Lei Wang (@wanglei-hust) Bsky

MetaFold-RNA: Accurate prediction of RNA secondary structure using a meta-learning-guided deep network Accurately predicting the secondary structure of ribonucleic acid (RNA) is a critical step toward deciphering its biological roles and engineering novel RNA-based technologies. However, achieving high...

MetaFold-RNA: Accurate prediction of RNA secondary structure using a meta-learning-guided deep network www.biorxiv.org/content/10.1...

7 months ago 2 0 0 0

I’d be happy to help with screening—background in bioinformatics, and I really appreciate what bioRxiv is doing. Let me know if I can assist!

8 months ago 1 0 0 0

Excited to re-share work from
@yoakiyama.bsky.social and Zhidian Zhang on MSA pairformer. (1/4)

8 months ago 26 5 1 0

GitHub - microsoft/dayhoff Contribute to microsoft/dayhoff development by creating an account on GitHub.

Our models, code, and data are openly available on Github, Zenodo, and Huggingface.

github.com/microsoft/da...
huggingface.co/collections/...
zenodo.org/records/1526...

8 months ago 3 2 1 0

This is the unfriendly aspect of the Nature series journal submission system. There is no information.

9 months ago 0 0 0 0

Help needed: submitted a manuscript to Nature Methods, and although I received a notification that it was rejected, I never received a formal decision letter. Has anyone experienced something similar? Any suggestions on how to phrase it? 🙏

#ManuscriptSubmission #NatureMethods

9 months ago 0 0 1 0

SSAlign: Ultrafast and Sensitive Protein Structure Search at Scale www.biorxiv.org/content/10.1101/2025.07....

9 months ago 5 2 0 0

We honestly didn't check for prior work before choosing the name, and we apologize for the oversight. Just to be clear, our tool is entirely different from the other 'SSAlign', but we understand this will cause confusion. We are now looking into the possibility of changing the name.🤣

9 months ago 0 0 1 0

SSAlign: Ultrafast and Sensitive Protein Structure Search at Scale The advent of highly accurate structure prediction techniques such as AlphaFold3 is driving an unprecedented expansion of protein structure databases. This rapid growth creates an urgent demand for novel search tools, as even the current fastest available methods like Foldseek face significant limitations in sensitivity and scalability when confronted with these massive repositories. To meet this challenge, we have developed SSAlign, a protein structure retrieval tool that leverages protein language models to jointly encode sequence and structural information, and adopts a two-stage alignment strategy optimized with multi-GPU and multi-process parallelization. On large-scale datasets such as AFDB50, SSAlign outpaces Foldseek by two to three orders of magnitude in search speed, offering unmatched scalability for high-throughput structural analysis. Compared to Foldseek, SSAlign retrieves substantially more high-quality matches on Swiss-Prot and achieves marked performance improvements on SCOPe40, with relative AUC increases of +20.2% at the family level and +33.3% at the superfamily level, demonstrating significantly enhanced sensitivity and recall. In sum, SSAlign achieves TM-align-comparable accuracy with Foldseek-surpassing speed and coverage, offering an efficient, sensitive, and scalable solution for large-scale structural biology and structure-based drug discovery. ### Competing Interest Statement The authors have declared no competing interest. National Natural Science Foundation of China, 62172172 Hubei Provincial Natural Science Foundation of China, 2025AFB159 The Postdoctoral Fellowship Program of CPSF, GZC20240545

"SSAlign, a protein structure retrieval tool that leverages protein language models to jointly encode sequence and structural information...On large-scale datasets such as AFDB50, SSAlign outpaces Foldseek by two to three orders of magnitude in search speed"

www.biorxiv.org/content/10.1...

9 months ago 33 12 2 0

Posts by Lei Wang