Identifying antimicrobial peptides using word embedding with deep recurrent neural networks

ActTRANS: Functional classification in active transport proteins based on transfer learning and contextual representations

MOTIVATION

Primary and secondary active transport are two types of active transport that involve using energy to move the substances. Active transport mechanisms do use proteins to assist in transport and play essential roles to regulate the traffic of ions or small molecules across a cell membrane against the concentration gradient. In this study, the two main types of proteins involved in such transport are classified from transmembrane transport proteins. We propose a Support Vector Machine (SVM) with contextualized word embeddings from Bidirectional Encoder Representations from Transformers (BERT) to represent protein sequences. BERT is a powerful model in transfer learning, a deep learning language representation model developed by Google and one of the highest performing pre-trained model for Natural Language Processing (NLP) tasks. The idea of transfer learning with pre-trained model from BERT is applied to extract fixed feature vectors from the hidden layers and learn contextual relations between amino acids in the protein sequence. Therefore, the contextualized word representations of proteins are introduced to effectively model complex structures of amino acids in the sequence and the variations of these amino acids in the context. By generating context information, we capture multiple meanings for the same amino acid to reveal the importance of specific residues in the protein sequence.

RESULTS

The performance of the proposed method is evaluated using five-fold cross-validation and independent test. The proposed method achieves an accuracy of 85.44 %, 88.74 % and 92.84 % for Class-1, Class-2, and Class-3, respectively. Experimental results show that this approach can outperform from other feature extraction methods using context information, effectively classify two types of active transport and improve the overall performance.

Clustering FunFams using sequence embeddings improves EC purity

Motivation

Classifying proteins into functional families can improve our understanding of protein function and can allow transferring annotations within one family. For this, functional families need to be ‘pure’, i.e., contain only proteins with identical function. Functional Families (FunFams) cluster proteins within CATH superfamilies into such groups of proteins sharing function. 11% of all FunFams (22 830 of 203 639) contain EC annotations and of those, 7% (1526 of 22 830) have inconsistent functional annotations.

Results

We propose an approach to further cluster FunFams into functionally more consistent sub-families by encoding their sequences through embeddings. These embeddings originate from language models transferring knowledge gained from predicting missing amino acids in a sequence (ProtBERT) and have been further optimized to distinguish between proteins belonging to the same or a different CATH superfamily (PB-Tucker). Using distances between embeddings and DBSCAN to cluster FunFams and identify outliers, doubled the number of pure clusters per FunFam compared to random clustering. Our approach was not limited to FunFams but also succeeded on families created using sequence similarity alone. Complementing EC annotations, we observed similar results for binding annotations. Thus, we expect an increased purity also for other aspects of function. Our results can help generating FunFams; the resulting clusters with improved functional consistency allow more reliable inference of annotations. We expect this approach to succeed equally for any other grouping of proteins by their phenotypes.

Availability and implementation

Code and embeddings are available via GitHub: https://github.com/Rostlab/FunFamsClustering.

Supplementary information

Supplementary data are available at Bioinformatics online.

Deep-ABPpred: identifying antibacterial peptides in protein sequences using bidirectional LSTM with word2vec

The overuse of antibiotics has led to emergence of antimicrobial resistance, and as a result, antibacterial peptides (ABPs) are receiving significant attention as an alternative. Identification of effective ABPs in lab from natural sources is a cost-intensive and time-consuming process. Therefore, there is a need for the development of in silico models, which can identify novel ABPs in protein sequences for chemical synthesis and testing. In this study, we propose a deep learning classifier named Deep-ABPpred that can identify ABPs in protein sequences. We developed Deep-ABPpred using bidirectional long short-term memory algorithm with amino acid level features from word2vec. The results show that Deep-ABPpred outperforms other state-of-the-art ABP classifiers on both test and independent datasets. Our proposed model achieved the precision of approximately 97 and 94% on test dataset and independent dataset, respectively. The high precision suggests applicability of Deep-ABPpred in proposing novel ABPs for synthesis and experimentation. By utilizing Deep-ABPpred, we identified ABPs in the tail protein sequences of Streptococcus bacteriophages, chemically synthesized identified peptides in lab and tested their activity in vitro. These ABPs showed potent antibacterial activity against selected Gram-positive and Gram-negative bacteria, which confirms the capability of Deep-ABPpred in identifying novel ABPs in protein sequences. Based on the proposed approach, an online prediction server is also developed, which is freely accessible at https://abppred.anvil.app/. This web server takes the protein sequence as input and provides ABPs with high probability (>0.95) as output.

