@antigenomics

Bioinformatics, immunogenetics, high-throughput immune repertoire sequencing. Decoding adaptive immunity.

 Third Rome
isalgo.dev
Joined May 2014
  • Tweets710
  • Following1K
  • Followers1.4K
65Media
1/7 We are pleased to report the 2026 VDJdb release, just published in Nucleic Acids Research: 203,230 TCR:pMHC records over 2,090 epitopes and 236 MHC alleles, 37-fold the first release, 4-fold our 2022 COVID-19 compendium. #immunology #bioinformatics academic.oup.com/nar/advance…

VDJdb in 2026: boosting T-cell receptor recognition evidence using paratope embeddings and AI-based...

Abstract. We present a significant update to VDJdb, introducing substantial enhancements to both the data content and the technical infrastructure. The int

academic.oup.com
3
11
32
1,939
Mikhail Shugay retweeted
Eric Topol
@EricTopolOct 22
Targeting neoantigens, the proteins or peptides on the surface of cancer cells, is the basis for personalized cancer vaccines. What is the ideal neoantigen? @Cancer_Cell sciencedirect.com/science/ar…
8
52
181
20,083
Which model can best distinguish which TCR-pMHC pairs show validating reactivity? Very excited to find out!IMMREP26 is now live and will be running until 2nd November! kaggle.com/competitions/immr…

IMMREP26: Validation of public TCR-pMHC data

Competitors will predict whether TCR-pMHC pairs reported in public databases can be validated

kaggle.com
MariusMessemaker@MariusMessemak1Oct 7
Out in @ImmunityCP : We expanded to >2,500 TCRs and 8 epitopes and find that ~half of TCR-pMHC pairs do not validate. On clean data, we show that modeling reactivity with AF3 & tcrdist3 is more feasible than assumed. Is your model better? Join IMMREP26! 🧵 cell.com/immunity/fulltext/S…

Functional evaluation of TCR-pMHC pairs at scale allows in silico TCR reactivity prediction

Messemaker et al. develop a TCR rapid assembly platform (T-RAP) and use it to generate a large high-quality dataset of functionally validated TCR-pMHC pairs. With the resulting validated TCR-pMHC...

cell.com
2
1
11
1,271
Mikhail Shugay retweeted
Nature Methods@naturemethodsOct 14
Bottlenecks in the study of TCR-antigen specificity: nature.com/articles/s41592-0…

Towards high-quality large-scale T cell receptor antigen specificity data: challenges and promises

Nature Methods - Antigen recognition by T cells through their highly diverse T cell receptors (TCRs) is central to adaptive immunity, and recent high‑throughput methods and databases have...

nature.com
21
1
79
8,558
Filling the massive AI drug discovery data gap nature.com/articles/d41573-0… Charlotte Deane, co-leader of the OpenBind initiative, discusses the need for more protein–small molecule binding data

Filling the massive AI drug discovery data gap

Nature Reviews Drug Discovery - Charlotte Deane, co-leader of the OpenBind initiative, discusses the need for more protein–small molecule binding data.

nature.com
7
13
3
46
3,595
Mikhail Shugay retweeted
Joe Sabatino@jsabatino37Oct 5
The trogocytosis plot of T cell-B cell interactions thickens! T–B interactions yield CD3+ B cells and CD20+ T cells with pathogenic features in multiple sclerosis pnas.org/doi/10.1073/pnas.26…

T–B interactions yield CD3+ B cells and CD20+ T cells with pathogenic features in multiple sclero...

Classically, B and T cells are differentiated by their mutually exclusive expression of surface markers such as CD3 and CD20, but it is now establi...

pnas.org
1
33
4
130
16,713
The emerging reproducibility crisis in AI-driven biomedicine will only intensify unless the community redefines multiomics data quality nature.com/articles/s41587-0… rdcu.be/a3yYAYF4vAya

Ensuring multiomics data reproducibility for artificial intelligence with reference materials as a...

