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

iPADD: A Computational Tool for Predicting Potential Antidiabetic Drugs Using Machine Learning Algorithms

Diabetes mellitus is a chronic metabolic disease, which causes an imbalance in blood glucose homeostasis and further leads to severe complications. With the increasing population of diabetes, there is an urgent need to develop drugs to treat diabetes. The development of artificial intelligence provides a powerful tool for accelerating the discovery of antidiabetic drugs. This work aims to establish a predictor called iPADD for discovering potential antidiabetic drugs. In the predictor, we used four kinds of molecular fingerprints and their combinations to encode the drugs and then adopted minimum-redundancy-maximum-relevance (mRMR) combined with an incremental feature selection strategy to screen optimal features. Based on the optimal feature subset, eight machine learning algorithms were applied to train models by using 5-fold cross-validation. The best model could produce an accuracy (Acc) of 0.983 with the area under the receiver operating characteristic curve (auROC) value of 0.989 on an independent test set. To further validate the performance of iPADD, we selected 65 natural products for case analysis, including 13 natural products in clinical trials as positive samples and 52 natural products as negative samples. Except for abscisic acid, our model can give correct prediction results. Molecular docking illustrated that quercetin and resveratrol stably bound with the diabetes target NR1I2. These results are consistent with the model prediction results of iPADD, indicating that the machine learning model has a strong generalization ability. The source code of iPADD is available at https://github.com/llllxw/iPADD.

Integrating reduced amino acid composition into PSSM for improving copper ion-binding protein prediction

Copper ion-binding proteins play an essential role in metabolic processes and are critical factors in many diseases, such as breast cancer, lung cancer, and Menkes disease. Many algorithms have been developed for predicting metal ion classification and binding sites, but none have been applied to copper ion-binding proteins. In this study, we developed a copper ion-bound protein classifier, RPCIBP, which integrating the reduced amino acid composition into position-specific score matrix (PSSM). The reduced amino acid composition filters out a large number of useless evolutionary features, improving the operational efficiency and predictive ability of the model (feature dimension from 2900 to 200, ACC from 83 % to 85.1 %). Compared with the basic model using only three sequence feature extraction methods (ACC in training set between 73.8 %-86.2 %, ACC in test set between 69.3 %-87.5 %), the model integrating the evolutionary features of the reduced amino acid composition showed higher accuracy and robustness (ACC in training set between 83.1 %-90.8 %, ACC in test set between 79.1 %-91.9 %). Best copper ion-binding protein classifiers filtered by feature selection progress were deployed in a user-friendly web server (http://bioinfor.imu.edu.cn/RPCIBP). RPCIBP can accurately predict copper ion-binding proteins, which is convenient for further structural and functional studies, and conducive to mechanism exploration and target drug development.

Fast and Efficient Design of Deep Neural Networks for Predicting N7-Methylguanosine Sites Using autoBioSeqpy

N⁷-Methylguanosine (m⁷G) is a crucial post-transcriptional RNA modification that plays a pivotal role in regulating gene expression. Accurately identifying m⁷G sites is a fundamental step in understanding the biological functions and regulatory mechanisms associated with this modification. While whole-genome sequencing is the gold standard for RNA modification site detection, it is a time-consuming, expensive, and intricate process. Recently, computational approaches, especially deep learning (DL) techniques, have gained popularity in achieving this objective. Convolutional neural networks and recurrent neural networks are examples of DL algorithms that have emerged as versatile tools for modeling biological sequence data. However, developing an efficient network architecture with superior performance remains a challenging task, requiring significant expertise, time, and effort. To address this, we previously introduced a tool called autoBioSeqpy, which streamlines the design and implementation of DL networks for biological sequence classification. In this study, we utilized autoBioSeqpy to develop, train, evaluate, and fine-tune sequence-level DL models for predicting m⁷G sites. We provided detailed descriptions of these models, along with a step-by-step guide on their execution. The same methodology can be applied to other systems dealing with similar biological questions. The benchmark data and code utilized in this study can be accessed for free at http://github.com/jingry/autoBioSeeqpy/tree/2.0/examples/m7G.

