA GeForce RTX 3060. Trained on a continuous disorder scale (CheZOD scores), our method captured subtle variations in disorder, thereby providing important information beyond the binary classification of most methods. High performance paired with speed revealed that SETH's nuanced disorder predictions for entire proteomes capture aspects of the evolution of organisms. Additionally, SETH could also be used to filter out regions or proteins with probable low-quality AlphaFold2 3D structures to prioritize running the compute-intensive predictions for large data sets. SETH is freely publicly available at: https://github.com/Rostlab/SETH.

Inter-Residue Distance Prediction From Duet Deep Learning Models

Residue distance prediction from the sequence is critical for many biological applications such as protein structure reconstruction, protein–protein interaction prediction, and protein design. However, prediction of fine-grained distances between residues with long sequence separations still remains challenging. In this study, we propose DuetDis, a method based on duet feature sets and deep residual network with squeeze-and-excitation (SE), for protein inter-residue distance prediction. DuetDis embraces the ability to learn and fuse features directly or indirectly extracted from the whole-genome/metagenomic databases and, therefore, minimize the information loss through ensembling models trained on different feature sets. We evaluate DuetDis and 11 widely used peer methods on a large-scale test set (610 proteins chains). The experimental results suggest that 1) prediction results from different feature sets show obvious differences; 2) ensembling different feature sets can improve the prediction performance; 3) high-quality multiple sequence alignment (MSA) used for both training and testing can greatly improve the prediction performance; and 4) DuetDis is more accurate than peer methods for the overall prediction, more reliable in terms of model prediction score, and more robust against shallow multiple sequence alignment (MSA).

DeepIDP-2L: protein intrinsically disordered region prediction by combining convolutional attention network and hierarchical attention network

MOTIVATION

Intrinsically disordered regions (IDRs) are widely distributed in proteins. Accurate prediction of IDRs is critical for the protein structure and function analysis. The IDRs are divided into long disordered regions (LDRs) and short disordered regions (SDRs) according to their lengths. Previous studies have shown that LDRs and SDRs have different proprieties. However, the existing computational methods fail to extract different features for LDRs and SDRs separately. As a result, they achieve unstable performance on datasets with different ratios of LDRs and SDRs.

RESULTS

In this study, a two-layer predictor was proposed called DeepIDP-2L. In the first layer, two kinds of attention-based models are used to extract different features for LDRs and SDRs, respectively. The hierarchical attention network is used to capture the distribution pattern features of LDRs, and convolutional attention network is used to capture the local correlation features of SDRs. The second layer of DeepIDP-2L maps the feature extracted in the first layer into a new feature space. Convolutional network and bidirectional long short term memory are used to capture the local and long-range information for predicting both SDRs and LDRs. Experimental results show that DeepIDP-2L can achieve more stable performance than other exiting predictors on independent test sets with different ratios of SDRs and LDRs.

AVAILABILITY AND IMPLEMENTATION

For the convenience of most experimental scientists, a user-friendly and publicly accessible web-server for the new predictor has been established at http://bliulab.net/DeepIDP-2L/. It is anticipated that DeepIDP-2L will become a very useful tool for identification of intrinsically disordered regions.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Predicting Protein Conformational Disorder and Disordered Binding Sites

In the last two decades it has become increasingly evident that a large number of proteins adopt either a fully or a partially disordered conformation. Intrinsically disordered proteins are ubiquitous proteins that fulfill essential biological functions while lacking a stable 3D structure. Their conformational heterogeneity is encoded by the amino acid sequence, thereby allowing intrinsically disordered proteins or regions to be recognized based on their sequence properties. The identification of disordered regions facilitates the functional annotation of proteins and is instrumental for delineating boundaries of protein domains amenable to crystallization. This chapter focuses on the methods currently employed for predicting protein disorder and identifying intrinsically disordered binding sites.

Surveying over 100 predictors of intrinsic disorder in proteins

INTRODUCTION

Intrinsic disorder prediction field develops, assesses, and deploys computational predictors of disorder in protein sequences and constructs and disseminates databases of these predictions. Over 40 years of research resulted in the release of numerous resources.

AREAS COVERED

We identify and briefly summarize the most comprehensive to date collection of over 100 disorder predictors. We focus on their predictive models, availability and predictive performance. We categorize and study them from a historical point of view to highlight informative trends.

EXPERT OPINION

We find a consistent trend of improvements in predictive quality as newer and more advanced predictors are developed. The original focus on machine learning methods has shifted to meta-predictors in early 2010s, followed by a recent transition to deep learning. The use of deep learners will continue in foreseeable future given recent and convincing success of these methods. Moreover, a broad range of resources that facilitate convenient collection of accurate disorder predictions is available to users. They include web servers and standalone programs for disorder prediction, servers that combine prediction of disorder and disorder functions, and large databases of pre-computed predictions. We also point to the need to address the shortage of accurate methods that predict disordered binding regions.

Evidence for a synergistic effect of post-translational modifications and genomic composition of eEF-1α on the adaptation of Phytophthora infestans

Genetic variation plays a fundamental role in pathogen's adaptation to environmental stresses. Pathogens with low genetic variation tend to survive and proliferate more poorly due to their lack of genotypic/phenotypic polymorphisms in responding to fluctuating environments. Evolutionary theory hypothesizes that the adaptive disadvantage of genes with low genomic variation can be compensated for structural diversity of proteins through post-translation modification (PTM) but this theory is rarely tested experimentally and its implication to sustainable disease management is hardly discussed. In this study, we analyzed nucleotide characteristics of eukaryotic translation elongation factor-1α (eEF-lα) gene from 165 Phytophthora infestans isolates and the physical and chemical properties of its derived proteins. We found a low sequence variation of eEF-lα protein, possibly attributable to purifying selection and a lack of intra-genic recombination rather than reduced mutation. In the only two isoforms detected by the study, the major one accounted for >95% of the pathogen collection and displayed a significantly higher fitness than the minor one. High lysine representation enhances the opportunity of the eEF-1α protein to be methylated and the absence of disulfide bonds is consistent with the structural prediction showing that many disordered regions are existed in the protein. Methylation, structural disordering, and possibly other PTMs ensure the ability of the protein to modify its functions during biological, cellular and biochemical processes, and compensate for its adaptive disadvantage caused by sequence conservation. Our results indicate that PTMs may function synergistically with nucleotide codes to regulate the adaptive landscape of eEF-1α, possibly as well as other housekeeping genes, in P. infestans. Compensatory evolution between pre- and post-translational phase in eEF-1α could enable pathogens quickly adapting to disease management strategies while efficiently maintaining critical roles of the protein playing in biological, cellular, and biochemical activities. Implications of these results to sustainable plant disease management are discussed.

