Dataset Information

A convolution based computational approach towards DNA N6-methyladenine site identification and motif extraction in rice genome.

ABSTRACT: DNA N6-methylation (6mA) in Adenine nucleotide is a post replication modification responsible for many biological functions. Automated and accurate computational methods can help to identify 6mA sites in long genomes saving significant time and money. Our study develops a convolutional neural network (CNN) based tool i6mA-CNN capable of identifying 6mA sites in the rice genome. Our model coordinates among multiple types of features such as PseAAC (Pseudo Amino Acid Composition) inspired customized feature vector, multiple one hot representations and dinucleotide physicochemical properties. It achieves auROC (area under Receiver Operating Characteristic curve) score of 0.98 with an overall accuracy of 93.97% using fivefold cross validation on benchmark dataset. Finally, we evaluate our model on three other plant genome 6mA site identification test datasets. Results suggest that our proposed tool is able to generalize its ability of 6mA site identification on plant genomes irrespective of plant species. An algorithm for potential motif extraction and a feature importance analysis procedure are two by products of this research. Web tool for this research can be found at: https://cutt.ly/dgp3QTR .

SUBMITTER: Rahman CR

PROVIDER: S-EPMC8121938 | biostudies-literature | 2021 May

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

A convolution based computational approach towards DNA N6-methyladenine site identification and motif extraction in rice genome.

Rahman Chowdhury Rafeed CR Amin Ruhul R Shatabda Swakkhar S Toaha Md Sadrul Islam MSI

Scientific reports 20210514 1

DNA N6-methylation (6mA) in Adenine nucleotide is a post replication modification responsible for many biological functions. Automated and accurate computational methods can help to identify 6mA sites in long genomes saving significant time and money. Our study develops a convolutional neural network (CNN) based tool i6mA-CNN capable of identifying 6mA sites in the rice genome. Our model coordinates among multiple types of features such as PseAAC (Pseudo Amino Acid Composition) inspired customiz ...[more]

PMID: 33990665

Similar Datasets

Project description:RNA N$^{6}$-methyladenosine (m$^{6}$A) is a critical epigenetic modification closely related to rice growth, development, and stress response. m$^{6}$A accurate identification, directly related to precision rice breeding and improvement, is fundamental to revealing phenotype regulatory and molecular mechanisms. Faced on rice m$^{6}$A variable-length sequence, to input into the model, the maximum length padding and label encoding usually adapt to obtain the max-length padded sequence for prediction. Although this can retain complete sequence information, resulting in sparse information and invalid padding, reducing feature extraction accuracy. Simultaneously, existing rice-specific m$^{6}$A prediction methods are still at an early stage. To address these issues, we develop a new end-to-end deep learning framework, MFDm$^{6}$ARice, for predicting rice m$^{6}$A sites. In particular, to alleviate sparseness, we construct a multi-kernel feature fusion module to mine essential information in max-length padded sequences by multi-kernel feature extraction function and effectively transfer information through global-local dynamic fusion function. Concurrently, considering the complexity and computational efficiency of high-dimensional features caused by invalid padding, we design a downsampling residual feature embedding module to optimize feature space compression and achieve accurate feature expression and efficient computational performance. Experiments show that MFDm$^{6}$ARice outperforms comparison methods in cross-validation, same- and cross-species independent test sets, demonstrating good robustness and generalization. The application on maize m$^{6}$A indicates the MFDm$^{6}$ARice's scalability. Further investigations have shown that combining different kernel features, focusing on global channel-local spatial, and employing reasonable downsampling and residual connections can improve feature representation and extraction, ensure effective information transfer, and significantly enhance model performance.

Project description:BackgroundIn recent years, the prevalence of Alzheimer's disease (AD) has increased, which places a great burden on society and families and creates considerable challenges for medical services. N6-methyladenine (m6A) deoxyribonucleic acid (DNA) adenine methylation is a novel biomarker and is abundant in the brain, but less common in AD. We support to analyze the relationship between DNA m6A and cognition in patients with AD and normal controls (NCs) in China.AimTo analyze the relationship between the novel m6A DNA and cognition in patients with AD and NCs in China.MethodsA total of 179 AD patients (mean age 71.60 ± 9.89 years; males: 91; females: 88) and 147 NCs (mean age 69.59 ± 11.22 years; males: 77; females: 70) who were age- and sex-matched were included in our study. All subjects underwent neuropsychological scale assessment and magnetic resonance imaging examination. Apolipoprotein E (APOE) genotypes were measured through agarose gel electrophoresis. Global m6A levels were evaluated by a MethylFlash m6A DNA Methylation ELISA Kit (colorimetric). Global m6A levels in total DNA from ten AD patients with 18F-AV-45 (florbetapir) positron emission tomography (PET) positivity and ten NCs with PET negativity were analyzed by dot blotting to determine the results.ResultsOur ELISA results showed that the global m6A DNA levels in peripheral blood were different between patients with AD and NCs (P = 0.002; < 0.05). And ten AD patients who were PET positive and ten NCs who were PET negative also showed the same results through dot blotting. There were significant differences between the two groups, which indicated that the leukocyte m6A DNA levels were different (P = 0.005; < 0.05). The m6A level was approximately 8.33% lower in AD patients than in NCs (mean 0.011 ± 0.006 vs 0.012 ± 0.005). A significant correlation was found between the Montreal Cognitive Assessment score and the peripheral blood m6A level in the tested population (r = 0.143, P = 0.01; < 0.05). However, no relationship was found with APOE ε4 (P = 0.633, > 0.05). Further studies should be performed to validate these findings.ConclusionOur results show that reduced global m6A DNA methylation levels are significantly lower in AD patients than in NCs by approximately 8.33% in China.

Dataset Information

A convolution based computational approach towards DNA N6-methyladenine site identification and motif extraction in rice genome.

Publications

A convolution based computational approach towards DNA N6-methyladenine site identification and motif extraction in rice genome.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets