A novel features ranking metric with application to scalable visual and bioinformatics data classification

Prediction of Hormone-Binding Proteins Based on K-mer Feature Representation and Naive Bayes

Hormone binding protein (HBP) is a soluble carrier protein that interacts selectively with different types of hormones and has various effects on the body's life activities. HBPs play an important role in the growth process of organisms, but their specific role is still unclear. Therefore, correctly identifying HBPs is the first step towards understanding and studying their biological function. However, due to their high cost and long experimental period, it is difficult for traditional biochemical experiments to correctly identify HBPs from an increasing number of proteins, so the real characterization of HBPs has become a challenging task for researchers. To measure the effectiveness of HBPs, an accurate and reliable prediction model for their identification is desirable. In this paper, we construct the prediction model HBP_NB. First, HBPs data were collected from the UniProt database, and a dataset was established. Then, based on the established high-quality dataset, the k-mer (K = 3) feature representation method was used to extract features. Second, the feature selection algorithm was used to reduce the dimensionality of the extracted features and select the appropriate optimal feature set. Finally, the selected features are input into Naive Bayes to construct the prediction model, and the model is evaluated by using 10-fold cross-validation. The final results were 95.45% accuracy, 94.17% sensitivity and 96.73% specificity. These results indicate that our model is feasible and effective.

Mul-SNO: A novel prediction tool for S-nitrosylation sites based on deep learning methods

Protein s-nitrosylation (SNO is one of the most important post-translational modifications and is formed by the covalent modification of nitric oxide and cysteine residues. Extensive studies have shown that SNO plays a pivotal role in the plant immune response and treating various major human diseases. In recent years, SNO sites have become a hot research topic. Traditional biochemical methods for SNO site identification are time-consuming and costly. In this study, we developed an economical and efficient SNO site prediction tool named Mul-SNO. Mul-SNO ensembled current popular and powerful deep learning model bidirectional long short-term memory (BiLSTM and bidirectional encoder representations from Transformers (BERT . Compared with existing state-of-the-art methods, Mul-SNO obtained better ACC of 0.911 and 0.796 based on 10-fold cross-validation and independent data sets, respectively. The prediction server can be obtained for free at http://lab.malab.cn/~mjq/Mul-SNO/.

DeepStack-DTIs: Predicting Drug-Target Interactions Using LightGBM Feature Selection and Deep-Stacked Ensemble Classifier

Accurate prediction of drug-target interactions (DTIs), which is often used in the fields of drug discovery and drug repositioning, is regarded a key challenge in the study of drug science. In this paper, a new method called DeepStack-DTIs is proposed to predict DTIs. First, for the target protein, pseudo-position specific score matrix, pseudo amino acid composition and SPIDER3 are used to extract the different feature information of the target protein. Meanwhile, the path-based fingerprint features of each drug are extracted. Then, the synthetic minority oversampling technique (SMOTE) and light gradient boosting machine (LightGBM) are used for data balancing and feature selection, respectively. Finally, the processed features are input to the deep-stacked ensemble classifier composed of gated recurrent unit (GRU), deep neural network (DNN), support vector machine (SVM), eXtreme gradient boosting (XGBoost) and logistic regression (LR) to predict DTIs. Under the five-fold cross-validation and compared with existing methods, the proposed method achieves higher prediction accuracy on the gold standard dataset. To evaluate the predictive power of DeepStack-DTIs, we validate the method on another dataset and predict the drug-target interaction network. The results indicate that DeepStack-DTIs has excellent predictive ability than the other methods, and provides novel insights for the prediction of DTIs. A novel method DeepStack-DTIs for drug-target interactions prediction. PsePSSM, PseAAC, SPIDER3 and FP2 are fused to convert protein sequence and drug molecule information into digital information, respectively. The SMOTE algorithm is used to balance the dataset and LightGBM feature selection algorithm is employed to remove redundant and irrelevant features to select the optimal feature subset. This optimal feature subset is inputted into the deep-stacked ensemble classifier to predict drug-target interactions. The experimental results show DeepStack-DTIs method can significantly improve the prediction accuracy of drug-target interactions.

iEnhancer-KL: A Novel Two-Layer Predictor for Identifying Enhancers by Position Specific of Nucleotide Composition

An enhancer is a short region of DNA with the ability to recruit transcription factors and their complexes, increasing the likelihood of the transcription of a particular gene. Considering the importance of enhancers, enhancer identification is a prevailing problem in computational biology. In this paper, we propose a novel two-layer enhancer predictor called iEnhancer-KL, using computational biology algorithms to identify enhancers and then classify these enhancers into strong or weak types. Kullback-Leibler (KL) divergence is creatively taken into consideration to improve the feature extraction method PSTNPss. Then, LASSO is used to reduce the dimension of features and finally helps to get better prediction performance. Furthermore, the selected features are tested on several machine learning models, and the SVM algorithm achieves the best performance. The rigorous cross-validation indicates that our predictor is remarkably superior to the existing state-of-the-art methods with an Acc of 84.23 percent and the MCC of 0.6849 for identifying enhancers. Our code and results can be freely downloaded from https://github.com/Not-so-middle/iEnhancer-KL.git.

iTTCA-RF: a random forest predictor for tumor T cell antigens

BACKGROUND

Cancer is one of the most serious diseases threatening human health. Cancer immunotherapy represents the most promising treatment strategy due to its high efficacy and selectivity and lower side effects compared with traditional treatment. The identification of tumor T cell antigens is one of the most important tasks for antitumor vaccines development and molecular function investigation. Although several machine learning predictors have been developed to identify tumor T cell antigen, more accurate tumor T cell antigen identification by existing methodology is still challenging.

METHODS

In this study, we used a non-redundant dataset of 592 tumor T cell antigens (positive samples) and 393 tumor T cell antigens (negative samples). Four types feature encoding methods have been studied to build an efficient predictor, including amino acid composition, global protein sequence descriptors and grouped amino acid and peptide composition. To improve the feature representation ability of the hybrid features, we further employed a two-step feature selection technique to search for the optimal feature subset. The final prediction model was constructed using random forest algorithm.

RESULTS

Finally, the top 263 informative features were selected to train the random forest classifier for detecting tumor T cell antigen peptides. iTTCA-RF provides satisfactory performance, with balanced accuracy, specificity and sensitivity values of 83.71%, 78.73% and 88.69% over tenfold cross-validation as well as 73.14%, 62.67% and 83.61% over independent tests, respectively. The online prediction server was freely accessible at http://lab.malab.cn/~acy/iTTCA .

CONCLUSIONS

We have proven that the proposed predictor iTTCA-RF is superior to the other latest models, and will hopefully become an effective and useful tool for identifying tumor T cell antigens presented in the context of major histocompatibility complex class I.