i2OM: Toward a better prediction of 2'-O-methylation in human RNA

2'-O-methylation (2OM) is an omnipresent post-transcriptional modification in RNAs. It is important for the regulation of RNA stability, mRNA splicing and translation, as well as innate immunity. With the increase in publicly available 2OM data, several computational tools have been developed for the identification of 2OM sites in human RNA. Unfortunately, these tools suffer from the low discriminative power of redundant features, unreasonable dataset construction or overfitting. To address those issues, based on four types of 2OM (2OM-adenine (A), cytosine (C), guanine (G), and uracil (U)) data, we developed a two-step feature selection model to identify 2OM. For each type, the one-way analysis of variance (ANOVA) combined with mutual information (MI) was proposed to rank sequence features for obtaining the optimal feature subset. Subsequently, four predictors based on eXtreme Gradient Boosting (XGBoost) or support vector machine (SVM) were presented to identify the four types of 2OM sites. Finally, the proposed model could produce an overall accuracy of 84.3 % on the independent set. To provide a convenience for users, an online tool called i2OM was constructed and can be freely access at i2om.lin-group.cn. The predictor may provide a reference for the study of the 2OM.

iRNA-ac4C: A novel computational method for effectively detecting N4-acetylcytidine sites in human mRNA

RNA N4-acetylcytidine (ac4C) is the acetylation of cytidine at the nitrogen-4 position, which is a highly conserved RNA modification and involves a variety of biological processes. Hence, accurate identification of genome-wide ac4C sites is vital for understanding regulation mechanism of gene expression. In this work, a novel predictor, named iRNA-ac4C, was established to identify ac4C sites in human mRNA based on three feature extraction methods, including nucleotide composition, nucleotide chemical property, and accumulated nucleotide frequency. Subsequently, minimum-Redundancy-Maximum-Relevance combined with incremental feature selection strategies was utilized to select the optimal feature subset. According to the optimal feature subset, the best ac4C classification model was trained by gradient boosting decision tree with 10-fold cross-validation. The results of independent testing set indicated that our proposed method could produce encouraging generalization capabilities. For the convenience of other researchers, we established a user-friendly web server which is freely available at http://lin-group.cn/server/iRNA-ac4C/. We hope that the tool could provide guide for wet-experimental scholars.

An Effective Deep Learning-Based Architecture for Prediction of N7-Methylguanosine Sites in Health Systems

N7-methylguanosine (m7G) is one of the most important epigenetic modifications found in rRNA, mRNA, and tRNA, and performs a promising role in gene expression regulation. Owing to its significance, well-equipped traditional laboratory-based techniques have been performed for the identification of N7-methylguanosine (m7G). Consequently, these approaches were found to be time-consuming and cost-ineffective. To move on from these traditional approaches to predict N7-methylguanosine sites with high precision, the concept of artificial intelligence has been adopted. In this study, an intelligent computational model called N7-methylguanosine-Long short-term memory (m7G-LSTM) is introduced for the prediction of N7-methylguanosine sites. One-hot encoding and word2vec feature schemes are used to express the biological sequences while the LSTM and CNN algorithms have been employed for classification. The proposed “m7G-LSTM” model obtained an accuracy value of 95.95%, a specificity value of 95.94%, a sensitivity value of 95.97%, and Matthew’s correlation coefficient (MCC) value of 0.919. The proposed predictive m7G-LSTM model has significantly achieved better outcomes than previous models in terms of all evaluation parameters. The proposed m7G-LSTM computational system aims to support the drug industry and help researchers in the fields of bioinformatics to enhance innovation for the prediction of the behavior of N7-methylguanosine sites.

i5hmCVec: Identifying 5-Hydroxymethylcytosine Sites of Drosophila RNA Using Sequence Feature Embeddings

5-Hydroxymethylcytosine (5hmC), one of the most important RNA modifications, plays an important role in many biological processes. Accurately identifying RNA modification sites helps understand the function of RNA modification. In this work, we propose a computational method for identifying 5hmC-modified regions using machine learning algorithms. We applied a sequence feature embedding method based on the dna2vec algorithm to represent the RNA sequence. The results showed that the performance of our model is better that of than state-of-art methods. All dataset and source codes used in this study are available at: https://github.com/liu-h-y/5hmC_model.

