Genomic Island Prediction via Chi-Square Test and Random Forest Algorithm

Prediction of cell-type-specific cohesin-mediated chromatin loops based on chromatin state

Chromatin loop is of crucial importance for the regulation of gene transcription. Cohesin is a type of chromatin-associated protein that mediates the interaction of chromatin through the loop extrusion. Cohesin-mediated chromatin interactions have strong cell-type specificity, posing a challenge for predicting chromatin loops. Existing computational methods perform poorly in predicting cell-type-specific chromatin loops. To address this issue, we propose a random forest model to predict cell-type-specific cohesin-mediated chromatin loops based on chromatin states identified by ChromHMM and the occupancy of related factors. Our results show that chromatin state is responsible for cell-type-specificity of loops. Using only chromatin states as features, the model achieved high accuracy in predicting cell-type-specific loops between two cell types and can be applied to different cell types. Furthermore, when chromatin states are combined with the occurrence frequency of CTCF, RAD21, YY1, and H3K27ac ChIP-seq peaks, more accurate prediction can be achieved. Our feature extraction method provides novel insights into predicting cell-type-specific chromatin loops and reveals the relationship between chromatin state and chromatin loop formation.

FEOpti-ACVP: identification of novel anti-coronavirus peptide sequences based on feature engineering and optimization

Anti-coronavirus peptides (ACVPs) represent a relatively novel approach of inhibiting the adsorption and fusion of the virus with human cells. Several peptide-based inhibitors showed promise as potential therapeutic drug candidates. However, identifying such peptides in laboratory experiments is both costly and time consuming. Therefore, there is growing interest in using computational methods to predict ACVPs. Here, we describe a model for the prediction of ACVPs that is based on the combination of feature engineering (FE) optimization and deep representation learning. FEOpti-ACVP was pre-trained using two feature extraction frameworks. At the next step, several machine learning approaches were tested in to construct the final algorithm. The final version of FEOpti-ACVP outperformed existing methods used for ACVPs prediction and it has the potential to become a valuable tool in ACVP drug design. A user-friendly webserver of FEOpti-ACVP can be accessed at http://servers.aibiochem.net/soft/FEOpti-ACVP/.

Improved multi-label classifiers for predicting protein subcellular localization

Protein functions are closely related to their subcellular locations. At present, the prediction of protein subcellular locations is one of the most important problems in protein science. The evident defects of traditional methods make it urgent to design methods with high efficiency and low costs. To date, lots of computational methods have been proposed. However, this problem is far from being completely solved. Recently, some multi-label classifiers have been proposed to identify subcellular locations of human, animal, Gram-negative bacterial and eukaryotic proteins. These classifiers adopted the protein features derived from gene ontology information. Although they provided good performance, they can be further improved by adopting more powerful machine learning algorithms. In this study, four improved multi-label classifiers were set up for identification of subcellular locations of the above four protein types. The random k-labelsets (RAKEL) algorithm was used to tackle proteins with multiple locations, and random forest was used as the basic prediction engine. All classifiers were tested by jackknife test, indicating their high performance. Comparisons with previous classifiers further confirmed the superiority of the proposed classifiers.

DLC-ac4C: A Prediction Model for N4-acetylcytidine Sites in Human mRNA Based on DenseNet and Bidirectional LSTM Methods

Introduction

N4 acetylcytidine (ac4C) is a highly conserved nucleoside modification that is essential for the regulation of immune functions in organisms. Currently, the identification of ac4C is primarily achieved using biological methods, which can be time-consuming and labor-intensive. In contrast, accurate identification of ac4C by computational methods has become a more effective method for classification and prediction.

Aim

To the best of our knowledge, although there are several computational methods for ac4C locus prediction, the performance of the models they constructed is poor, and the network structure they used is relatively simple and suffers from the disadvantage of network degradation. This study aims to improve these limitations by proposing a predictive model based on integrated deep learning to better help identify ac4C sites.

Methods

In this study, we propose a new integrated deep learning prediction framework, DLC-ac4C. First, we encode RNA sequences based on three feature encoding schemes, namely C2 encoding, nucleotide chemical property (NCP) encoding, and nucleotide density (ND) encoding. Second, one-dimensional convolutional layers and densely connected convolutional networks (DenseNet) are used to learn local features, and bi-directional long short-term memory networks (Bi-LSTM) are used to learn global features. Third, a channel attention mechanism is introduced to determine the importance of sequence characteristics. Finally, a homomorphic integration strategy is used to limit the generalization error of the model, which further improves the performance of the model.

