4.7 Article

BERT2OME: Prediction of 2'-O-Methylation Modifications From RNA Sequence by Transformer Architecture Based on BERT

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Biochemical Research Methods

NmRF: identification of multispecies RNA 2′-O-methylation modification sites from RNA sequences

Chunyan Ao et al.

Summary: This study developed a predictor based on machine learning to identify 2'-O-methylation modification sites in RNA. The predictor showed high efficiency and accuracy in identifying modification sites across multiple species, outperforming existing tools.

BRIEFINGS IN BIOINFORMATICS (2022)

Article Biochemistry & Molecular Biology

Therapeutic target database update 2022: facilitating drug discovery with enriched comparative data of targeted agents

Ying Zhou et al.

Summary: Drug discovery relies not only on knowledge of drugs and targets, but also on understanding comparative agents and targets. This study introduces a major update to the Therapeutic Target Database, providing valuable data on poor binders, non-binders, prodrug-drug pairs, co-targets, and drug-like properties, as well as additional features for advanced search and cross-links to target structures. The database is accessible without login requirement at: https://idrblab.org/ttd/.

NUCLEIC ACIDS RESEARCH (2022)

Article Biotechnology & Applied Microbiology

ProbC: joint modeling of epigenome and transcriptome effects in 3D genome

Emre Sefer

Summary: The proposed probabilistic method ProbC accurately predicts and explains chromatin marks in Hi-C and Micro-C interactions, with histone modifications being more predictive than transcription factor binding sites, showing superiority across cell types and species.

BMC GENOMICS (2022)

Article Biochemical Research Methods

EMDLP: Ensemble multiscale deep learning model for RNA methylation site prediction

Honglei Wang et al.

Summary: This study presents an ensemble multiscale deep learning predictor (EMDLP) for identifying RNA methylation sites. By combining dilated convolution and Bidirectional LSTM (BiLSTM), EMDLP effectively utilizes both local and global information for site prediction. Experimental results show that EMDLP outperforms existing models and a user-friendly webserver is publicly available.

BMC BIOINFORMATICS (2022)

Article Computer Science, Artificial Intelligence

A Convolutional Neural Network Using Dinucleotide One-hot Encoder for identifying DNA N6-Methyladenine Sites in the Rice Genome

Zhibin Lv et al.

Summary: N6-methyladenine (m(6)A) is a crucial epigenetic modification related to the control of various DNA processes. The iRicem6A-CNN protocol, using machine learning, achieved high accuracy in identifying m(6)A sites in the rice genome, outperforming other predictors.

NEUROCOMPUTING (2021)

Article Biochemistry & Molecular Biology

RMDisease: a database of genetic variants that affect RNA modifications, with implications for epitranscriptome pathogenesis

Kunqi Chen et al.

Summary: Recent studies suggest a significant role of RNA modifications in biological mechanisms and disease progression. RMDisease is a database containing information on 202,307 human SNPs that may affect RNA modifications, with 4,289 disease-associated SNPs potentially playing a role in disease pathogenesis, along with essential post-transcriptional regulation information.

NUCLEIC ACIDS RESEARCH (2021)

Article Biochemical Research Methods

DNABERT: pre-trained Bidirectional Encoder Representations from Transformers model for DNA-language in genome

Yanrong Ji et al.

Summary: This study introduces a novel pre-trained bidirectional encoder representation called DNABERT for understanding genomic DNA sequences, showing superior performance in predicting genome-wide regulatory elements.

BIOINFORMATICS (2021)

Article Biochemical Research Methods

A transformer architecture based on BERT and 2D convolutional neural network to identify DNA enhancers from sequence information

Nguyen Quoc Khanh Le et al.

Summary: The study incorporated BERT-based multilingual model in bioinformatics to represent DNA sequence information, showing significant improvement in sensitivity, specificity, accuracy, and Matthews correlation coefficient for DNA enhancer prediction. Advanced experiments revealed the potential of deep learning, particularly through 2D CNN, in learning BERT features for biological modeling.

BRIEFINGS IN BIOINFORMATICS (2021)

Article Genetics & Heredity

Effects of DNA Methylation on TFs in Human Embryonic Stem Cells

Ximei Luo et al.

Summary: Research shows that TFs can bind to methylated DNA regions, especially in H1-hESC cells. Some TFs are sensitive to methylation, while others can bind to methylated DNA with different motifs. TF binding can interactively alter local DNA methylation.

FRONTIERS IN GENETICS (2021)

Article Biochemical Research Methods

STREME: accurate and versatile sequence motif discovery

Timothy L. Bailey

Summary: The STREME algorithm is a state-of-the-art tool for motif discovery, offering high accuracy and versatility in identifying motifs in large datasets, both short and long. It also provides a statistical estimate of the significance of each motif discovered, making it a valuable resource for bioinformatics analysis.

BIOINFORMATICS (2021)

Article Cell Biology

DeepOMe: A Web Server for the Prediction of 2′-O-Me Sites Based on the Hybrid CNN and BLSTM Architecture

Hongyu Li et al.

Summary: 2'-O-methylations play a crucial role in regulating gene expression, and a novel hybrid deep-learning algorithm named DeepOMe has been proposed to accurately predict 2'-O-Me sites in human transcriptome, showing high performance in cross-validation and outperforming existing methods.

FRONTIERS IN CELL AND DEVELOPMENTAL BIOLOGY (2021)

Article Biochemical Research Methods

EDLm6APred: ensemble deep learning approach for mRNA m6A site prediction

Lin Zhang et al.