The Development of Machine Learning Methods in discriminating Secretory Proteins of Malaria Parasite

Malaria caused by Plasmodium falciparum is one of the major infectious diseases in the world. It is essential to exploit an effective method to predict secretory proteins of malaria parasites to develop effective cures and treatment. Biochemical assays can provide details for accurate identification of the secretory proteins, but these methods are expensive and time-consuming. In this paper, we summarized the machine learning-based identification algorithms and compared the construction strategies between different computational methods. Also, we discussed the use of machine learning to improve the ability of algorithms to identify proteins secreted by malaria parasites.

prPred-DRLF: Plant R protein predictor using deep representation learning features

Plant resistance (R) proteins play a significant role in the detection of pathogen invasion. Accurately predicting plant R proteins is a key task in phytopathology. Most plant R protein predictors are dependent on traditional feature extraction methods. Recently, deep representation learning methods have been successfully applied in solving protein classification problems. Motivated by this, we propose a new computational approach, called prPred-DRLF, which uses deep representation learning feature models to encode the amino acids as numerical vectors. The results show that the fused features of bidirectional long short-term memory (BiLSTM) embedding and unified representation (UniRep) embedding have a better performance than other features for plant R protein identification using a light gradient boosting machine (LGBM) classifier. The model was evaluated using an independent test achieving an accuracy of 0.956, F1-score of 0.933, and area under the receiver operating characteristic (ROC) curve (AUC) of 0.997. Meanwhile, compared with the state-of-the-art prPred and HMMER method, prPred-DRLF shows an overall improvement in accuracy, F1-score, AUC, and recall. prPred-DRLF is a higher-performance plant R protein prediction tool based on two kinds of deep representation learning technologies and offers a user-friendly interface for inspecting possible plant R proteins. We hope that prPred-DRLF will become a useful tool for biological research. A user-friendly webserver for prPred-DRLF is freely accessible at http://lab.malab.cn/soft/prPred-DRLF. The Python script can be downloaded from https://github.com/Wangys-prog/prPred-DRLF.

Automated detection of bioimages using novel deep feature fusion algorithm and effective high-dimensional feature selection approach

The classification of bioimages plays an important role in several biological studies, such as subcellular localisation, phenotype identification and other types of histopathological examinations. The objective of the present study was to develop a computer-aided bioimage classification method for the classification of bioimages across nine diverse benchmark datasets. A novel algorithm was developed, which systematically fused the features extracted from nine different convolution neural network architectures. A systematic fusion of features boosts the performance of a classifier but at the cost of the high dimensionality of the fused feature set. Therefore, non-discriminatory and redundant features need to be removed from a high-dimensional fused feature set to improve the classification performance and reduce the time complexity. To achieve this aim, a method based on analysis of variance and evolutionary feature selection was developed to select an optimal set of discriminatory features from the fused feature set. The proposed method was evaluated on nine different benchmark datasets. The experimental results showed that the proposed method achieved superior performance, with a significant reduction in the dimensionality of the fused feature set for most bioimage datasets. The performance of the proposed feature selection method was better than that of some of the most recent and classical methods used for feature selection. Thus, the proposed method was desirable because of its superior performance and high compression ratio, which significantly reduced the computational complexity.

EMCBOW-GPCR: A method for identifying G-protein coupled receptors based on word embedding and wordbooks

•

An computational method was developed to identify G-protein coupled receptors.

•

Three word-embedding models and a bag-of-words model are used to extract original features.

•

A high accuracy was achieved by using fusion information.

•

A powerful tool was established.

G Protein-Coupled Receptors (GPCRs) are one of the largest membrane protein receptor family in human, which are also important targets for many drugs. Thence, it’s of great significance to judge whether a protein is a GPCR or not. However, identifying GPCRs by experimental methods is very expensive and time-consuming. As more and more GPCR primary sequences are accumulated, it’s feasible to develop a computational model to predict GPCRs precisely and quickly. In this paper, a novel method called EMCBOW-GPCR has been proposed to improve the accuracy of identifying GPCRs based on natural language processing (NLP). For representing GPCRs, three word-embedding models and a bag-of-words model are used to extract original features. Then, the original features are thrown into a Deep-learning algorithm to extract features further and reduce the dimension. Finally, the obtained features are fed into Extreme Gradient Boosting. As shown with the results comparison, the overall prediction metrics of EMCBOW-GPCR are higher than the state of the arts. In order to be convenient for more researchers to use EMCBOW-GPCR, the method and source code have been opened in github, which are available at https://github.com/454170054/EMCBOW-GPCR, and a user-friendly web-server for EMCBOW-GPCR has been established at http://www.jci-bioinfo.cn/emcbowgpcr.

Empirical comparison and analysis of web-based cell-penetrating peptide prediction tools

Cell-penetrating peptides (CPPs) facilitate the delivery of therapeutically relevant molecules, including DNA, proteins and oligonucleotides, into cells both in vitro and in vivo. This unique ability explores the possibility of CPPs as therapeutic delivery and its potential applications in clinical therapy. Over the last few decades, a number of machine learning (ML)-based prediction tools have been developed, and some of them are freely available as web portals. However, the predictions produced by various tools are difficult to quantify and compare. In particular, there is no systematic comparison of the web-based prediction tools in performance, especially in practical applications. In this work, we provide a comprehensive review on the biological importance of CPPs, CPP database and existing ML-based methods for CPP prediction. To evaluate current prediction tools, we conducted a comparative study and analyzed a total of 12 models from 6 publicly available CPP prediction tools on 2 benchmark validation sets of CPPs and non-CPPs. Our benchmarking results demonstrated that a model from the KELM-CPPpred, namely KELM-hybrid-AAC, showed a significant improvement in overall performance, when compared to the other 11 prediction models. Moreover, through a length-dependency analysis, we find that existing prediction tools tend to more accurately predict CPPs and non-CPPs with the length of 20-25 residues long than peptides in other length ranges.

DNN-DTIs: Improved drug-target interactions prediction using XGBoost feature selection and deep neural network

Analysis and prediction of drug-target interactions (DTIs) play an important role in understanding drug mechanisms, as well as drug repositioning and design. Machine learning (ML)-based methods for DTIs prediction can mitigate the shortcomings of time-consuming and labor-intensive experimental approaches, while providing new ideas and insights for drug design. We propose a novel pipeline for predicting drug-target interactions, called DNN-DTIs. First, the target information is characterized by a number of features, namely, pseudo-amino acid composition, pseudo position-specific scoring matrix, conjoint triad composition, transition and distribution, Moreau-Broto autocorrelation, and structural features. The drug compounds are subsequently encoded using substructure fingerprints. Next, eXtreme gradient boosting (XGBoost) is used to determine the subset of non-redundant features of importance. The optimal balanced set of sample vectors is obtained by applying the synthetic minority oversampling technique (SMOTE). Finally, a DTIs predictor, DNN-DTIs, is developed based on a deep neural network (DNN) via a layer-by-layer learning scheme. Experimental results indicate that DNN-DTIs achieves better performance than other state-of-the-art predictors with ACC values of 98.78%, 98.60%, 97.98%, 98.24% and 98.00% on Enzyme, Ion Channels (IC), GPCR, Nuclear Receptors (NR) and Kuang's datasets. Therefore, the accurate prediction performance of DNN-DTIs makes it a favored choice for contributing to the study of DTIs, especially drug repositioning.