Results

The DLC-ac4C model performed well in terms of sensitivity (Sn), specificity (Sp), accuracy (Acc), Mathews correlation coefficient (MCC), and area under the curve (AUC) for the independent test data with 86.23%, 79.71%, 82.97%, 66.08%, and 90.42%, respectively, which was significantly better than the prediction accuracy of the existing methods.

Conclusion

Our model not only combines DenseNet and Bi-LSTM, but also uses the channel attention mechanism to better capture hidden information features from a sequence perspective, and can identify ac4C sites more effectively.

Prediction of thermophilic protein using 2-D general series correlation pseudo amino acid features

The demand for thermophilic protein has been increasing in protein engineering recently. Many machine-learning methods for identifying thermophilic proteins have emerged during this period. However, most machine learning-based thermophilic protein identification studies have only focused on accuracy. The relationship between the features' meaning and the proteins' physicochemical properties has yet to be studied in depth. In this article, we focused on the relationship between the features and the thermal stability of thermophilic proteins. This method used 2-D general series correlation pseudo amino acid (SC-PseAAC-General) features and realized accuracy of 82.76% using the J48 classifier. In addition, this research found the presence of higher frequencies of glutamic acid in thermophilic proteins, which help thermophilic proteins maintain their thermal stability by forming hydrogen bonds and salt bridges that prevent denaturation at high temperatures.

MSFC: a new feature construction method for accurate diagnosis of mass spectrometry data

Mass spectrometry technology can realize dynamic detection of many complex matrix samples in a simple, rapid, compassionate, precise, and high-throughput manner and has become an indispensable tool in accurate diagnosis. The mass spectrometry data analysis is mainly to analyze all metabolites in the organism quantitatively and to find the relative relationship between metabolites and physiological and pathological changes. A feature construction of mass spectrometry data (MSFS) method is proposed to construct the features of the original mass spectrometry data, so as to reduce the noise in the mass spectrometry data, reduce the redundancy of the original data and improve the information content of the data. Chi-square test is used to select the optimal non-redundant feature subset from high-dimensional features. And the optimal feature subset is visually analyzed and corresponds to the original mass spectrum interval. Training in 10 kinds of supervised learning models, and evaluating the classification effect of the models through various evaluation indexes. Taking two public mass spectrometry datasets as examples, the feasibility of the method proposed in this paper is verified. In the coronary heart disease dataset, during the identification process of mixed batch samples, the classification accuracy on the test set reached 1.000; During the recognition process, the classification accuracy on the test set advanced to 0.979. On the colorectal liver metastases data set, the classification accuracy on the test set reached 1.000. This paper attempts to use a new raw mass spectrometry data preprocessing method to realize the alignment operation of the raw mass spectrometry data, which significantly improves the classification accuracy and provides another new idea for mass spectrometry data analysis. Compared with MetaboAnalyst software and existing experimental results, the method proposed in this paper has obtained better classification results.

Multi-view local hyperplane nearest neighbor model based on independence criterion for identifying vesicular transport proteins

Vesicular transport proteins participate in various biological processes and play a significant role in the movement of substances within cells. These proteins are associated with numerous human diseases, making their identification particularly important. In this study, we developed a novel strategy for accurately identifying vesicular transport proteins. We developed a novel multi-view classifier called graph-regularized k-local hyperplane distance nearest neighbor model (HSIC-GHKNN), which combines the Hilbert-Schmidt independence criterion (HSIC)-based multi-view learning method with a local hyperplane distance nearest-neighbor classifier. We first extracted protein evolution information using two feature extraction methods, pseudo-position-specific scoring matrix (PsePSSM) and AATP, and addressed dataset imbalance using the Edited Nearest Neighbors (ENN) algorithm. Subsequently, we employed a local hyperplane distance nearest-neighbor classifier for each view identification and added an HSIC term to maintain independence between views. We then assessed the performance of our identification strategy and analyzed the PsePSSM and AATP feature sets to determine the influencing factors of the classification results. The experimental results demonstrate that the accurate and Matthew correlation coefficients of our strategy on the independent test set are 85.8 % and 0.548, respectively. Our approach outperformed existing methods in most evaluation metrics. In addition, the proposed multi-view classification model can easily be applied to similar identification tasks.

