Krishnaswamy Lab

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)

Our very own Smita Krishnaswamy is a key investigator in the new $25M @CancerGrand Challenges REWIRE-CAN team! @KrishnaswamyLab will use cutting-edge ML to understand how to reprogram cancer cells. Learn more here 👇👇🏾👇🏽👇🏿👇🏻 medicine.yale.edu/genetics/news-…

In Sydney at the @GarvanInstitute for the #allclear consortium’s annual meeting! Excited to hear about cancer, metastasis and dormant cells! Thanks @c_chaffer and Peter Croucher for putting it together!

CellWhisperer can now run on your laptop. Talk to your cells! And check out our paper: nature.com/articles/s4158…

Congrats to @DanqiLiao73090 on her successful thesis defense! Can’t wait to see what she does next!!

Proud to be part of this new CRUK cancer grand challenge team REWIRE-CAN with colleagues Chris Tape and Bart Vanhaesebroeck from @ucl @broadinstitute @MSKCancerCenter @UUBeta !! Our team plans to reprogram cancer cells into vulnerable states by disrupting their finely tuned “Goldilocks” level of oncogenic signalling. See more at cancergrandchallenges.org/rewire-can

@DanqiLiao73090 is defending her dissertation on Thursday!! If you're in come listen to her exciting work incorporating, mutual information, manifold learning and deep learning!

How does the brain know which neurons to adjust during learning in order to optimize behavior? MIT researchers discovered that brains can use cell-by-cell error signals to do this — surprisingly similar to how AI systems are trained via backpropagation. mcgovern.mit.edu/2026/02/25/neu…

Excited to be part of this team with@RevaliaBio @DraperLab and others!

@ChrisHayduk I have just built a data pipeline for PDB structures and MSA features as part of our open-sourced project that works for AlphaFold2. You might find that useful to your project. github.com/KrishnaswamyLa…

Yale medicine feature on our Immunostruct model medicine.yale.edu/news-article/u… !

Great visit to @WeillCornell earlier this week. Insightful to hear about the close collaboration between their clinical and academic research ! Thanks @dbetel @mason_lab @ekta_khurana @ElementoLab !

We're excited to share that the data and model weights for #ImmunoStruct are now open-sourced. This includes the multimodal data with sequences and structures, along with all preprocessing scripts including the folding pipeline we used. All available at: github.com/KrishnaswamyLa…

The Geometry Behind Maximum Likelihood Estimation (MLE): Maximum Likelihood Estimation (MLE) has a rich geometric interpretation that views statistical models as curved surfaces embedded in high-dimensional probability spaces. Each parameter value corresponds to a point on a statistical manifold, and the likelihood function defines a landscape whose peaks represent the most plausible explanations of the data. Gradients and Hessians of the log-likelihood describe local geometry, while the Fisher information acts as a Riemannian metric, measuring how distinguishable nearby distributions are. From this perspective, MLE becomes a problem of finding geodesic directions of steepest ascent on a curved surface rather than in flat Euclidean space. In statistics, this geometry explains efficiency, curvature bias, and asymptotic normality. In machine learning and deep learning, natural gradient methods, information geometry, and mirror descent exploit this structure to accelerate training and improve stability. The geometric view reveals that learning is not just optimization, but navigation on a curved space of probability models.

🖱️ Meet the Yale Computer Society (y/cs)! We are building tools that are used across campus while giving members hands-on experience on real-world projects –from apps to peer training and community events. Join us! loom.ly/Dww8S_g #YaleStudentClubs #ComputerScience

Yann LeCun says the real world is far more complex than the world of language LLMs can accumulate knowledge, but they fail with high-dimensional, continuous, noisy sensory data "the next revolution is physical AI" Systems that can truly plan, reason, and understand the physical environment

OK, so the $ bio ai assistants are: Ascent Bio - ascentbio.ai Bio Protocol BIOS - ai.bio.xyz Edison Scientific - edisonscientific.com K-Dense - k-dense.ai Potato - potato.ai SciSpace - scispace.com/biomedical/ Did I miss any?

@jmuiuc Congrats!!

Honored and grateful to be named an ACM Fellow. cs.cmu.edu/news/2026/ma-a…

Congrats to @KrishnaswamyLab alumni for developing this AI scientist and releasing it to the public!

@kishalaydaskd Congratulations @kishalaydaskd !! Looking forward to having you join us soon!

Officially Dr. Kishalay Das 😊 #thesisdefended