Identifying DNA N4-methylcytosine sites in the rosaceae genome with a deep learning model relying on distributed feature representation

DNA N4-methylcytosine (4mC), an epigenetic modification found in prokaryotic and eukaryotic species, is involved in numerous biological functions, including host defense, transcription regulation, gene expression, and DNA replication. To identify 4mC sites, previous computational studies mostly focused on finding hand-crafted features. This area of research, therefore, would benefit from the development of a computational approach that relies on automatic feature selection to identify relevant sites. We here report 4mC-w2vec, a computational method that learned automatic feature discrimination in the Rosaceae genomes, especially in Rosa chinensis (R. chinensis) and Fragaria vesca (F. vesca), based on distributed feature representation and through the word embedding technique ‘word2vec’. While a few bioinformatics tools are currently employed to identify 4mC sites in these genomes, their prediction performance is inadequate. Our system processed 4mC and non-4mC sites through a word embedding process, including sub-word information of its biological words through k-mer, which then served as features that were fed into a double layer of convolutional neural network (CNN) to classify whether the sample sequences contained 4mCs or non-4mCs sites. Our tool demonstrated performance superior to current tools that use the same genomic datasets. Additionally, 4mC-w2vec is effective for balanced and imbalanced class datasets alike, and the online web-server is currently available at: http://nsclbio.jbnu.ac.kr/tools/4mC-w2vec/.

Incorporating Machine Learning into Established Bioinformatics Frameworks

The exponential growth of biomedical data in recent years has urged the application of numerous machine learning techniques to address emerging problems in biology and clinical research. By enabling the automatic feature extraction, selection, and generation of predictive models, these methods can be used to efficiently study complex biological systems. Machine learning techniques are frequently integrated with bioinformatic methods, as well as curated databases and biological networks, to enhance training and validation, identify the best interpretable features, and enable feature and model investigation. Here, we review recently developed methods that incorporate machine learning within the same framework with techniques from molecular evolution, protein structure analysis, systems biology, and disease genomics. We outline the challenges posed for machine learning, and, in particular, deep learning in biomedicine, and suggest unique opportunities for machine learning techniques integrated with established bioinformatics approaches to overcome some of these challenges.

BERT4Bitter: a bidirectional encoder representations from transformers (BERT)-based model for improving the prediction of bitter peptides

MOTIVATION

The identification of bitter peptides through experimental approaches is an expensive and time-consuming endeavor. Due to the huge number of newly available peptide sequences in the post-genomic era, the development of automated computational models for the identification of novel bitter peptides is highly desira-ble.

RESULTS

In this work, we present BERT4Bitter, a bidirectional encoder representation from transformers (BERT)-based model for predicting bitter peptides directly from their amino acid sequence without using any structural information. To the best of our knowledge, this is the first time a BERT-based model has been employed to identify bitter peptides. Compared to widely used machine learning models, BERT4Bitter achieved the best performance with accuracy of 0.861 and 0.922 for cross-validation and independent tests, respectively. Furthermore, extensive empirical benchmarking experiments on the independent dataset demonstrated that BERT4Bitter clearly outperformed the existing method with improvements of > 8% accuracy and >16% Matthews coefficient correlation, highlighting the effectiveness and robustness of BERT4Bitter. We believe that the BERT4Bitter method proposed herein will be a useful tool for rapidly screening and identifying novel bitter peptides for drug development and nutritional research.