DP-AOP: A novel SVM-based antioxidant proteins identifier

The identification of antioxidant proteins is a challenging yet meaningful task, as they can protect against the damage caused by some free radicals. In addition to time-consuming, laborious, and expensive experimental identification methods, efficient identification of antioxidant proteins through machine learning algorithms has become increasingly common. In recent years, researchers have proposed models for identifying antioxidant proteins; unfortunately, although the accuracy of models is already high, their sensitivity is too low, indicating the possibility of overfitting in the model. Therefore, we developed a new model called DP-AOP for the recognition of antioxidant proteins. We used the SMOTE algorithm to balance the dataset, selected Wei's proposed feature extraction algorithm to obtain 473 dimensional feature vectors, and based on the sorting function in MRMD, scored and ranked each feature to obtain a feature set with contribution values ranging from high to low. To effectively reduce the feature dimension, we combined the dynamic programming idea to make the local eight features the optimal subset. After obtaining the 36 dimensional feature vectors, we finally selected 17 features through experimental analysis. The SVM classification algorithm was used to implement the model through the libsvm tool. The model achieved satisfactory performance, with an accuracy rate of 91.076 %, SN of 96.4 %, SP of 85.8 %, MCC of 82.6 %, and F1 core of 91.5 %. Furthermore, we built a free web server to facilitate researchers' subsequent unfolding studies of antioxidant protein recognition. The website is http://112.124.26.17:8003/#/.

Using the Random Forest for Identifying Key Physicochemical Properties of Amino Acids to Discriminate Anticancer and Non-Anticancer Peptides

Anticancer peptides (ACPs) represent a promising new therapeutic approach in cancer treatment. They can target cancer cells without affecting healthy tissues or altering normal physiological functions. Machine learning algorithms have increasingly been utilized for predicting peptide sequences with potential ACP effects. This study analyzed four benchmark datasets based on a well-established random forest (RF) algorithm. The peptide sequences were converted into 566 physicochemical features extracted from the amino acid index (AAindex) library, which were then subjected to feature selection using four methods: light gradient-boosting machine (LGBM), analysis of variance (ANOVA), chi-squared test (Chi²), and mutual information (MI). Presenting and merging the identified features using Venn diagrams, 19 key amino acid physicochemical properties were identified that can be used to predict the likelihood of a peptide sequence functioning as an ACP. The results were quantified by performance evaluation metrics to determine the accuracy of predictions. This study aims to enhance the efficiency of designing peptide sequences for cancer treatment.

Inferring drug-disease associations by a deep analysis on drug and disease networks

Drugs, which treat various diseases, are essential for human health. However, developing new drugs is quite laborious, time-consuming, and expensive. Although investments into drug development have greatly increased over the years, the number of drug approvals each year remain quite low. Drug repositioning is deemed an effective means to accelerate the procedures of drug development because it can discover novel effects of existing drugs. Numerous computational methods have been proposed in drug repositioning, some of which were designed as binary classifiers that can predict drug-disease associations (DDAs). The negative sample selection was a common defect of this method. In this study, a novel reliable negative sample selection scheme, named RNSS, is presented, which can screen out reliable pairs of drugs and diseases with low probabilities of being actual DDAs. This scheme considered information from k-neighbors of one drug in a drug network, including their associations to diseases and the drug. Then, a scoring system was set up to evaluate pairs of drugs and diseases. To test the utility of the RNSS, three classic classification algorithms (random forest, bayes network and nearest neighbor algorithm) were employed to build classifiers using negative samples selected by the RNSS. The cross-validation results suggested that such classifiers provided a nearly perfect performance and were significantly superior to those using some traditional and previous negative sample selection schemes.

