Great presentation from @gittacoaker.bsky.social on kinase mediated defense responses and harnessing the power of language models for receptor/ ligand prediction. These LMs will help us in engineering more resilient crops #2025ISMPMI
#2025ISMPMI đź“Ł In silico screening of PRR-epitope interactions is now possible!
Here, we developed mamp-ml to predict their immunogenic outcomes without structural context. Let's accelerate engineering plant receptors for robust resistance! 🚀🌱 Small 🧵
www.biorxiv.org/content/10.1...
While there's lots of work to be done, mamp-ml is a critical advancement in plant immunology for accelerating receptor-epitope characterization and engineering resistance. Mamp-ml is on Github and we implemented a version on Google Colab for easy use. Please check it out!
github.com/DanielleMSte...
An artificial intelligence tool developed by @microsoft.com researchers can predict the multiple conformational states of proteins in minutes with a fraction of the resources required by other techniques. cen.acs.org/biological-c... #chemsky 🧪
Finally, we also tested its ability to predict outcomes for convergently evolved receptors. SCORE, a csp22 receptor found in Citrus and relatives, was recently discovered by @brunongou.bsky.social. We preliminarily found mamp-ml can zero-shot predict immunogenic outcomes!
Mamp-ml was built upon two decades of foundational research. To generate the training data required, I manually pulled receptor and epitope sequences from every paper I could find, small or large. In total, we were able to capture over 1,300+ combinations across 11 receptors and 91 plant species.
Dani Stevens, Ph.D.
Dani Stevens, Ph.D.
Dani Stevens, Ph.D.
Dani Stevens, Ph.D.
Dani Stevens, Ph.D.
C&EN (Chemical & Engineering News)
We then generated a pipeline that combines AlphaFold2 and LRR-Annotation to precisely extract the LRR ectodomain as well as generated features to improve model training. This even includes tracking which residues interface with the ligand!
Compared to other state-of-the-art models such as AlphaFold3, mamp-ml can predict these outcomes with higher confidence, even when a solved structure is not available. We anticipate users can now screen for immunogenic outcomes of receptor-ligand variants before spending time and $$ in the lab.
Mamp-ml harnesses the power of protein language models (ESM-2) to build a classifier model for immunogenic outcomes.
Previously immunogenicity was primarily characterized in the lab but was a expensive bottleneck considering the variation captured computationally!