Identification of Disease-Related 2-Oxoglutarate/Fe (II)-Dependent Oxygenase Based on Reduced Amino Acid Cluster Strategy

The 2-oxoglutarate/Fe (II)-dependent (2OG) oxygenase superfamily is mainly responsible for protein modification, nucleic acid repair and/or modification, and fatty acid metabolism and plays important roles in cancer, cardiovascular disease, and other diseases. They are likely to become new targets for the treatment of cancer and other diseases, so the accurate identification of 2OG oxygenases is of great significance. Many computational methods have been proposed to predict functional proteins to compensate for the time-consuming and expensive experimental identification. However, machine learning has not been applied to the study of 2OG oxygenases. In this study, we developed OGFE_RAAC, a prediction model to identify whether a protein is a 2OG oxygenase. To improve the performance of OGFE_RAAC, 673 amino acid reduction alphabets were used to determine the optimal feature representation scheme by recoding the protein sequence. The 10-fold cross-validation test showed that the accuracy of the model in identifying 2OG oxygenases is 91.04%. Besides, the independent dataset results also proved that the model has excellent generalization and robustness. It is expected to become an effective tool for the identification of 2OG oxygenases. With further research, we have also found that the function of 2OG oxygenases may be related to their polarity and hydrophobicity, which will help the follow-up study on the catalytic mechanism of 2OG oxygenases and the way they interact with the substrate. Based on the model we built, a user-friendly web server was established and can be friendly accessed at http://bioinfor.imu.edu.cn/ogferaac.

Comparison and Analysis of Computational Methods for Identifying N6-Methyladenosine Sites in Saccharomyces cerevisiae

BACKGROUND

N⁶-methyladenosine (m⁶A) plays critical roles in a broad range of biological processes. Knowledge about the precise location of m⁶A site in the transcriptome is vital for deciphering its biological functions. Although experimental techniques have made substantial contributions to identify m⁶A, they are still labor intensive and time consuming. As complement to experimental methods, in the past few years, a series of computational approaches have been proposed to identify m⁶A sites.

METHODS

In order to facilitate researchers to select appropriate methods for identifying m⁶A sites, it is necessary to conduct a comprehensive review and comparison of existing methods.

RESULTS

Since research works on m⁶A in Saccharomyces cerevisiae are relatively clear, in this review, we summarized recent progress of computational prediction of m⁶A sites in S. cerevisiae and assessed the performance of existing computational methods. Finally, future directions of computationally identifying m⁶A sites are presented.

CONCLUSION

Taken together, we anticipate that this review will serve as an important guide for computational analysis of m⁶A modifications.

Application of Machine Learning for Drug-Target Interaction Prediction

Exploring drug–target interactions by biomedical experiments requires a lot of human, financial, and material resources. To save time and cost to meet the needs of the present generation, machine learning methods have been introduced into the prediction of drug–target interactions. The large amount of available drug and target data in existing databases, the evolving and innovative computer technologies, and the inherent characteristics of various types of machine learning have made machine learning techniques the mainstream method for drug–target interaction prediction research. In this review, details of the specific applications of machine learning in drug–target interaction prediction are summarized, the characteristics of each algorithm are analyzed, and the issues that need to be further addressed and explored for future research are discussed. The aim of this review is to provide a sound basis for the construction of high-performance models.

The accurate prediction and characterization of cancerlectin by a combined machine learning and GO analysis

Cancerlectins, lectins linked to tumor progression, have become the focus of cancer therapy research for their carbohydrate-binding specificity. However, the specific characterization for cancerlectins involved in tumor progression is still unclear. By taking advantage of the g-gap tripeptide and tetrapeptide composition feature descriptors, we increased the accuracy of the classification model of cancerlectin and lectin to 98.54% and 95.38%, respectively. About 36 cancerlectin and 135 lectin features were selected for functional characterization by P/N feature ranking method, which particularly selects the features in positive samples. The specific protein domains of cancerlectins are found to be p-GalNAc-T, crystal and annexin by comparing with lectins through the exclusion method. Moreover, the combined GO analysis showed that the conserved cation binding sites of cancerlectin specific domains are covered by selected feature peptides, suggesting that the capability of cation binding, critical for enzyme activity and stability, could be the key characteristic of cancerlectins in tumor progression. These results will help to identify potential cancerlectin and provide clues for mechanism study of cancerlectin in tumor progression.

A hybrid feature selection model based on improved squirrel search algorithm and rank aggregation using fuzzy techniques for biomedical data classification

Feature selection has gained its importance due to the voluminous nature of the data. Owing to the computational complexity of wrapper approaches, the poor performance of filtering techniques, and the classifier dependency of embedded approaches, hybrid approaches are more commonly used in feature selection. Hybrid approaches use filtering metrics to reduce the computational complexity of wrapper algorithms and are proved to yield better feature subset. Though filtering metrics select the features based on their significance, most of them are unstable and biased towards the metric used. Moreover, the choice of filtering metrics depends largely on the distribution of data and data types. Biomedical datasets contain features with different distribution and types adding to the complexity in the choice of filtering metric. We address this problem by proposing a stable filtering method based on rank aggregation in hybrid feature selection model with Improved Squirrel search algorithm for biomedical datasets. Our proposed model is compared with other well-known and state-of-the-art methods and the results prove that our model exhibited superior performance in terms of classification accuracy and computational time. The robustness of our proposed model is proved by conducting experiments on nine biomedical datasets and with three different classifiers.

Application of artificial intelligence for detection of chemico-biological interactions associated with oxidative stress and DNA damage

In recent years, various AI-based methods have been developed in order to uncover chemico-biological interactions associated with DNA damage and oxidative stress. Various decision trees, bayesian networks, random forests, logistic regression models, support vector machines as well as deep learning tools, have great potential in the area of molecular biology and toxicology, and it is estimated that in the future, they will greatly contribute to our understanding of molecular and cellular mechanisms associated with DNA damage and repair. In this concise review, we discuss recent attempts to build machine learning tools for assessment of radiation - induced DNA damage as well as algorithms that can analyze the data from the most frequently used DNA damage assays in molecular biology. We also review recent works on the detection of antioxidant proteins with machine learning, and the use of AI-related methods for prediction and evaluation of noncoding DNA sequences. Finally, we discuss previously published research on the potential application of machine learning tools in aging research.