Identification of genes related to immune enhancement caused by heterologous ChAdOx1-BNT162b2 vaccines in lymphocytes at single-cell resolution with machine learning methods

The widely used ChAdOx1 nCoV-19 (ChAd) vector and BNT162b2 (BNT) mRNA vaccines have been shown to induce robust immune responses. Recent studies demonstrated that the immune responses of people who received one dose of ChAdOx1 and one dose of BNT were better than those of people who received vaccines with two homologous ChAdOx1 or two BNT doses. However, how heterologous vaccines function has not been extensively investigated. In this study, single-cell RNA sequencing data from three classes of samples: volunteers vaccinated with heterologous ChAdOx1-BNT and volunteers vaccinated with homologous ChAd-ChAd and BNT-BNT vaccinations after 7 days were divided into three types of immune cells (3654 B, 8212 CD4+ T, and 5608 CD8+ T cells). To identify differences in gene expression in various cell types induced by vaccines administered through different vaccination strategies, multiple advanced feature selection methods (max-relevance and min-redundancy, Monte Carlo feature selection, least absolute shrinkage and selection operator, light gradient boosting machine, and permutation feature importance) and classification algorithms (decision tree and random forest) were integrated into a computational framework. Feature selection methods were in charge of analyzing the importance of gene features, yielding multiple gene lists. These lists were fed into incremental feature selection, incorporating decision tree and random forest, to extract essential genes, classification rules and build efficient classifiers. Highly ranked genes include PLCG2, whose differential expression is important to the B cell immune pathway and is positively correlated with immune cells, such as CD8+ T cells, and B2M, which is associated with thymic T cell differentiation. This study gave an important contribution to the mechanistic explanation of results showing the stronger immune response of a heterologous ChAdOx1-BNT vaccination schedule than two doses of either BNT or ChAdOx1, offering a theoretical foundation for vaccine modification.

A model with deep analysis on a large drug network for drug classification

Drugs are an important means to treat various diseases. They are classified into several classes to indicate their properties and effects. Those in the same class always share some important features. The Kyoto Encyclopedia of Genes and Genomes (KEGG) DRUG recently reported a new drug classification system that classifies drugs into 14 classes. Correct identification of the class for any possible drug-like compound is helpful to roughly determine its effects for a particular type of disease. Experiments could be conducted to confirm such latent effects, thus accelerating the procedures for discovering novel drugs. In this study, this classification system was investigated. A classification model was proposed to assign one of the classes in the system to any given drug for the first time. Different from traditional fingerprint features, which indicated essential drug properties alone and were very popular in investigating drug-related problems, drugs were represented by novel features derived from a large drug network via a well-known network embedding algorithm called Node2vec. These features abstracted the drug associations generated from their essential properties, and they could overview each drug with all drugs as background. As class sizes were of great differences, synthetic minority over-sampling technique (SMOTE) was employed to tackle the imbalance problem. A balanced dataset was fed into the support vector machine to build the model. The 10-fold cross-validation results suggested the excellent performance of the model. This model was also superior to models using other drug features, including those generated by another network embedding algorithm and fingerprint features. Furthermore, this model provided more balanced performance across all classes than that without SMOTE.

Identification of Two CDK5R1-Related Subtypes and Characterization of Immune Infiltrates in Alzheimer's Disease Based on an Integrated Bioinformatics Analysis

Background

Alzheimer's disease (AD) is a neurodegenerative disorder and the major cause of senile dementia. The Reelin pathway has been involved in both learning and AD pathogenesis. However, the specific Reelin-related gene signature during the pathological process remains unknown.

Methods

Reelin-related gene (CDK5R1) expression was analyzed using the GEO datasets. The relevant genes of CDK5R1 were identified using differential expression analysis and weighted gene correlation network analysis (WGCNA) based on the GSE43850 dataset. ConsensusClusterPlus analysis was applied to identify subtypes (C1 and C2) of AD. The CIBERSORT algorithm was used to assess the immune cell infiltration between the two AD subtypes.

Results

CDK5R1 was downregulated in AD. 244 differentially expressed CDK5R1-related genes (DECRGs) between the two subgroups were mainly enriched in GABAergic synapse, neuroactive ligand-receptor interaction, synapse organization, neurotransmitter transport, etc. Furthermore, the GSVA results indicated that immune-related pathways were significantly enriched in the C1 subgroup. Interestingly, 10 Reelin pathway-related genes (CRK, DAB2IP, LRP8, RELN, STAT5A, CDK5, CDK5R1, DAB1, FYN, and SH3KBP1) were abnormally expressed between the two subgroups. The proportion of T cell gamma delta, monocytes, macrophage M2, and dendritic cells activated decreased from C1 to C2, while the proportion of plasma cells, T cell follicular helper, and NK cells activated increased.

