1. ENTER #mRNAvaccines for #pancreaticcancer! Long-term #PDAC survivor story PART3. "Do #PDACs REALLY have vaccine neoantigens (NAs)"? (aren’t they lowly mutated?) If each patient = own NAs, how do you vaccinate? Maybe mRNA? But how? nature nature.com/articles/s4158… 👇🏽 [1/32]

So honored to receive this award! A million thanks and congratulations to my partner in crime Julia Zhao, and to ISCB and ISMB organizers for an all-around amazing conference! One of my favorites to date🎉

So excited to be in Hawaii ICML Conference presenting work w/ Quaid Morris, and to win best poster award!! Thanks for a great workshop ICML-Compbio-Workshop

Thank you to all organizers and sponsors CZI Science GSK for another outstanding ICML-Compbio-Workshop workshop ICML Conference #ICML2023 photos courtesy of Lingting Shi

Thank you to the phenomenal grad students from our 6 Tri-I PhD (and MDPhD) programs who openly talked to our summer students & #MSKBridge scholars about "Is graduate school right for me and how do I get in?"

Super excited to share the first preprint from Karuna Ganesh Lab! An amazing collaboration with dana_peer, led by the phenomenal andrew moorman @f_cambuli and Ellie Benitez Memorial Sloan Kettering Cancer Center. Progressive #Plasticity during #ColorectalCancer #Metastasis. biorxiv.org/content/10.110…

Very grateful to receive the U.S. National Science Foundation grfp! And a huge thank you to Quaid Morris and Tri-I CBM for the support!

Treatment options are limited for the 3-5% of patients who have cancers of unknown primary. So, we are excited to present 💥GDD-ENS💥: a highly accurate, comprehensive tumor type classifier based on data from a routinely applied FDA-authorized test 🧵 medrxiv.org/content/10.110…

✨New paper alert Cancer Discovery✨ - GDD-ENS distinguishes 38 cancer types (>96% of patients) w/ high accuracy using routinely collected DNA sequencing data #MSKIMPACT and generalizes well to other gene panels w/o retraining - CNAs (arm/gene level) are key features for classification

Microsoft + Apple are building AI-enabled recall into their next devices. I built a version of this to recall websites I've visited - usable today. With Dewey, instantly save and semantically search important webpages, all run on your own device. Download the extension here:

Metient reconstructs the migration histories of metastatic cancers by scoring a Pareto front of parsimonious histories. It can be auto-calibrated to different cohorts. Superstar PhD student Divya Koyyalagunta will present at #ISMB2024 in MLCSB Check it out: biorxiv.org/content/10.110…

Excited to share our preprint "Multiome Perturb-seq unlocks scalable discovery of integrated perturbation effects on the transcriptome & epigenome". This work extends single-cell CRISPR screens to simultaneously profile gene expression & chromatin accessibility.

Can we recreate the transcriptional states seen in single-cell atlas projects? In our new preprint we try to do this using large-scale Perturb-seq experiments. Along the way we discuss off-target effects of CRISPR epigenetic editors and identify drivers of key fibroblast states.

Our opinion piece is out today, "The origin of novel traits in cancer"! Do the phenotypes come first and only later are they locked in by genetic or epigenetic changes? Insights from evolutionary biology are super useful for understanding cancer! cell.com/trends/cancer/… #S_Frank

Thrilled to share our paper now out nature delineating #plasticity during #CRC #metastasis, a fantastic collaboration led by Andrew Moorman Ellie Benitez, and @f_cambuli from the Karuna Ganesh Lab and @dana_per lab! nature.com/articles/s4158… rdcu.be/dYAVK. A 🧵

When we started Cartesia, we set out to reimagine the fundamental building blocks for interactive ML. today, our tech is powering thousands of voice AI applications around the world. The journey is just beginning, and I couldn't be more excited about what's ahead. 🚀

So proud to share that Farsight has announced our Series A! Over the past year, we've seen incredible traction with leading investment banks, PE firms, and hedge funds who are using our platform to automate everything from deal sourcing to complex financial modeling. We're at

We're excited to release 𝐦𝐑𝐍𝐀𝐁𝐞𝐧𝐜𝐡, a new benchmark suite for mRNA biology containing 10 diverse datasets with 59 prediction tasks, evaluating 18 foundation model families. Paper: biorxiv.org/content/10.110… GitHub: github.com/morrislab/mRNA… Blog: blank.bio/post/mrnabench

I am excited to introduce mRNABench, a comprehensive benchmarking suite that we used to evaluate the representational capabilities of 18 families of nucleotide foundation models on mature mRNA specific tasks. Paper: doi.org/10.1101/2025.0… Code: github.com/morrislab/mRNA… A 🧵

(4) Together with Divya Koyyalagunta, we further assess the ability for foundation models to compositionally generalize from learned motifs. Models are exposed to either sequence element that promotes translation, but never both, and we task them with predicting the unseen combination.