Reposted by Dhuvi KarthikeyanEric Kernfeld @ekernf01.bsky.social · 12/10/2025This is so friggin cool. You don't have to rewrite all that FORTRAN to do autodiff on it. "Enzyme" 041
Reposted by Dhuvi KarthikeyanKilian Schober @kischober.bsky.social · 08/10/2025When a T cell carries both its natural TCR and an engineered CAR, do these two receptors cooperate - or compete? Our new preprint on bioRxiv shows that TCR activation can enhance CAR-T activation but impairs CAR-mediated killing when targets are on separate cells. www.biorxiv.org/content/10.1...biorxiv.orgTCR activation impairs CAR-T cytotoxicity against separate target cellsChimeric antigen receptor T cells (CAR-T) are effective therapeutics against cancer and autoimmunity, but whether the endogenous T cell receptor (TCR) is beneficial, detrimental or irrelevant for CAR ... 2145
Reposted by Dhuvi KarthikeyanbioRxiv Microbiology @biorxiv-microbiol.bsky.social · 10/09/2025No Distinct Gut Microbiome Signature in Alzheimer's Disease: A Reanalysis with Modern Tools www.biorxiv.org/content/10.1101/202… 063
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 09/09/2025Now out in @natmachintell.nature.com TCRT5 is a rapid generator of target-conditioned CDR3b, leads SoTA, and yields the first AI-designed self-tolerant binder to an OOD non-viral epitope (w val) 📑: www.nature.com/articles/s42... 🤗: huggingface.co/dkarthikeyan1 👨💻: github.com/pirl-unc/tcr_translate 142
Reposted by Dhuvi KarthikeyanAlex Rubinsteyn @alexr.bsky.social · 09/09/2025tl;dr T5 style translation model to generate T cell receptors from targets actually kinda works Caveats: not full TCR (CDR3b), strong signal that public data biased towards “polyspecific” TCRs — lo and behold, generated TCR-T is polyspecific in vitro. Open weights, go wild. 193
Reposted by Dhuvi KarthikeyanAlex Rubinsteyn @alexr.bsky.social · 09/09/2025With some key contributions by Sarah Bennet in actually turning predicted TCRs into TCR-Ts and testing them! Hopefully this raises the bar on TCR generation evals, I think we the best in silico metrics and 1 in 20 TCRs just kinda works. 041
Reposted by Dhuvi KarthikeyanJamie Heather @jamieheather.bsky.social · 08/09/2025This is a cool story that I've watched with great interest - making big steps in the field of de novo TCR generation! Great work @dkarthikey1.bsky.social / @benjamingvincent.bsky.social / @alexr.bsky.social et al 2104
Reposted by Dhuvi KarthikeyanAlphaFold Unofficial @alphafold.bsky.social · 19/05/2025Today’s news about Joe Biden makes it almost difficult not to reflect on the unrealistic promises from AI leaders who claim AI could end disease and usher in radical abundance. Disease will persist. AI is a tool, not a cure-all. People deserve truth, not hype. www.cbsnews.com/amp/news/art...cbsnews.comArtificial intelligence could end disease, lead to "radical abundance," Google DeepMind CEO Demis Hassabis saysAt Google DeepMind, researchers are chasing what's called artificial general intelligence: a silicon intellect as versatile as a human's, but with superhuman speed and knowledge. 0194
Reposted by Dhuvi KarthikeyanDustin Rubenstein @dustinrubenstein.com · 10/05/2025NSF to ONLY fund research in five areas: artificial intelligence, quantum information science, biotechnology, nuclear energy, and translational science. Can this be happening? www.science.org/content/arti...science.orgNSF slashes number of ‘rotators’ and well-paid managers as part of restructuringSmaller future budgets will require fewer people, NSF official tells staff 23257145
Reposted by Dhuvi Karthikeyankyunghyuncho.bsky.social @kyunghyuncho.bsky.social · 08/05/2025what do you teach at the first-year graduate course on machine learning, in this era of LLM and large-scale compute? here's my experiment on answering this question: let's teach everything that admits SGD and that is not LLM, and ask students to read old papers. 1423
Reposted by Dhuvi KarthikeyanGeorge Takei @georgetakei.bsky.social · 03/05/2025We hadn’t won World War II by May 8th. I know because my family and I were still in an internment camp in Tule Lake, California. 2180310956399