Intrinsically Disordered Proteins as Regulators of Transient Biological Processes and as Untapped Drug Targets

Intrinsically disordered proteins (IDPs) are critical players in the dynamic control of diverse cellular processes, and provide potential new drug targets because their dysregulation is closely related to many diseases. This review focuses on several medicinal studies that have identified low-molecular-weight inhibitors of IDPs. In addition, clinically relevant liquid-liquid phase separations-which critically involve both intermolecular interactions between IDPs and their posttranslational modification-are analyzed to understand the potential of IDPs as new drug targets.

IDP-Seq2Seq: identification of intrinsically disordered regions based on sequence to sequence learning

MOTIVATION

Related to many important biological functions, intrinsically disordered regions (IDRs) are widely distributed in proteins. Accurate prediction of IDRs is critical for the protein structure and function analysis. However, the existing computational methods construct the predictive models solely in the sequence space, failing to convert the sequence space into the 'semantic space' to reflect the structure characteristics of proteins. Furthermore, although the length-dependent predictors showed promising results, new fusion strategies should be explored to improve their predictive performance and the generalization.

RESULTS

In this study, we applied the Sequence to Sequence Learning (Seq2Seq) derived from natural language processing (NLP) to map protein sequences to 'semantic space' to reflect the structure patterns with the help of predicted residue-residue contacts (CCMs) and other sequence-based features. Furthermore, the Attention mechanism was used to capture the global associations between all residue pairs in the proteins. Three length-dependent predictors were constructed: IDP-Seq2Seq-L for long disordered region prediction, IDP-Seq2Seq-S for short disordered region prediction and IDP-Seq2Seq-G for both long and short disordered region predictions. Finally, these three predictors were fused into one predictor called IDP-Seq2Seq to improve the discriminative power and generalization. Experimental results on four independent test datasets and the CASP test dataset showed that IDP-Seq2Seq is insensitive with the ratios of long and short disordered regions and outperforms other competing methods.

AVAILABILITY AND IMPLEMENTATION

For the convenience of most experimental scientists, a user-friendly and publicly accessible web-server for the powerful new predictor has been established at http://bliulab.net/IDP-Seq2Seq/. It is anticipated that IDP-Seq2Seq will become a very useful tool for identification of IDRs.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Dark Proteome Database: Studies on Disorder

There is a misconception that intrinsic disorder in proteins is equivalent to darkness. The present study aims to establish, in the scope of the Swiss-Prot and Dark Proteome databases, the relationship between disorder and darkness. Three distinct predictors were used to calculate the disorder of Swiss-Prot proteins. The analysis of the results obtained with the used predictors and visualization paradigms resulted in the same conclusion that was reached before: disorder is mostly unrelated to darkness.

Modeling aspects of the language of life through transfer-learning protein sequences

BACKGROUND

Predicting protein function and structure from sequence is one important challenge for computational biology. For 26 years, most state-of-the-art approaches combined machine learning and evolutionary information. However, for some applications retrieving related proteins is becoming too time-consuming. Additionally, evolutionary information is less powerful for small families, e.g. for proteins from the Dark Proteome. Both these problems are addressed by the new methodology introduced here.

RESULTS

We introduced a novel way to represent protein sequences as continuous vectors (embeddings) by using the language model ELMo taken from natural language processing. By modeling protein sequences, ELMo effectively captured the biophysical properties of the language of life from unlabeled big data (UniRef50). We refer to these new embeddings as SeqVec (Sequence-to-Vector) and demonstrate their effectiveness by training simple neural networks for two different tasks. At the per-residue level, secondary structure (Q3 = 79% ± 1, Q8 = 68% ± 1) and regions with intrinsic disorder (MCC = 0.59 ± 0.03) were predicted significantly better than through one-hot encoding or through Word2vec-like approaches. At the per-protein level, subcellular localization was predicted in ten classes (Q10 = 68% ± 1) and membrane-bound were distinguished from water-soluble proteins (Q2 = 87% ± 1). Although SeqVec embeddings generated the best predictions from single sequences, no solution improved over the best existing method using evolutionary information. Nevertheless, our approach improved over some popular methods using evolutionary information and for some proteins even did beat the best. Thus, they prove to condense the underlying principles of protein sequences. Overall, the important novelty is speed: where the lightning-fast HHblits needed on average about two minutes to generate the evolutionary information for a target protein, SeqVec created embeddings on average in 0.03 s. As this speed-up is independent of the size of growing sequence databases, SeqVec provides a highly scalable approach for the analysis of big data in proteomics, i.e. microbiome or metaproteome analysis.

CONCLUSION

Transfer-learning succeeded to extract information from unlabeled sequence databases relevant for various protein prediction tasks. SeqVec modeled the language of life, namely the principles underlying protein sequences better than any features suggested by textbooks and prediction methods. The exception is evolutionary information, however, that information is not available on the level of a single sequence.

A comprehensive review and comparison of existing computational methods for intrinsically disordered protein and region prediction

Intrinsically disordered proteins and regions are widely distributed in proteins, which are associated with many biological processes and diseases. Accurate prediction of intrinsically disordered proteins and regions is critical for both basic research (such as protein structure and function prediction) and practical applications (such as drug development). During the past decades, many computational approaches have been proposed, which have greatly facilitated the development of this important field. Therefore, a comprehensive and updated review is highly required. In this regard, we give a review on the computational methods for intrinsically disordered protein and region prediction, especially focusing on the recent development in this field. These computational approaches are divided into four categories based on their methodologies, including physicochemical-based method, machine-learning-based method, template-based method and meta method. Furthermore, their advantages and disadvantages are also discussed. The performance of 40 state-of-the-art predictors is directly compared on the target proteins in the task of disordered region prediction in the 10th Critical Assessment of protein Structure Prediction. A more comprehensive performance comparison of 45 different predictors is conducted based on seven widely used benchmark data sets. Finally, some open problems and perspectives are discussed.

