Sign in

Dani Stevens, Ph.D.

@danimstevens.bsky.social
946 followers 558 following 19 posts

Plant Immunologist x Machine Learning, occasional biochemist | 🌱-🧫 interactions | UC Berkeley Postdoc | 2 x USDA NIFA Fellow

PostsRepliesMedia
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/09/2025
100% agree. Especially with how much money is spent a year toward pub fees (10-30K+) that could go to other career opportunities. Plus, I can get high quality reviews from peers without a formal journal system. Sadly as a postdoc, I feel like my hands are tied, but I would love to help the cause.
042
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/09/2025
Many times, we come back to traditional journals in the end because like NIH grants, preprints don't hold the same weight/merit in trainee fellowships, tenure process, etc. It is still a challenge, though I'd like to think that if established groups move away from trad pubs, others will follow.
110
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/09/2025
Yes, @kseniakrasileva.bsky.social have moved to an increasingly open science model where we not only preprint early, sometimes far before journal submission, but even make datasets open before preprinting (wheat genome example: zenodo.org/records/1021...). We welcome feedback from our community.
zenodo.org
Chromosome-level genome assembly of Triticum turgidum var 'Kronos'
This data is made available under the Toronto Agreement. All of the data listed here is available under the prepublication data sharing principle of the Toronto agreement (1). By using this data, you ...
1103
Dani Stevens, Ph.D. @danimstevens.bsky.social · 18/08/2025
Sweet! Those look beautiful. I wish sharing pymol/chimeraX scripts were as common as other computational work and languages.
030
Dani Stevens, Ph.D. @danimstevens.bsky.social · 26/07/2025
This is quite interesting, especially since myself and others have found the opposite (ROS, no MAPK)! If I were to $$ on it, my guess is the binding interaction in-complex is causing different PTM modifications on the kinase domain, leading to a bimodal signaling cascade. 🤔 Can't wait to read more!
110
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
While there's lots of work to be done, mamp-ml is a critical advancement in plant immunology for accelerating receptor-epitope characterization and engineering resistance. Mamp-ml is on Github and we implemented a version on Google Colab for easy use. Please check it out! github.com/DanielleMSte...
github.com
GitHub - DanielleMStevens/mamp-ml: mamp-ml: Prediction of immunogenic outcomes of LRR-PRRs and protein ligands in plants using pLM ESM-2
mamp-ml: Prediction of immunogenic outcomes of LRR-PRRs and protein ligands in plants using pLM ESM-2 - DanielleMStevens/mamp-ml
0103
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
Finally, we also tested its ability to predict outcomes for convergently evolved receptors. SCORE, a csp22 receptor found in Citrus and relatives, was recently discovered by @brunongou.bsky.social. We preliminarily found mamp-ml can zero-shot predict immunogenic outcomes!
162
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
Compared to other state-of-the-art models such as AlphaFold3, mamp-ml can predict these outcomes with higher confidence, even when a solved structure is not available. We anticipate users can now screen for immunogenic outcomes of receptor-ligand variants before spending time and $$ in the lab.
162
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
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!
121
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
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!
121
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
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.
152
Dani Stevens, Ph.D. @danimstevens.bsky.social · 16/07/2025
#2025ISMPMI 📣 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...
biorxiv.org
mamp-ml: A deep learning approach to epitope immunogenicity in plants
Eukaryotes detect biomolecules through surface-localized receptors, key signaling components. A subset of receptors survey for pathogens, induce immunity, and restrict pathogen growth. Comparative gen...
17741
Reposted by Dani Stevens, Ph.D.