ANOX: A robust computational model for predicting the antioxidant proteins based on multiple features

As an indispensable component of various living organisms, the antioxidant proteins have been studied for anti-aging and prevention of various diseases, such as altitude sickness, coronary heart disease, and even cancer. However, the traditional experimental methods for identifying the antioxidant proteins are very expensive and time-consuming. Thus, to address the challenge, a new predictor, named ANOX, was developed in this study. Multiple features, such as frequency matrix features (FRE), amino acid and dipeptide composition (AADP), evolutionary difference formula features (EEDP), k-separated bigrams (KSB), and PSI-PRED secondary structure (PRED), were extracted to generate the original feature space. To find the optimized feature subset, the Max-Relevance-Max-Distance (MRMD) algorithm was implemented for feature ranking and our model received the best performance with the top 1170 features. Rigorous tests were performed to evaluate the performance of ANOX, and the results showed that ANOX achieved a major improvement in the prediction accuracy of the antioxidant proteins (AUC:0.930 and 0.935 using 5-fold cross-validation or the jackknife test) compared to the state-of-the-art predictor AOPs-SVM (AUC:0.869 and 0.885). The dataset used in this study and the source code of ANOX are all available at https://github.com/NWAFU-LiuLab/ANOX.

A New Sequential Forward Feature Selection (SFFS) Algorithm for Mining Best Topological and Biological Features to Predict Protein Complexes from Protein-Protein Interaction Networks (PPINs)

Protein-protein interaction plays an important role in the understanding of biological processes in the body. A network of dynamic protein complexes within a cell that regulates most biological processes is known as a protein-protein interaction network (PPIN). Complex prediction from PPINs is a challenging task. Most of the previous computation approaches mine cliques, stars, linear and hybrid structures as complexes from PPINs by considering topological features and fewer of them focus on important biological information contained within protein amino acid sequence. In this study, we have computed a wide variety of topological features and integrate them with biological features computed from protein amino acid sequence such as bag of words, physicochemical and spectral domain features. We propose a new Sequential Forward Feature Selection (SFFS) algorithm, i.e., random forest-based Boruta feature selection for selecting the best features from computed large feature set. Decision tree, linear discriminant analysis and gradient boosting classifiers are used as learners. We have conducted experiments by considering two reference protein complex datasets of yeast, i.e., CYC2008 and MIPS. Human and mouse complex information is taken from CORUM 3.0 dataset. Protein interaction information is extracted from the database of interacting proteins (DIP). Our proposed SFFS, i.e., random forest-based Brouta feature selection in combination with decision trees, linear discriminant analysis and Gradient Boosting Classifiers outperforms other state of art algorithms by achieving precision, recall and F-measure rates, i.e. 94.58%, 94.92% and 94.45% for MIPS, 96.31%, 93.55% and 96.02% for CYC2008, 98.84%, 98.00%, 98.87 % for CORUM humans and 96.60%, 96.70%, 96.32% for CORUM mouse dataset complexes, respectively.

An Ensemble Learning-Based Method for Inferring Drug-Target Interactions Combining Protein Sequences and Drug Fingerprints

Identifying the interactions of the drug-target is central to the cognate areas including drug discovery and drug reposition. Although the high-throughput biotechnologies have made tremendous progress, the indispensable clinical trials remain to be expensive, laborious, and intricate. Therefore, a convenient and reliable computer-aided method has become the focus on inferring drug-target interactions (DTIs). In this research, we propose a novel computational model integrating a pyramid histogram of oriented gradients (PHOG), Position-Specific Scoring Matrix (PSSM), and rotation forest (RF) classifier for identifying DTIs. Specifically, protein primary sequences are first converted into PSSMs to describe the potential biological evolution information. After that, PHOG is employed to mine the highly representative features of PSSM from multiple pyramid levels, and the complete describers of drug-target pairs are generated by combining the molecular substructure fingerprints and PHOG features. Finally, we feed the complete describers into the RF classifier for effective prediction. The experiments of 5-fold Cross-Validations (CV) yield mean accuracies of 88.96%, 86.37%, 82.88%, and 76.92% on four golden standard data sets (enzyme, ion channel, G protein-coupled receptors (GPCRs), and nuclear receptor, respectively). Moreover, the paper also conducts the state-of-art light gradient boosting machine (LGBM) and support vector machine (SVM) to further verify the performance of the proposed model. The experimental outcomes substantiate that the established model is feasible and reliable to predict DTIs. There is an excellent prospect that our model is capable of predicting DTIs as an efficient tool on a large scale.

A machine learning approach to unmask novel gene signatures and prediction of Alzheimer's disease within different brain regions

Alzheimer's disease (AD) is a progressive neurodegenerative disorder whose aetiology is currently unknown. Although numerous studies have attempted to identify the genetic risk factor(s) of AD, the interpretability and/or the prediction accuracies achieved by these studies remained unsatisfactory, reducing their clinical significance. Here, we employ the ensemble of random-forest and regularized regression model (LASSO) to the AD-associated microarray datasets from four brain regions - Prefrontal cortex, Middle temporal gyrus, Hippocampus, and Entorhinal cortex- to discover novel genetic biomarkers through a machine learning-based feature-selection classification scheme. The proposed scheme unraveled the most optimum and biologically significant classifiers within each brain region, which achieved by far the highest prediction accuracy of AD in 5-fold cross-validation (99% average). Interestingly, along with the novel and prominent biomarkers including CORO1C, SLC25A46, RAE1, ANKIB1, CRLF3, PDYN, numerous non-coding RNA genes were also observed as discriminator, of which AK057435 and BC037880 are uncharacterized long non-coding RNA genes.

Computational identification of N4-methylcytosine sites in the mouse genome with machine-learning method

N4-methylcytosine (4mC) is a kind of DNA modification which could regulate multiple biological processes. Correctly identifying 4mC sites in genomic sequences can provide precise knowledge about their genetic roles. This study aimed to develop an ensemble model to predict 4mC sites in the mouse genome. In the proposed model, DNA sequences were encoded by k-mer, enhanced nucleic acid composition and composition of k-spaced nucleic acid pairs. Subsequently, these features were optimized by using minimum redundancy maximum relevance (mRMR) with incremental feature selection (IFS) and five-fold cross-validation. The obtained optimal features were inputted into random forest classifier for discriminating 4mC from non-4mC sites in mouse. On the independent dataset, our model could yield the overall accuracy of 85.41%, which was approximately 3.8% -6.3% higher than the two existing models, i4mC-Mouse and 4mCpred-EL respectively. The data and source code of the model can be freely download from https://github.com/linDing-groups/model_4mc.