Reposted by Dhuvi KarthikeyanCarolien van de Sandt @cvandesandt.bsky.social · 24/04/2025Your immune system gradually loses it top team players when we get older 👱➡️👵 Our study in @ebiomedicine.bsky.social investigates how long good immune cells stay around – a 🧵⬇️ go.unimelb.edu.au/4sep @katherinekedz.bsky.social @thedohertyinst.bsky.social #Influenza #AgingResearch #Immunity #TCR 12113
Reposted by Dhuvi KarthikeyanShobita Parthasarathy @shobitap.org · 21/04/2025My PhD student's NSF grant was terminated today. Her dissertation investigates why air pollution monitoring, metrics, and regulations don't properly capture the harms experienced by marginalized communities--esp in the most polluted Detroit neighborhoods. She and I are happy to talk with press etc.nsf.gov NSF Award Search: Award # 2240343 - Constructing Credible Knowledge and Expertise in Air Pollution Regulation and Monitoring: The Problem of Quantification Lock 452195949
Reposted by Dhuvi KarthikeyanAmy Pomeroy @amypomeroy.bsky.social · 10/04/2025I am so excited to share that our new paper is out! A model of intratumor and interpatient heterogeneity explains clinical trials of curative combination therapy for lymphoma Out in Blood Cancer Discovery doi.org/10.1158/2643-3230.BCD-24-0230 #mathonc #lymsm #BloodCancer 1/ndoi.orgA model of intra-tumor and inter-patient heterogeneity explains clinical trials of curative combination therapy for lymphomaAbstract. Models of tumor drug response have illuminated important concepts in oncology, but there remains a need for theory that combines intra-tumor and inter-patient heterogeneity to explain patien... 174
Reposted by Dhuvi KarthikeyanGisela Gabernet @ggabernet.bsky.social · 31/03/2025Do you analyze large BCR and TCR sequencing datasets? Answer our survey for improving nf-core/airrflow, a Nextflow pipeline to analyze bulk and single-cell AIRRseq data (doi.org/10.1371/jour...). We’re interested in your opinion on useful new features! yalesurvey.ca1.qualtrics.com/jfe/form/SV_...doi.orgnf-core/airrflow: An adaptive immune receptor repertoire analysis workflow employing the Immcantation frameworkAuthor summary We have created nf-core/airrflow, a workflow to help researchers study the immune system in healthy and disease states, such as infections, autoimmunity, and cancer. The adaptive immune... 0105
Reposted by Dhuvi KarthikeyanEric Topol @erictopol.bsky.social · 24/03/2025HHS's Office of Long COVID Research and Practice has been DOGEd. Closing this week. 37463512907
Reposted by Dhuvi KarthikeyanNathan C. Frey @ncfrey.bsky.social · 26/02/2025We @prescientdesign.bsky.social Genentech pre-printed our "Lab-in-the-loop for therapeutic antibody design." We built a general ML system to accelerate molecule design for challenging, therapeutically relevant targets. www.biorxiv.org/content/10.1...biorxiv.org 1238
Reposted by Dhuvi Karthikeyanjp flores (he/him) @jpflores.rbind.io · 25/02/2025You in the Triangle area and thinking about standing up for science? Come to my beloved 2nd workplace and make a sign 😊🍻 supplies provided! You can leave a sign w me and i can bring it up to DC! @standupforscience.bsky.social 35519
Reposted by Dhuvi KarthikeyanJamie Heather @jamieheather.bsky.social · 25/02/2025Dear TCR researchers of #immunosky, you may be interested to know that our tool Stitchr - for the automated production of full-length T cell receptor sequences - has just had a nice little update: jamieheather.github.io/stitchr/jamieheather.github.iostitchr — stitchr documentation 2367
Reposted by Dhuvi KarthikeyanDarby Saxbe @darbysaxbe.bsky.social · 04/02/2025🚨BREAKING. From a program officer at the National Science Foundation, a list of keywords that can cause a grant to be pulled. I will be sharing screenshots of these keywords along with a decision tree. Please share widely. This is a crisis for academic freedom & science. 12652769415654