Detection of transcription factors binding to methylated DNA by deep recurrent neural network

Transcription factors (TFs) are proteins specifically involved in gene expression regulation. It is generally accepted in epigenetics that methylated nucleotides could prevent the TFs from binding to DNA fragments. However, recent studies have confirmed that some TFs have capability to interact with methylated DNA fragments to further regulate gene expression. Although biochemical experiments could recognize TFs binding to methylated DNA sequences, these wet experimental methods are time-consuming and expensive. Machine learning methods provide a good choice for quickly identifying these TFs without experimental materials. Thus, this study aims to design a robust predictor to detect methylated DNA-bound TFs. We firstly proposed using tripeptide word vector feature to formulate protein samples. Subsequently, based on recurrent neural network with long short-term memory, a two-step computational model was designed. The first step predictor was utilized to discriminate transcription factors from non-transcription factors. Once proteins were predicted as TFs, the second step predictor was employed to judge whether the TFs can bind to methylated DNA. Through the independent dataset test, the accuracies of the first step and the second step are 86.63% and 73.59%, respectively. In addition, the statistical analysis of the distribution of tripeptides in training samples showed that the position and number of some tripeptides in the sequence could affect the binding of TFs to methylated DNA. Finally, on the basis of our model, a free web server was established based on the proposed model, which can be available at https://bioinfor.nefu.edu.cn/TFPM/.

Identifying N7-methylguanosine sites by integrating multiple features

Recent studies reported that N7-methylguanosine (m7G) plays a vital role in gene expression regulation. As a consequence, determining the distribution of m7G is a crucial step towards further understanding its biological functions. Although biological experimental approaches are capable of accurately locating m7G sites, they are labor-intensive, costly, and time-consuming. Therefore, it is necessary to develop more effective and robust computational methods to replace, or at least complement current experimental methods. In this study, we developed a novel sequence-based computational tool to identify RNA m7G sites. In this model, 22 kinds of dinucleotide physicochemical (PC) properties were employed to encode the RNA sequence. Three types of descriptors, including auto-covariance, cross-covariance, and discrete wavelet transform were adopted to extract effective features from the PC matrix. The least absolute shrinkage and selection operator (LASSO) algorithm was utilized to reduce the influence of irrelevant or redundant features. Finally, these selected features were fed into a support vector machine (SVM) for distinguishing m7G from non-m7G sites. The proposed method significantly outperforms existing predictors across all evaluation metrics. It indicates that the approach is effective in identifying RNA m7G sites.

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.

Machine learning applications in RNA modification sites prediction

Ribonucleic acid (RNA) modifications are post-transcriptional chemical composition changes that have a fundamental role in regulating the main aspect of RNA function. Recently, large datasets have become available thanks to the recent development in deep sequencing and large-scale profiling. This availability of transcriptomic datasets has led to increased use of machine learning based approaches in epitranscriptomics, particularly in identifying RNA modifications. In this review, we comprehensively explore machine learning based approaches used for the prediction of 11 RNA modification types, namely,m 1 A ,m 6 A ,m 5 C , 5 hmC , ψ , 2 ' - O - Me , ac 4 C ,m 7 G , A - to - I ,m 2 G , and D . This review covers the life cycle of machine learning methods to predict RNA modification sites including available benchmark datasets, feature extraction, and classification algorithms. We compare available methods in terms of datasets, target species, approach, and accuracy for each RNA modification type. Finally, we discuss the advantages and limitations of the reviewed approaches and suggest future perspectives.

The impact of gene-body H3K36me3 patterns on gene expression level changes in chronic myelogenous leukemia

Chronic myelogenous leukemia (CML) is a malignant clonal disease of hematopoietic stem cells. Researches have exhibited that the progression of CML is related to histone modifications. Here, we perform the systematic analyses of H3K36me3 patterns and gene expression level changes. We observe that the genes with higher gene-body H3K36me3 levels in normal cells show fewer expression changes during leukemogenesis, while the genes with lower gene-body H3K36me3 levels in normal cells yield obvious expression changes during leukemogenesis (ρ = -0.98, P = 9.30 × 10^-8). These findings are conserved in human lung/breast cancers and mouse CML, regardless of gene expression levels and gene lengths. Regulatory element analysis and Random Forest regression display that Hoxd13, Rara, Scl, Smad3, Smad4 and Tgif1 induce the up-regulation of genes with lower H3K36me3 levels (ρ = 0.97, P = 2.35 × 10^-56). Enrichment analysis shows that the differentially expressed genes with lower H3K36me3 levels are involved in leukemia-related pathways, such as leukocyte migration and regulation of leukocyte activation. Finally, six driver genes (Tp53, Wt1, Dnmt3a, Cacna1b, Phactr1 and Gbp4) with lower H3K36me3 levels are identified. Our analyses indicate that lower gene-body H3K36me3 levels may serve as a biomarker for the progression of CML.