Identification of Intrinsically Disordered Proteins and Regions by Length-Dependent Predictors Based on Conditional Random Fields

Accurate identification of intrinsically disordered proteins/regions (IDPs/IDRs) is critical for predicting protein structure and function. Previous studies have shown that IDRs of different lengths have different characteristics, and several classification-based predictors have been proposed for predicting different types of IDRs. Compared with these classification-based predictors, the previously proposed predictor IDP-CRF exhibits state-of-the-art performance for predicting IDPs/IDRs, which is a sequence labeling model based on conditional random fields (CRFs). Motivated by these methods, we propose a predictor called IDP-FSP, which is an ensemble of three CRF-based predictors called IDP-FSP-L, IDP-FSP-S, and IDP-FSP-G. These three predictors are specially designed to predict long, short, and generic disordered regions, respectively, and they are constructed based on different features. To the best of our knowledge, IDP-FSP is the first predictor that combines a sequence labeling algorithm with IDRs of different lengths. Experimental results using two independent test datasets show that IDP-FSP achieves better or at least comparable predictive performance with 26 existing state-of-the-art methods in this field, proving the effectiveness of IDP-FSP.

IDP⁻CRF: Intrinsically Disordered Protein/Region Identification Based on Conditional Random Fields

Accurate prediction of intrinsically disordered proteins/regions is one of the most important tasks in bioinformatics, and some computational predictors have been proposed to solve this problem. How to efficiently incorporate the sequence-order effect is critical for constructing an accurate predictor because disordered region distributions show global sequence patterns. In order to capture these sequence patterns, several sequence labelling models have been applied to this field, such as conditional random fields (CRFs). However, these methods suffer from certain disadvantages. In this study, we proposed a new computational predictor called IDP⁻CRF, which is trained on an updated benchmark dataset based on the MobiDB database and the DisProt database, and incorporates more comprehensive sequence-based features, including PSSMs (position-specific scoring matrices), kmer, predicted secondary structures, and relative solvent accessibilities. Experimental results on the benchmark dataset and two independent datasets show that IDP⁻CRF outperforms 25 existing state-of-the-art methods in this field, demonstrating that IDP⁻CRF is a very useful tool for identifying IDPs/IDRs (intrinsically disordered proteins/regions). We anticipate that IDP⁻CRF will facilitate the development of protein sequence analysis.

Drug targeted virtual screening and molecular dynamics of LipU protein of Mycobacterium tuberculosis and Mycobacterium leprae

The lipolytic protein LipU was conserved in mycobacterium sp. including M. tuberculosis (MTB LipU) and M. leprae (MLP LipU). The MTB LipU was identified in extracellular fraction and was reported to be essential for the survival of mycobacterium. Therefore to address the problem of drug resistance in pathogen, LipU was selected as a drug target and the viability of finding out some FDA approved drugs as LipU inhibitors in both the cases was explored. Three-dimensional (3D) model structures of MTB LipU and MLP LipU were generated and stabilized through molecular dynamics (MD). FDA approved drugs were screened against these proteins. The result showed that the top-scoring compounds for MTB LipU were Diosmin, Acarbose and Ouabain with the Glide XP score of -12.8, -11.9 and -11.7 kcal/mol, respectively, whereas for MLP LipU protein, Digoxin (-9.2 kcal/mol), Indinavir (-8.2 kcal/mol) and Travoprost (-8.2 kcal/mol) showed highest affinity. These drugs remained bound in the active site pocket of MTB LipU and MLP LipU structure and interaction grew stronger after dynamics. RMSD, RMSF and Rg were found to be persistent throughout the simulation period. Hydrogen bonds along with large number of hydrophobic interactions stabilized the complex structures. Binding free energies obtained through Prime/MM-GBSA were found in the significant range from -63.85 kcal/mol to -34.57 kcal/mol for MTB LipU and -71.33 kcal/mol to -23.91 kcal/mol for MLP LipU. The report suggested high probability of these drugs to demolish the LipU activity and could be probable drug candidates to combat TB and leprosy disease.

Improving protein disorder prediction by deep bidirectional long short-term memory recurrent neural networks

Motivation

Capturing long-range interactions between structural but not sequence neighbors of proteins is a long-standing challenging problem in bioinformatics. Recently, long short-term memory (LSTM) networks have significantly improved the accuracy of speech and image classification problems by remembering useful past information in long sequential events. Here, we have implemented deep bidirectional LSTM recurrent neural networks in the problem of protein intrinsic disorder prediction.

Results

The new method, named SPOT-Disorder, has steadily improved over a similar method using a traditional, window-based neural network (SPINE-D) in all datasets tested without separate training on short and long disordered regions. Independent tests on four other datasets including the datasets from critical assessment of structure prediction (CASP) techniques and >10 000 annotated proteins from MobiDB, confirmed SPOT-Disorder as one of the best methods in disorder prediction. Moreover, initial studies indicate that the method is more accurate in predicting functional sites in disordered regions. These results highlight the usefulness combining LSTM with deep bidirectional recurrent neural networks in capturing non-local, long-range interactions for bioinformatics applications.

Availability and Implementation

SPOT-disorder is available as a web server and as a standalone program at: http://sparks-lab.org/server/SPOT-disorder/index.php .

Contact

j.hanson@griffith.edu.au or yuedong.yang@griffith.edu.au or yaoqi.zhou@griffith.edu.au.

Supplementary information

Supplementary data is available at Bioinformatics online.

