Bjørn Kwee
@Bjornformatics
Followers
92
Following
1K
Media
0
Statuses
23
PhD student @Schumacher_Lab @NKI_nl | protein LLMs | Bioinformatics | Cancer Immunology | High-Performance Computing
Amsterdam, Nederland
Joined January 2021
It's not the models, it's the data!. We show that a substantial proportion of a widely used TCR-pMHC database does not functionally validate, causing underestimation of performance of TCR-pMHC prediction models.
A functionally validated TCR-pMHC database for TCR specificity model development #biorxiv_immuno.
1
8
30
Alongside TCRvdb, we introduced TCRbridge - an AlphaFold3-based model for predicting TCR-pMHC specificity (built upon AlphaBridge). The code is now live on GitHub 👉
github.com
TCRbridge predicts TCR-pMHC reactivity from AlphaFold3 output. - schumacherlab/TCRbridge
It's not the models, it's the data! . We show that a substantial proportion of a widely used TCR-pMHC database does not functionally validate, causing underestimation of performance of TCR-pMHC prediction models.🧵.
0
1
3
Incredibly excited and grateful for the opportunity to present at Antwerp TCR in 3 weeks. There’s no place more relevant to showcase what we have been up to. If you want to have a sneak preview; check out the thread of @MariusMessemak1 & our pre-print
biorxiv.org
Accurate prediction of TCR specificity forms a holy grail in immunology and large language models and computational structure predictions provide a path to achieve this. Importantly, current TCR-pMHC...
1
4
9
RT @biorxiv_immuno: A functionally validated TCR-pMHC database for TCR specificity model development #biorxiv_immuno.
biorxiv.org
Accurate prediction of TCR specificity forms a holy grail in immunology and large language models and computational structure predictions provide a path to achieve this. Importantly, current TCR-pMHC...
0
14
0
RT @myESMO: #ESMOImmuno24: According to the 2024 ESMO Immuno-Oncology Awardee, @Schumacher_lab, tackling the T-cell receptor challenge w/ v….
0
3
0
RT @CancerGrand: Congratulations David Baker (@UW, member of #CancerGrandChallenges team MATCHMAKERS), who's won the 2024 Nobel Prize in Ch….
cancergrandchallenges.org
Meet MATCHMAKERS, whose challenge is to decipher the T-cell receptor cancer-recognition code.
0
8
0
RT @CRUKresearch: Ton Schumacher is closing #CancerHostTI24 discussing neoantigens and neoadjuvant therapy. With his research group he cre….
0
4
0
RT @NKI_nl: Researchers from the group of @HaanenJohn and @Schumacher_lab have successfully developed a novel method that enables the ident….
0
13
0
RT @NKI_nl: We’re excited to reveal that Team MATCHMAKERS has been selected by @CancerGrand to receive up to $25m over five years to take o….
0
11
0
RT @Schumacher_lab: Excited to share STAPLER, a language model to predict TCR – pMHC reactivity that outperforms prior models. And for ML….
biorxiv.org
The prediction of peptide-MHC (pMHC) recognition by αβ T-cell receptors (TCRs) remains a major biomedical challenge. Here, we develop STAPLER (Shared TCR And Peptide Language bidirectional Encoder...
0
37
0
Preprint alert 🚨🚨. Large language models can predict TCR - pMHC reactivity!🧬🔬. Proud to have worked on this project with @MariusMessemak1 and all other amazing co-authors.
Excited to share STAPLER, a language model to predict TCR – pMHC reactivity that outperforms prior models. And for ML aficionados: Description of a new data leakage problem inherent to a common negative data generation strategy. 🧵👇.
1
4
8
RT @MyriamChalabi: Woohoo 🙌🙌🙌! If you’re into immunology and immunotherapy, then you must know Ton Schumacher! Follow the lab’s new twitter….
0
3
0
Follow the Schumacher lab! (Exciting stuff coming up).
Hello world! The Schumacher lab is now also on Twitter!😃🔬.
0
1
3
RT @NatureBiotech: Identification of patient-specific CD4⁺ and CD8⁺ T cell neoantigens through HLA-unbiased genetic screens .
0
25
0
RT @BenNicolet: Gene function is associated with distinct mRNA – protein levels. We show that mRNA, protein, and mRNA-protein levels are as….
0
8
0