Identification of cyclin protein using gradient boost decision tree algorithm

Cyclin proteins are capable to regulate the cell cycle by forming a complex with cyclin-dependent kinases to activate cell cycle. Correct recognition of cyclin proteins could provide key clues for studying their functions. However, their sequences share low similarity, which results in poor prediction for sequence similarity-based methods. Thus, it is urgent to construct a machine learning model to identify cyclin proteins. This study aimed to develop a computational model to discriminate cyclin proteins from non-cyclin proteins. In our model, protein sequences were encoded by seven kinds of features that are amino acid composition, composition of k-spaced amino acid pairs, tri peptide composition, pseudo amino acid composition, geary correlation, normalized moreau-broto autocorrelation and composition/transition/distribution. Afterward, these features were optimized by using analysis of variance (ANOVA) and minimum redundancy maximum relevance (mRMR) with incremental feature selection (IFS) technique. A gradient boost decision tree (GBDT) classifier was trained on the optimal features. Five-fold cross-validated results showed that our model would identify cyclins with an accuracy of 93.06% and AUC value of 0.971, which are higher than the two recent studies on the same data.

Detection of circRNA Biomarker for Acute Myocardial Infarction Based on System Biological Analysis of RNA Expression

Acute myocardial infarction (AMI) is myocardial necrosis caused by the persistent interruption of myocardial blood supply, which has high incidence rate and high mortality in middle-aged and elderly people in the worldwide. Biomarkers play an important role in the early diagnosis and treatment of AMI. Recently, more and more researches confirmed that circRNA may be a potential diagnostic biomarker and therapeutic target for cardiovascular diseases. In this paper, a series of biological analyses were performed to find new effective circRNA biomarkers for AMI. Firstly, the expression levels of circRNAs in blood samples of patients with AMI and those with mild coronary stenosis were compared to reveal circRNAs which were involved in AMI. Then, circRNAs which were significant expressed abnormally in the blood samples of patients with AMI were selected from those circRNAs. Next, a ceRNA network was constructed based on interactions of circRNA, miRNA and mRNA through biological analyses to detect crucial circRNA associated with AMI. Finally, one circRNA was selected as candidate biomarker for AMI. To validate effectivity and efficiency of the candidate biomarker, fluorescence in situ hybridization, hypoxia model of human cardiomyocytes, and knockdown and overexpression analyses were performed on candidate circRNA biomarker. In conclusion, experimental results demonstrated that the candidate circRNA was an effective biomarker for diagnosis and therapy of AMI.

The Regulation of RNA Modification Systems: The Next Frontier in Epitranscriptomics?

RNA modifications, long considered to be molecular curiosities embellishing just abundant and non-coding RNAs, have now moved into the focus of both academic and applied research. Dedicated research efforts (epitranscriptomics) aim at deciphering the underlying principles by determining RNA modification landscapes and investigating the molecular mechanisms that establish, interpret and modulate the information potential of RNA beyond the combination of four canonical nucleotides. This has resulted in mapping various epitranscriptomes at high resolution and in cataloguing the effects caused by aberrant RNA modification circuitry. While the scope of the obtained insights has been complex and exciting, most of current epitranscriptomics appears to be stuck in the process of producing data, with very few efforts to disentangle cause from consequence when studying a specific RNA modification system. This article discusses various knowledge gaps in this field with the aim to raise one specific question: how are the enzymes regulated that dynamically install and modify RNA modifications? Furthermore, various technologies will be highlighted whose development and use might allow identifying specific and context-dependent regulators of epitranscriptomic mechanisms. Given the complexity of individual epitranscriptomes, determining their regulatory principles will become crucially important, especially when aiming at modifying specific aspects of an epitranscriptome both for experimental and, potentially, therapeutic purposes.

