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%.

A microRNA is a small noncoding RNA molecule, which functions in RNA silencing and posttranscriptional regulation of gene expression. To understand the mechanism of the activation of microRNA genes, the location of promoter regions driving their expression is required to be annotated precisely. Only a fraction of microRNA genes have confirmed transcription start sites (TSSs), which hinders our understanding of the transcription factor binding events. With the development of the next generation sequencing technology, the chromatin states can be inferred precisely by virtue of a combination of specific histone modifications. Using the genome-wide profiles of nine histone markers including H3K4me2, H3K4me3, H3K9Ac, H3K9me2, H3K18Ac, H3K27me1, H3K27me3, H3K36me2, and H3K36me3, we developed a computational strategy to identify the promoter regions of most microRNA genes inArabidopsis, based upon the assumption that the distribution of histone markers around the TSSs of microRNA genes is similar to the TSSs of protein coding genes. Among 298 miRNA genes, our model identified 42 independent miRNA TSSs and 132 miRNA TSSs, which are located in the promoters of upstream genes. The identification of promoters will provide better understanding of microRNA regulation and can play an important role in the study of diseases at genetic level.

MicroRNAs (miRNAs) are short (~22 nucleotides) noncoding RNAs and disseminated throughout the genome, either in the intergenic regions or in the intronic sequences of protein-coding genes. MiRNAs have been proved to play important roles in regulating gene expression. Hence, understanding the transcriptional mechanism of miRNA genes is a very critical step to uncover the whole regulatory network. A number of miRNA promoter prediction models have been proposed in the past decade. This review summarized several most popular miRNA promoter prediction models which used genome sequence features, or other features, for example, histone markers, RNA Pol II binding sites, and nucleosome-free regions, achieved by high-throughput sequencing data. Some databases were described as resources for miRNA promoter information. We then performed comprehensive discussion on prediction and identification of transcription factor mediated microRNA regulatory networks.

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.

Thermophilicity is a very important property of proteins, as it sometimes determines denaturation and cell death. Thus, methods for predicting thermophilic proteins and non-thermophilic proteins are of interest and can contribute to the design and engineering of proteins. In this article, we describe the use of feature dimension reduction technology and LIBSVM to identify thermophilic proteins. The highest accuracy obtained by cross-validation was 96.02% with 119 parameters. When using only 16 features, we obtained an accuracy of 93.33%. We discuss the importance of the different characteristics in identification and report a comparison of the performance of support vector machine to that of other methods.

Most essential functions are associated with various protein–protein interactions, particularly the cytokine–receptor interaction. Knowledge of the heterogeneous network of cytokine– receptor interactions provides insights into various human physiological functions. However, only a few studies are focused on the computational prediction of these interactions. In this study, we propose a novel machine-learning-based method for predicting cytokine–receptor interactions. A protein sequence is first transformed by incorporating the sequence evolutional information and then formulated with the following three aspects: (1) the k-skip-n-gram model, (2) physicochemical properties, and (3) local pseudo position-specific score matrix (local PsePSSM). The random forest classifier is subsequently employed to predict potential cytokine–receptor interactions. Experimental results on a dataset of Homo sapiens show that the proposed method exhibits improved performance, with 3.4% higher overall prediction accuracy, than existing methods.