RNAcentral release 23 is now live! Check it out at We’ve got quite a few new things to show you, so here’s a short thread: 1/8.

RT @EMBLEBIjobs: 🚨 @emblebi is hiring a Project Leader to shape the future of RNA resources! Lead RNAcentral & Rfam, collaborate with globa….

12/12 Big thanks to our co-authors @AntonIPetrov, @nanoNancy, @Alexbateman1, @blake_a_sweeney and others! Read the full paper here: #bioinformatics #LLM #AI.

11/12 But overall, this shows that with careful prompting and checking, LLMs can help address the curation bottleneck in bioinformatics! 🎯.

10/12 Some limitations: We can only use open-access papers (highlighting the importance of #OpenAccess!), and LLMs sometimes struggle with complex information synthesis.

9/12 We've also made our entire dataset of contexts and summaries available:

8/12 Want to try it yourself? Search for RNAs with summaries at:

7/12 All summaries are now available through @RNAcentral - making it easier than ever to quickly understand what we know about specific RNAs.

6/12 The results? We generated >4,600 summaries covering ~28,700 RNA transcripts! Expert evaluation showed 94% were rated good or excellent quality. 📈.

5/12 The key innovation is our multi-stage checking system:.- Reference validation.- Automated fact-checking.- Self-consistency verification This helps ensure accuracy and proper attribution.

4/12 Our solution: Use GPT-4 with carefully designed prompts to read scientific papers and generate accurate summaries, complete with proper citations! 📷.

3/12 Non-coding RNAs face a particularly acute curation gap. Most databases lack good summaries of what each RNA does, making it harder for researchers to quickly understand their function.

2/12 Why did we build this? Curation of scientific literature is becoming increasingly challenging. There’s a growing gap between publication rates and the number of available curators.

1/12 Excited to share our new paper in @OxfordJournals DATABASE on LitSumm - our system that uses large language models to automatically generate high-quality literature summaries for non-coding RNAs! 🧬📚.

RT @EMBLEBIjobs: 🚀 We're hiring a Full Stack Software Developer for the RNA Resources team! Work with cutting-edge tech (Django, React, Kub….

7/ 💬 We want to hear from you! If you have any feedback or questions, reach out via email, Twitter, or GitHub. Your input helps us continually improve RNAcentral for the RNA research community. #RNAcentral #RNAresearch #bioinformatics.

6/ 🗂️ We've updated data from Ensembl, FlyBase, GeneCards, lncRNAdb, MalaCards, Rfam, RefSeq, and more. As always, all data is freely available on our website, API, database, and FTP archive.

5/ 🤖 LitSumm, which generates ncRNA gene summaries, has been upgraded to GPT-4 for even better results. Explore the summaries and watch for API access coming soon!.

4/ 📄 LitScan, our text mining tool, now covers 1.1 million papers associated with 2.5 million RNA sequences. It also actively monitors and removes retracted articles to keep results up-to-date.

3/ 🔍 Our improved taxonomic search makes it a breeze to find sequences of interest, including subspecies. For example, search for all E. coli and subspecies sequences with a single click!.

2/ 🦠 The tmRNA Website has undergone a major overhaul, with 96,670 extensively annotated sequences now hosted at RNAcentral. Easily find tmRNAs using the expert_db:"tmRNA Website" search.