Comprehensive Research on Druggable Proteins: From PSSM to Pre-Trained Language Models

Identification of druggable proteins can greatly reduce the cost of discovering new potential drugs. Traditional experimental approaches to exploring these proteins are often costly, slow, and labor-intensive, making them impractical for large-scale research. In response, recent decades have seen a rise in computational methods. These alternatives support drug discovery by creating advanced predictive models. In this study, we proposed a fast and precise classifier for the identification of druggable proteins using a protein language model (PLM) with fine-tuned evolutionary scale modeling 2 (ESM-2) embeddings, achieving 95.11% accuracy on the benchmark dataset. Furthermore, we made a careful comparison to examine the predictive abilities of ESM-2 embeddings and position-specific scoring matrix (PSSM) features by using the same classifiers. The results suggest that ESM-2 embeddings outperformed PSSM features in terms of accuracy and efficiency. Recognizing the potential of language models, we also developed an end-to-end model based on the generative pre-trained transformers 2 (GPT-2) with modifications. To our knowledge, this is the first time a large language model (LLM) GPT-2 has been deployed for the recognition of druggable proteins. Additionally, a more up-to-date dataset, known as Pharos, was adopted to further validate the performance of the proposed model.

DPI_CDF: druggable protein identifier using cascade deep forest

BACKGROUND

Drug targets in living beings perform pivotal roles in the discovery of potential drugs. Conventional wet-lab characterization of drug targets is although accurate but generally expensive, slow, and resource intensive. Therefore, computational methods are highly desirable as an alternative to expedite the large-scale identification of druggable proteins (DPs); however, the existing in silico predictor's performance is still not satisfactory.

METHODS

In this study, we developed a novel deep learning-based model DPI_CDF for predicting DPs based on protein sequence only. DPI_CDF utilizes evolutionary-based (i.e., histograms of oriented gradients for position-specific scoring matrix), physiochemical-based (i.e., component protein sequence representation), and compositional-based (i.e., normalized qualitative characteristic) properties of protein sequence to generate features. Then a hierarchical deep forest model fuses these three encoding schemes to build the proposed model DPI_CDF.

RESULTS

The empirical outcomes on 10-fold cross-validation demonstrate that the proposed model achieved 99.13 % accuracy and 0.982 of Matthew's-correlation-coefficient (MCC) on the training dataset. The generalization power of the trained model is further examined on an independent dataset and achieved 95.01% of maximum accuracy and 0.900 MCC. When compared to current state-of-the-art methods, DPI_CDF improves in terms of accuracy by 4.27% and 4.31% on training and testing datasets, respectively. We believe, DPI_CDF will support the research community to identify druggable proteins and escalate the drug discovery process.

AVAILABILITY

The benchmark datasets and source codes are available in GitHub: http://github.com/Muhammad-Arif-NUST/DPI_CDF .

PredLLPS_PSSM: a novel predictor for liquid-liquid protein separation identification based on evolutionary information and a deep neural network

The formation of biomolecular condensates by liquid-liquid phase separation (LLPS) has become a universal mechanism for spatiotemporal coordination of biological activities in cells and has been widely observed to directly regulate the key cellular processes involved in cancer cell pathology. However, the complexity of protein sequences and the diversity of conformations are inherently disordered, which poses great challenges for LLPS protein calculations and experimental research. Herein, we proposed a novel predictor named PredLLPS_PSSM for LLPS protein identification based only on sequence evolution information. Because finding real and reliable samples is the cornerstone of building predictors, we collected anew and collated the LLPS proteins from the latest versions of three databases. By comparing the performance of the position-specific score matrix (PSSM) and word embedding, PredLLPS_PSSM combined PSSM-based information and two deep learning frameworks. Independent tests using three existing independent test datasets and two newly constructed independent test datasets demonstrated the superiority of PredLLPS_PSSM compared with state-of-the-art methods. Furthermore, we tested PredLLPS_PSSM on nine experimentally identified LLPS proteins from three insects that were not included in any of the databases. In addition, the powerful Shapley Additive exPlanation algorithm and heatmap were applied to find the most critical amino acids relevant to LLPS.

High-throughput deep learning variant effect prediction with Sequence UNET

Understanding coding mutations is important for many applications in biology and medicine but the vast mutation space makes comprehensive experimental characterisation impossible. Current predictors are often computationally intensive and difficult to scale, including recent deep learning models. We introduce Sequence UNET, a highly scalable deep learning architecture that classifies and predicts variant frequency from sequence alone using multi-scale representations from a fully convolutional compression/expansion architecture. It achieves comparable pathogenicity prediction to recent methods. We demonstrate scalability by analysing 8.3B variants in 904,134 proteins detected through large-scale proteomics. Sequence UNET runs on modest hardware with a simple Python package.

Pfeature: A Tool for Computing Wide Range of Protein Features and Building Prediction Models

In the last three decades, a wide range of protein features have been discovered to annotate a protein. Numerous attempts have been made to integrate these features in a software package/platform so that the user may compute a wide range of features from a single source. To complement the existing methods, we developed a method, Pfeature, for computing a wide range of protein features. Pfeature allows to compute more than 200,000 features required for predicting the overall function of a protein, residue-level annotation of a protein, and function of chemically modified peptides. It has six major modules, namely, composition, binary profiles, evolutionary information, structural features, patterns, and model building. Composition module facilitates to compute most of the existing compositional features, plus novel features. The binary profile of amino acid sequences allows to compute the fraction of each type of residue as well as its position. The evolutionary information module allows to compute evolutionary information of a protein in the form of a position-specific scoring matrix profile generated using Position-Specific Iterative Basic Local Alignment Search Tool (PSI-BLAST); fit for annotation of a protein and its residues. A structural module was developed for computing of structural features/descriptors from a tertiary structure of a protein. These features are suitable to predict the therapeutic potential of a protein containing non-natural or chemically modified residues. The model-building module allows to implement various machine learning techniques for developing classification and regression models as well as feature selection. Pfeature also allows the generation of overlapping patterns and features from a protein. A user-friendly Pfeature is available as a web server python library and stand-alone package.