Application of Machine Learning Methods in Predicting Nuclear Receptors and their Families

Nuclear receptors (NRs) are a superfamily of ligand-dependent transcription factors that are closely related to cell development, differentiation, reproduction, homeostasis, and metabolism. According to the alignments of the conserved domains, NRs are classified and assigned the following seven subfamilies or eight subfamilies: (1) NR1: thyroid hormone like (thyroid hormone, retinoic acid, RAR-related orphan receptor, peroxisome proliferator activated, vitamin D3- like), (2) NR2: HNF4-like (hepatocyte nuclear factor 4, retinoic acid X, tailless-like, COUP-TFlike, USP), (3) NR3: estrogen-like (estrogen, estrogen-related, glucocorticoid-like), (4) NR4: nerve growth factor IB-like (NGFI-B-like), (5) NR5: fushi tarazu-F1 like (fushi tarazu-F1 like), (6) NR6: germ cell nuclear factor like (germ cell nuclear factor), and (7) NR0: knirps like (knirps, knirpsrelated, embryonic gonad protein, ODR7, trithorax) and DAX like (DAX, SHP), or dividing NR0 into (7) NR7: knirps like and (8) NR8: DAX like. Different NRs families have different structural features and functions. Since the function of a NR is closely correlated with which subfamily it belongs to, it is highly desirable to identify NRs and their subfamilies rapidly and effectively. The knowledge acquired is essential for a proper understanding of normal and abnormal cellular mechanisms. With the advent of the post-genomics era, huge amounts of sequence-known proteins have increased explosively. Conventional methods for accurately classifying the family of NRs are experimental means with high cost and low efficiency. Therefore, it has created a greater need for bioinformatics tools to effectively recognize NRs and their subfamilies for the purpose of understanding their biological function. In this review, we summarized the application of machine learning methods in the prediction of NRs from different aspects. We hope that this review will provide a reference for further research on the classification of NRs and their families.

Predicting Cell Wall Lytic Enzymes Using Combined Features

Due to the overuse of antibiotics, people are worried that existing antibiotics will become ineffective against pathogens with the rapid rise of antibiotic-resistant strains. The use of cell wall lytic enzymes to destroy bacteria has become a viable alternative to avoid the crisis of antimicrobial resistance. In this paper, an improved method for cell wall lytic enzymes prediction was proposed and the amino acid composition (AAC), the dipeptide composition (DC), the position-specific score matrix auto-covariance (PSSM-AC), and the auto-covariance average chemical shift (acACS) were selected to predict the cell wall lytic enzymes with support vector machine (SVM). In order to overcome the imbalanced data classification problems and remove redundant or irrelevant features, the synthetic minority over-sampling technique (SMOTE) was used to balance the dataset. The F-score was used to select features. The S_n, S_p, MCC, and Acc were 99.35%, 99.02%, 0.98, and 99.19% with jackknife test using the optimized combination feature AAC+DC+acACS+PSSM-AC. The S_n, S_p, MCC, and Acc of cell wall lytic enzymes in our predictive model were higher than those in existing methods. This improved method may be helpful for protein function prediction.

MRMD2.0: A Python Tool for Machine Learning with Feature Ranking and Reduction

Aims:

The study aims to find a way to reduce the dimensionality of the dataset.

Background:

Dimensionality reduction is the key issue of the machine learning process. It does not only improve the prediction performance but also could recommend the intrinsic features and help to explore the biological expression of the machine learning “black box”.

Objective:

A variety of feature selection algorithms are used to select data features to achieve dimensionality reduction.

Methods:

First, MRMD2.0 integrated 7 different popular feature ranking algorithms with PageRank strategy. Second, optimized dimensionality was detected with forward adding strategy.

Result:

We have achieved good results in our experiments.

Conclusion:

Several works have been tested with MRMD2.0. It showed well performance. Otherwise, it also can draw the performance curves according to the feature dimensionality. If users want to sacrifice accuracy for fewer features, they can select the dimensionality from the performance curves.

Other:

We developed friendly python tools together with the web server. The users could upload their csv, arff or libsvm format files. Then the webserver would help to rank features and find the optimized dimensionality.

Recent Advances in Predicting Protein S-Nitrosylation Sites

Protein S-nitrosylation (SNO) is a process of covalent modification of nitric oxide (NO) and its derivatives and cysteine residues. SNO plays an essential role in reversible posttranslational modifications of proteins. The accurate prediction of SNO sites is crucial in revealing a certain biological mechanism of NO regulation and related drug development. Identification of the sites of SNO in proteins is currently a very hot topic. In this review, we briefly summarize recent advances in computationally identifying SNO sites. The challenges and future perspectives for identifying SNO sites are also discussed. We anticipate that this review will provide insights into research on SNO site prediction.

Basic polar and hydrophobic properties are the main characteristics that affect the binding of transcription factors to methylation sites

MOTIVATION

Methylation and transcription factors (TFs) are part of the mechanisms regulating gene expression. However, the numerous mechanisms regulating the interactions between methylation and TFs remain unknown. We employ machine-learning techniques to discover the characteristics of TFs that bind to methylation sites.

RESULTS

The classical machine-learning analysis process focuses on improving the performance of the analysis method. Conversely, we focus on the functional properties of the TF sequences. We obtain the principal properties of TFs, namely, the basic polar and hydrophobic Ile amino acids affecting the interaction between TFs and methylated DNA. The recall of the positive instances is 0.878 when their basic polar value is >0.1743. Both basic polar and hydrophobic Ile amino acids distinguish 74% of TFs bound to methylation sites. Therefore, we infer that basic polar amino acids affect the interactions of TFs with methylation sites. Based on our results, the role of the hydrophobic Ile residue is consistent with that described in previous studies, and the basic polar amino acids may also be a key factor modulating the interactions between TFs and methylation.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Indicator Regularized Non-Negative Matrix Factorization Method-Based Drug Repurposing for COVID-19

A novel coronavirus, named COVID-19, has become one of the most prevalent and severe infectious diseases in human history. Currently, there are only very few vaccines and therapeutic drugs against COVID-19, and their efficacies are yet to be tested. Drug repurposing aims to explore new applications of approved drugs, which can significantly reduce time and cost compared with de novo drug discovery. In this study, we built a virus-drug dataset, which included 34 viruses, 210 drugs, and 437 confirmed related virus-drug pairs from existing literature. Besides, we developed an Indicator Regularized non-negative Matrix Factorization (IRNMF) method, which introduced the indicator matrix and Karush-Kuhn-Tucker condition into the non-negative matrix factorization algorithm. According to the 5-fold cross-validation on the virus-drug dataset, the performance of IRNMF was better than other methods, and its Area Under receiver operating characteristic Curve (AUC) value was 0.8127. Additionally, we analyzed the case on COVID-19 infection, and our results suggested that the IRNMF algorithm could prioritize unknown virus-drug associations.