AVAILABILITY

The user-friendly web server of the proposed BERT4Bitter is freely accessible at: http://pmlab.pythonanywhere.com/BERT4Bitter.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

GT-Finder: Classify the family of glucose transporters with pre-trained BERT language models

Recently, language representation models have drawn a lot of attention in the field of natural language processing (NLP) due to their remarkable results. Among them, BERT (Bidirectional Encoder Representations from Transformers) has proven to be a simple, yet powerful language model that has achieved novel state-of-the-art performance. BERT adopted the concept of contextualized word embeddings to capture the semantics and context in which words appear. We utilized pre-trained BERT models to extract features from protein sequences for discriminating three families of glucose transporters: the major facilitator superfamily of glucose transporters (GLUTs), the sodium-glucose linked transporters (SGLTs), and the sugars will eventually be exported transporters (SWEETs). We treated protein sequences as sentences and transformed them into fixed-length meaningful vectors where a 768- or 1024-dimensional vector represents each amino acid. We observed that BERT-Base and BERT-Large models improved the performance by more than 4% in terms of average sensitivity and Matthews correlation coefficient (MCC), indicating the efficiency of this approach. We also developed a bidirectional transformer-based protein model (TransportersBERT) for comparison with existing pre-trained BERT models.

DNA sequences performs as natural language processing by exploiting deep learning algorithm for the identification of N4-methylcytosine

N4-methylcytosine is a biochemical alteration of DNA that affects the genetic operations without modifying the DNA nucleotides such as gene expression, genomic imprinting, chromosome stability, and the development of the cell. In the proposed work, a computational model, 4mCNLP-Deep, used the word embedding approach as a vector formulation by exploiting deep learning based CNN algorithm to predict 4mC and non-4mC sites on the C.elegans genome dataset. Diversity of ranges employed for the experimental such as corpus k-mer and k-fold cross-validation to obtain the prevailing capabilities. The 4mCNLP-Deep outperform from the state-of-the-art predictor by achieving the results in five evaluation metrics by following; Accuracy (ACC) as 0.9354, Mathew’s correlation coefficient (MCC) as 0.8608, Specificity (Sp) as 0.89.96, Sensitivity (Sn) as 0.9563, and Area under curve (AUC) as 0.9731 by using 3-mer corpus word2vec and 3-fold cross-validation and attained the increment of 1.1%, 0.6%, 0.58%, 0.77%, and 4.89%, respectively. At last, we developed the online webserver http://nsclbio.jbnu.ac.kr/tools/4mCNLP-Deep/, for the experimental researchers to get the results easily.

Incorporating a transfer learning technique with amino acid embeddings to efficiently predict N-linked glycosylation sites in ion channels

Glycosylation is a dynamic enzymatic process that attaches glycan to proteins or other organic molecules such as lipoproteins. Research has shown that such a process in ion channel proteins plays a fundamental role in modulating ion channel functions. This study used a computational method to predict N-linked glycosylation sites, the most common type, in ion channel proteins. From segments of ion channel proteins centered around N-linked glycosylation sites, the amino acid embedding vectors of each residue were concatenated to create features for prediction. We experimented with two different models for converting amino acids to their corresponding embeddings: one was fed with ion channel sequences and the other with a large dataset composed of more than one million protein sequences. The latter model stemmed from the idea of transfer learning technique and emerged as a more efficient feature extractor. Our best model was obtained from this transfer learning approach and a hyperparameter tuning process with a random search on 5-fold cross-validation data. It achieved an accuracy, specificity, sensitivity, and Matthews correlation coefficient of 93.4%, 92.8%, 98.6%, and 0.726, respectively. Corresponding scores on an independent test were 92.9%, 92.2%, 99%, and 0.717. These results outperform the position-specific scoring matrix features that are predominantly employed in post-translational modification site predictions. Furthermore, compared to N-GlyDE, GlycoEP, SPRINT-Gly, the most recent N-linked glycosylation site predictors, our model yields higher scores on the above 4 metrics, thus further demonstrating the efficiency of our approach.

