The semantic segmentation of a brain tumor is of paramount importance for its treatment and prevention. Recently, researches have proposed various neural network-based architectures to improve the performance of segmentation of brain tumor sub-regions. Brain tumor segmentation, being a challenging area of research, requires improvement in its performance. This paper proposes a 2D image segmentation method, BU-Net, to contribute to brain tumor segmentation research. Residual extended skip (RES) and wide context (WC) are used along with the customized loss function in the baseline U-Net architecture. The modifications contribute by finding more diverse features, by increasing the valid receptive field. The contextual information is extracted with the aggregating features to get better segmentation performance. The proposed BU-Net was evaluated on the high-grade glioma (HGG) datasets of the BraTS2017 Challenge—the test datasets of the BraTS 2017 and 2018 Challenge datasets. Three major labels to segmented were tumor core (TC), whole tumor (WT), and enhancing core (EC). To compare the performance quantitatively, the dice score was utilized. The proposed BU-Net outperformed the existing state-of-the-art techniques. The high performing BU-Net can have a great contribution to researchers from the field of bioinformatics and medicine.

Efficient segmentation of Magnetic Resonance (MR) brain tumor images is of the utmost value for the diagnosis of tumor region. In recent years, advancement in the field of neural networks has been used to refine the segmentation performance of brain tumor sub-regions. The brain tumor segmentation has proven to be a complicated task even for neural networks, due to the small-scale tumor regions. These small-scale tumor regions are unable to be identified, the reason being their tiny size and the huge difference between area occupancy by different tumor classes. In previous state-of-the-art neural network models, the biggest problem was that the location information along with spatial details gets lost in deeper layers. To address these problems, we have proposed an encoder–decoder based model named BrainSeg-Net. The Feature Enhancer (FE) block is incorporated into the BrainSeg-Net architecture which extracts the middle-level features from low-level features from the shallow layers and shares them with the dense layers. This feature aggregation helps to achieve better performance of tumor identification. To address the problem associated with imbalance class, we have used a custom-designed loss function. For evaluation of BrainSeg-Net architecture, three benchmark datasets are utilized: BraTS2017, BraTS 2018, and BraTS 2019. Segmentation of Enhancing Core (EC), Whole Tumor (WT), and Tumor Core (TC) is carried out. The proposed architecture have exhibited good improvement when compared with existing baseline and state-of-the-art techniques. The MR brain tumor segmentation by BrainSeg-Net uses enhanced location and spatial features, which performs better than the existing plethora of brain MR image segmentation approaches.

N4-methylcytosine as one kind of modification of DNA has a critical role which alters genetic performance such as protein interactions, conformation, stability in DNA as well as the regulation of gene expression same cell developmental and genomic imprinting. Some different 4mC site identifiers have been proposed for various species. Herein, we proposed a computational model, DNC4mC-Deep, including six encoding techniques plus a deep learning model to predict 4mC sites in the genome of F. vesca, R. chinensis, and Cross-species dataset. It was demonstrated by the 10-fold cross-validation test to get superior performance. The DNC4mC-Deep obtained 0.829 and 0.929 of MCC on F. vesca and R. chinensis training dataset, respectively, and 0.814 on cross-species. This means the proposed method outperforms the state-of-the-art predictors at least 0.284 and 0.265 on F. vesca and R. chinensis training dataset in turn. Furthermore, the DNC4mC-Deep achieved 0.635 and 0.565 of MCC on F. vesca and R. chinensis independent dataset, respectively, and 0.562 on cross-species which shows it can achieve the best performance to predict 4mC sites as compared to the state-of-the-art predictor.

An important role is played by N6-methyladenosine (m6A) in RNA methylation modification. The modification information is crucially required for development in the field of medicine. Biochemical experiments for m6A identification have demonstrated high-quality results. However, this process is not a feasible solution due to its cost and time constraints. Recently, artificial intelligence has played a role to produce effective models which can be utilized for speedy and efficient identification of N6-methyladenosine sites. In consensus, a computational model named as m6A-NeuralTool is proposed in this study. The m6A-NeuralTool makes the final prediction for the identification of m6A sites by applying majority voting on three different sub-architectures. These sub-architectures uses a set of Convolution layers to extract the important features from the one-hot encoded input sequence. Further, one of the sub-architectures uses fully connected layers for the classification while the other two uses Support Vector Machine and Naive Bayes. The proposed m6A-NeuralTool is evaluated on four different species datasets using 10-fold cross-validation, where the proposed tool outperformed the existing state-of-art models for modification identification of m6A sites. When compared with existing models the proposed model increased the accuracy by 14.8%, 8.8%, 6.3%, and 4.9% for the datasets of Saccharomyces cerevisiae (S. cerevisiae), Arabidopsis thaliana (A. thaliana), Mus musculus (M. musculus) and Homo sapiens (H. sapiens) species respectively. The proposed model will allow the researchers from the field of bioinformatics and medicine to accurately identify the modification in m6A sites and use the information in the development of different products which would be beneficial for the community. The m6A-NeuralTool can be accessed freely at: http://nsclbio.jbnu.ac.kr/tools/m6A-NeuralTool/.

It is becoming increasingly clear that RNA 5-hydroxymethylcytosine (5hmC), which plays an important role in several biological processes, is one of the most important objects of study in the field of RNA epigenetics. Biochemical experiments using various sequencing-based technologies are capable of achieving high-throughput identification of 5hmC, but current methods are labor-intensive, costly, and time-consuming. There is an imperative need to develop more efficient and robust computational methods to replace, or at least complement, such high-throughput methods. Although one such machine learning-based model to achieve this has already been developed, its performance is limited. In this study, we developed iRhm5CNN, an efficient and reliable computational predictive model for the identification of RNA 5hmC sites. Our model is based on a convolution neural network (CNN) that extracts the most reliable feature from the RNA sequence inevitably. The results of our experiments show significant outperformance across all evaluation metrics of our proposed architecture when compared to the only existing state of the art computational model in all the evaluation metrics. The proposed model can be accessed for free at http://nsclbio.jbnu.ac.kr/tools/iRhm5CNN/.