Distinguishing Enzymes and Non-enzymes Based on Structural Information with an Alignment Free Approach

Background:

Knowledge of protein functions is very crucial for the understanding of biological processes. Experimental methods for protein function prediction are powerless to treat the growing amount of protein sequence and structure data.

Objective:

To develop some computational techniques for the protein function prediction.

Method:

Based on the residue interaction network features and the motion mode information, an SVM model was constructed and used as the predictor. The role of these features was analyzed and some interesting results were obtained.

Results:

An alignment-free method for the classification of enzyme and non-enzyme is developed in this work. There is not any single feature that occupies a dominant position in the prediction process. The topological and the information-theoretic residue interaction network features have a better performance. The combination of the fast mode and the slow mode can get a better explanation for the classification result.

Conclusion:

The method proposed in this paper can act as a classifier for the enzymes and nonenzymes.

Identification of Sub-Golgi protein localization by use of deep representation learning features

Motivation

The Golgi apparatus has a key functional role in protein biosynthesis within the eukaryotic cell with malfunction resulting in various neurodegenerative diseases. For a better understanding of the Golgi apparatus, it is essential to identification of sub-Golgi protein localization. Although some machine learning methods have been used to identify sub-Golgi localization proteins by sequence representation fusion, more accurate sub-Golgi protein identification is still challenging by existing methodology.

Results

we developed a protein sub-Golgi localization identification protocol using deep representation learning features with 107 dimensions. By this protocol, we demonstrated that instead of multi-type protein sequence feature representation fusion as in previous state-of-the-art sub-Golgi-protein localization classifiers, it is sufficient to exploit only one type of feature representation for more accurately identification of sub-Golgi proteins. Compared with independent testing results for benchmark datasets, our protocol is able to perform generally, reliably and robustly for sub-Golgi protein localization prediction.

Availabilityand implementation

A use-friendly webserver is freely accessible at http://isGP-DRLF.aibiochem.net and the prediction code is accessible at https://github.com/zhibinlv/isGP-DRLF.

Supplementary information

Supplementary data are available at Bioinformatics online.

PPTPP: a novel therapeutic peptide prediction method using physicochemical property encoding and adaptive feature representation learning

MOTIVATION

Peptide is a promising candidate for therapeutic and diagnostic development due to its great physiological versatility and structural simplicity. Thus, identifying therapeutic peptides and investigating their properties are fundamentally important. As an inexpensive and fast approach, machine learning-based predictors have shown their strength in therapeutic peptide identification due to excellences in massive data processing. To date, no reported therapeutic peptide predictor can perform high-quality generic prediction and informative physicochemical properties (IPPs) identification simultaneously.

RESULTS

In this work, Physicochemical Property-based Therapeutic Peptide Predictor (PPTPP), a Random Forest-based prediction method was presented to address this issue. A novel feature encoding and learning scheme were initiated to produce and rank physicochemical property-related features. Besides being capable of predicting multiple therapeutics peptides with high comparability to established predictors, the presented method is also able to identify peptides' informative IPP. Results presented in this work not only illustrated the soundness of its working capacity but also demonstrated its potential for investigating other therapeutic peptides.

AVAILABILITY AND IMPLEMENTATION

https://github.com/YPZ858/PPTPP.

SUPPLEMENTARY INFORMATION

Supplementary data are available at Bioinformatics online.

Characterization and identification of lysine crotonylation sites based on machine learning method on both plant and mammalian

Lysine crotonylation (Kcr) is a type of protein post-translational modification (PTM), which plays important roles in a variety of cellular regulation and processes. Several methods have been proposed for the identification of crotonylation. However, most of these methods can predict efficiently only on histone or non-histone protein. Therefore, this work aims to give a more balanced performance in different species, here plant (non-histone) and mammalian (histone) are involved. SVM (support vector machine) and RF (random forest) were employed in this study. According to the results of cross-validations, the RF classifier based on EGAAC attribute achieved the best predictive performance which performs competitively good as existed methods, meanwhile more robust when dealing with imbalanced datasets. Moreover, an independent test was carried out, which compared the performance of this study and existed methods based on the same features or the same classifier. The classifiers of SVM and RF could achieve best performances with 92% sensitivity, 88% specificity, 90% accuracy, and an MCC of 0.80 in the mammalian dataset, and 77% sensitivity, 83% specificity, 70% accuracy and 0.54 MCC in a relatively small dataset of mammalian and a large-scaled plant dataset respectively. Moreover, a cross-species independent testing was also carried out in this study, which has proved the species diversity in plant and mammalian.

PredAmyl-MLP: Prediction of Amyloid Proteins Using Multilayer Perceptron

Amyloid is generally an aggregate of insoluble fibrin; its abnormal deposition is the pathogenic mechanism of various diseases, such as Alzheimer's disease and type II diabetes. Therefore, accurately identifying amyloid is necessary to understand its role in pathology. We proposed a machine learning-based prediction model called PredAmyl-MLP, which consists of the following three steps: feature extraction, feature selection, and classification. In the step of feature extraction, seven feature extraction algorithms and different combinations of them are investigated, and the combination of SVMProt-188D and tripeptide composition (TPC) is selected according to the experimental results. In the step of feature selection, maximum relevant maximum distance (MRMD) and binomial distribution (BD) are, respectively, used to remove the redundant or noise features, and the appropriate features are selected according to the experimental results. In the step of classification, we employed multilayer perceptron (MLP) to train the prediction model. The 10-fold cross-validation results show that the overall accuracy of PredAmyl-MLP reached 91.59%, and the performance was better than the existing methods.

Identification of Cancerlectins By Using Cascade Linear Discriminant Analysis and Optimal g-gap Tripeptide Composition

Background:

Lectins are a diverse group of glycoproteins or glycoconjugate proteins that can be extracted from plants, invertebrates and higher animals. Cancerlectins, a kind of lectins, which play a key role in the process of tumor cells interacting with each other and are being employed as therapeutic agents. A full understanding of cancerlectins is significant because it provides a tool for the future direction of cancer therapy.

Objective:

To develop an accurate and practically useful timesaving tool to identify cancerlectins. A novel sequence-based method is proposed along with a correlative webserver to access the proposed tool.

Methods:

Firstly, protein features were extracted in a newly feature building way termed, g-gap tripeptide composition. After which a proposed cascade linear discriminant analysis (Cascade LDA) is used to alleviate the high dimensional difficulties with the Analysis Of Variance (ANOVA) as a feature importance criterion. Finally, Support Vector Machine (SVM) is used as the classifier to identify cancerlectins.