Learning transferable deep convolutional neural networks for the classification of bacterial virulence factors

MOTIVATION

Identification of virulence factors (VFs) is critical to the elucidation of bacterial pathogenesis and prevention of related infectious diseases. Current computational methods for VF prediction focus on binary classification or involve only several class(es) of VFs with sufficient samples. However, thousands of VF classes are present in real-world scenarios, and many of them only have a very limited number of samples available.

RESULTS

We first construct a large VF dataset, covering 3446 VF classes with 160 495 sequences, and then propose deep convolutional neural network models for VF classification. We show that (i) for common VF classes with sufficient samples, our models can achieve state-of-the-art performance with an overall accuracy of 0.9831 and an F1-score of 0.9803; (ii) for uncommon VF classes with limited samples, our models can learn transferable features from auxiliary data and achieve good performance with accuracy ranging from 0.9277 to 0.9512 and F1-score ranging from 0.9168 to 0.9446 when combined with different predefined features, outperforming traditional classifiers by 1-13% in accuracy and by 1-16% in F1-score.

AVAILABILITY AND IMPLEMENTATION

All of our datasets are made publicly available at http://www.mgc.ac.cn/VFNet/, and the source code of our models is publicly available at https://github.com/zhengdd0422/VFNet.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Design, Screening, and Testing of Non-Rational Peptide Libraries with Antimicrobial Activity: In Silico and Experimental Approaches

One of the challenges of modern biotechnology is to find new routes to mitigate the resistance to conventional antibiotics. Antimicrobial peptides (AMPs) are an alternative type of biomolecules, naturally present in a wide variety of organisms, with the capacity to overcome the current microorganism resistance threat. Here, we reviewed our recent efforts to develop a new library of non-rationally produced AMPs that relies on bacterial genome inherent diversity and compared it with rationally designed libraries. Our approach is based on a four-stage workflow process that incorporates the interplay of recent developments in four major emerging technologies: artificial intelligence, molecular dynamics, surface-display in microorganisms, and microfluidics. Implementing this framework is challenging because to obtain reliable results, the in silico algorithms to search for candidate AMPs need to overcome issues of the state-of-the-art approaches that limit the possibilities for multi-space data distribution analyses in extremely large databases. We expect to tackle this challenge by using a recently developed classification algorithm based on deep learning models that rely on convolutional layers and gated recurrent units. This will be complemented by carefully tailored molecular dynamics simulations to elucidate specific interactions with lipid bilayers. Candidate AMPs will be recombinantly-expressed on the surface of microorganisms for further screening via different droplet-based microfluidic-based strategies to identify AMPs with the desired lytic abilities. We believe that the proposed approach opens opportunities for searching and screening bioactive peptides for other applications.

Antimicrobial Peptides: Classification, Design, Application and Research Progress in Multiple Fields

Antimicrobial peptides (AMPs) are a class of small peptides that widely exist in nature and they are an important part of the innate immune system of different organisms. AMPs have a wide range of inhibitory effects against bacteria, fungi, parasites and viruses. The emergence of antibiotic-resistant microorganisms and the increasing of concerns about the use of antibiotics resulted in the development of AMPs, which have a good application prospect in medicine, food, animal husbandry, agriculture and aquaculture. This review introduces the progress of research on AMPs comprehensively and systematically, including their classification, mechanism of action, design methods, environmental factors affecting their activity, application status, prospects in various fields and problems to be solved. The research progress on antivirus peptides, especially anti-coronavirus (COVID-19) peptides, has been introduced given the COVID-19 pandemic worldwide in 2020.

Incorporating Deep Learning With Word Embedding to Identify Plant Ubiquitylation Sites

Protein ubiquitylation is an important posttranslational modification (PTM), which is involved in diverse biological processes and plays an essential role in the regulation of physiological mechanisms and diseases. The Protein Lysine Modifications Database (PLMD) has accumulated abundant ubiquitylated proteins with their substrate sites for more than 20 kinds of species. Numerous works have consequently developed a variety of ubiquitylation site prediction tools across all species, mainly relying on the predefined sequence features and machine learning algorithms. However, the difference in ubiquitylated patterns between these species stays unclear. In this work, the sequence-based characterization of ubiquitylated substrate sites has revealed remarkable differences among plants, animals, and fungi. Then an improved word-embedding scheme based on the transfer learning strategy was incorporated with the multilayer convolutional neural network (CNN) for identifying protein ubiquitylation sites. For the prediction of plant ubiquitylation sites, the proposed deep learning scheme could outperform the machine learning-based methods, with the accuracy of 75.6%, precision of 73.3%, recall of 76.7%, F-score of 0.7493, and 0.82 AUC on the independent testing set. Although the ubiquitylated specificity of substrate sites is complicated, this work has demonstrated that the application of the word-embedding method can enable the extraction of informative features and help the identification of ubiquitylated sites. To accelerate the investigation of protein ubiquitylation, the data sets and source code used in this study are freely available at https://github.com/wang-hong-fei/DL-plant-ubsites-prediction.

A Pilot Study of Multi-Input Recurrent Neural Networks for Drug-Kinase Binding Prediction

The use of virtual drug screening can be beneficial to research teams, enabling them to narrow down potentially useful compounds for further study. A variety of virtual screening methods have been developed, typically with machine learning classifiers at the center of their design. In the present study, we created a virtual screener for protein kinase inhibitors. Experimental compound-target interaction data were obtained from the IDG-DREAM Drug-Kinase Binding Prediction Challenge. These data were converted and fed as inputs into two multi-input recurrent neural networks (RNNs). The first network utilized data encoded in one-hot representation, while the other incorporated embedding layers. The models were developed in Python, and were designed to output the IC50 of the target compounds. The performance of the models was assessed primarily through analysis of the Q2 values produced from runs of differing sample and epoch size; recorded loss values were also reported and graphed. The performance of the models was limited, though multiple changes are proposed for potential improvement of a multi-input recurrent neural network-based screening tool.

A Survey of Network Embedding for Drug Analysis and Prediction

Traditional network-based computational methods have shown good results in drug analysis and prediction. However, these methods are time consuming and lack universality, and it is difficult to exploit the auxiliary information of nodes and edges. Network embedding provides a promising way for alleviating the above problems by transforming network into a low-dimensional space while preserving network structure and auxiliary information. This thus facilitates the application of machine learning algorithms for subsequent processing. Network embedding has been introduced into drug analysis and prediction in the last few years, and has shown superior performance over traditional methods. However, there is no systematic review of this issue. This article offers a comprehensive survey of the primary network embedding methods and their applications in drug analysis and prediction. The network embedding technologies applied in homogeneous network and heterogeneous network are investigated and compared, including matrix decomposition, random walk, and deep learning. Especially, the Graph neural network (GNN) methods in deep learning are highlighted. Further, the applications of network embedding in drug similarity estimation, drug-target interaction prediction, adverse drug reactions prediction, protein function and therapeutic peptides prediction are discussed. Several future potential research directions are also discussed.

DeepVF: a deep learning-based hybrid framework for identifying virulence factors using the stacking strategy