Conclusion

Two CDK5R1-related subtypes of AD were identified, helping us to better understand the role of CDK5R1 in the pathological process of AD.

Identifying anal and cervical tumorigenesis-associated methylation signaling with machine learning methods

Cervical and anal carcinoma are neoplastic diseases with various intraepithelial neoplasia stages. The underlying mechanisms for cancer initiation and progression have not been fully revealed. DNA methylation has been shown to be aberrantly regulated during tumorigenesis in anal and cervical carcinoma, revealing the important roles of DNA methylation signaling as a biomarker to distinguish cancer stages in clinics. In this research, several machine learning methods were used to analyze the methylation profiles on anal and cervical carcinoma samples, which were divided into three classes representing various stages of tumor progression. Advanced feature selection methods, including Boruta, LASSO, LightGBM, and MCFS, were used to select methylation features that are highly correlated with cancer progression. Some methylation probes including cg01550828 and its corresponding gene RNF168 have been reported to be associated with human papilloma virus-related anal cancer. As for biomarkers for cervical carcinoma, cg27012396 and its functional gene HDAC4 were confirmed to regulate the glycolysis and survival of hypoxic tumor cells in cervical carcinoma. Furthermore, we developed effective classifiers for identifying various tumor stages and derived classification rules that reflect the quantitative impact of methylation on tumorigenesis. The current study identified methylation signals associated with the development of cervical and anal carcinoma at qualitative and quantitative levels using advanced machine learning methods.

Identification of methylation signatures and rules for predicting the severity of SARS-CoV-2 infection with machine learning methods

Patients infected with SARS-CoV-2 at various severities have different clinical manifestations and treatments. Mild or moderate patients usually recover with conventional medical treatment, but severe patients require prompt professional treatment. Thus, stratifying infected patients for targeted treatment is meaningful. A computational workflow was designed in this study to identify key blood methylation features and rules that can distinguish the severity of SARS-CoV-2 infection. First, the methylation features in the expression profile were deeply analyzed by a Monte Carlo feature selection method. A feature list was generated. Next, this ranked feature list was fed into the incremental feature selection method to determine the optimal features for different classification algorithms, thereby further building optimal classifiers. These selected key features were analyzed by functional enrichment to detect their biofunctional information. Furthermore, a set of rules were set up by a white-box algorithm, decision tree, to uncover different methylation patterns on various severity of SARS-CoV-2 infection. Some genes (PARP9, MX1, IRF7), corresponding to essential methylation sites, and rules were validated by published academic literature. Overall, this study contributes to revealing potential expression features and provides a reference for patient stratification. The physicians can prioritize and allocate health and medical resources for COVID-19 patients based on their predicted severe clinical outcomes.

Identification of methylation signatures associated with CAR T cell in B-cell acute lymphoblastic leukemia and non-hodgkin’s lymphoma

CD19-targeted CAR T cell immunotherapy has exceptional efficacy for the treatment of B-cell malignancies. B-cell acute lymphocytic leukemia and non-Hodgkin’s lymphoma are two common B-cell malignancies with high recurrence rate and are refractory to cure. Although CAR T-cell immunotherapy overcomes the limitations of conventional treatments for such malignancies, failure of treatment and tumor recurrence remain common. In this study, we searched for important methylation signatures to differentiate CAR-transduced and untransduced T cells from patients with acute lymphoblastic leukemia and non-Hodgkin’s lymphoma. First, we used three feature ranking methods, namely, Monte Carlo feature selection, light gradient boosting machine, and least absolute shrinkage and selection operator, to rank all methylation features in order of their importance. Then, the incremental feature selection method was adopted to construct efficient classifiers and filter the optimal feature subsets. Some important methylated genes, namely, SERPINB6, ANK1, PDCD5, DAPK2, and DNAJB6, were identified. Furthermore, the classification rules for distinguishing different classes were established, which can precisely describe the role of methylation features in the classification. Overall, we applied advanced machine learning approaches to the high-throughput data, investigating the mechanism of CAR T cells to establish the theoretical foundation for modifying CAR T cells.