Prediction of protein disorder based on IUPred

Many proteins contain intrinsically disordered regions (IDRs), functional polypeptide segments that in isolation adopt a highly flexible conformational ensemble instead of a single, well-defined structure. Disorder prediction methods, which can discriminate ordered and disordered regions from the amino acid sequence, have contributed significantly to our current understanding of the distinct properties of intrinsically disordered proteins by enabling the characterization of individual examples as well as large-scale analyses of these protein regions. One popular method, IUPred provides a robust prediction of protein disorder based on an energy estimation approach that captures the fundamental difference between the biophysical properties of ordered and disordered regions. This paper reviews the energy estimation method underlying IUPred and the basic properties of the web server. Through an example, it also illustrates how the prediction output can be interpreted in a more complex case by taking into account the heterogeneous nature of IDRs. Various applications that benefited from IUPred to provide improved disorder predictions, complementing domain annotations and aiding the identification of functional short linear motifs are also described here. IUPred is freely available for noncommercial users through the web server (http://iupred.enzim.hu and http://iupred.elte.hu) . The program can also be downloaded and installed locally for large-scale analyses.

Discovery of numerous novel small genes in the intergenic regions of the Escherichia coli O157:H7 Sakai genome

In the past, short protein-coding genes were often disregarded by genome annotation pipelines. Transcriptome sequencing (RNAseq) signals outside of annotated genes have usually been interpreted to indicate either ncRNA or pervasive transcription. Therefore, in addition to the transcriptome, the translatome (RIBOseq) of the enteric pathogen Escherichia coli O157:H7 strain Sakai was determined at two optimal growth conditions and a severe stress condition combining low temperature and high osmotic pressure. All intergenic open reading frames potentially encoding a protein of ≥ 30 amino acids were investigated with regard to coverage by transcription and translation signals and their translatability expressed by the ribosomal coverage value. This led to discovery of 465 unique, putative novel genes not yet annotated in this E. coli strain, which are evenly distributed over both DNA strands of the genome. For 255 of the novel genes, annotated homologs in other bacteria were found, and a machine-learning algorithm, trained on small protein-coding E. coli genes, predicted that 89% of these translated open reading frames represent bona fide genes. The remaining 210 putative novel genes without annotated homologs were compared to the 255 novel genes with homologs and to 250 short annotated genes of this E. coli strain. All three groups turned out to be similar with respect to their translatability distribution, fractions of differentially regulated genes, secondary structure composition, and the distribution of evolutionary constraint, suggesting that both novel groups represent legitimate genes. However, the machine-learning algorithm only recognized a small fraction of the 210 genes without annotated homologs. It is possible that these genes represent a novel group of genes, which have unusual features dissimilar to the genes of the machine-learning algorithm training set.

Comprehensive review of methods for prediction of intrinsic disorder and its molecular functions

Computational prediction of intrinsic disorder in protein sequences dates back to late 1970 and has flourished in the last two decades. We provide a brief historical overview, and we review over 30 recent predictors of disorder. We are the first to also cover predictors of molecular functions of disorder, including 13 methods that focus on disordered linkers and disordered protein-protein, protein-RNA, and protein-DNA binding regions. We overview their predictive models, usability, and predictive performance. We highlight newest methods and predictors that offer strong predictive performance measured based on recent comparative assessments. We conclude that the modern predictors are relatively accurate, enjoy widespread use, and many of them are fast. Their predictions are conveniently accessible to the end users, via web servers and databases that store pre-computed predictions for millions of proteins. However, research into methods that predict many not yet addressed functions of intrinsic disorder remains an outstanding challenge.

AUCpreD: proteome-level protein disorder prediction by AUC-maximized deep convolutional neural fields

MOTIVATION

Protein intrinsically disordered regions (IDRs) play an important role in many biological processes. Two key properties of IDRs are (i) the occurrence is proteome-wide and (ii) the ratio of disordered residues is about 6%, which makes it challenging to accurately predict IDRs. Most IDR prediction methods use sequence profile to improve accuracy, which prevents its application to proteome-wide prediction since it is time-consuming to generate sequence profiles. On the other hand, the methods without using sequence profile fare much worse than using sequence profile.

METHOD

This article formulates IDR prediction as a sequence labeling problem and employs a new machine learning method called Deep Convolutional Neural Fields (DeepCNF) to solve it. DeepCNF is an integration of deep convolutional neural networks (DCNN) and conditional random fields (CRF); it can model not only complex sequence-structure relationship in a hierarchical manner, but also correlation among adjacent residues. To deal with highly imbalanced order/disorder ratio, instead of training DeepCNF by widely used maximum-likelihood, we develop a novel approach to train it by maximizing area under the ROC curve (AUC), which is an unbiased measure for class-imbalanced data.

RESULTS

Our experimental results show that our IDR prediction method AUCpreD outperforms existing popular disorder predictors. More importantly, AUCpreD works very well even without sequence profile, comparing favorably to or even outperforming many methods using sequence profile. Therefore, our method works for proteome-wide disorder prediction while yielding similar or better accuracy than the others.

AVAILABILITY AND IMPLEMENTATION

http://raptorx2.uchicago.edu/StructurePropertyPred/predict/

CONTACT

wangsheng@uchicago.edu, jinboxu@gmail.com

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Salt-bridge networks within globular and disordered proteins: characterizing trends for designable interactions

There has been considerable debate about the contribution of salt bridges to the stabilization of protein folds, in spite of their participation in crucial protein functions. Salt bridges appear to contribute to the activity-stability trade-off within proteins by bringing high-entropy charged amino acids into close contacts during the course of their functions. The current study analyzes the modes of association of salt bridges (in terms of networks) within globular proteins and at protein-protein interfaces. While the most common and trivial type of salt bridge is the isolated salt bridge, bifurcated salt bridge appears to be a distinct salt-bridge motif having a special topology and geometry. Bifurcated salt bridges are found ubiquitously in proteins and interprotein complexes. Interesting and attractive examples presenting different modes of interaction are highlighted. Bifurcated salt bridges appear to function as molecular clips that are used to stitch together large surface contours at interacting protein interfaces. The present work also emphasizes the key role of salt-bridge-mediated interactions in the partial folding of proteins containing long stretches of disordered regions. Salt-bridge-mediated interactions seem to be pivotal to the promotion of "disorder-to-order" transitions in small disordered protein fragments and their stabilization upon binding. The results obtained in this work should help to guide efforts to elucidate the modus operandi of these partially disordered proteins, and to conceptualize how these proteins manage to maintain the required amount of disorder even in their bound forms. This work could also potentially facilitate explorations of geometrically specific designable salt bridges through the characterization of composite salt-bridge networks. Graphical abstract ᅟ.

