Krishnaswamy Lab
@KrishnaswamyLab
We develop data geometric, topological, dynamic, deep learning methods for analysis, visualization and representation of big data, especially biomedical data.
Today, I’m proud to share our latest work published in @NatureBiotech describing MELD, a #MachineLearning algorithm for #SingleCell perturbation analysis. Read this #tweetorial to learn about the work led by @dbburkhardt and Jay Stanley 🥳🎉🧪 nature.com/articles/s4158… (1/16)
Pitch the dataset that could spark the next AI for Science revolution 🚀 The PDB revolutionized structural biology (and even helped win a🏅Nobel Prize in 2024). We’re hunting for the next breakthrough dataset that could unlock similar leaps across science—and we want your idea!
#MachineLearning loves data. #Topology loves shape. Let's bring them together! 👉The Euler Characteristic Transform (ECT) bridges both worlds, as I outline in a recent article in the Notices of the @amermathsoc. Engage! 🧵1/n
1/N I’m excited to share that our latest @OpenAI experimental reasoning LLM has achieved a longstanding grand challenge in AI: gold medal-level performance on the world’s most prestigious math competition—the International Math Olympiad (IMO).
Introducing OpenAI o3 and o4-mini—our smartest and most capable models to date. For the first time, our reasoning models can agentically use and combine every tool within ChatGPT, including web search, Python, image analysis, file interpretation, and image generation.
So proud of @dbhaskar92 --former postdoc of our lab! Can't wait to see what he does!!
(1/2) Thrilled to share that I’m joining @UWMadison_BME as a tenure-track Assistant Professor starting today! Endlessly grateful to my mentors, friends, and family - I wouldn’t be here without your support 🙏 Excited for what lies ahead! #NewFaculty #UWBadgers
A bit late, but excited to announce our new paper, "Defining and benchmarking open problems in single-cell analysis," a joint effort led by our team (@scottgigante, @DBBurkhardt ) at @Yale and the @fabian_theis and @MDLuecken at Helmholtz! 🚀 **Open Problems**, is a living,…
Headed to @icmlconf for day 3 and workshops like @genbioai , who’s there!? Happy to chat!
A multinational team co-led by @KrishnaswamyLab has developed and tested a new #AI tool that can better characterize individual #tumor cells, paving the way for targeted #cancer treatments: bit.ly/3I4WoeS
Defining and benchmarking open problems in single-cell analysis bit.ly/4l8dsiF
Now online in @CD_AACR: AAnet Resolves a Continuum of Spatially-Localized Cell States to Unveil Intratumoral Heterogeneity - by Aarthi Venkat, Scott Youlten, @BeatrizPerezSJ, @KrishnaswamyLab, @c_chaffer, and colleagues doi.org/10.1158/2159-8… @Yale @YaleMed @GarvanInstitute
Preprint drop from our team at @arcinstitute! Introducing STATE: a model that learns and predicts transcriptomic responses to chemical or genetic perturbations. This is the first model to beat simple linear baselines and our first step toward building a virtual cell model.
Introducing Arc Institute’s first virtual cell model: STATE
AI in the air at @AIXBIO, presented on our Immunostruct and Cellspicenet models as well as @emblebi on cellular dynamics. Thanks for hosting @e_petsalaki ! Nice also to see @AIXBIO organizers @mo_lotfollahi @deboramarks @mariabrbic !
Glad to be (briefly) @Mila_Quebec again for MOML portal.ml4dd.com. Thanks for organizing @dom_beaini and colleagues!
So excited to share our new paper, FORT! 🎉 We're showing a simple regression approach to train discrete normalizing flows (think CNFs!), which beats conventional maximum likelihood training in performance. Check it out! 👇
Excited to release FORT, a new regression-based approach for training normalizing flows 🔥! 🔗 Paper available here: arxiv.org/abs/2506.01158 New paper w/ @osclsd @jiarlu @tangjianpku @mmbronstein @Yoshua_Bengio @AlexanderTong7 @bose_joey 🧵1/6
Mark your calendars 🗓️ for June 23 for a @KavliAtYale Awards Research in Progress!🧠 Hear from awardees @dbhaskar92, @LaShae_NeuroXp, @JJaimeMarti, @kevinschen13, @aaron_t_kuan, @JoergBewersdorf, @EnockTeefeMD_, & @hongyan_hao as they share exciting updates on their projects.
1/ Introducing TxPert: a new model that predicts transcriptional responses across diverse biological contexts It’s designed to generalize across unseen single-gene perturbations, novel combinations of gene perturbations, and even new cell types 🧵