Identification of adaptor proteins by incorporating deep learning and PSSM profiles

Adaptor proteins, also known as signal transduction adaptor proteins, are important proteins in signal transduction pathways, and play a role in connecting signal proteins for signal transduction between cells. Studies have shown that adaptor proteins are closely related to some diseases, such as tumors and diabetes. Therefore, it is very meaningful to construct a relevant model to accurately identify adaptor proteins. In recent years, many studies have used a position-specific scoring matrix (PSSM) and neural network methods to identify adaptor proteins. However, ordinary neural network models cannot correlate the contextual information in PSSM profiles well, so these studies usually process 20×N (N > 20) PSSM into 20×20 dimensions, which results in the loss of a large amount of protein information; This research proposes an efficient method that combines one-dimensional convolution (1-D CNN) and a bidirectional long short-term memory network (biLSTM) to identify adaptor proteins. The complete PSSM profiles are the input of the model, and the complete information of the protein is retained during the training process. We perform cross-validation during model training and test the performance of the model on an independent test set; in the data set with 1224 adaptor proteins and 11,078 non-adaptor proteins, five indicators including specificity, sensitivity, accuracy, area under the receiver operating characteristic curve (AUC) metric and Matthews correlation coefficient (MCC), were employed to evaluate model performance. On the independent test set, the specificity, sensitivity, accuracy and MCC were 0.817, 0.865, 0.823 and 0.465, respectively. Those results show that our method is better than the state-of-the art methods. This study is committed to improve the accuracy of adaptor protein identification, and laid a foundation for further research on diseases related to adaptor protein. This research provided a new idea for the application of deep learning related models in bioinformatics and computational biology.

Target-AMP: Computational prediction of antimicrobial peptides by coupling sequential information with evolutionary profile

Antimicrobial peptides (AMPs) are gaining a lot of attention as cutting-edge treatments for many infectious disorders. The effectiveness of AMPs against bacteria, fungi, and viruses has persisted for a long period, making them the greatest option for addressing the growing problem of antibiotic resistance. Due to their wide-ranging actions, AMPs have become more prominent, particularly in therapeutic applications. The prediction of AMPs has become a difficult task for academics due to the explosive increase of AMPs documented in databases. Wet-lab investigations to find anti-microbial peptides are exceedingly costly, time-consuming, and even impossible for some species. Therefore, in order to choose the optimal AMPs candidate before to the in-vitro trials, an efficient computational method must be developed. In this study, an effort was made to develop a machine learning-based classification system that is effective, accurate, and can distinguish between anti-microbial peptides. The position-specific-scoring-matrix (PSSM), Pseudo Amino acid composition, di-peptide composition, and combination of these three were utilized in the suggested scheme to extract salient aspects from AMPs sequences. The classification techniques K-nearest neighbor (KNN), Random Forest (RF), and Support Vector Machine (SVM) were employed. On the independent dataset and training dataset, the accuracy levels achieved by the suggested predictor (Target-AMP) are 97.07% and 95.71%, respectively. The results show that, when compared to other techniques currently used in the literature, our Target-AMP had the best success rate.

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

Background

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

Results

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

Conclusions

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

Supplementary Information

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

Incorporating support vector machine with sequential minimal optimization to identify anticancer peptides

BACKGROUND

Cancer is one of the major causes of death worldwide. To treat cancer, the use of anticancer peptides (ACPs) has attracted increased attention in recent years. ACPs are a unique group of small molecules that can target and kill cancer cells fast and directly. However, identifying ACPs by wet-lab experiments is time-consuming and labor-intensive. Therefore, it is significant to develop computational tools for ACPs prediction. Though some ACP prediction tools have been developed recently, their performances are not well enough and most of them do not offer a function to distinguish ACPs from antimicrobial peptides (AMPs). Considering the fact that a growing number of studies have shown that some AMPs exhibit anticancer function, this work tries to build a model for distinguishing AMPs from ACPs in addition to a model that predicts ACPs from whole peptides.

RESULTS

This study chooses amino acid composition, N5C5, k-space, position-specific scoring matrix (PSSM) as features, and analyzes them by machine learning methods, including support vector machine (SVM) and sequential minimal optimization (SMO) to build a model (model 2) for distinguishing ACPs from whole peptides. Another model (model 1) that distinguishes ACPs from AMPs is also developed. Comparing to previous models, models developed in this research show better performance (accuracy: 85.5% for model 1 and 95.2% for model 2).

CONCLUSIONS

This work utilizes a new feature, PSSM, which contributes to better performance than other features. In addition to SVM, SMO is used in this research for optimizing SVM and the SMO-optimized models show better performance than non-optimized models. Last but not least, this work provides two different functions, including distinguishing ACPs from AMPs and distinguishing ACPs from all peptides. The second SMO-optimized model, which utilizes PSSM as a feature, performs better than all other existing tools.

Moonlighting protein prediction using physico-chemical and evolutional properties via machine learning methods

Background

Moonlighting proteins (MPs) are a subclass of multifunctional proteins in which more than one independent or usually distinct function occurs in a single polypeptide chain. Identification of unknown cellular processes, understanding novel protein mechanisms, improving the prediction of protein functions, and gaining information about protein evolution are the main reasons to study MPs. They also play an important role in disease pathways and drug-target discovery. Since detecting MPs experimentally is quite a challenge, most of them are detected randomly. Therefore, introducing an appropriate computational approach to predict MPs seems reasonable.

Results

In this study, we introduced a competent model for detecting moonlighting and non-MPs through extracted features from protein sequences. We attempted to set up a well-judged scheme for detecting outlier proteins. Consequently, 37 distinct feature vectors were utilized to study each protein’s impact on detecting MPs. Furthermore, 8 different classification methods were assessed to find the best performance. To detect outliers, each one of the classifications was executed 100 times by tenfold cross-validation on feature vectors; proteins which misclassified 90 times or more were grouped. This process was applied to every single feature vector and eventually the intersection of these groups was determined as the outlier proteins. The results of tenfold cross-validation on a dataset of 351 samples (containing 215 moonlighting and 136 non-moonlighting proteins) reveal that the SVM method on all feature vectors has the highest performance among all methods in this study and other available methods. Besides, the study of outliers showed that 57 of 351 proteins in the dataset could be an appropriate candidate for the outlier. Among the outlier proteins, there were non-MPs (such as P69797) that have been misclassified in 8 different classification methods with 16 different feature vectors. Because these proteins have been obtained by computational methods, the results of this study could reduce the likelihood of hypothesizing whether these proteins are non-moonlighting at all.

Conclusions

MPs are difficult to be identified through experimentation. Using distinct feature vectors, our method enabled identification of novel moonlighting proteins. The study also pinpointed that a number of non-MPs are likely to be moonlighting.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04194-5.