Proteus: a random forest classifier to predict disorder-to-order transitioning binding regions in intrinsically disordered proteins

The focus of the computational structural biology community has taken a dramatic shift over the past one-and-a-half decades from the classical protein structure prediction problem to the possible understanding of intrinsically disordered proteins (IDP) or proteins containing regions of disorder (IDPR). The current interest lies in the unraveling of a disorder-to-order transitioning code embedded in the amino acid sequences of IDPs/IDPRs. Disordered proteins are characterized by an enormous amount of structural plasticity which makes them promiscuous in binding to different partners, multi-functional in cellular activity and atypical in folding energy landscapes resembling partially folded molten globules. Also, their involvement in several deadly human diseases (e.g. cancer, cardiovascular and neurodegenerative diseases) makes them attractive drug targets, and important for a biochemical understanding of the disease(s). The study of the structural ensemble of IDPs is rather difficult, in particular for transient interactions. When bound to a structured partner, an IDPR adapts an ordered conformation in the complex. The residues that undergo this disorder-to-order transition are called protean residues, generally found in short contiguous stretches and the first step in understanding the modus operandi of an IDP/IDPR would be to predict these residues. There are a few available methods which predict these protean segments from their amino acid sequences; however, their performance reported in the literature leaves clear room for improvement. With this background, the current study presents ‘Proteus’, a random forest classifier that predicts the likelihood of a residue undergoing a disorder-to-order transition upon binding to a potential partner protein. The prediction is based on features that can be calculated using the amino acid sequence alone. Proteus compares favorably with existing methods predicting twice as many true positives as the second best method (55 vs. 27%) with a much higher precision on an independent data set. The current study also sheds some light on a possible ‘disorder-to-order’ transitioning consensus, untangled, yet embedded in the amino acid sequence of IDPs. Some guidelines have also been suggested for proceeding with a real-life structural modeling involving an IDPR using Proteus.

Intrinsic Disorder and Semi-disorder Prediction by SPINE-D

Over the past decade, it has become evident that a large proportion of proteins contain intrinsically disordered regions, which play important roles in pivotal cellular functions. Many computational tools have been developed with the aim of identifying the level and location of disorder within a protein. In this chapter, we describe a neural network based technique called SPINE-D that employs a unique three-state design and can accurately capture disordered residues in both short and long disordered regions. SPINE-D was trained on a large database of 4229 non-redundant proteins, and yielded an AUC of 0.86 on a cross-validation test and 0.89 on an independent test. SPINE-D can also detect a semi-disordered state that is associated with induced folders and aggregation-prone regions in disordered proteins and weakly stable or locally unfolded regions in structured proteins. We implement an online web service and an offline stand-alone program for SPINE-D, they are freely available at http://sparks-lab.org/SPINE-D/ . We then walk you through how to use the online and offline SPINE-D in making disorder predictions, and examine the disorder and semi-disorder prediction in a case study on the p53 protein.

How disordered is my protein and what is its disorder for? A guide through the "dark side" of the protein universe

In the last 2 decades it has become increasingly evident that a large number of proteins are either fully or partially disordered. Intrinsically disordered proteins lack a stable 3D structure, are ubiquitous and fulfill essential biological functions. Their conformational heterogeneity is encoded in their amino acid sequences, thereby allowing intrinsically disordered proteins or regions to be recognized based on properties of these sequences. The identification of disordered regions facilitates the functional annotation of proteins and is instrumental for delineating boundaries of protein domains amenable to structural determination with X-ray crystallization. This article discusses a comprehensive selection of databases and methods currently employed to disseminate experimental and putative annotations of disorder, predict disorder and identify regions involved in induced folding. It also provides a set of detailed instructions that should be followed to perform computational analysis of disorder.

AUC-Maximized Deep Convolutional Neural Fields for Protein Sequence Labeling

Deep Convolutional Neural Networks (DCNN) has shown excellent performance in a variety of machine learning tasks. This paper presents Deep Convolutional Neural Fields (DeepCNF), an integration of DCNN with Conditional Random Field (CRF), for sequence labeling with an imbalanced label distribution. The widely-used training methods, such as maximum-likelihood and maximum labelwise accuracy, do not work well on imbalanced data. To handle this, we present a new training algorithm called maximum-AUC for DeepCNF. That is, we train DeepCNF by directly maximizing the empirical Area Under the ROC Curve (AUC), which is an unbiased measurement for imbalanced data. To fulfill this, we formulate AUC in a pairwise ranking framework, approximate it by a polynomial function and then apply a gradient-based procedure to optimize it. Our experimental results confirm that maximum-AUC greatly outperforms the other two training methods on 8-state secondary structure prediction and disorder prediction since their label distributions are highly imbalanced and also has similar performance as the other two training methods on solvent accessibility prediction, which has three equally-distributed labels. Furthermore, our experimental results show that our AUC-trained DeepCNF models greatly outperform existing popular predictors of these three tasks. The data and software related to this paper are available at https://github.com/realbigws/DeepCNF_AUC.

Translatomics combined with transcriptomics and proteomics reveals novel functional, recently evolved orphan genes in Escherichia coli O157:H7 (EHEC)

Background

Genomes of E. coli, including that of the human pathogen Escherichia coli O157:H7 (EHEC) EDL933, still harbor undetected protein-coding genes which, apparently, have escaped annotation due to their small size and non-essential function. To find such genes, global gene expression of EHEC EDL933 was examined, using strand-specific RNAseq (transcriptome), ribosomal footprinting (translatome) and mass spectrometry (proteome).

Results

Using the above methods, 72 short, non-annotated protein-coding genes were detected. All of these showed signals in the ribosomal footprinting assay indicating mRNA translation. Seven were verified by mass spectrometry. Fifty-seven genes are annotated in other enterobacteriaceae, mainly as hypothetical genes; the remaining 15 genes constitute novel discoveries. In addition, protein structure and function were predicted computationally and compared between EHEC-encoded proteins and 100-times randomly shuffled proteins. Based on this comparison, 61 of the 72 novel proteins exhibit predicted structural and functional features similar to those of annotated proteins. Many of the novel genes show differential transcription when grown under eleven diverse growth conditions suggesting environmental regulation. Three genes were found to confer a phenotype in previous studies, e.g., decreased cattle colonization.