Virulence factors (VFs) enable pathogens to infect their hosts. A wealth of individual, disease-focused studies has identified a wide variety of VFs, and the growing mass of bacterial genome sequence data provides an opportunity for computational methods aimed at predicting VFs. Despite their attractive advantages and performance improvements, the existing methods have some limitations and drawbacks. Firstly, as the characteristics and mechanisms of VFs are continually evolving with the emergence of antibiotic resistance, it is more and more difficult to identify novel VFs using existing tools that were previously developed based on the outdated data sets; secondly, few systematic feature engineering efforts have been made to examine the utility of different types of features for model performances, as the majority of tools only focused on extracting very few types of features. By addressing the aforementioned issues, the accuracy of VF predictors can likely be significantly improved. This, in turn, would be particularly useful in the context of genome wide predictions of VFs. In this work, we present a deep learning (DL)-based hybrid framework (termed DeepVF) that is utilizing the stacking strategy to achieve more accurate identification of VFs. Using an enlarged, up-to-date dataset, DeepVF comprehensively explores a wide range of heterogeneous features with popular machine learning algorithms. Specifically, four classical algorithms, including random forest, support vector machines, extreme gradient boosting and multilayer perceptron, and three DL algorithms, including convolutional neural networks, long short-term memory networks and deep neural networks are employed to train 62 baseline models using these features. In order to integrate their individual strengths, DeepVF effectively combines these baseline models to construct the final meta model using the stacking strategy. Extensive benchmarking experiments demonstrate the effectiveness of DeepVF: it achieves a more accurate and stable performance compared with baseline models on the benchmark dataset and clearly outperforms state-of-the-art VF predictors on the independent test. Using the proposed hybrid ensemble model, a user-friendly online predictor of DeepVF (http://deepvf.erc.monash.edu/) is implemented. Furthermore, its utility, from the user's viewpoint, is compared with that of existing toolkits. We believe that DeepVF will be exploited as a useful tool for screening and identifying potential VFs from protein-coding gene sequences in bacterial genomes.

SG-LSTM-FRAME: a computational frame using sequence and geometrical information via LSTM to predict miRNA-gene associations

MOTIVATION

MircroRNAs (miRNAs) regulate target genes and are responsible for lethal diseases such as cancers. Accurately recognizing and identifying miRNA and gene pairs could be helpful in deciphering the mechanism by which miRNA affects and regulates the development of cancers. Embedding methods and deep learning methods have shown their excellent performance in traditional classification tasks in many scenarios. But not so many attempts have adapted and merged these two methods into miRNA-gene relationship prediction. Hence, we proposed a novel computational framework. We first generated representational features for miRNAs and genes using both sequence and geometrical information and then leveraged a deep learning method for the associations' prediction.

RESULTS

We used long short-term memory (LSTM) to predict potential relationships and proved that our method outperformed other state-of-the-art methods. Results showed that our framework SG-LSTM got an area under curve of 0.94 and was superior to other methods. In the case study, we predicted the top 10 miRNA-gene relationships and recommended the top 10 potential genes for hsa-miR-335-5p for SG-LSTM-core. We also tested our model using a larger dataset, from which 14 668 698 miRNA-gene pairs were predicted. The top 10 unknown pairs were also listed.

AVAILABILITY

Our work can be download in https://github.com/Xshelton/SG_LSTM.

CONTACT

luojiawei@hnu.edu.cn.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Briefings in Bioinformatics online.

Bidirectional Molecule Generation with Recurrent Neural Networks

Recurrent neural networks (RNNs) are able to generate de novo molecular designs using simplified molecular input line entry systems (SMILES) string representations of the chemical structure. RNN-based structure generation is usually performed unidirectionally, by growing SMILES strings from left to right. However, there is no natural start or end of a small molecule, and SMILES strings are intrinsically nonunivocal representations of molecular graphs. These properties motivate bidirectional structure generation. Here, bidirectional generative RNNs for SMILES-based molecule design are introduced. To this end, two established bidirectional methods were implemented, and a new method for SMILES string generation and data augmentation is introduced-the bidirectional molecule design by alternate learning (BIMODAL). These three bidirectional strategies were compared to the unidirectional forward RNN approach for SMILES string generation, in terms of the (i) novelty, (ii) scaffold diversity, and (iii) chemical-biological relevance of the computer-generated molecules. The results positively advocate bidirectional strategies for SMILES-based molecular de novo design, with BIMODAL showing superior results to the unidirectional forward RNN for most of the criteria in the tested conditions. The code of the methods and the pretrained models can be found at URL https://github.com/ETHmodlab/BIMODAL.