DeepRTCP: Predicting ATP-Binding Cassette Transporters Based on 1-Dimensional Convolutional Network

ATP-binding cassette (ABC) transporters can promote cells to absorb nutrients and excrete harmful substances. It plays a vital role in the transmembrane transport of macromolecules. Therefore, the identification of ABC transporters is of great significance for the biological research. This paper will introduce a novel method called DeepRTCP. DeepRTCP uses the deep convolutional neural network and a feature combined of reduced amino acid alphabet based tripeptide composition and PSSM to recognize ABC transporters. We constructed a dataset named ABC_2020. It contains the latest ABC transporters downloaded from Uniprot. We performed 10-fold cross-validation on DeepRTCP, and the average accuracy of DeepRTCP was 95.96%. Compared with the start-of-the-art method for predicting ABC transporters, DeepRTCP improved the accuracy by 9.29%. It is anticipated that DeepRTCP can be used as an effective ABC transporter classifier which provides a reliable guidance for the research of ABC transporters.

Identification and characterization of the LRR repeats in plant LRR-RLKs

Background

Leucine-rich-repeat receptor-like kinases (LRR-RLKs) play central roles in sensing various signals to regulate plant development and environmental responses. The extracellular domains (ECDs) of plant LRR-RLKs contain LRR motifs, consisting of highly conserved residues and variable residues, and are responsible for ligand perception as a receptor or co-receptor. However, there are few comprehensive studies on the ECDs of LRR-RLKs due to the difficulty in effectively identifying the divergent LRR repeats.

Results

In the current study, an efficient LRR motif prediction program, the “Phyto-LRR prediction” program, was developed based on the position-specific scoring matrix algorithm (PSSM) with some optimizations. This program was trained by 16-residue plant-specific LRR-highly conserved segments (HCS) from LRR-RLKs of 17 represented land plant species and a database containing more than 55,000 predicted LRRs based on this program was constructed. Both the prediction tool and database are freely available at http://phytolrr.com/ for website usage and at http://github.com/phytolrr for local usage. The LRR-RLKs were classified into 18 subgroups (SGs) according to the maximum-likelihood phylogenetic analysis of kinase domains (KDs) of the sequences. Based on the database and the SGs, the characteristics of the LRR motifs in the ECDs of the LRR-RLKs were examined, such as the arrangement of the LRRs, the solvent accessibility, the variable residues, and the N-glycosylation sites, revealing a comprehensive profile of the plant LRR-RLK ectodomains.

Conclusion

The “Phyto-LRR prediction” program is effective in predicting the LRR segments in plant LRR-RLKs, which, together with the database, will facilitate the exploration of plant LRR-RLKs functions. Based on the database, comprehensive sequential characteristics of the plant LRR-RLK ectodomains were profiled and analyzed.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12860-021-00344-y.

An efficient computational method for predicting drug-target interactions using weighted extreme learning machine and speed up robot features

Background

Prediction of novel Drug–Target interactions (DTIs) plays an important role in discovering new drug candidates and finding new proteins to target. In consideration of the time-consuming and expensive of experimental methods. Therefore, it is a challenging task that how to develop efficient computational approaches for the accurate predicting potential associations between drug and target.

Results

In the paper, we proposed a novel computational method called WELM-SURF based on drug fingerprints and protein evolutionary information for identifying DTIs. More specifically, for exploiting protein sequence feature, Position Specific Scoring Matrix (PSSM) is applied to capturing protein evolutionary information and Speed up robot features (SURF) is employed to extract sequence key feature from PSSM. For drug fingerprints, the chemical structure of molecular substructure fingerprints was used to represent drug as feature vector. Take account of the advantage that the Weighted Extreme Learning Machine (WELM) has short training time, good generalization ability, and most importantly ability to efficiently execute classification by optimizing the loss function of weight matrix. Therefore, the WELM classifier is used to carry out classification based on extracted features for predicting DTIs. The performance of the WELM-SURF model was evaluated by experimental validations on enzyme, ion channel, GPCRs and nuclear receptor datasets by using fivefold cross-validation test. The WELM-SURF obtained average accuracies of 93.54, 90.58, 85.43 and 77.45% on enzyme, ion channels, GPCRs and nuclear receptor dataset respectively. We also compared our performance with the Extreme Learning Machine (ELM), the state-of-the-art Support Vector Machine (SVM) on enzyme and ion channels dataset and other exiting methods on four datasets. By comparing with experimental results, the performance of WELM-SURF is significantly better than that of ELM, SVM and other previous methods in the domain.

Conclusion

The results demonstrated that the proposed WELM-SURF model is competent for predicting DTIs with high accuracy and robustness. It is anticipated that the WELM-SURF method is a useful computational tool to facilitate widely bioinformatics studies related to DTIs prediction.

Identification of Cancer Biomarkers in Human Body Fluids by Using Enhanced Physicochemical-incorporated Evolutionary Conservation Scheme

OBJECTIVE

Cancer is one of the most serious diseases affecting human health. Among all current cancer treatments, early diagnosis and control significantly help increase the chances of cure. Detecting cancer biomarkers in body fluids now is attracting more attention within oncologists. In-silico predictions of body fluid-related proteins, which can be served as cancer biomarkers, open a door for labor-intensive and time-consuming biochemical experiments.

METHODS

In this work, we propose a novel method for high-throughput identification of cancer biomarkers in human body fluids. We incorporate physicochemical properties into the weighted observed percentages (WOP) and position-specific scoring matrices (PSSM) profiles to enhance their attributes that reflect the evolutionary conservation of the body fluid-related proteins. The least absolute selection and shrinkage operator (LASSO) feature selection strategy is introduced to generate the optimal feature subset.

RESULTS

The ten-fold cross-validation results on training datasets demonstrate the accuracy of the proposed model. We also test our proposed method on independent testing datasets and apply it to the identification of potential cancer biomarkers in human body fluids.

CONCLUSION

The testing results promise a good generalization capability of our approach.

Predicting Self-Interacting Proteins Using a Recurrent Neural Network and Protein Evolutionary Information

Self-interacting proteins (SIPs) play crucial roles in biological activities of organisms. Many high-throughput methods can be used to identify SIPs. However, these methods are both time-consuming and expensive. How to develop effective computational approaches for identifying SIPs is a challenging task. In the article, we present a novel computational method called RRN-SIFT, which combines the recurrent neural network (RNN) with scale invariant feature transform (SIFT) to predict SIPs based on protein evolutionary information. The main advantage of the proposed RNN-SIFT model is that it uses SIFT for extracting key feature by exploring the evolutionary information embedded in Position-Specific Iterated BLAST–constructed position-specific scoring matrix and employs an RNN classifier to perform classification based on extracted features. Extensive experiments show that the RRN-SIFT obtained average accuracy of 94.34% and 97.12% on the yeast and human dataset, respectively. We also compared our performance with the back propagation neural network (BPNN), the state-of-the-art support vector machine (SVM), and other existing methods. By comparing with experimental results, the performance of RNN-SIFT is significantly better than that of the BPNN, SVM, and other previous methods in the domain. Therefore, we conclude that the proposed RNN-SIFT model is a useful tool for predicting SIPs, as well to solve other bioinformatics tasks. To facilitate widely studies and encourage future proteomics research, a freely available web server called RNN-SIFT-SIPs was developed at http://219.219.62.123:8888/RNNSIFT/ including the source code and the SIP datasets.