Conclusions

These findings demonstrate that ribosomal footprinting can be used to detect novel protein coding genes, contributing to the growing body of evidence that hypothetical genes are not annotation artifacts and opening an additional way to study their functionality. All 72 genes are taxonomically restricted and, therefore, appear to have evolved relatively recently de novo.

Electronic supplementary material

The online version of this article (doi:10.1186/s12864-016-2456-1) contains supplementary material, which is available to authorized users.

Predicting Conformational Disorder

In the last two decades, it has become increasingly evident that a large number of proteins are either fully or partially disordered. Intrinsically disordered proteins are ubiquitous proteins that fulfill essential biological functions while lacking a stable 3D structure. Their conformational heterogeneity is encoded at the amino acid sequence level, thereby allowing intrinsically disordered proteins or regions to be recognized based on their sequence properties. The identification of disordered regions facilitates the functional annotation of proteins and is instrumental for delineating boundaries of protein domains amenable to crystallization. This chapter focuses on the methods currently employed for predicting disorder and identifying regions involved in induced folding.

Protein disorder reduced in Saccharomyces cerevisiae to survive heat shock

Recent experiments established that a culture of Saccharomyces cerevisiae (baker’s yeast) survives sudden high temperatures by specifically duplicating the entire chromosome III and two chromosomal fragments (from IV and XII). Heat shock proteins (HSPs) are not significantly over-abundant in the duplication. In contrast, we suggest a simple algorithm to “ postdict” the experimental results: Find a small enough chromosome with minimal protein disorder and duplicate this region. This algorithm largely explains all observed duplications. In particular, all regions duplicated in the experiment reduced the overall content of protein disorder. The differential analysis of the functional makeup of the duplication remained inconclusive. Gene Ontology (GO) enrichment suggested over-representation in processes related to reproduction and nutrient uptake. Analyzing the protein-protein interaction network (PPI) revealed that few network-central proteins were duplicated. The predictive hypothesis hinges upon the concept of reducing proteins with long regions of disorder in order to become less sensitive to heat shock attack.

DisPredict: A Predictor of Disordered Protein Using Optimized RBF Kernel

Intrinsically disordered proteins or, regions perform important biological functions through their dynamic conformations during binding. Thus accurate identification of these disordered regions have significant implications in proper annotation of function, induced fold prediction and drug design to combat critical diseases. We introduce DisPredict, a disorder predictor that employs a single support vector machine with RBF kernel and novel features for reliable characterization of protein structure. DisPredict yields effective performance. In addition to 10-fold cross validation, training and testing of DisPredict was conducted with independent test datasets. The results were consistent with both the training and test error minimal. The use of multiple data sources, makes the predictor generic. The datasets used in developing the model include disordered regions of various length which are categorized as short and long having different compositions, different types of disorder, ranging from fully to partially disordered regions as well as completely ordered regions. Through comparison with other state of the art approaches and case studies, DisPredict is found to be a useful tool with competitive performance. DisPredict is available at https://github.com/tamjidul/DisPredict_v1.0.

Environmental Pressure May Change the Composition Protein Disorder in Prokaryotes

Many prokaryotic organisms have adapted to incredibly extreme habitats. The genomes of such extremophiles differ from their non-extremophile relatives. For example, some proteins in thermophiles sustain high temperatures by being more compact than homologs in non-extremophiles. Conversely, some proteins have increased volumes to compensate for freezing effects in psychrophiles that survive in the cold. Here, we revealed that some differences in organisms surviving in extreme habitats correlate with a simple single feature, namely the fraction of proteins predicted to have long disordered regions. We predicted disorder with different methods for 46 completely sequenced organisms from diverse habitats and found a correlation between protein disorder and the extremity of the environment. More specifically, the overall percentage of proteins with long disordered regions tended to be more similar between organisms of similar habitats than between organisms of similar taxonomy. For example, predictions tended to detect substantially more proteins with long disordered regions in prokaryotic halophiles (survive high salt) than in their taxonomic neighbors. Another peculiar environment is that of high radiation survived, e.g. by Deinococcus radiodurans. The relatively high fraction of disorder predicted in this extremophile might provide a shield against mutations. Although our analysis fails to establish causation, the observed correlation between such a simplistic, coarse-grained, microscopic molecular feature (disorder content) and a macroscopic variable (habitat) remains stunning.

DeepCNF-D: Predicting Protein Order/Disorder Regions by Weighted Deep Convolutional Neural Fields

Intrinsically disordered proteins or protein regions are involved in key biological processes including regulation of transcription, signal transduction, and alternative splicing. Accurately predicting order/disorder regions ab initio from the protein sequence is a prerequisite step for further analysis of functions and mechanisms for these disordered regions. This work presents a learning method, weighted DeepCNF (Deep Convolutional Neural Fields), to improve the accuracy of order/disorder prediction by exploiting the long-range sequential information and the interdependency between adjacent order/disorder labels and by assigning different weights for each label during training and prediction to solve the label imbalance issue. Evaluated by the CASP9 and CASP10 targets, our method obtains 0.855 and 0.898 AUC values, which are higher than the state-of-the-art single ab initio predictors.

Conformational Entropy of Intrinsically Disordered Proteins from Amino Acid Triads

This work quantitatively characterizes intrinsic disorder in proteins in terms of sequence composition and backbone conformational entropy. Analysis of the normalized relative composition of the amino acid triads highlights a distinct boundary between globular and disordered proteins. The conformational entropy is calculated from the dihedral angles of the middle amino acid in the amino acid triad for the conformational ensemble of the globular, partially and completely disordered proteins relative to the non-redundant database. Both Monte Carlo (MC) and Molecular Dynamics (MD) simulations are used to characterize the conformational ensemble of the representative proteins of each group. The results show that the globular proteins span approximately half of the allowed conformational states in the Ramachandran space, while the amino acid triads in disordered proteins sample the entire range of the allowed dihedral angle space following Flory’s isolated-pair hypothesis. Therefore, only the sequence information in terms of the relative amino acid triad composition may be sufficient to predict protein disorder and the backbone conformational entropy, even in the absence of well-defined structure. The predicted entropies are found to agree with those calculated using mutual information expansion and the histogram method.