Mathematical Modeling and Computational Prediction of High-Risk Types of Human Papillomaviruses

Cervical cancer is one of the main causes of cancer death all over the world. Most diseases such as cervical epithelial atypical hyperplasia and invasive cervical cancer are closely related to the continuous infection of high-risk types of human papillomavirus. Therefore, the high-risk types of human papillomavirus are the key to the prevention and treatment of cervical cancer. With the accumulation of high-throughput and clinical data, the use of systematic and quantitative methods for mathematical modeling and computational prediction has become more and more important. This paper summarizes the mathematical models and prediction methods of the risk types of human papillomavirus, especially around the key steps such as feature extraction, feature selection, and prediction algorithms. We summarized and discussed the advantages and disadvantages of existing algorithms, which provides a theoretical basis for follow-up research.

Gm-PLoc: A Subcellular Localization Model of Multi-Label Protein Based on GAN and DeepFM

Identifying the subcellular localization of a given protein is an essential part of biological and medical research, since the protein must be localized in the correct organelle to ensure physiological function. Conventional biological experiments for protein subcellular localization have some limitations, such as high cost and low efficiency, thus massive computational methods are proposed to solve these problems. However, some of these methods need to be improved further for protein subcellular localization with class imbalance problem. We propose a new model, generating minority samples for protein subcellular localization (Gm-PLoc), to predict the subcellular localization of multi-label proteins. This model includes three steps: using the position specific scoring matrix to extract distinguishable features of proteins; synthesizing samples of the minority category to balance the distribution of categories based on the revised generative adversarial networks; training a classifier with the rebalanced dataset to predict the subcellular localization of multi-label proteins. One benchmark dataset is selected to evaluate the performance of the presented model, and the experimental results demonstrate that Gm-PLoc performs well for the multi-label protein subcellular localization.

MPMABP: A CNN and Bi-LSTM-Based Method for Predicting Multi-Activities of Bioactive Peptides

Bioactive peptides are typically small functional peptides with 2–20 amino acid residues and play versatile roles in metabolic and biological processes. Bioactive peptides are multi-functional, so it is vastly challenging to accurately detect all their functions simultaneously. We proposed a convolution neural network (CNN) and bi-directional long short-term memory (Bi-LSTM)-based deep learning method (called MPMABP) for recognizing multi-activities of bioactive peptides. The MPMABP stacked five CNNs at different scales, and used the residual network to preserve the information from loss. The empirical results showed that the MPMABP is superior to the state-of-the-art methods. Analysis on the distribution of amino acids indicated that the lysine preferred to appear in the anti-cancer peptide, the leucine in the anti-diabetic peptide, and the proline in the anti-hypertensive peptide. The method and analysis are beneficial to recognize multi-activities of bioactive peptides.

Identifying Functions of Proteins in Mice With Functional Embedding Features

In current biology, exploring the biological functions of proteins is important. Given the large number of proteins in some organisms, exploring their functions one by one through traditional experiments is impossible. Therefore, developing quick and reliable methods for identifying protein functions is necessary. Considerable accumulation of protein knowledge and recent developments on computer science provide an alternative way to complete this task, that is, designing computational methods. Several efforts have been made in this field. Most previous methods have adopted the protein sequence features or directly used the linkage from a protein–protein interaction (PPI) network. In this study, we proposed some novel multi-label classifiers, which adopted new embedding features to represent proteins. These features were derived from functional domains and a PPI network via word embedding and network embedding, respectively. The minimum redundancy maximum relevance method was used to assess the features, generating a feature list. Incremental feature selection, incorporating RAndom k-labELsets to construct multi-label classifiers, used such list to construct two optimum classifiers, corresponding to two key measurements: accuracy and exact match. These two classifiers had good performance, and they were superior to classifiers that used features extracted by traditional methods.

