Doron Stupp

MD-PhD. Previously Google AI Resident at @GoogleAI, PhD at @HebrewU. Interested in AI for Healthcare.

[Doron Stupp @doronst1]

Excited to share the preprint of our work on structuring A&P sections in clinical notes!
In it we provide a dataset and build ML models to identify problems, their assessments and plan action items.

https://t.co/aUES5XEoG7
@GoogleAI @GoogleHealth
#MedTwitter

[Eran Segal @segal_eran]

Our lab at the Weizmann Institute was hit tonight by Iran

We will rebuild and return 💪

[Google AI @GoogleAI]

Oran Lang innovates at Google, advancing medical explainability with Generative AI and now with Gemini. His project, StylEx, uses StyleGAN to visualize decision-making. This breakthrough aids understanding and detects biases, opening new research avenues. Explore Oran's impactful work at Google Research. → https://t.co/N4VvC8CW3m

[The Lancet Digital Health @LancetDigitalH]

NEW Research: A #DeepLearning model for novel systemic #biomarkers in photographs of the external eye. @GoogleHealth

Read it here: https://t.co/IjF3YOPl0h

[Doron Stupp @doronst1]

The accompanying dataset, containing annotations of almost 580 notes and over 30K annotations over physician notes from the MIMIC-III dataset, is available at Zenodo: https://t.co/0XfVeUeCSy

Our code is available on GitHub: https://t.co/EiGeP9YHZt

[Doron Stupp @doronst1]

Excited to share the preprint of our work on structuring A&P sections in clinical notes!
In it we provide a dataset and build ML models to identify problems, their assessments and plan action items.

https://t.co/aUES5XEoG7
@GoogleAI @GoogleHealth
#MedTwitter

[Doron Stupp @doronst1]

We show that in this task, incorporating domain knowledge in the form of weak supervision on heuristics and data augmentation improves performance with fewer labels and generalization across departments.

[medRxiv @medrxivpreprint]

Mondo: Unifying diseases for the world, by the world https://t.co/AZfOfRK0kl #medRxiv

[Nature Communications @NatureComms]

Protein structure prediction by deep learning was just named the @naturemethods Method of the Year, and now @TomerTsaban @jvarga92 @AvrahamOrly @OraFurman et al. show that #AlphaFold 2 can be adapted to predict protein-peptide complex structures @FurmanLab https://t.co/WjqZrim7jY

[Nicole Mitchell @nicki_mitch]

Excited to share the release of my first paper @GoogleAI with Johannes Ballé, @MatharyCharles and Jakub Konečný! https://t.co/432aHGqnqY

We leverage rate-distortion theory to achieve competitive accuracy at a fraction of the communication cost in federated learning.

[Ora Furman Lab 🎗 @FurmanLab]

Our paper on peptide-protein docking with @AlphaFold2 was published today in @NatureComms 🥳🥳🥳 Now it also includes calibration of the method and further analysis of the results!
Have a look at: https://t.co/DZbhY26xVF

[Or Zuk @or_zuk]

We published a new supervised functional prediction method based on integrating clade-specific co-evolution signals. Led by @doronst1, with Elad Sharon and Idit Bloch, all from @YTabach lab, and with @marinkazitnik

https://t.co/DXnKTLek7q

[Doron Stupp @doronst1]

@_atanas_ Thanks for recognizing our work! @YTabach @dbcr_huji

[Doron Stupp @doronst1]

@Caroline_Bartma I think WikiGenes (https://t.co/4cpRfbL9bH) and WikiPathways (https://t.co/fhGSxfHv1z) have this aim in mind, I find both to be quite useful

[Jason Sheltzer @JSheltzer]

Our new paper is out today. We used CRISPR to uncover some really striking findings with several drugs and drug targets in clinical trials. Also, we accidentally found the first-ever inhibitor of the cyclin-dependent kinase CDK11. https://t.co/Rthvr67cyk

[Doron Stupp @doronst1]

Come see my poster (K-31) at #ISMBECCB and talk about functional interaction prediction using machine learning and phylogenetic profiling! #evolcompgen

[Doron Stupp @doronst1]

A really mind blowing talk by Olivier Lichtarge about modeling evolutionary fitness with Calculus. Interesting to see how powerful these basic principles are in modeling evolution. #ISMBECCB

[Doron Stupp @doronst1]

Great talk from Wei Wang at #ISMBECCB about extracting clinical knowledge from case reports using deep learning. Turning case reports into graphs @bio_kare

[Ross Cloney @rosscloney]

Timothy Lu's group presents SPECS for screening and identify #synbio synthetic promoters with cell-state specificity

Out now @NatureComms

https://t.co/qLp0XhyyjY

[Doron Stupp @doronst1]

Excited for my first co-author paper! Published today @NatureComms
https://t.co/3zKbob3gqm

A high-throughput screening and computation platform for identifying synthetic promoters with enhanced cell-state specificity (SPECS)
#phdchat #mdphd #Science #scitwitter #rstats