Summary: This study focused on feature extraction and classification of m(6)A methylation sites using natural language processing methods, combining feature extraction and classification simultaneously, taking into account the upstream and downstream information of m(6)A sites. Different approaches like One-hot encoding, RNA word embedding, and Word2vec were used to represent the m(6)A sites from different perspectives. The BiLSTM model was employed to distinguish sequences with potential m(6)A sites, and an ensemble deep learning predictor (EDLm(6)APred) was constructed for m(6)A site prediction. The results showed that considering base, upstream, and downstream information is essential for effective m(6)A site detection.

BMC BIOINFORMATICS (2021)

Article Multidisciplinary Sciences

Attention-based multi-label neural networks for integrated prediction and interpretation of twelve widely occurring RNA modifications

Zitao Song et al.

Summary: Recent study introduces MultiRM, a method that predicts and interprets twelve common post-transcriptional RNA modifications simultaneously, revealing potential associations among different types of RNA modifications. This research offers a solution for detecting multiple RNA modifications and gaining a deeper understanding of the mechanisms behind sequence-based RNA modifications.

NATURE COMMUNICATIONS (2021)

Article Biochemical Research Methods

Metric Labeling and Semimetric Embedding for Protein Annotation Prediction

Emre Sefer et al.

Summary: Computational techniques have been used to predict protein function through Metric Labeling combinatorial optimization problem, showing superior performance in inferring function from networks and demonstrating the effectiveness of LSD minimization in converting heuristic distances to a metric.

JOURNAL OF COMPUTATIONAL BIOLOGY (2021)

Article Computer Science, Artificial Intelligence

DeepETC: A deep convolutional neural network architecture for investigating and classifying electron transport chain's complexes

Nguyen Quoc Khanh Le et al.

NEUROCOMPUTING (2020)

Article Biochemistry & Molecular Biology

VARIDT 1.0: variability of drug transporter database

Jiayi Yin et al.

NUCLEIC ACIDS RESEARCH (2020)

Article Biochemical Research Methods

iMRM: a platform for simultaneously identifying multiple kinds of RNA modifications

Kewei Liu et al.

BIOINFORMATICS (2020)

Article Biotechnology & Applied Microbiology

Identification of methylation states of DNA regions for Illumina methylation BeadChip

Ximei Luo et al.

BMC GENOMICS (2020)

Article Computer Science, Information Systems

DeepAVP: A Dual-Channel Deep Neural Network for Identifying Variable-Length Antiviral Peptides

Jiawei Li et al.

IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS (2020)

Review Biochemistry & Molecular Biology

Bioinformatics approaches for deciphering the epitranscriptome: Recent progress and emerging topics

Lian Liu et al.

COMPUTATIONAL AND STRUCTURAL BIOTECHNOLOGY JOURNAL (2020)

Article Biochemical Research Methods

Enhancer-5Step: Identifying enhancers using hidden information of DNA sequences via Chou's 5-step rule and word embedding

Nguyen Quoc Khanh Le et al.

ANALYTICAL BIOCHEMISTRY (2019)

Article Biochemical Research Methods

Modeling aspects of the language of life through transfer-learning protein sequences

Michael Heinzinger et al.

BMC BIOINFORMATICS (2019)

Article Biochemistry & Molecular Biology

RMBase v2.0: deciphering the map of RNA modifications from epitranscriptome sequencing data

Jia-Jia Xuan et al.

NUCLEIC ACIDS RESEARCH (2018)

Article Biochemical Research Methods

Prediction of potential disease-associated microRNAs using structural perturbation method

Xiangxiang Zeng et al.

BIOINFORMATICS (2018)

Article Biotechnology & Applied Microbiology

Imbalance learning for the prediction of N6-Methylation sites in mRNAs

Zhixun Zhao et al.

BMC GENOMICS (2018)

Article Biochemical Research Methods

iRNA-2OM: A Sequence-Based Predictor for Identifying 2′-O-Methylation Sites in Homo sapiens

Hui Yang et al.

JOURNAL OF COMPUTATIONAL BIOLOGY (2018)

Article Biochemistry & Molecular Biology

High-throughput single-base resolution mapping of RNA 2′-O-methylated residues

Danny Incarnato et al.

NUCLEIC ACIDS RESEARCH (2017)

Review Biotechnology & Applied Microbiology

Methods of MicroRNA Promoter Prediction and Transcription Factor Mediated Regulatory Network

Yuming Zhao et al.

BIOMED RESEARCH INTERNATIONAL (2017)

Article Biochemical Research Methods

Deconvolution of Ensemble Chromatin Interaction Data Reveals the Latent Mixing Structures in Cell Subpopulations

Emre Sefer et al.

JOURNAL OF COMPUTATIONAL BIOLOGY (2016)

Article Biochemistry & Molecular Biology

Transcriptome-wide mapping reveals reversible and dynamic N1-methyladenosine methylome

Xiaoyu Li et al.

NATURE CHEMICAL BIOLOGY (2016)

Article Biotechnology & Applied Microbiology

MicroRNA Promoter Identification in Arabidopsis Using Multiple Histone Markers

Yuming Zhao et al.

BIOMED RESEARCH INTERNATIONAL (2015)

Article Multidisciplinary Sciences

Continuous Distributed Representation of Biological Sequences for Deep Proteomics and Genomics

Ehsaneddin Asgari et al.

PLOS ONE (2015)

Article Computer Science, Information Systems

The CART decision tree for mining data streams

Leszek Rutkowski et al.

INFORMATION SCIENCES (2014)

Article Biochemistry & Molecular Biology

RTL-P: a sensitive approach for detecting sites of 2′-O-methylation in RNA molecules

Zhi-Wei Dong et al.

NUCLEIC ACIDS RESEARCH (2012)

Review Biochemistry & Molecular Biology

The expanding snoRNA world

JP Bachellerie et al.

BIOCHIMIE (2002)

Article Computer Science, Artificial Intelligence

Random forests

L Breiman

MACHINE LEARNING (2001)