Results:

The proposed method achieved an accuracy of 91.34% with sensitivity of 89.89%, specificity of 92.48% and an 0.8318 Mathew’s correlation coefficient based on only 13 fusion features in jackknife cross validation, the result of which is superior to other published methods in this domain.

Conclusion:

In this study, a new method based only on primary structure of protein is proposed and experimental results show that it could be a promising tool to identify cancerlectins. An openaccess webserver is made available in this work to facilitate other related works.

Predicting MicroRNA Sequence Using CNN and LSTM Stacked in Seq2Seq Architecture

CNN and LSTM have proven their ability in feature extraction and natural language processing, respectively. So, we tried to use their ability to process the language of RNAs, i.e., predicting sequence of microRNAs using the sequence of mRNA. The idea is to extract the features from sequence of mRNA using CNN and use LSTM network for prediction of miRNA. The model has learned the basic features such as seed match at first 2-8 nucleotides starting at the 5' end and counting toward the 3' end. Also, it was able to predict G-U wobble base pair in seed region. While validating on experimentally validated data, the model was able to predict on average 72 percent of miRNAs for specific mRNA and shows highest positive expression fold change of predicted targets on a microarray data generated using anti 25 miRNAs compare to other predicted tools. Codes are available at https://github.com/rajkumar1501/sequence-prediction-using-CNN-and-LSTMs.

Identifying Antioxidant Proteins by Using Amino Acid Composition and Protein-Protein Interactions

Excessive oxidative stress responses can threaten our health, and thus it is essential to produce antioxidant proteins to regulate the body’s oxidative responses. The low number of antioxidant proteins makes it difficult to extract their representative features. Our experimental method did not use structural information but instead studied antioxidant proteins from a sequenced perspective while focusing on the impact of data imbalance on sensitivity, thus greatly improving the model’s sensitivity for antioxidant protein recognition. We developed a method based on the Composition of k-spaced Amino Acid Pairs (CKSAAP) and the Conjoint Triad (CT) features derived from the amino acid composition and protein-protein interactions. SMOTE and the Max-Relevance-Max-Distance algorithm (MRMD) were utilized to unbalance the training data and select the optimal feature subset, respectively. The test set used 10-fold crossing validation and a random forest algorithm for classification according to the selected feature subset. The sensitivity was 0.792, the specificity was 0.808, and the average accuracy was 0.8.

A Method for Identifying Vesicle Transport Proteins Based on LibSVM and MRMD

With the development of computer technology, many machine learning algorithms have been applied to the field of biology, forming the discipline of bioinformatics. Protein function prediction is a classic research topic in this subject area. Though many scholars have made achievements in identifying protein by different algorithms, they often extract a large number of feature types and use very complex classification methods to obtain little improvement in the classification effect, and this process is very time-consuming. In this research, we attempt to utilize as few features as possible to classify vesicular transportation proteins and to simultaneously obtain a comparative satisfactory classification result. We adopt CTDC which is a submethod of the method of composition, transition, and distribution (CTD) to extract only 39 features from each sequence, and LibSVM is used as the classification method. We use the SMOTE method to deal with the problem of dataset imbalance. There are 11619 protein sequences in our dataset. We selected 4428 sequences to train our classification model and selected other 1832 sequences from our dataset to test the classification effect and finally achieved an accuracy of 71.77%. After dimension reduction by MRMD, the accuracy is 72.16%.

Literature review and analysis on big data stream classification techniques

Rapid growth in technology and information lead the human to witness the improved growth in velocity, volume of data, and variety. The data in the business organizations demonstrate the development of big data applications. Because of the improving demand of applications, analysis of sophisticated streaming big data tends to become a significant area in data mining. One of the significant aspects of the research is employing deep learning approaches for effective extraction of complex data representations. Accordingly, this survey provides the detailed review of big data classification methodologies, like deep learning based techniques, Convolutional Neural Network (CNN) based techniques, K-Nearest Neighbor (KNN) based techniques, Neural Network (NN) based techniques, fuzzy based techniques, and Support vector based techniques, and so on. Moreover, a detailed study is made by concerning the parameters, like evaluation metrics, implementation tool, employed framework, datasets utilized, adopted classification methods, and accuracy range obtained by various techniques. Eventually, the research gaps and issues of various big data classification schemes are presented.

T4SE-XGB: Interpretable Sequence-Based Prediction of Type IV Secreted Effectors Using eXtreme Gradient Boosting Algorithm

Type IV secreted effectors (T4SEs) can be translocated into the cytosol of host cells via type IV secretion system (T4SS) and cause diseases. However, experimental approaches to identify T4SEs are time- and resource-consuming, and the existing computational tools based on machine learning techniques have some obvious limitations such as the lack of interpretability in the prediction models. In this study, we proposed a new model, T4SE-XGB, which uses the eXtreme gradient boosting (XGBoost) algorithm for accurate identification of type IV effectors based on optimal features based on protein sequences. After trying 20 different types of features, the best performance was achieved when all features were fed into XGBoost by the 5-fold cross validation in comparison with other machine learning methods. Then, the ReliefF algorithm was adopted to get the optimal feature set on our dataset, which further improved the model performance. T4SE-XGB exhibited highest predictive performance on the independent test set and outperformed other published prediction tools. Furthermore, the SHAP method was used to interpret the contribution of features to model predictions. The identification of key features can contribute to improved understanding of multifactorial contributors to host-pathogen interactions and bacterial pathogenesis. In addition to type IV effector prediction, we believe that the proposed framework can provide instructive guidance for similar studies to construct prediction methods on related biological problems. The data and source code of this study can be freely accessed at https://github.com/CT001002/T4SE-XGB.

A Computational Method for the Identification of Endolysins and Autolysins

BACKGROUND

Cell lytic enzyme is a kind of highly evolved protein, which can destroy the cell structure and kill the bacteria. Compared with antibiotics, cell lytic enzyme will not cause serious problem of drug resistance of pathogenic bacteria. Thus, the study of cell wall lytic enzymes aims at finding an efficient way for curing bacteria infectious. Compared with using antibiotics, the problem of drug resistance becomes more serious. Therefore, it is a good choice for curing bacterial infections by using cell lytic enzymes. Cell lytic enzyme includes endolysin and autolysin and the difference between them is the purpose of the break of cell wall. The identification of the type of cell lytic enzymes is meaningful for the study of cell wall enzymes.

OBJECTIVE

In this article, our motivation is to predict the type of cell lytic enzyme. Cell lytic enzyme is helpful for killing bacteria, so it is meaningful for study the type of cell lytic enzyme. However, it is time consuming to detect the type of cell lytic enzyme by experimental methods. Thus, an efficient computational method for the type of cell lytic enzyme prediction is proposed in our work.

METHODS

We propose a computational method for the prediction of endolysin and autolysin. First, a data set containing 27 endolysins and 41 autolysins is built. Then the protein is represented by tripeptides composition. The features are selected with larger confidence degree. At last, the classifier is trained by the labeled vectors based on support vector machine. The learned classifier is used to predict the type of cell lytic enzyme.

RESULTS

Following the proposed method, the experimental results show that the overall accuracy can attain 97.06%, when 44 features are selected. Compared with Ding's method, our method improves the overall accuracy by nearly 4.5% ((97.06-92.9)/92.9%). The performance of our proposed method is stable, when the selected feature number is from 40 to 70. The overall accuracy of tripeptides optimal feature set is 94.12%, and the overall accuracy of Chou's amphiphilic PseAAC method is 76.2%. The experimental results also demonstrate that the overall accuracy is improved by nearly 18% when using the tripeptides optimal feature set.

CONCLUSION

The paper proposed an efficient method for identifying endolysin and autolysin. In this paper, support vector machine is used to predict the type of cell lytic enzyme. The experimental results show that the overall accuracy of the proposed method is 94.12%, which is better than some existing methods. In conclusion, the selected 44 features can improve the overall accuracy for identification of the type of cell lytic enzyme. Support vector machine performs better than other classifiers when using the selected feature set on the benchmark data set.

ICTC-RAAC: An improved web predictor for identifying the types of ion channel-targeted conotoxins by using reduced amino acid cluster descriptors

Conotoxins are small peptide toxins which are rich in disulfide and have the unique diversity of sequences. It is significant to correctly identify the types of ion channel-targeted conotoxins because that they are considered as the optimal pharmacological candidate medicine in drug design owing to their ability specifically binding to ion channels and interfering with neural transmission. Comparing with other feature extracting methods, the reduced amino acid cluster (RAAC) better resolved in simplifying protein complexity and identifying functional conserved regions. Thus, in our study, 673 RAACs generated from 74 types of reduced amino acid alphabet were comprehensively assessed to establish a state-of-the-art predictor for predicting ion channel-targeted conotoxins. The results showed Type 20, Cluster 9 (T = 20, C = 9) in the tripeptide composition (N = 3) achieved the best accuracy, 89.3%, which was based on the algorithm of amino acids reduction of variance maximization. Further, the ANOVA with incremental feature selection (IFS) was used for feature selection to improve prediction performance. Finally, the cross-validation results showed that the best overall accuracy we calculated was 96.4% and 1.8% higher than the best accuracy of previous studies. Based on the predictor we proposed, a user-friendly webserver was established and can be friendly accessed at http://bioinfor.imu.edu.cn/ictcraac.

A novel fusion based on the evolutionary features for protein fold recognition using support vector machines

Protein fold recognition plays a crucial role in discovering three-dimensional structure of proteins and protein functions. Several approaches have been employed for the prediction of protein folds. Some of these approaches are based on extracting features from protein sequences and using a strong classifier. Feature extraction techniques generally utilize syntactical-based information, evolutionary-based information and physicochemical-based information to extract features. In recent years, finding an efficient technique for integrating discriminate features have been received advancing attention. In this study, we integrate Auto-Cross-Covariance and Separated dimer evolutionary feature extraction methods. The results’ features are scored by Information gain to define and select several discriminated features. According to three benchmark datasets, DD, RDD ,and EDD, the results of the support vector machine show more than 6\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\%$$\end{document}% improvement in accuracy on these benchmark datasets.

iPromoter-5mC: A Novel Fusion Decision Predictor for the Identification of 5-Methylcytosine Sites in Genome-Wide DNA Promoters

The hypomethylation of the whole cancer genome and the hypermethylation of the promoter of specific tumor suppressor genes are the important reasons for the rapid proliferation of cancer cells. Therefore, obtaining the distribution of 5-methylcytosine (5mC) in promoters is a key step to further understand the relationship between promoter methylation and mRNA gene expression regulation. Large-scale detection of DNA 5mC through wet experiments is still time-consuming and laborious. Therefore, it is urgent to design a method for identifying the 5mC site of genome-wide DNA promoters. Based on promoter methylation data of the small cell lung cancer (SCLC) from the database named cancer cell line Encyclopedia (CCLE), we built a fusion decision predictor called iPromoter-5mC for identifying methylation modification sites in promoters using deep neural network (DNN). One-Hot Encoding (One-hot) was used to encode the promoter samples for the classification. The method achieves average AUC of 0.957 on the independent testing dataset, indicating that our predictor is robust and reliable. A user-friendly web-server called iPromoter-5mC could be freely accessible at http://www.jci-bioinfo.cn/iPromoter-5mC, which will provide simple and effective means for users to study promoter 5mC modification. The source code of the proposed methods is freely available for academic research at https://github.com/zlwuxi/iPromoter-5mC.

Predicting Preference of Transcription Factors for Methylated DNA Using Sequence Information

Transcription factors play key roles in cell-fate decisions by regulating 3D genome conformation and gene expression. The traditional view is that methylation of DNA hinders transcription factors binding to them, but recent research has shown that many transcription factors prefer to bind to methylated DNA. Therefore, identifying such transcription factors and understanding their functions is a stepping-stone for studying methylation-mediated biological processes. In this paper, a two-step discriminated method was proposed to recognize transcription factors and their preference for methylated DNA based only on sequences information. In the first step, the proposed model was used to discriminate transcription factors from non-transcription factors. The areas under the curve (AUCs) are 0.9183 and 0.9116, respectively, for the 5-fold cross-validation test and independent dataset test. Subsequently, for the classification of transcription factors that prefer methylated DNA and transcription factors that prefer non-methylated DNA, our model could produce the AUCs of 0.7744 and 0.7356, respectively, for the 5-fold cross-validation test and independent dataset test. Based on the proposed model, a user-friendly web server called TFPred was built, which can be freely accessed at http://lin-group.cn/server/TFPred/.

Prediction of N7-methylguanosine sites in human RNA based on optimal sequence features

N-7 methylguanosine (m7G) modification is a ubiquitous post-transcriptional RNA modification which is vital for maintaining RNA function and protein translation. Developing computational tools will help us to easily predict the m7G sites in RNA sequence. In this work, we designed a sequence-based method to identify the modification site in human RNA sequences. At first, several kinds of sequence features were extracted to code m7G and non-m7G samples. Subsequently, we used mRMR, F-score, and Relief to obtain the optimal subset of features which could produce the maximum prediction accuracy. In 10-fold cross-validation, results showed that the highest accuracy is 94.67% achieved by support vector machine (SVM) for identifying m7G sites in human genome. In addition, we examined the performances of other algorithms and found that the SVM-based model outperformed others. The results indicated that the predictor could be a useful tool for studying m7G. A prediction model is available at https://github.com/MapFM/m7g_model.git.