MRCNN: a deep learning model for regression of genome-wide DNA methylation
Qi Tian, Jianxiao Zou, Jianxiong Tang, Yuan Fang, Zhongli Yu, Shicai Fan
BMC Genomics· 2019· article· cited by 51
importance 5/10
partially solved
Epigenetics and DNA Methylation epigenetics stage: research
Problem
Accurately predicting genome-wide DNA methylation levels is difficult; existing methods require many features or only handle hyper/hypomethylation.
Why it matters
DNA methylation modulates gene expression and is linked to cancer, so precise prediction aids basic research and drug development.
What the AI did
A convolutional neural network (MRCNN) performs methylation regression by minimizing a continuous loss function, improving prediction precision.
Results
Claimed more precise than state-of-the-art DeepCpG in evaluation; specific metrics not stated in source (abstract truncated).
Impact
Peer-reviewed model reported to outperform DeepCpG; cited 51 times.
Record
| Venue |
BMC Genomics
|
| Published |
2019
|
| Work type |
article
|
| Authors |
Qi Tian, Jianxiao Zou, Jianxiong Tang, Yuan Fang, Zhongli Yu, Shicai Fan
|
| Citations |
51 (OpenAlex, at import time)
|
| References |
27
|
| Model or method |
MRCNN (CNN-based)
|
| Organization |
not stated in source
|
| Primary source |
https://doi.org/10.1186/s12864-019-5488-5
|
| Open access |
gold
|
| Keywords |
DNA methylation, deep learning, CNN, epigenetics, DeepCpG, regression
|
Importance rating
5
/ 10
real but narrower advance
Genome-wide methylation prediction aids basic research and drug development; cancer link noted but impact is a research tool advance, no scale stated.
Basis: inferred.
Judged from the source text, which gives no explicit scale.
Stated scale: not stated in source. Method and limits.
More in Biology & Life Sciences
| # |
Paper |
Year |
Citations |
Importance |
| 1 |
AlphaFold Protein Structure Database: massively expanding the structural coverage of protein-sequence space with high-accuracy models
Mihály Váradi, Stephen Anyango, Mandar Deshpande, Sreenath Sasidharan...
|
2021 |
7,782 |
9
|
| 2 |
Evolutionary-scale prediction of atomic-level protein structure with a language model
Zeming Lin, Halil Akin, Roshan Rao, Brian Hie, Zhongkai Zhu, Wenting L...
|
2023 |
5,455 |
9
|
| 3 |
Accurate prediction of protein structures and interactions using a three-track neural network
Minkyung Baek, Frank DiMaio, Ivan V. Anishchenko, Justas Dauparas, Ser...
|
2021 |
5,468 |
9
|
| 4 |
De novo design of protein structure and function with RFdiffusion
Joseph L. Watson, David Juergens, Nathaniel R. Bennett, Brian L. Tripp...
|
2023 |
2,294 |
9
|
| 5 |
Structure Prediction and Computational Protein Design for Efficient Biocatalysts and Bioactive Proteins
Rebecca Buller, Jiřı́ Damborský, Donald Hilvert, Uwe T. Bornscheuer
|
2024 |
40 |
9
|