Identification of self-interacting proteins by integrating random projection classifier and finite impulse response filter

Background

Identification of protein-protein interactions (PPIs) is crucial for understanding biological processes and investigating the cellular functions of genes. Self-interacting proteins (SIPs) are those in which more than two identical proteins can interact with each other and they are the specific type of PPIs. More and more researchers draw attention to the SIPs detection, and several prediction model have been proposed, but there are still some problems. Hence, there is an urgent need to explore a efficient computational model for SIPs prediction.

Results

In this study, we developed an effective model to predict SIPs, called RP-FIRF, which merges the Random Projection (RP) classifier and Finite Impulse Response Filter (FIRF) together. More specifically, each protein sequence was firstly transformed into the Position Specific Scoring Matrix (PSSM) by exploiting Position Specific Iterated BLAST (PSI-BLAST). Then, to effectively extract the discriminary SIPs feature to improve the performance of SIPs prediction, a FIRF method was used on PSSM. The R’classifier was proposed to execute the classification and predict novel SIPs. We evaluated the performance of the proposed RP-FIRF model and compared it with the state-of-the-art support vector machine (SVM) on human and yeast datasets, respectively. The proposed model can achieve high average accuracies of 97.89 and 97.35% using five-fold cross-validation. To further evaluate the high performance of the proposed method, we also compared it with other six exiting methods, the experimental results demonstrated that the capacity of our model surpass that of the other previous approaches.

Conclusion

Experimental results show that self-interacting proteins are accurately well-predicted by the proposed model on human and yeast datasets, respectively. It fully show that the proposed model can predict the SIPs effectively and sufficiently. Thus, RP-FIRF model is an automatic decision support method which should provide useful insights into the recognition of SIPs.

iProDNA-CapsNet: identifying protein-DNA binding residues using capsule neural networks

BACKGROUND

Since protein-DNA interactions are highly essential to diverse biological events, accurately positioning the location of the DNA-binding residues is necessary. This biological issue, however, is currently a challenging task in the age of post-genomic where data on protein sequences have expanded very fast. In this study, we propose iProDNA-CapsNet - a new prediction model identifying protein-DNA binding residues using an ensemble of capsule neural networks (CapsNets) on position specific scoring matrix (PSMM) profiles. The use of CapsNets promises an innovative approach to determine the location of DNA-binding residues. In this study, the benchmark datasets introduced by Hu et al. (2017), i.e., PDNA-543 and PDNA-TEST, were used to train and evaluate the model, respectively. To fairly assess the model performance, comparative analysis between iProDNA-CapsNet and existing state-of-the-art methods was done.

RESULTS

Under the decision threshold corresponding to false positive rate (FPR) ≈ 5%, the accuracy, sensitivity, precision, and Matthews's correlation coefficient (MCC) of our model is increased by about 2.0%, 2.0%, 14.0%, and 5.0% with respect to TargetDNA (Hu et al., 2017) and 1.0%, 75.0%, 45.0%, and 77.0% with respect to BindN+ (Wang et al., 2010), respectively. With regards to other methods not reporting their threshold settings, iProDNA-CapsNet also shows a significant improvement in performance based on most of the evaluation metrics. Even with different patterns of change among the models, iProDNA-CapsNets remains to be the best model having top performance in most of the metrics, especially MCC which is boosted from about 8.0% to 220.0%.

CONCLUSIONS

According to all evaluation metrics under various decision thresholds, iProDNA-CapsNet shows better performance compared to the two current best models (BindN and TargetDNA). Our proposed approach also shows that CapsNet can potentially be used and adopted in other biological applications.

Classification of adaptor proteins using recurrent neural networks and PSSM profiles

BACKGROUND

Adaptor proteins are carrier proteins that play a crucial role in signal transduction. They commonly consist of several modular domains, each having its own binding activity and operating by forming complexes with other intracellular-signaling molecules. Many studies determined that the adaptor proteins had been implicated in a variety of human diseases. Therefore, creating a precise model to predict the function of adaptor proteins is one of the vital tasks in bioinformatics and computational biology. Few computational biology studies have been conducted to predict the protein functions, and in most of those studies, position specific scoring matrix (PSSM) profiles had been used as the features to be fed into the neural networks. However, the neural networks could not reach the optimal result because the sequential information in PSSMs has been lost. This study proposes an innovative approach by incorporating recurrent neural networks (RNNs) and PSSM profiles to resolve this problem.

RESULTS

Compared to other state-of-the-art methods which had been applied successfully in other problems, our method achieves enhancement in all of the common measurement metrics. The area under the receiver operating characteristic curve (AUC) metric in prediction of adaptor proteins in the cross-validation and independent datasets are 0.893 and 0.853, respectively.

CONCLUSIONS

This study opens a research path that can promote the use of RNNs and PSSM profiles in bioinformatics and computational biology. Our approach is reproducible by scientists that aim to improve the performance results of different protein function prediction problems. Our source code and datasets are available at https://github.com/ngphubinh/adaptors.

Recent Advances in Machine Learning Based Prediction of RNA-protein Interactions

The interactions between RNAs and proteins play critical roles in many biological processes. Therefore, characterizing these interactions becomes critical for mechanistic, biomedical, and clinical studies. Many experimental methods can be used to determine RNA-protein interactions in multiple aspects. However, due to the facts that RNA-protein interactions are tissuespecific and condition-specific, as well as these interactions are weak and frequently compete with each other, those experimental techniques can not be made full use of to discover the complete spectrum of RNA-protein interactions. To moderate these issues, continuous efforts have been devoted to developing high quality computational techniques to study the interactions between RNAs and proteins. Many important progresses have been achieved with the application of novel techniques and strategies, such as machine learning techniques. Especially, with the development and application of CLIP techniques, more and more experimental data on RNA-protein interaction under specific biological conditions are available. These CLIP data altogether provide a rich source for developing advanced machine learning predictors. In this review, recent progresses on computational predictors for RNA-protein interaction were summarized in the following aspects: dataset, prediction strategies, and input features. Possible future developments were also discussed at the end of the review.

