Sushant Patkar

Computer scientist, aspiring musician, cat dad

[Sushant Patkar @spatkar94]

⚡️Thrilled to share our paper applying transfer learning techniques to identify novel biomarkers in canine osteosarcomas that could potentially inform more personalized treatment options for human patients!

https://t.co/TRy2G5Hhjr

[Randall Balestriero @randall_balestr]

With LeJEPA (https://t.co/RR9kcXEqSk) it has never been easier to train JEPAs! And this matters A LOT because JEPAs have numerous provable benefits over the good-old reconstruction based methods (https://t.co/bOg6uibdHP).
NeurIPS spotlight: Wed, 11 a.m. PST, Hall C,D,E #2613

[Stephen Tang @stephentang23]

Genome maintenance by telomerase is a fundamental process in nearly all eukaryotes. But where does it come from?

Today, we report the discovery of telomerase homologs in a family of antiviral RTs, revealing an unexpected evolutionary origin in bacteria.

https://t.co/OlU6HOLQfK

[Sushant Patkar @spatkar94]

Very cool!

[Georg Wölflein @gwoelflein]

🚀 New preprint! 🚀

LLM Agents Making Their Own Tools? Meet ToolMaker 🛠️

Our latest work explores how LLM agents can autonomously transform scientific code repositories into LLM-compatible tools – paving the way towards fully autonomous scientific workflows! 🧑‍🔬🤖

Paper: https://t.co/mjLUQ1jqi2
Code & benchmark: https://t.co/cP2LpG1OkJ

Special shoutout to @Dykex6 for proposing the idea and being an incredible collaborator! 🙌 Also grateful to @DanielTruhn, @Oggie_A, and @jnkath for making this happen!

#AI #LLMAgents #ToolCreation #AI4Science #MachineLearning #ComputationalPathology #ToolMaker

[Waggoner Lab @LabWaggoner]

Integrative spatial analysis reveals tumor heterogeneity and immune colony niche related to clinical outcomes in small cell lung cancer @Cancer_Cell
https://t.co/T7lHos1vCR

[Eric Topol @EricTopol]

Our new piece in @TheLancet on the potential of AI agents in medicine @james_y_zou
https://t.co/AWBTcDdKSO

[Faisal Mahmood @AI4Pathology]

✨📣Introducing THREADS: a multimodal foundation model for pathology trained on paired histology and genomic data 🔬+🧬
We show that: (a) THREADS achieves SOTA performance on >50 tasks in oncologic pathology with much less pre-training data than other models, highlighting the importance of multimodal foundation models (b) THREADS particularly does better on more difficult tasks such as treatment response prediction highlighting how capturing the molecular landscape underlying morphological patterns is important. See the pre-print and read the blog for additional insights:

Preprint: https://t.co/jIDbAEoGUq
Blog post: https://t.co/y6oQFUwd0V
Code & Model: Coming soon keep an eye out at https://t.co/tsqmTiEeVi

Congratulations to @anurag_vaidya7 @GuillaumeJaume @aspartate_ai and everyone else who contributed to this work.

[Eduard Porta @eportacangen]

It took 3 years, 4 rounds of reviews, 96 VISIUM samples, 10 cancer types, and 1 clinical trial, but it's finally out:

The spatial landscape of Cancer Hallmarks reveals patterns of tumor ecological dynamics and drug sensitivity

Here's what's new 👇

https://t.co/WMCyTWhVOX

[Manel Esteller @ManelEsteller]

Thrilled to introduce our Cell Reports @cellreports
article, showing how the iconic '#Hallmarks of #Cancer' are located in the space of real human primary tumors. A team effort co-led by Eduard Porta @eportacangen , Matthew H. Bailey, and yours truly. #SpatialBiology #Visium
https://t.co/mmPZlXtBjl

[Eric Topol @EricTopol]

Generative #AI accuracy outperformed experts for detection of ovarian cancer via ultrasound
https://t.co/54XIlrErh5 @NatureMedicine

[Nature Rev Immunol @NatRevImmunol]

Cancer immune evasion, immunoediting and intratumour heterogeneity https://t.co/YK66BfY83U

[NEJM @NEJM]

The combination of nivolumab and ipilimumab in patients with metastatic colorectal cancer led to 24-month progression-free survival of 72%, as compared with 14% with chemotherapy. Read the full CheckMate 8HW trial results: https://t.co/fEAbVvLFj0

[Baris Turkbey MD @radiolobt]

✨Excited to share our new publication: "Predicting the tumor microenvironment composition and immunotherapy response in non-small cell lung cancer from digital histopathology images"
🎉Congratulations to @spatkar94 and Tamara Jamaspishvili for leading this groundbreaking work, and 👏 kudos to our incredible team for their contributions
💡This study demonstrates how artificial intelligence can advance our understanding of the tumor microenvironment and its role in personalizing cancer treatment.
https://t.co/Sg6bmpPx9g
#TumorMicroenvironment #ArtificialIntelligence #AI #TeamScience

[Dr. Ron DePinho @RonDePinho]

An interesting conceptualization of the processes underlying cancer cell immune evasion. @Cancer_Cell https://t.co/oWEaA2tV8B

[Eytan Ruppin, MD, PhD @EytanRuppin]

Exciting news! 🌟 Our paper, "Tumor and Blood B Cell Abundance Outperforms Established ICB Response Prediction Signatures in Head and Neck Cancer," is now published in @Annals_Oncology! Explore our findings: https://t.co/RWPEpp0VXn

[Journal for ImmunoTherapy of Cancer @jitcancer]

It's TME time! Brush up on this recent #JITC article from Alvaro Lopez Janeiro et al and head over to session 301 at #SITC24 for Alex Chen's talk on predicting the #TME molecular composition to assess IO efficacy (abstract 77) https://t.co/0GgKuDetfB

[Zhaolian Lu @ZhaolianLu]

Excited to share our recent publication in @Nature! We mapped single-cell phylogenies in mouse models of intestinal tumorigenesis, revealing a polyclonal origin for colorectal precancerous lesions. Check it out here: https://t.co/h2zTIoA7vb

[Cancer Cell @Cancer_Cell]

Online Now: Overcoming tyrosine kinase inhibitor resistance in lung cancer brain metastasis with CTLA4 blockade https://t.co/hhKt2C83V3

[Sushant Patkar @spatkar94]

This work was made possible thanks to collaboration with the @theNCI Comparative Oncology Program and Artificial Intelligence Resource. @radiolobt, @DrSHarmon

[Sushant Patkar @spatkar94]

⚡️Thrilled to share our paper applying transfer learning techniques to identify novel biomarkers in canine osteosarcomas that could potentially inform more personalized treatment options for human patients!

https://t.co/TRy2G5Hhjr

[Eytan Ruppin, MD, PhD @EytanRuppin]

🚀 Proud to launch ⭐Path2Space⭐ — the first AI to discover spatial biomarkers for cancer treatment!
It predicts spatial gene expression from histopathology, enabling large-scale tumor microenvironment profiling.
https://t.co/kYFfWEYqyi 🧵1/11