Identification of Type 2 Diabetes Biomarkers From Mixed Single-Cell Sequencing Data With Feature Selection Methods

Diabetes is the most common disease and a major threat to human health. Type 2 diabetes (T2D) makes up about 90% of all cases. With the development of high-throughput sequencing technologies, more and more fundamental pathogenesis of T2D at genetic and transcriptomic levels has been revealed. The recent single-cell sequencing can further reveal the cellular heterogenicity of complex diseases in an unprecedented way. With the expectation on the molecular essence of T2D across multiple cell types, we investigated the expression profiling of more than 1,600 single cells (949 cells from T2D patients and 651 cells from normal controls) and identified the differential expression profiling and characteristics at the transcriptomics level that can distinguish such two groups of cells at the single-cell level. The expression profile was analyzed by several machine learning algorithms, including Monte Carlo feature selection, support vector machine, and repeated incremental pruning to produce error reduction (RIPPER). On one hand, some T2D-associated genes (MTND4P24, MTND2P28, and LOC100128906) were discovered. On the other hand, we revealed novel potential pathogenic mechanisms in a rule manner. They are induced by newly recognized genes and neglected by traditional bulk sequencing techniques. Particularly, the newly identified T2D genes were shown to follow specific quantitative rules with diabetes prediction potentials, and such rules further indicated several potential functional crosstalks involved in T2D.

CNNLSTMac4CPred: A Hybrid Model for N4-Acetylcytidine Prediction

N4-Acetylcytidine (ac4C) is a highly conserved post-transcriptional and an extensively existing RNA modification, playing versatile roles in the cellular processes. Due to the limitation of techniques and knowledge, large-scale identification of ac4C is still a challenging task. RNA sequences are like sentences containing semantics in the natural language. Inspired by the semantics of language, we proposed a hybrid model for ac4C prediction. The model used long short-term memory and convolution neural network to extract the semantic features hidden in the sequences. The semantic and the two traditional features (k-nucleotide frequencies and pseudo tri-tuple nucleotide composition) were combined to represent ac4C or non-ac4C sequences. The eXtreme Gradient Boosting was used as the learning algorithm. Five-fold cross-validation over the training set consisting of 1160 ac4C and 10,855 non-ac4C sequences obtained the area under the receiver operating characteristic curve (AUROC) of 0.9004, and the independent test over 469 ac4C and 4343 non-ac4C sequences reached an AUROC of 0.8825. The model obtained a sensitivity of 0.6474 in the five-fold cross-validation and 0.6290 in the independent test, outperforming two state-of-the-art methods. The performance of semantic features alone was better than those of k-nucleotide frequencies and pseudo tri-tuple nucleotide composition, implying that ac4C sequences are of semantics. The proposed hybrid model was implemented into a user-friendly web-server which is freely available to scientific communities: http://47.113.117.61/ac4c/ . The presented model and tool are beneficial to identify ac4C on large scale.

Identification of protein functions in mouse with a label space partition method

Protein is very important for almost all living creatures because it participates in most complicated and essential biological processes. Determining the functions of given proteins is one of the most essential problems in protein science. Such determination can be conducted through traditional experiments. However, the experimental methods are always time-consuming and of high costs. In recent years, computational methods give useful aids for identification of protein functions. This study presented a new multi-label classifier for identifying functions of mouse proteins. Due to the number of functional types, which were termed as labels in the classification procedure, a label space partition method was employed to divide labels into some partitions. On each partition, a multi-label classifier was constructed. The classifiers based on all partitions were integrated in the proposed classifier. The cross-validation results proved that the proposed classifier was of good performance. Classifiers with label partition were superior to those without label partition or with random label partition.

Predicting RNA 5-Methylcytosine Sites by Using Essential Sequence Features and Distributions

Methylation is one of the most common and considerable modifications in biological systems mediated by multiple enzymes. Recent studies have shown that methylation has been widely identified in different RNA molecules. RNA methylation modifications have various kinds, such as 5-methylcytosine (m5C). However, for individual methylation sites, their functions still remain to be elucidated. Testing of all methylation sites relies heavily on high-throughput sequencing technology, which is expensive and labor consuming. Thus, computational prediction approaches could serve as a substitute. In this study, multiple machine learning models were used to predict possible RNA m5C sites on the basis of mRNA sequences in human and mouse. Each site was represented by several features derived from $k$ -mers of an RNA subsequence containing such site as center. The powerful max-relevance and min-redundancy (mRMR) feature selection method was employed to analyse these features. The outcome feature list was fed into incremental feature selection method, incorporating four classification algorithms, to build efficient models. Furthermore, the sites related to features used in the models were also investigated.