ProteinNet: a standardized data set for machine learning of protein structure

Background

Rapid progress in deep learning has spurred its application to bioinformatics problems including protein structure prediction and design. In classic machine learning problems like computer vision, progress has been driven by standardized data sets that facilitate fair assessment of new methods and lower the barrier to entry for non-domain experts. While data sets of protein sequence and structure exist, they lack certain components critical for machine learning, including high-quality multiple sequence alignments and insulated training/validation splits that account for deep but only weakly detectable homology across protein space.

Results

We created the ProteinNet series of data sets to provide a standardized mechanism for training and assessing data-driven models of protein sequence-structure relationships. ProteinNet integrates sequence, structure, and evolutionary information in programmatically accessible file formats tailored for machine learning frameworks. Multiple sequence alignments of all structurally characterized proteins were created using substantial high-performance computing resources. Standardized data splits were also generated to emulate the difficulty of past CASP (Critical Assessment of protein Structure Prediction) experiments by resetting protein sequence and structure space to the historical states that preceded six prior CASPs. Utilizing sensitive evolution-based distance metrics to segregate distantly related proteins, we have additionally created validation sets distinct from the official CASP sets that faithfully mimic their difficulty.

Conclusion

ProteinNet represents a comprehensive and accessible resource for training and assessing machine-learned models of protein structure.

Sequence-based Prediction of Protein-Protein Interactions Using Gray Wolf Optimizer-Based Relevance Vector Machine

Protein-protein interactions (PPIs) are essential to a number of biological processes. The PPIs generated by biological experiment are both time-consuming and expensive. Therefore, many computational methods have been proposed to identify PPIs. However, most of these methods are limited as they are difficult to compute and rely on a large number of homologous proteins. Accordingly, it is urgent to develop effective computational methods to detect PPIs using only protein sequence information. The kernel parameter of relevance vector machine (RVM) is set by experience, which may not obtain the optimal solution, affecting the prediction performance of RVM. In this work, we presented a novel computational approach called GWORVM-BIG, which used Bi-gram (BIG) to represent protein sequences on a position-specific scoring matrix (PSSM) and GWORVM classifier to perform classification for predicting PPIs. More specifically, the proposed GWORVM model can obtain the optimum solution of kernel parameters using gray wolf optimizer approach, which has the advantages of less control parameters, strong global optimization ability, and ease of implementation compared with other optimization algorithms. The experimental results on yeast and human data sets demonstrated the good accuracy and efficiency of the proposed GWORVM-BIG method. The results showed that the proposed GWORVM classifier can significantly improve the prediction performance compared with the RVM model using other optimizer algorithms including grid search (GS), genetic algorithm (GA), and particle swarm optimization (PSO). In addition, the proposed method is also compared with other existing algorithms, and the experimental results further indicated that the proposed GWORVM-BIG model yields excellent prediction performance. For facilitating extensive studies for future proteomics research, the GWORVMBIG server is freely available for academic use at http://219.219.62.123:8888/GWORVMBIG.

Residue Adjacency Matrix Based Feature Engineering for Predicting Cysteine Reactivity in Proteins

Free radicals that form from reactive species of nitrogen and oxygen can react dangerously with cellular components and are involved with the pathogenesis of diabetes, cancer, Parkinson's, and heart disease. Cysteine amino acids, due to their reactive nature, are prone to oxidation by these free radicals. Determining which cysteines oxidize within proteins is crucial to our understanding of these chronic diseases. Wet lab techniques, like differential alkylation, to determine which cysteines oxidize are often expensive and time-consuming. We utilize machine learning as a fast and inexpensive approach to identifying cysteines with oxidative capabilities. We created the original features RAMmod and RAMseq for use in classification. We also incorporated well-known features such as PROPKA, SASA, PSS, and PSSM. Our algorithm requires only the protein sequence to operate; however, we do use template matching by MODELLER to acquire 3D coordinates for additional feature extraction. There was a mean improvement of RAM over N6C by 22.04% MCC. It was statistically significant with a p-value of 0.015. RAM provided a significant increase over PSSM with a p-value of 0.040 and an average 70.09% improvement MCC.

Identification of protein subcellular localization via integrating evolutionary and physicochemical information into Chou's general PseAAC

Identifying the location of proteins in a cell plays an important role in understanding their functions, such as drug design, therapeutic target discovery and biological research. However, the traditional subcellular localization experiments are time-consuming, laborious and small scale. With the development of next-generation sequencing technology, the number of proteins has grown exponentially, which lays the foundation of the computational method for identifying protein subcellular localization. Although many methods for predicting subcellular localization of proteins have been proposed, most of them are limited to single-location. In this paper, we propose a multi-kernel SVM to predict subcellular localization of both multi-location and single-location proteins. First, we make use of the evolutionary information extracted from position specific scoring matrix (PSSM) and physicochemical properties of proteins, by Chou's general PseAAC and other efficient functions. Then, we propose a multi-kernel support vector machine (SVM) model to identify multi-label protein subcellular localization. As a result, our method has a good performance on predicting subcellular localization of proteins. It achieves an average precision of 0.7065 and 0.6889 on two human datasets, respectively. All results are higher than those achieved by other existing methods. Therefore, we provide an efficient system via a novel perspective to study the protein subcellular localization.

Accurate Prediction of ncRNA-Protein Interactions From the Integration of Sequence and Evolutionary Information

Non-coding RNA (ncRNA) plays a crucial role in numerous biological processes including gene expression and post-transcriptional gene regulation. The biological function of ncRNA is mostly realized by binding with related proteins. Therefore, an accurate understanding of interactions between ncRNA and protein has a significant impact on current biological research. The major challenge at this stage is the waste of a great deal of redundant time and resource consumed on classification in traditional interaction pattern prediction methods. Fortunately, an efficient classifier named LightGBM can solve this difficulty of long time consumption. In this study, we employed LightGBM as the integrated classifier and proposed a novel computational model for predicting ncRNA and protein interactions. More specifically, the pseudo-Zernike Moments and singular value decomposition algorithm are employed to extract the discriminative features from protein and ncRNA sequences. On four widely used datasets RPI369, RPI488, RPI1807, and RPI2241, we evaluated the performance of LGBM and obtained an superior performance with AUC of 0.799, 0.914, 0.989, and 0.762, respectively. The experimental results of 10-fold cross-validation shown that the proposed method performs much better than existing methods in predicting ncRNA-protein interaction patterns, which could be used as a useful tool in proteomics research.