Rebecca (BeKa) Leuschen-Kohl @bleuschenkohl.bsky.social · 14/07/2025
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
0296
Dani Stevens, Ph.D. @danimstevens.bsky.social · 12/07/2025
While I'm not going to be at #2025ISMPMI this year (🥲), @kseniakrasileva.bsky.social will be there presenting on some of our latest work that was submitted to BioRxiv today. Teaser: Plant immunity + large language models will transform receptor discovery and engineering for disease resistance. 🌱🚀
0195
Reposted by Dani Stevens, Ph.D.
C&EN (Chemical & Engineering News) @cenmag.bsky.social · 11/07/2025
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 🧪
cen.acs.org
Microsoft AI predicts protein conformations
The open-source tool goes beyond AlphaFold by finding proteins’ multiple equilibrium states and free energies
0135
Reposted by Dani Stevens, Ph.D.
Ksenia Krasileva @kseniakrasileva.bsky.social · 16/05/2025
The Resistance awakens: Diversity at the DNA, RNA, and protein levels informs engineering of plant immune receptors from Arabidopsis to crops 🧬🌱 💫🚀 by Chandler Sutherland @danimstevens.bsky.social @weiweibio.bsky.social Kyungyong Seong academic.oup.com/plcell/advan...
academic.oup.com
The Resistance awakens: Diversity at the DNA, RNA, and protein levels informs engineering of plant immune receptors from Arabidopsis to crops
Plants are natural bioengineers, and we illustrate how the stunning diversity in plant immune receptors can be translated into engineering efforts from Ara
02014
Dani Stevens, Ph.D. @danimstevens.bsky.social · 04/02/2025
It was great to catch up with so many people! Super thankful to Grey Monroe for the invite and enjoyed all the engaging questions. Can’t wait to wrap up this project and get it out there! 😁
000
Dani Stevens, Ph.D. @danimstevens.bsky.social · 01/02/2025
2025 has been quite a whirlwind. Learned of good funding news, had my first faculty (zoom) interview, will give my first dept. seminar on Monday at Davis all while trying to keep cool with the current news events. 😆😬🫠 To UC Davis folks, if anyone wants to meet up on Monday, feel free to reach out.
040
Dani Stevens, Ph.D. @danimstevens.bsky.social · 06/12/2024
This was such a fun review to be part of and truly a group effort! 😄please feel free to check it out. 🌱
011
Reposted by Dani Stevens, Ph.D.
Pierre Buscaill @pierrebuscaill.bsky.social · 02/12/2024
🌿 Excited to share our latest research on how host proteases regulate immune activation! Read more about how SBT5.2 releases and inactivates flg22: www.nature.com/articles/s41... rdcu.be/d1UsT Congratulations to all involved! #PlantImmunity #PlantPathology #PlantChemeticsLab
nature.com
Subtilase SBT5.2 inactivates flagellin immunogenicity in the plant apoplast - Nature Communications
Plants recognize bacteria by perceiving a 22-residue epitope in flagellin. Plant-secreted SBT5.2 subtilases are found to inactivate this epitope, leading to elicitor removal and reducing costly immuni...
13023
Reposted by Dani Stevens, Ph.D.
Mauricio Contreras @mpcontreras.bsky.social · 14/11/2024
One bacterial NLR recognizing three different phage proteins vis direct interaction! How cool is that? www.nature.com/articles/s41...
nature.com
Diversification of molecular pattern recognition in bacterial NLR-like proteins - Nature Communications
Avs proteins are bacterial anti-phage pattern recognition receptors evolutionarily related to eukaryotic NLRs. Here, Béchon et al show that a single bacterial Avs can recognize different phage protein...
0106
Dani Stevens, Ph.D. @danimstevens.bsky.social · 14/11/2024
This is the one I would suggest! Was one of the first papers read as part of a phylogenetics journal club/class I took several years ago.
030
Dani Stevens, Ph.D. @danimstevens.bsky.social · 13/11/2024
Sometimes the smallest things warm the soul ❤️ so thankful to be part of such a great lab group!
071
Dani Stevens, Ph.D. @danimstevens.bsky.social · 12/11/2024
Interested in how immune responses change over different stages of root development? 🍅🌱 Check out the preprint lead by @bleuschenkohl.bsky.social! 🥳 www.biorxiv.org/content/10.1...
biorxiv.org
Tomato roots exhibit distinct, development-specific responses to bacterial-derived peptides
### Competing Interest Statement The authors have declared no competing interest.
084