IHEC_RAAC: a online platform for identifying human enzyme classes via reduced amino acid cluster strategy

Enzymes have been proven to play considerable roles in disease diagnosis and biological functions. The feature extraction that truly reflects the intrinsic properties of protein is the most critical step for the automatic identification of enzymes. Although lots of feature extraction methods have been proposed, some challenges remain. In this study, we developed a predictor called IHEC_RAAC, which has the capability to identify whether a protein is a human enzyme and distinguish the function of the human enzyme. To improve the feature representation ability, protein sequences were encoded by a new feature-vector called 'reduced amino acid cluster'. We calculated 673 amino acid reduction alphabets to determine the optimal feature representative scheme. The tenfold cross-validation test showed that the accuracy of IHEC_RAAC to identify human enzymes was 74.66% and further discriminate the human enzyme classes with an accuracy of 54.78%, which was 2.06% and 8.68% higher than the state-of-the-art predictors, respectively. Additionally, the results from the independent dataset indicated that IHEC_RAAC can effectively predict human enzymes and human enzyme classes to further provide guidance for protein research. A user-friendly web server, IHEC_RAAC, is freely accessible at http://bioinfor.imu.edu.cn/ihecraac .

Screening of Prospective Plant Compounds as H1R and CL1R Inhibitors and Its Antiallergic Efficacy through Molecular Docking Approach

Allergens have the ability to enter the body and cause illness. Leukotriene is the widespread allergen which could stimulate mast cells to discharge histamine which causes allergy symptoms. An effective strategy for treating leukotriene-induced allergy is to find the inhibitors of leukotriene or histamine activity from phytochemicals. For this purpose, a library of 8,500 phytochemicals was generated using MOE software. The structures of histamine-1 receptor and cysteinyl leukotriene receptor-1 were predicted by the homology modeling method through the SWISS model. The phytochemicals were docked with predicted structures of histamine-1 and cysteinyl leukotriene receptor-1 in MOE software to determine the binding affinity of the phytochemicals against the targets. Moreover, chemoinformatics properties and ADMET of phytochemicals were assessed to find the drug likeness behavior of compounds. Compound ID 10054216 has the lowest $S$ -score value for H-1 receptor that is -18.9186 kcal/mol which is lower than the value of standard -15.167 kcal/mol. The other compounds 393471, 71448939, 10722577, and 442614 also showed good $S$ -score values than the standard. Moreover, compound ID 11843082 has the lowest $S$ -score value for CL1R that is -15.481 kcal/mol which is lower than the value of standard -12.453 kcal/mol. The other compounds 72284, 5282102, 66559251, and 102506430 also showed good $S$ -score values than the standard. In this research article, we performed molecular docking to find the best inhibitors against H1R and CL1R and their antiallergic efficacy. This in silico knowledge will be helpful in near future for the design of novel, safe, and less costing H-1 receptor and CL1R inhibitors with the aim to improve human life quality.

Identification and Classification of Enhancers Using Dimension Reduction Technique and Recurrent Neural Network

Enhancers are noncoding fragments in DNA sequences, which play an important role in gene transcription and translation. However, due to their high free scattering and positional variability, the identification and classification of enhancers have a higher level of complexity than those of coding genes. In order to solve this problem, many computer studies have been carried out in this field, but there are still some deficiencies in these prediction models. In this paper, we use various feature extraction strategies, dimension reduction technology, and a comprehensive application of machine model and recurrent neural network model to achieve an accurate prediction of enhancer identification and classification with the accuracy of was 76.7% and 84.9%, respectively. The model proposed in this paper is superior to the previous methods in performance index or feature dimension, which provides inspiration for the prediction of enhancers by computer technology in the future.

Identifying Heat Shock Protein Families from Imbalanced Data by Using Combined Features

Heat shock proteins (HSPs) are ubiquitous in living organisms. HSPs are an essential component for cell growth and survival; the main function of HSPs is controlling the folding and unfolding process of proteins. According to molecular function and mass, HSPs are categorized into six different families: HSP20 (small HSPS), HSP40 (J-proteins), HSP60, HSP70, HSP90, and HSP100. In this paper, improved methods for HSP prediction are proposed—the split amino acid composition (SAAC), the dipeptide composition (DC), the conjoint triad feature (CTF), and the pseudoaverage chemical shift (PseACS) were selected to predict the HSPs with a support vector machine (SVM). In order to overcome the imbalance data classification problems, the syntactic minority oversampling technique (SMOTE) was used to balance the dataset. The overall accuracy was 99.72% with a balanced dataset in the jackknife test by using the optimized combination feature SAAC+DC+CTF+PseACS, which was 4.81% higher than the imbalanced dataset with the same combination feature. The Sn, Sp, Acc, and MCC of HSP families in our predictive model were higher than those in existing methods. This improved method may be helpful for protein function prediction.