Sequence Similarity Searching

Sequence similarity searching has become an important part of the daily routine of molecular biologists, bioinformaticians and biophysicists. With the rapidly growing sequence databanks, this computational approach is commonly applied to determine functions and structures of unannotated sequences, to investigate relationships between sequences, and to construct phylogenetic trees. We introduce arguably the most popular BLAST-based family of the sequence similarity search tools. We explain basic concepts related to the sequence alignment and demonstrate how to search the current databanks using Web site versions of BLASTP, PSI-BLAST and BLASTN. We also describe the standalone BLAST+ tool. Moreover, this unit discusses the inputs, parameter settings and outputs of these tools. Lastly, we cover recent advances in the sequence similarity searching, focusing on the fast MMseqs2 method. © 2018 by John Wiley & Sons, Inc.

A New Method for Recognizing Cytokines Based on Feature Combination and a Support Vector Machine Classifier

Research on cytokine recognition is of great significance in the medical field due to the fact cytokines benefit the diagnosis and treatment of diseases, but the current methods for cytokine recognition have many shortcomings, such as low sensitivity and low F-score. Therefore, this paper proposes a new method on the basis of feature combination. The features are extracted from compositions of amino acids, physicochemical properties, secondary structures, and evolutionary information. The classifier used in this paper is SVM. Experiments show that our method is better than other methods in terms of accuracy, sensitivity, specificity, F-score and Matthew's correlation coefficient.

A Deep Learning Framework for Robust and Accurate Prediction of ncRNA-Protein Interactions Using Evolutionary Information

The interactions between non-coding RNAs (ncRNAs) and proteins play an important role in many biological processes, and their biological functions are primarily achieved by binding with a variety of proteins. High-throughput biological techniques are used to identify protein molecules bound with specific ncRNA, but they are usually expensive and time consuming. Deep learning provides a powerful solution to computationally predict RNA-protein interactions. In this work, we propose the RPI-SAN model by using the deep-learning stacked auto-encoder network to mine the hidden high-level features from RNA and protein sequences and feed them into a random forest (RF) model to predict ncRNA binding proteins. Stacked assembling is further used to improve the accuracy of the proposed method. Four benchmark datasets, including RPI2241, RPI488, RPI1807, and NPInter v2.0, were employed for the unbiased evaluation of five established prediction tools: RPI-Pred, IPMiner, RPISeq-RF, lncPro, and RPI-SAN. The experimental results show that our RPI-SAN model achieves much better performance than other methods, with accuracies of 90.77%, 89.7%, 96.1%, and 99.33%, respectively. It is anticipated that RPI-SAN can be used as an effective computational tool for future biomedical researches and can accurately predict the potential ncRNA-protein interacted pairs, which provides reliable guidance for biological research.

Prediction of zinc binding sites in proteins using sequence derived information

Zinc is one the most abundant catalytic cofactor and also an important structural component of a large number of metallo-proteins. Hence prediction of zinc metal binding sites in proteins can be a significant step in annotation of molecular function of a large number of proteins. Majority of existing methods for zinc-binding site predictions are based on a data-set of proteins, which has been compiled nearly a decade ago. Hence there is a need to develop zinc-binding site prediction system using the current updated data to include recently added proteins. Herein, we propose a support vector machine-based method, named as ZincBinder, for prediction of zinc metal-binding site in a protein using sequence profile information. The predictor was trained using fivefold cross validation approach and achieved 85.37% sensitivity with 86.20% specificity during training. Benchmarking on an independent non-redundant data-set, which was not used during training, showed better performance of ZincBinder vis-à-vis existing methods. Executable versions, source code, sample datasets, and usage instructions are available at http://proteininformatics.org/mkumar/znbinder/.

EL_PSSM-RT: DNA-binding residue prediction by integrating ensemble learning with PSSM Relation Transformation

Background

Prediction of DNA-binding residue is important for understanding the protein-DNA recognition mechanism. Many computational methods have been proposed for the prediction, but most of them do not consider the relationships of evolutionary information between residues.

Results

In this paper, we first propose a novel residue encoding method, referred to as the Position Specific Score Matrix (PSSM) Relation Transformation (PSSM-RT), to encode residues by utilizing the relationships of evolutionary information between residues. PDNA-62 and PDNA-224 are used to evaluate PSSM-RT and two existing PSSM encoding methods by five-fold cross-validation. Performance evaluations indicate that PSSM-RT is more effective than previous methods. This validates the point that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction. An ensemble learning classifier (EL_PSSM-RT) is also proposed by combining ensemble learning model and PSSM-RT to better handle the imbalance between binding and non-binding residues in datasets. EL_PSSM-RT is evaluated by five-fold cross-validation using PDNA-62 and PDNA-224 as well as two independent datasets TS-72 and TS-61. Performance comparisons with existing predictors on the four datasets demonstrate that EL_PSSM-RT is the best-performing method among all the predicting methods with improvement between 0.02–0.07 for MCC, 4.18–21.47% for ST and 0.013–0.131 for AUC. Furthermore, we analyze the importance of the pair-relationships extracted by PSSM-RT and the results validates the usefulness of PSSM-RT for encoding DNA-binding residues.

Conclusions

We propose a novel prediction method for the prediction of DNA-binding residue with the inclusion of relationship of evolutionary information and ensemble learning. Performance evaluation shows that the relationship of evolutionary information between residues is indeed useful in DNA-binding residue prediction and ensemble learning can be used to address the data imbalance issue between binding and non-binding residues. A web service of EL_PSSM-RT (http://hlt.hitsz.edu.cn:8080/PSSM-RT_SVM/) is provided for free access to the biological research community.

Electronic supplementary material

The online version of this article (doi:10.1186/s12859-017-1792-8) contains supplementary material, which is available to authorized users.

Enhanced identification of β-lactamases and its classes using sequence, physicochemical and evolutionary information with sequence feature characterization of the classes

β-lactamases provides one of the most successful means of evading the therapeutic effects of β lactam class of antibiotics by many gram positive and gram negative bacteria. On the basis of sequence identity, β-lactamases have been identified into four distinct classes- A, B, C and D. The classes A, C and D are the serine β-lactamases and class B is the metallo-lactamse. In the present study, we developed a two stage cascade classification system. The first-stage performs the classification of β-lactamases from non-β-lactamases and the second-stage performs the further classification of β-lactamases into four different β-lactamase classes. In the first-stage binary classification, we obtained an accuracy of 97.3% with a sensitivity of 89.1% and specificity of 98.0% and for the second stage multi-class classification, we obtained an accuracy of 87.3% for the class A, 91.0% for the class B, 96.3% for the class C and 96.4% for class D. A systematic statistical analysis is carried out on the sieved-out, correctly-predicted instances from the second stage classifier, which revealed some interesting patterns. We analyzed different classes of β-lactamases on the basis of sequence and physicochemical property differences between them. Among amino acid composition, H, W, Y and V showed significant differences between the different β-lactamases classes. Differences in average physicochemical properties are observed for isoelectric point, volume, flexibility, hydrophobicity, bulkiness and charge in one or more β-lactamase classes. The key differences in physicochemical property groups can be observed in small and aromatic groups. Among amino acid property group n-grams except charged n-grams, all other property group n-grams are significant in one or more classes. Statistically significant differences in dipeptide counts among different β-lactamase classes are also reported.

