←
RNAcentral652 posts
RNAcentral avatar

RNAcentral

@RNAcentral

The non-coding RNA sequence database providing unified access to a comprehensive and up-to-date set of non-coding RNAs

◷ Joined May 2014▧ 94 Photos and videos
Pedro Madrigal avatar
⟳ RNAcentral retweeted
Pedro Madrigal@compBiology·Nov 7

Great to see @RNAcentral and @RfamDB used in structRFM, a structure-guided RNA foundation model in @Nature: RNAcentral sequences for pre-training, and Rfam families for benchmarking and generalisation tests. Congratulations to the authors! nature.com/articles/s41586-0… #RNA #AI

Andrew Green avatar
⟳ RNAcentral retweeted
Andrew Green@afg1781·Jan 7

1/9 🧵 Excited to share our latest paper: GOFlowLLM - Curating miRNA literature with Large Language Models and flowcharts. Read the full paper here: doi.org/10.1093/bioinformati… or highlights below!

RNAcentral avatar
RNAcentral@RNAcentral·Jan 5

Major structural change: RNAcentral now groups related transcripts into gene-level entries! Using ML + graph clustering, we built 103,814 human ncRNA genes from 600,225 transcripts. Better reflects biology and enables comparative analyses.

RNAcentral avatar
RNAcentral@RNAcentral·Jan 5

LitSumm uses GPT-4 to generate functional summaries from scientific literature. Currently covers ~4,600 human ncRNAs prioritized by community interest. See AI-powered summaries on any sequence page! Link to LitSumm paper: doi.org/10.1093/database/baa…

RNAcentral avatar
RNAcentral@RNAcentral·Jan 5

RNAcentral has grown to 45M ncRNA sequences, now includes 52 expert databases, including 10 new databases and major updates to existing sources 📈

RNAcentral avatar
RNAcentral@RNAcentral·8 Oct 2025

Gene identifiers will be stable across releases, even as new transcripts are added. Each gene gets metadata including RNA type and description from expert databases. Find genes via text search, sequence pages, or download them in our GFF files.

RNAcentral avatar
RNAcentral@RNAcentral·8 Oct 2025

We built 103,814 human ncRNA genes from 600,225 transcripts using machine learning + graph clustering. The pipeline was trained on Ensembl/GENCODE data and achieved 99.4% accuracy. Most genes are lncRNAs (65,187), followed by antisense lncRNAs (16,790) and pre-miRNAs (8,560).