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 01/02/2025Musks method of ruthlessly enforcing efficiency by removing things and adding them back if the system breaks has worked well for pruning complexity of products, pipelines and entire companies. But applying this methodology to govt is dangerous and will result in greater harm to the American people 110
Reposted by Dhuvi KarthikeyanEric Topol @erictopol.bsky.social · 12/01/2025Good combo! A nasal vaccine with self-amplifying RNA (much less dose required for v potent immune response), complete protection effective vs both H5N1 and H7N9 viruses in experimental models www.biorxiv.org/content/10.1...biorxiv.orgAn intranasal, NLC-delivered self-amplifying RNA vaccine establishes protective immunity against pre-pandemic H5N1 and H7N9 influenzaSeasonal and pandemic influenzas are continuous threats to human health, requiring rapid development of vaccines to multiple evolving viral strains. New RNA vaccine technologies have the adaptability ... 19551114
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 30/12/2024On the merits of reading papers, attending conferences, preprinting manuscripts… Overseen at the Library of Congress. 000
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 21/12/2024Unsure if people on bsky are aware of o3s existence. But if anyone wants to talk I’ve been itching all day 010
Reposted by Dhuvi KarthikeyanQ-Immuno lab at UCL @qimmuno.bsky.social · 19/12/2024How 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 co-specificity that generalize to unseen ligands ! ✨ arxiv.org/abs/2412.13722 095
Reposted by Dhuvi KarthikeyanDiego del Alamo @delalamo.xyz · 11/12/2024Ideal test is antibody CDRH3s which often conformationally rigidify during affinity maturation. MSAs only report inter-species evolution, not intra-species maturation, so existing methods fail. Pics from doi.org/10.3389/fimmu.2018.03065 & doi.org/10.3389/fmolb.2020.00182 0102
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 04/12/2024Given the subtext here I wouldn’t be surprised if both X and Bsky develop extremely close but distinct niches: the former to blast information and reach broader audiences, and the latter as a place of discourse with members of a particular community. 021
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 04/12/2024🧙🪄Summoning Alex to 💙🦋 so the Bio x ML community can celebrate ESM-C with him on here as well 030
Reposted by Dhuvi KarthikeyanJamie Heather @jamieheather.bsky.social · 26/11/2024My usual go to is VDJdb. Set antigen species to human, minimal confidence score to 3, and paired A+B. It's not perfect, but it filters out most of the cruft. There's also a new DB called TRAIT which has a nice pack of TCRs that are being/have been trialed, which are mostly against human epitopes. 171
Reposted by Dhuvi KarthikeyanSander Wuyts, PhD 🧬 @swuyts.bsky.social · 21/11/2024Calling all T-cell aficionado's. Come and join us next year (27-28 May 2025) for the fourth Antwerp T-Cell Receptor conference organised by @pmeysman.bsky.social, @krislaukens.bsky.social and Benson Ogunjimi. I'll also be there! www.uantwerpen.be/en/conferenc... #ImmunoSky 12512
Reposted by Dhuvi KarthikeyanMohammed AlQuraishi @moalquraishi.bsky.social · 20/11/2024#GoodThingsComeToThoseWait Sorry it's taking us a while. Promise that the wait will be well worth it! #OpenFold3 Love all the great work that's already been done #HelixFold3 #Ligo #Chai1 #Protenix #Boltz1 311926
Reposted by Dhuvi KarthikeyanDr. Glaucomflecken @glaucomflecken.bsky.social · 19/11/2024Surely I misheard. There’s no way Dr. Oz, the OG grifter, president of grift university, has been tapped to lead the largest and most influential US healthcare entity. 1782304312
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 19/11/2024My first Skeetorial! 💻🧬TCR-TRANSLATE - A new framework for thinking about the TCR:pMHC specificity problem. TLDR: We pretrained LLMs on ~8M TCR & pMHC seqs Finetuned on sparse pMHC->TCR pair data Validated CDR3b sequences to unseen antigens >> random performance on IMMREP2023 "private" antigens 13014