Fast H-DROP: A thirty times accelerated version of H-DROP for interactive SVM-based prediction of helical domain linkers

Efficient and rapid prediction of domain regions from amino acid sequence information alone is often required for swift structural and functional characterization of large multi-domain proteins. Here we introduce Fast H-DROP, a thirty times accelerated version of our previously reported H-DROP (Helical Domain linker pRediction using OPtimal features), which is unique in specifically predicting helical domain linkers (boundaries). Fast H-DROP, analogously to H-DROP, uses optimum features selected from a set of 3000 ones by combining a random forest and a stepwise feature selection protocol. We reduced the computational time from 8.5 min per sequence in H-DROP to 14 s per sequence in Fast H-DROP on an 8 Xeon processor Linux server by using SWISS-PROT instead of Genbank non-redundant (nr) database for generating the PSSMs. The sensitivity and precision of Fast H-DROP assessed by cross-validation were 33.7 and 36.2%, which were merely ~2% lower than that of H-DROP. The reduced computational time of Fast H-DROP, without affecting prediction performances, makes it more interactive and user-friendly. Fast H-DROP and H-DROP are freely available from http://domserv.lab.tuat.ac.jp/ .

Classify vertebrate hemoglobin proteins by incorporating the evolutionary information into the general PseAAC with the hybrid approach

Hemoglobin is an oxygen-binding protein widely present in all kingdoms of life from prokaryotic to eukaryotic, but well established in the vertebrate system. An attempt was made to determine the Vertebrate hemoglobin (VerHb) protein on their animal classifications, based on general pseudo amino acid composition (PseAAC)'s evolutionary profiles and hybrid approach. The support vector machine (SVM) has been applied to develop all models, the prediction results further compared according to their animal classification. The performance of the approaches estimated using five-fold cross-validation techniques. The prediction performance was further investigated by receiver operating characteristic (ROC) and prediction score graphs. The prediction accuracy (ACC), sensitivity (SN) and specificity (SP) were examined to find the accurate predictions on the threshold level. Based on the approach, a web-tool has been developed for identifying the VerHb proteins.

A systematic, large-scale comparison of transcription factor binding site models

Background

The modelling of gene regulation is a major challenge in biomedical research. This process is dominated by transcription factors (TFs) and mutations in their binding sites (TFBSs) may cause the misregulation of genes, eventually leading to disease. The consequences of DNA variants on TF binding are modelled in silico using binding matrices, but it remains unclear whether these are capable of accurately representing in vivo binding.

In this study, we present a systematic comparison of binding models for 82 human TFs from three freely available sources: JASPAR matrices, HT-SELEX-generated models and matrices derived from protein binding microarrays (PBMs). We determined their ability to detect experimentally verified “real” in vivo TFBSs derived from ENCODE ChIP-seq data. As negative controls we chose random downstream exonic sequences, which are unlikely to harbour TFBS. All models were assessed by receiver operating characteristics (ROC) analysis.

Results

While the area-under-curve was low for most of the tested models with only 47 % reaching a score of 0.7 or higher, we noticed strong differences between the various position-specific scoring matrices with JASPAR and HT-SELEX models showing higher success rates than PBM-derived models. In addition, we found that while TFBS sequences showed a higher degree of conservation than randomly chosen sequences, there was a high variability between individual TFBSs.

Conclusions

Our results show that only few of the matrix-based models used to predict potential TFBS are able to reliably detect experimentally confirmed TFBS.

We compiled our findings in a freely accessible web application called ePOSSUM (http:/mutationtaster.charite.de/ePOSSUM/) which uses a Bayes classifier to assess the impact of genetic alterations on TF binding in user-defined sequences. Additionally, ePOSSUM provides information on the reliability of the prediction using our test set of experimentally confirmed binding sites.

Electronic supplementary material

The online version of this article (doi:10.1186/s12864-016-2729-8) contains supplementary material, which is available to authorized users.

RVMAB: Using the Relevance Vector Machine Model Combined with Average Blocks to Predict the Interactions of Proteins from Protein Sequences

Protein-Protein Interactions (PPIs) play essential roles in most cellular processes. Knowledge of PPIs is becoming increasingly more important, which has prompted the development of technologies that are capable of discovering large-scale PPIs. Although many high-throughput biological technologies have been proposed to detect PPIs, there are unavoidable shortcomings, including cost, time intensity, and inherently high false positive and false negative rates. For the sake of these reasons, in silico methods are attracting much attention due to their good performances in predicting PPIs. In this paper, we propose a novel computational method known as RVM-AB that combines the Relevance Vector Machine (RVM) model and Average Blocks (AB) to predict PPIs from protein sequences. The main improvements are the results of representing protein sequences using the AB feature representation on a Position Specific Scoring Matrix (PSSM), reducing the influence of noise using a Principal Component Analysis (PCA), and using a Relevance Vector Machine (RVM) based classifier. We performed five-fold cross-validation experiments on yeast and Helicobacter pylori datasets, and achieved very high accuracies of 92.98% and 95.58% respectively, which is significantly better than previous works. In addition, we also obtained good prediction accuracies of 88.31%, 89.46%, 91.08%, 91.55%, and 94.81% on other five independent datasets C. elegans, M. musculus, H. sapiens, H. pylori, and E. coli for cross-species prediction. To further evaluate the proposed method, we compare it with the state-of-the-art support vector machine (SVM) classifier on the yeast dataset. The experimental results demonstrate that our RVM-AB method is obviously better than the SVM-based method. The promising experimental results show the efficiency and simplicity of the proposed method, which can be an automatic decision support tool. To facilitate extensive studies for future proteomics research, we developed a freely available web server called RVMAB-PPI in Hypertext Preprocessor (PHP) for predicting PPIs. The web server including source code and the datasets are available at http://219.219.62.123:8888/ppi_ab/.