Improving accuracy of protein contact prediction using balanced network deconvolution

Residue contact map is essential for protein three-dimensional structure determination. But most of the current contact prediction methods based on residue co-evolution suffer from high false-positives as introduced by indirect and transitive contacts (i.e., residues A-B and B-C are in contact, but A-C are not). Built on the work by Feizi et al. (Nat Biotechnol 2013; 31:726-733), which demonstrated a general network model to distinguish direct dependencies by network deconvolution, this study presents a new balanced network deconvolution (BND) algorithm to identify optimized dependency matrix without limit on the eigenvalue range in the applied network systems. The algorithm was used to filter contact predictions of five widely used co-evolution methods. On the test of proteins from three benchmark datasets of the 9th critical assessment of protein structure prediction (CASP9), CASP10, and PSICOV (precise structural contact prediction using sparse inverse covariance estimation) database experiments, the BND can improve the medium- and long-range contact predictions at the L/5 cutoff by 55.59% and 47.68%, respectively, without additional central processing unit cost. The improvement is statistically significant, with a P-value < 5.93 × 10(-3) in the Student's t-test. A further comparison with the ab initio structure predictions in CASPs showed that the usefulness of the current co-evolution-based contact prediction to the three-dimensional structure modeling relies on the number of homologous sequences existing in the sequence databases. BND can be used as a general contact refinement method, which is freely available at: http://www.csbio.sjtu.edu.cn/bioinf/BND/.

Prediction and analysis of intrinsically disordered proteins

Intrinsically disordered proteins and protein regions (IDPs/IDRs) do not adopt a well-defined folded structure under physiological conditions. Instead, these proteins exist as heterogeneous and dynamical conformational ensembles. IDPs are widespread in eukaryotic proteomes and are involved in fundamental biological processes, mostly related to regulation and signaling. At the same time, disordered regions often pose significant challenges to the structure determination process, which generally requires highly homogeneous proteins samples. In this book chapter, we provide a brief overview of protein disorder, describe various bioinformatics resources that have been developed in recent years for their characterization, and give a general outline of their applications in various types of structural genomics projects. Traditionally, disordered segments were filtered out to optimize the yield of structure determination pipelines. However, it is becoming increasingly clear that the structural characterization of proteins cannot be complete without the incorporation of intrinsically disordered regions.

Structural determinants allowing transferase activity in SENSITIVE TO FREEZING 2, classified as a family I glycosyl hydrolase

SENSITIVE TO FREEZING 2 (SFR2) is classified as a family I glycosyl hydrolase but has recently been shown to have galactosyltransferase activity in Arabidopsis thaliana. Natural occurrences of apparent glycosyl hydrolases acting as transferases are interesting from a biocatalysis standpoint, and knowledge about the interconversion can assist in engineering SFR2 in crop plants to resist freezing. To understand how SFR2 evolved into a transferase, the relationship between its structure and function are investigated by activity assay, molecular modeling, and site-directed mutagenesis. SFR2 has no detectable hydrolase activity, although its catalytic site is highly conserved with that of family 1 glycosyl hydrolases. Three regions disparate from glycosyl hydrolases are identified as required for transferase activity as follows: a loop insertion, the C-terminal peptide, and a hydrophobic patch adjacent to the catalytic site. Rationales for the effects of these regions on the SFR2 mechanism are discussed.

PredictProtein--an open resource for online prediction of protein structural and functional features

PredictProtein is a meta-service for sequence analysis that has been predicting structural and functional features of proteins since 1992. Queried with a protein sequence it returns: multiple sequence alignments, predicted aspects of structure (secondary structure, solvent accessibility, transmembrane helices (TMSEG) and strands, coiled-coil regions, disulfide bonds and disordered regions) and function. The service incorporates analysis methods for the identification of functional regions (ConSurf), homology-based inference of Gene Ontology terms (metastudent), comprehensive subcellular localization prediction (LocTree3), protein–protein binding sites (ISIS2), protein–polynucleotide binding sites (SomeNA) and predictions of the effect of point mutations (non-synonymous SNPs) on protein function (SNAP2). Our goal has always been to develop a system optimized to meet the demands of experimentalists not highly experienced in bioinformatics. To this end, the PredictProtein results are presented as both text and a series of intuitive, interactive and visually appealing figures. The web server and sources are available at http://ppopen.rostlab.org.

Probing the impact of GFP tagging on Robo1-heparin interaction

Green fluorescent proteins (GFPs) and their derivatives are widely used as markers to visualize cells, protein localizations in in vitro and in vivo studies. The use of GFP fusion protein for visualization is generally thought to have negligible effects on cellular function. However, a number of reports suggest that the use of GFP may impact the biological activity of these proteins. Heparin is a glycosaminoglycan (GAG) that interacts with a number of proteins mediating diverse patho-physiological processes. In the heparin-based interactome studies, heparin-binding proteins are often prepared as GFP fusion proteins. In this report, we use surface plasmon resonance (SPR) spectroscopy to study the impact of the GFP tagging on the binding interaction between heparin and a heparin-binding protein, the Roundabout homolog 1 (Robo1). SPR reveals that heparin binds with higher affinity to Robo1 than GFP-tagged Robo1 and through a different kinetic mechanism. A conformational change is observed in the heparin-Robo1 interaction, but not in the heparin-Robo1-GFP interaction. Furthermore the GFP-tagged Robo1 requires a shorter (hexasaccharide) than the tag-free Robo1 (octadecasaccharide). These data demonstrate that GFP tagging can reduce the binding affinity of Robo1 to heparin and hinder heparin binding-induced Robo1 conformation change.

