Joined June 2021
- Tweets26
- Following161
- Followers65
- Likes57
Pinned Tweet
Excited to announce that our work on #TCR representation modelling is now out on @CellSystemsCP! You can try our model SCEPTR at sceptr.readthedocs.io 🚀
This Post is from an account that no longer exists. Learn more
Remember this? This used to only be possible with GPU acceleration. Our updates mean now practically anyone can cluster 10^7 TCRs within seconds using only consumer CPUs! Preprint v2 at arxiv.org/abs/2403.09010 and as ever the software is open-source at github.com/yutanagano/symsca…
Ever dreamed of clustering 10^6 TCR sequences in one second? Or 10^7 TCRs in 10 seconds? Well now you can, thanks to amazing work by @heartnetkung and @andimscience! Check it out: arxiv.org/pdf/2403.09010.pdf
If anyone uses #Prettier to auto-format #Markdown notes, and wishes there was an auto-bullet list plugin for #NeoVim that has the same formatting conventions, you might like github.com/yutanagano/smark.…
Yuta Nagano retweeted
Our work on contrastive learning of T cell receptor representations is now out in Cell Systems!
Give SCEPTR embeddings a try for your TCR analysis applications: sceptr.readthedocs.io/en/sta…
This Post is from an account that no longer exists. Learn more
Quant-immuno people: you should know that @andimscience is hiring! As his former PhD student I can attest his group is a perfect mix of brilliant minds with an open, collaborative culture and you'll have an amazing time. qimmuno.com/openings/
Yuta Nagano retweeted
How to learn generalizable rules across complex sequence-function maps? 💡In our new preprint we propose a framework for learning two-point statistics and use it to discover biophysical rules of TCR specificity that generalize to unseen ligands ! ✨ arxiv.org/abs/2412.13722
Yuta Nagano retweeted
Using information theory to study the immune receptor code? 👉 check out this short popular summary of our recent @PNASNews paper by first author @jhenderson_sci on @GrowKudos growkudos.com/publications/1…
Yuta Nagano retweeted
What are the rules of the immune receptor code? In my talk @KITP_UCSB last Friday I summarised our recent findings, provide a perspective on why ML approaches have so far not achieved breakthrough success, and propose a path forward:
online.kitp.ucsb.edu/online/…
Yuta Nagano retweeted
Information theory of the T cell receptor sequence-function map -- our paper now out @PNASNews ! 🔥
How informative (in bits) is the α or β chain? When does partial information limit predictions? + insights into synergy, Renyi entropy, optimal compression & more 👉
ALT https://www.pnas.org/doi/10.1073/pnas.2408696121
Yuta Nagano retweeted
🚨 Fresh #preprint 🚨
Targeting #DUX4 protein diffusion when designing #FSHD #therapeutics looks to be a great strategy!
Read more here: biorxiv.org/content/10.1101/…
Lovely as always working with @FSHresearch, Prof. Pete Zammit, and Dr Christopher Banerji.
Yuta Nagano retweeted
Very happy to share our latest pre-print studying T cell dynamics in multiple myeloma disease evolution 🧵1/10.
medrxiv.org/content/10.1101/…
How can we better align protein language model (PLM) pre-training with downstream tasks of interest? For TCR specificity prediction, it turns out that autocontrastive learning is really beneficial! Check out our preprint: arxiv.org/abs/2406.06397
We also find that performance on TCR specificity prediction is not currently bottlenecked by model size.
A huge and sincere thank you to my supervisors @BennyChain @andimscience and co-authors Andrew Pyo @Martina_Milig @jhenderson_sci and Prof. John Shawe-Taylor. It's been great fun and I've learned so much working on this with all of you 🙏💪
Yuta Nagano retweeted
The latest exciting step forward in T cell receptor representation ! @YutaNotUtah outperforms TCR-BERT ! arxiv.org/pdf/2406.06397
Yuta Nagano retweeted
How to pre-train protein language model to optimize transfer learning? @YutaNotUtah’s PhD work shows prior PLMs struggle to predict TCR specificty & uses contrastive learning to overcome this limitation. 👉arxiv.org/abs/2406.06397
Really proud and grateful to be part of this amazing work led by @Martina_Milig!
New preprint!
We investigated the molecular interactions between the TCR CDR loops and find that these may be important in shaping TCR specificity and sequence
biorxiv.org/content/10.1101/…
Yuta Nagano retweeted
Happy to release our preprint introducing an information theory of T cell specificity!
We rank TCR features by their relevance to predicting epitope specificity and bound how accurately T cell specificity can be predicted from partial information.
arxiv.org/abs/2404.12565
Yuta Nagano retweeted
New preprint: Annie Baker & @BennyChain have led the development of "FUME-TCRseq" a new T-cell receptor seq assay sensitive & robust enough to work on microdissected FFPE samples. Enables profiling of TCR clones & their tissue microenvironment together. biorxiv.org/content/10.1101/…