FootprintDB: Analysis of Plant Cis-Regulatory Elements, Transcription Factors, and Binding Interfaces

FootprintDB is a database and search engine that compiles regulatory sequences from open access libraries of curated DNA cis-elements and motifs, and their associated transcription factors (TFs). It systematically annotates the binding interfaces of the TFs by exploiting protein-DNA complexes deposited in the Protein Data Bank. Each entry in footprintDB is thus a DNA motif linked to the protein sequence of the TF(s) known to recognize it, and in most cases, the set of predicted interface residues involved in specific recognition. This chapter explains step-by-step how to search for DNA motifs and protein sequences in footprintDB and how to focus the search to a particular organism. Two real-world examples are shown where this software was used to analyze transcriptional regulation in plants. Results are described with the aim of guiding users on their interpretation, and special attention is given to the choices users might face when performing similar analyses.

Psychological Sense of University Membership: An Adaptation Study of the PSSM Scale for Turkish University Students

The Psychological Sense of School Membership Scale (PSSM) is a widely used instrument to assess the sense of belonging to a school among adolescents. Despite its widespread use in middle and high school students, to date no particular adaptation study has been conducted for its use among university students. For this reason, the present study conducted an adaptation of the PSSM scale for these students. Five hundred and nine students at a Turkish university voluntarily participated in the study, and the PSSM Scale's factor structure was examined by exploratory and confirmatory factor analyses, identifying three factors representing the students' sense of university membership with acceptable internal consistencies: acceptance by faculty members (.70), belonging (.75), and acceptance by students (.76). The internal consistency of the 18-item scale was calculated as .84. As hypothesized, the convergent and discriminant validity of the scale was also tested. The self-report sense of belonging and degree of satisfaction with the university were positively correlated with the three dimensions of the scale. Also, the scores regarding the students' intention to drop out of university along with loneliness were negatively correlated with all the dimension of the PSSM scale.

MATEPRED-A-SVM-Based Prediction Method for Multidrug And Toxin Extrusion (MATE) Proteins

The growth and spread of drug resistance in bacteria have been well established in both mankind and beasts and thus is a serious public health concern. Due to the increasing problem of drug resistance, control of infectious diseases like diarrhea, pneumonia etc. is becoming more difficult. Hence, it is crucial to understand the underlying mechanism of drug resistance mechanism and devising novel solution to address this problem. Multidrug And Toxin Extrusion (MATE) proteins, first characterized as bacterial drug transporters, are present in almost all species. It plays a very important function in the secretion of cationic drugs across the cell membrane. In this work, we propose SVM based method for prediction of MATE proteins. The data set employed for training consists of 189 non-redundant protein sequences, that are further classified as positive (63 sequences) set comprising of sequences from MATE family, and negative (126 sequences) set having protein sequences from other transporters families proteins and random protein sequences taken from NCBI while in the test set, there are 120 protein sequences in all (8 in positive and 112 in negative set). The model was derived using Position Specific Scoring Matrix (PSSM) composition and achieved an overall accuracy 92.06%. The five-fold cross validation was used to optimize SVM parameter and select the best model. The prediction algorithm presented here is implemented as a freely available web server MATEPred, which will assist in rapid identification of MATE proteins.

Filling-in void and sparse regions in protein sequence space by protein-like artificial sequences enables remarkable enhancement in remote homology detection capability

Protein functional annotation relies on the identification of accurate relationships, sequence divergence being a key factor. This is especially evident when distant protein relationships are demonstrated only with three-dimensional structures. To address this challenge, we describe a computational approach to purposefully bridge gaps between related protein families through directed design of protein-like "linker" sequences. For this, we represented SCOP domain families, integrated with sequence homologues, as multiple profiles and performed HMM-HMM alignments between related domain families. Where convincing alignments were achieved, we applied a roulette wheel-based method to design 3,611,010 protein-like sequences corresponding to 374 SCOP folds. To analyze their ability to link proteins in homology searches, we used 3024 queries to search two databases, one containing only natural sequences and another one additionally containing designed sequences. Our results showed that augmented database searches showed up to 30% improvement in fold coverage for over 74% of the folds, with 52 folds achieving all theoretically possible connections. Although sequences could not be designed between some families, the availability of designed sequences between other families within the fold established the sequence continuum to demonstrate 373 difficult relationships. Ultimately, as a practical and realistic extension, we demonstrate that such protein-like sequences can be "plugged-into" routine and generic sequence database searches to empower not only remote homology detection but also fold recognition. Our richly statistically supported findings show that complementary searches in both databases will increase the effectiveness of sequence-based searches in recognizing all homologues sharing a common fold.

An SVM method using evolutionary information for the identification of allergenic proteins

This study presents an allergenic protein prediction system that appears to be capable of producing high sensitivity and specificity. The proposed system is based on support vector machine (SVM) using evolutionary information in the form of an amino acid position specific scoring matrix (PSSM). The performance of this system is assessed by a 10-fold cross-validation experiment using a dataset consisting of 693 allergens and 1041 non-allergens obtained from Swiss-Prot and Structural Database of Allergenic Proteins (SDAP). The PSSM method produced an accuracy of 90.1% in comparison to the methods based on SVM using amino acid, dipeptide composition, pseudo (5-tier) amino acid composition that achieved an accuracy of 86.3, 86.5 and 82.1% respectively. The results show that evolutionary information can be useful to build more effective and efficient allergen prediction systems.

Prediction of enzymes and non-enzymes from protein sequences based on sequence derived features and PSSM matrix using artificial neural network

The problem of predicting the enzymes and non-enzymes from the protein sequence information is still an open problem in bioinformatics. It is further becoming more important as the number of sequenced information grows exponentially over time. We describe a novel approach for predicting the enzymes and non-enzymes from its amino-acid sequence using artificial neural network (ANN). Using 61 sequence derived features alone we have been able to achieve 79 percent correct prediction of enzymes/non-enzymes (in the set of 660 proteins). For the complete set of 61 parameters using 5-fold cross-validated classification, ANN model reveal a superior model (accuracy = 78.79 plus or minus 6.86 percent, Q(pred) = 74.734 plus or minus 17.08 percent, sensitivity = 84.48 plus or minus 6.73 percent, specificity = 77.13 plus or minus 13.39 percent). The second module of ANN is based on PSSM matrix. Using the same 5-fold cross-validation set, this ANN model predicts enzymes/non-enzymes with more accuracy (accuracy = 80.37 plus or minus 6.59 percent, Q(pred) = 67.466 plus or minus 12.41 percent, sensitivity = 0.9070 plus or minus 3.37 percent, specificity = 74.66 plus or minus 7.17 percent).