Characterization of the RstB2 protein, the DNA-binding protein of CTXϕ phage from Vibrio cholerae

The low abundant protein RstB2, encoded in the RS2 region of CTXϕ, is essential for prophage formation. However, the only biochemical activity so far described is the single/double-stranded DNA-binding capacity of that protein. In this paper, a recombinant RstB2 (rRstB2) protein was overexpressed in E. coli with a yield of 58.4 mg l(-1) in shaken cultures, LB broth. The protein, purified to homogeneity, showed an identity with rRstB2 by peptide mass fingerprinting. The apparent molecular weight of the RstB2 native protein suggests that occurs mostly as a monomer in solution. The monomers were able of reacting immediately upon exposure to DNA molecules. After a year of storage at -20 °C, the protein remains biologically active. Bioinformatics analysis of the amino acid sequence of RstB2 predicts the C-end of this protein to be disordered and highly flexible, like in many other single-stranded DNA-binding proteins. When compared with the gVp of M13, conserved amino acids are found at structurally or functionally important relative positions. These results pave the way for additional studies of structure and molecular function of RstB2 for the biology of CTXϕ.

Combination of site directed mutagenesis and secondary structure analysis predicts the amino acids essential for stability of M. leprae MurE

The life-threatening infections caused by Mycobacterium leprae (Mle) remain a major challenge in developing countries as well as globe and there is a need to design potent anti-leprosy drugs. In our previous studies, ATP-dependent Mle-MurE ligase involved in biosynthesis of peptidoglycan was identified as one of the common drug targets, homology modeled and reported. In this work in silico site directed mutagenesis study was carried out on the homology modeled Mle-MurE ligase. This predicted the amino acids essential for stability. In addition, the distribution of these residues in different secondary structures and in active sites was analyzed. Finally, the role of the conserved residues in stability and function was analyzed. The availability of Mle-MurE ligase built model together with insights gained from stability studies and docking studies will promote the rational design of potent and selective Mle-MurE ligase inhibitors as anti-leprosy therapeutics.

Toward an accurate prediction of inter-residue distances in proteins using 2D recursive neural networks

Background

Protein inter-residue contact maps provide a translation and rotation invariant topological representation of a protein. They can be used as an intermediary step in protein structure predictions. However, the prediction of contact maps represents an unbalanced problem as far fewer examples of contacts than non-contacts exist in a protein structure.

In this study we explore the possibility of completely eliminating the unbalanced nature of the contact map prediction problem by predicting real-value distances between residues. Predicting full inter-residue distance maps and applying them in protein structure predictions has been relatively unexplored in the past.

Results

We initially demonstrate that the use of native-like distance maps is able to reproduce 3D structures almost identical to the targets, giving an average RMSD of 0.5Å. In addition, the corrupted physical maps with an introduced random error of ±6Å are able to reconstruct the targets within an average RMSD of 2Å.

After demonstrating the reconstruction potential of distance maps, we develop two classes of predictors using two-dimensional recursive neural networks: an ab initio predictor that relies only on the protein sequence and evolutionary information, and a template-based predictor in which additional structural homology information is provided. We find that the ab initio predictor is able to reproduce distances with an RMSD of 6Å, regardless of the evolutionary content provided. Furthermore, we show that the template-based predictor exploits both sequence and structure information even in cases of dubious homology and outperforms the best template hit with a clear margin of up to 3.7Å.

Lastly, we demonstrate the ability of the two predictors to reconstruct the CASP9 targets shorter than 200 residues producing the results similar to the state of the machine learning art approach implemented in the Distill server.

Conclusions

The methodology presented here, if complemented by more complex reconstruction protocols, can represent a possible path to improve machine learning algorithms for 3D protein structure prediction. Moreover, it can be used as an intermediary step in protein structure predictions either on its own or complemented by NMR restraints.

Analysis of Brassica napus ESTs: gene discovery and expression patterns of AP2/ERF-family transcription factors

Starting from expressed sequence tag sequences and using the conserved amino acid sequence of the Arabidopsis thaliana AP2/ERF domain as a probe, we used in silico cloning to identify 87 genes that encode putative AP2/ERF transcription factors (TFs) from the Brassica napus. Almost all of the putative AP2/ERF factors from B. napus were similar to genes previously defined as AP2/ERF genes from A. thaliana. Based on the number of AP2-domains and the function of the genes, the AP2/ERF TFs from B. napus were classified into four subfamilies, named the AP2, DREB, ERF, and RAV subfamilies. We then predicted and analyzed cDNA sequences and amino acid sequences, amino acid compositions, physical and chemical characteristics, phylogenetic trees, conserved domain sequences, functional domains, molecular models, and folding states of the proteins they are predicted to encode. Expression analysis showed that four factors, which belonged to the ERF and DREB subfamilies, were induced by abiotic stresses, as well as by hormone treatment. This suggests that those AP2/ERF factors may be involved in signaling pathways responsive to abiotic and biotic stresses. The results from this study, reported herein, form a basis for future functional analyses of B. napus TFs that belong to the AP2/ERF family.

Genome-scale prediction of proteins with long intrinsically disordered regions

Proteins with long disordered regions (LDRs), defined as having 30 or more consecutive disordered residues, are abundant in eukaryotes, and these regions are recognized as a distinct class of biologically functional domains. LDRs facilitate various cellular functions and are important for target selection in structural genomics. Motivated by the lack of methods that directly predict proteins with LDRs, we designed Super-fast predictor of proteins with Long Intrinsically DisordERed regions (SLIDER). SLIDER utilizes logistic regression that takes an empirically chosen set of numerical features, which consider selected physicochemical properties of amino acids, sequence complexity, and amino acid composition, as its inputs. Empirical tests show that SLIDER offers competitive predictive performance combined with low computational cost. It outperforms, by at least a modest margin, a comprehensive set of modern disorder predictors (that can indirectly predict LDRs) and is 16 times faster compared to the best currently available disorder predictor. Utilizing our time-efficient predictor, we characterized abundance and functional roles of proteins with LDRs over 110 eukaryotic proteomes. Similar to related studies, we found that eukaryotes have many (on average 30.3%) proteins with LDRs with majority of proteomes having between 25 and 40%, where higher abundance is characteristic to proteomes that have larger proteins. Our first-of-its-kind large-scale functional analysis shows that these proteins are enriched in a number of cellular functions and processes including certain binding events, regulation of catalytic activities, cellular component organization, biogenesis, biological regulation, and some metabolic and developmental processes. A webserver that implements SLIDER is available at http://biomine.ece.ualberta.ca/SLIDER/.