Reposted by Dhuvi KarthikeyanbioRxiv Synthetic Biology @biorxiv-synthbio.bsky.social · 13/11/2024TCR-TRANSLATE: Conditional Generation of Real Antigen Specific T-cell Receptor Sequences www.biorxiv.org/content/10.1101/202… biorxiv.orgTCR-TRANSLATE: Conditional Generation of Real Antigen Specific T-cell Receptor Sequences https://www.biorxiv.org/content/10.1101/2024.11.11.623124v1 The paradoxical nature of T-cell receptor (TCR) specificity, which requires both precise recognition 122
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 13/11/2024LLMs are fantastic learners of arbitrary sequence to sequence mappings. Text summarization, Q&A, and machine translation, etc. So what happens if you apply them to the many-to-many mapping of the TCR cross reactivity landscape? Turns out, some pretty cool things. Check it out 😏 042
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 05/11/2024The fate of this app hangs in the balance tonight… 000
Reposted by Dhuvi KarthikeyanbioRxiv Biophysics @biorxiv-biophys.bsky.social · 18/10/2024Load-based divergence in the dynamic allostery of two TCRs recognizing the same pMHC www.biorxiv.org/content/10.1101/202… biorxiv.orgLoad-based divergence in the dynamic allostery of two TCRs recognizing the same pMHC https://www.biorxiv.org/content/10.1101/2024.10.16.618634v1 Increasing evidence suggests that mechanical load on the {beta} T cell receptor (TCR) is crucial for 001
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 18/10/2024Someone should do an autopsy on Twitter. When did it stop being Twitter? I know it’s easy to point at Elon but what really happened? Beyond the obvious what second order phenomena can be traced to its decline? 3rd/4th? 000
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 18/10/2024Insane finding: repeat covid infections result in milder symptoms but a greater propensity for long-COVID. Something really interesting is going on here and I want to know if it’s T or B cell mediated 100
Reposted by Dhuvi KarthikeyanAlex Rubinsteyn @alexr.bsky.social · 17/10/2024What other keywords should I add to the MLSky feed? It's a tricky balance -- something too technical never triggers but eg #llm #chatgpt even "PyTorch" &c get mostly spam 442
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 17/10/2024It appears that my peoples (scientists) are preparing for a mass migration back onto here come election szn so whattup fam, I’m back 000
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 23/01/2024Back on here because I’m noticing a dangerous trend on Twitter where among other things bot engagement is being used to silence organic activity, particularly on controversial matters. Gonna try to use my codes to bring people on here as voting szn draws near. 000
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 09/10/2023Totally legit question for all the PIs on here: when working on a problem that has a lot of other people publishing on it, how does one write an introduction that doesn’t sound like a paraphrasing of 20 other papers 😩 000
Reposted by Dhuvi KarthikeyanMichael Love @mikelove.bsky.social · 24/09/2023The UNC Genetics Dept / BCB / GMB retreat was this week in Asheville NC and it was stellar. These two students from @alexr.bsky.social lab gave a hilarious and emotional rollercoaster of a presentation about getting scooped and still pulling through. Poster sessions and talks were all 👌 3122
Reposted by Dhuvi KarthikeyanDiego del Alamo @delalamo.xyz · 19/09/2023"The Protein Engineering Tournament: An Open Science Benchmark for Protein Modeling and Design" "A fully-remote, biennial competition for the development and benchmarking of computational methods in protein engineering" Hope you'll all participate! arxiv.org/abs/2309.09955 031
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 09/09/2023There are few pleasures in life that will even come close to enjoying chai and reading papers by a window in the rain 😌 020
Dhuvi Karthikeyan @dkarthikey1.bsky.social · 01/09/2023I’m looking for a man/machine that goes by Alf… 020