Classifying Promoters by Interpreting the Hidden Information of DNA Sequences via Deep Learning and Combination of Continuous FastText N-Grams

A promoter is a short region of DNA (100-1,000 bp) where transcription of a gene by RNA polymerase begins. It is typically located directly upstream or at the 5' end of the transcription initiation site. DNA promoter has been proven to be the primary cause of many human diseases, especially diabetes, cancer, or Huntington's disease. Therefore, classifying promoters has become an interesting problem and it has attracted the attention of a lot of researchers in the bioinformatics field. There were a variety of studies conducted to resolve this problem, however, their performance results still require further improvement. In this study, we will present an innovative approach by interpreting DNA sequences as a combination of continuous FastText N-grams, which are then fed into a deep neural network in order to classify them. Our approach is able to attain a cross-validation accuracy of 85.41 and 73.1% in the two layers, respectively. Our results outperformed the state-of-the-art methods on the same dataset, especially in the second layer (strength classification). Throughout this study, promoter regions could be identified with high accuracy and it provides analysis for further biological research as well as precision medicine. In addition, this study opens new paths for the natural language processing application in omics data in general and DNA sequences in particular.

Probabilistic variable-length segmentation of protein sequences for discriminative motif discovery (DiMotif) and sequence embedding (ProtVecX)

In this paper, we present peptide-pair encoding (PPE), a general-purpose probabilistic segmentation of protein sequences into commonly occurring variable-length sub-sequences. The idea of PPE segmentation is inspired by the byte-pair encoding (BPE) text compression algorithm, which has recently gained popularity in subword neural machine translation. We modify this algorithm by adding a sampling framework allowing for multiple ways of segmenting a sequence. PPE segmentation steps can be learned over a large set of protein sequences (Swiss-Prot) or even a domain-specific dataset and then applied to a set of unseen sequences. This representation can be widely used as the input to any downstream machine learning tasks in protein bioinformatics. In particular, here, we introduce this representation through protein motif discovery and protein sequence embedding. (i) DiMotif: we present DiMotif as an alignment-free discriminative motif discovery method and evaluate the method for finding protein motifs in three different settings: (1) comparison of DiMotif with two existing approaches on 20 distinct motif discovery problems which are experimentally verified, (2) classification-based approach for the motifs extracted for integrins, integrin-binding proteins, and biofilm formation, and (3) in sequence pattern searching for nuclear localization signal. The DiMotif, in general, obtained high recall scores, while having a comparable F1 score with other methods in the discovery of experimentally verified motifs. Having high recall suggests that the DiMotif can be used for short-list creation for further experimental investigations on motifs. In the classification-based evaluation, the extracted motifs could reliably detect the integrins, integrin-binding, and biofilm formation-related proteins on a reserved set of sequences with high F1 scores. (ii) ProtVecX: we extend k-mer based protein vector (ProtVec) embedding to variablelength protein embedding using PPE sub-sequences. We show that the new method of embedding can marginally outperform ProtVec in enzyme prediction as well as toxin prediction tasks. In addition, we conclude that the embeddings are beneficial in protein classification tasks when they are combined with raw amino acids k-mer features.

iEnhancer-5Step: Identifying enhancers using hidden information of DNA sequences via Chou's 5-step rule and word embedding

An enhancer is a short (50-1500bp) region of DNA that plays an important role in gene expression and the production of RNA and proteins. Genetic variation in enhancers has been linked to many human diseases, such as cancer, disorder or inflammatory bowel disease. Due to the importance of enhancers in genomics, the classification of enhancers has become a popular area of research in computational biology. Despite the few computational tools employed to address this problem, their resulting performance still requires improvements. In this study, we treat enhancers by the word embeddings, including sub-word information of its biological words, which then serve as features to be fed into a support vector machine algorithm to classify them. We present iEnhancer-5Step, a web server containing two-layer classifiers to identify enhancers and their strength. We are able to attain an independent test accuracy of 79% and 63.5% in the two layers, respectively. Compared to current predictors on the same dataset, our proposed method is able to yield superior performance as compared to the other methods. Moreover, this study provides a basis for further research that can enrich the field of applying natural language processing techniques in biological sequences. iEnhancer-5Step is freely accessible via http://biologydeep.com/fastenc/.