Nature Biotechnology - Reference materials should be adopted as a common calibrator for multiomics measurement and co‑profiled with study samples. Multiomics results should be reported as...

nature.com
7
28
4
94
13,154
Can we predict which T cell receptors will recognise which targets? That's the challenge being tackled by team MATCHMAKERS. Their latest research has shown that this may be more feasible than previously thought. Their work, built on a rigorously validated TCR dataset, reveals early predictive capabilities. There's still much more to do, but findings like these are helping to lay the foundations for a future where data-driven approaches can accelerate progress against cancer. Congratulations to @MariusMessemak1 (pictured right), Bjørn Kwee (pictured left) and Ton Schumacher from @NKI_nl, and all collaborators for publishing this latest research in @ImmunityCP. 🔗 Read the paper: bit.ly/4e89Hbr
7
30
2,189
Mikhail Shugay retweeted
Immunity@ImmunityCPOct 1
Online now: Functional evaluation of TCR-pMHC pairs at scale allows in silico TCR reactivity prediction dlvr.​it/TVkjcP
18
87
5,389
Hi, we would like to introduce PAIR-Scan, an HLA-agnostic library-on-library screening technology that can identify reactive TCR–antigen pairs with optimal killing activity among up to ~100,000 possible candidate pairs in a single-step. 🧵(1/7) biorxiv.org/content/10.64898…

PAIR-Scan: Single-step identification of highly potent TCR–neoantigen pairs through library-on-li...

Tumors contain a mixture of T cells with bystander reactivities and reactivities towards different, frequently patient-specific, cancer (neo)antigens. The one-step identification of highly active...

biorxiv.org
3
12
35
3,406
Missed our latest Unravelling T Cell Recognition seminar? Prof Chihiro Motozono, discusses the molecular basis of T cell antigen recognition and immune escape in viral infections, with lessons from SARS-CoV-2. The full seminar is now freely available 👇 youtu.be/x-Ox8MwcHjc
🤖 Made with AI
3
5
279
Anthropic's discovery of array-associated reverse transcriptases? Turns out it was already done by a Danish scientist. He used Claude for administrative tasks, but not in an agentic manner for the discovery. He already filed a patent and gave talks on it nytimes.com/2026/09/27/scien…

Did Anthropic’s A.I. Really Make a Scientific Discovery on Its Own?

An expert at the University of Copenhagen said his team had been sharing its research with the company’s A.I. model, Claude, and that its new finding matched their work.

nytimes.com
17
271
49
1,342
242,177
6/7 For structural evidence we modelled 14,612 TCR:pMHC complexes with TCRmodel2/AlphaFold2 across 39 epitopes, against 294 native structures, and report ipTM for each. In IMMREP25, only structure-based methods gained over random classifiers on unseen epitopes.
1
45
7/7 Which residues drive recognition? Explore CDR3–peptide contacts as interactive complementarity maps at vdjdb.com. All 14,612 models are on HuggingFace: AlphaFold output at scale, no GPU months required. huggingface.co/datasets/isal…
48
Mikhail Shugay retweeted
eLife - the journal@eLifeSep 19
Thymic selection of the T cell receptor repertoire is biased toward autoimmunity in females elifesciences.org/articles/1…

Thymic selection of the T cell receptor repertoire is biased toward autoimmunity in females

Sex-specific biases in thymic T cell receptor selection enrich female CD8 T cell repertoires for autoimmunity-associated self-antigens, helping explain women’s increased susceptibility to autoimmune...

elifesciences.org
6
1
17
5,979
Mikhail Shugay retweeted
Joe Sabatino@jsabatino37Sep 18
Universal seropositivity, markers of recurrent reactivation, and a convergent T-cell response implicate cytomegalovirus in Susac syndrome researchsquare.com/article/r…

Universal seropositivity, markers of recurrent reactivation, and a convergent T-cell response...

Susac syndrome (SuS) is a rare brain, retina, and inner ear endotheliopathy, in which CD8⁺ T cells are thought to target the microvascular endothelium. We applied unbiased, HLA-restricted antigen-s...

researchsquare.com
1
1
11
2,890
Load more