Tessera
Folgen

Raphael Gottardo

@rgottardo.bsky.social

Biomedical Data Science Center Director @CHUV. Professor at @UNIL and @EPFL. AI, ML, and statistical learning for high-dimensional (single-cell/spatial) data in clinical and translational medicine. Interdisciplinary scientist passionate about data.

38 Posts1858 Follower914 Folgt
Raphael Gottardo@rgottardo.bsky.social · last yr.

🧬 New paper out! 🔗 www.nature.com/articles/s41... Frustrated by noisy CITE-seq data? ADTNorm helps normalize it and introduces a staining index to assess antibody quality. Great work by former postdoc Ye Zheng. Supported by @hipcproject.bsky.social #CITEseq #SingleCell #ADTNorm

ADTnorm: robust integration of single-cell protein measurement across CITE-seq datasets - Nature Communications

Here the authors present a computational method that expands the potential of multimodal single-cell analyses by delivering an accurate, fast, and user-friendly approach for normalizing and comparing ...

nature.com

Raphael Gottardo@rgottardo.bsky.social · last yr.

Big shoutout to our own Jieran Sun onesinglecell.bsky.social for leading this team effort! 🧠📍 Benchmarking clustering in spatial transcriptomics isn’t easy — but here is SACCELERATOR Preprint: www.biorxiv.org/content/10.1... With markrobinsonca.bsky.social, Naveed Ishaque, Ahmed Mahfouz, Brian Long

Beyond benchmarking: an expert-guided consensus approach to spatially aware clustering

Spatial omics technologies have revolutionized the study of tissue architecture and cellular heterogeneity by integrating molecular profiles with spatial localization. In spatially resolved transcript...

biorxiv.org

Raphael Gottardo@rgottardo.bsky.social · last yr.

🎉 New paper alert. We benchmarked Visium, GeoMx, and Chromium for FFPE tumor analysis. Thanks @estellayixingdong.bsky.social for pushing this forward, & MOSAIC collaborators! 📄 www.nature.com/articles/s41... #SpatialTranscriptomics #CancerResearch cc: @owkin.bsky.social @10xgenomics.bsky.social

Transcriptome analysis of archived tumors by Visium, GeoMx DSP, and Chromium reveals patient heterogeneity - Nature Communications

Currently, there is an urgent need to evaluate the strengths and limitations of various probe-based full transcriptome methods for formalin-fixed paraffin-embedded tumor tissues. Here, the authors ana...

nature.com

Raphael Gottardo@rgottardo.bsky.social · 2y ago

Great news! Thrilled about this new appointment at EPFL to strengthen collaborations in biomedical data science across CHUV, @unil.bsky.social, and the EPFL. Excited to work closely with EPFL colleagues and students ! #datascience #AI #medicine #biology actu.epfl.ch/news/two-app...

Two appointments at the School of Life Sciences

The Board of the Swiss Federal Institutes of Technology has announced the appointment of professors at EPFL. Among them, are Professors Markus Jeschek and Raphael Gottardo at the School of Life Scienc...

actu.epfl.ch

Raphael Gottardo@rgottardo.bsky.social · 2y ago

Interesting work from @deep-mind.bsky.social on probabilistic weather forecasting (aka GenCast) www.nature.com/articles/s41... BUT why didn't they cite previous work in this space by Raftery and colleagues: www.science.org/doi/full/10.... journals.ametsoc.org/view/journal... and many other papers!

Probabilistic weather forecasting with machine learning - Nature

GenCast, a probabilistic weather model using artificial intelligence for weather forecasting, has greater skill and speed than the top operational medium-range weather forecast in the world and provid...

nature.com

Raphael Gottardo@rgottardo.bsky.social · 2y ago

@lpachter.bsky.social Interesting! Also, Louvain/Leiden determine the number of clusters automatically (through the resolution), often leading users to assume the default is optimal! However, identifying the correct number of clusters is a complex statistical problem, which shouldn't be ignored.

Lior Pachter@lpachter.bsky.social · 2y ago

Another example of the different results one gets from a Scanpy vs. Seurat analysis, in this case a Visium HD dataset from academic.oup.com/bioinformati... 13 vs. 20 clusters. And qualitatively different results, corroborating what we saw in biorxiv.org/content/10.1...

Raphael Gottardo@rgottardo.bsky.social · 2y ago

Ok, I’ve added a few more people to the list: go.bsky.app/73rcuJn Please reach out if you want to be added! The more the better. #AI #ML #DataScience #Omics #SingleCell #SpatialBiology

Raphael Gottardo@rgottardo.bsky.social · 2y ago

Ok, I tried to create my own list of people working on developing statistical or machine learning models applied to omics data. I am sure I missed a lot of cool people. If you'd like to be added, let me know. #Stats #ML #Omics go.bsky.app/73rcuJn

Raphael Gottardo@rgottardo.bsky.social · 2y ago

Jacques Fellay (EPFL) and I (UNIL/CHUV) will be discussing applications of #AI in #Health at 10:30 AM. This is one of the areas where #AI is poised to make the biggest impact in the coming decade. Join us, ask your questions, and be part of the conversation. Don’t miss it—be there or be square! 💡🌍

unil.bsky.social@unil.bsky.social · 2y ago

🧠 Vous souhaitez savoir comment fonctionne l’intelligence artificielle? Connaître son impact? Son histoire? Apprendre à l’utiliser? L'EPFL et l’UNIL proposent des ateliers ouverts à tous dès 10 ans. 📅 Le 23.11.24, au Rolex Learning Center. Inscription nécessaire: journee-ia.epfl.ch

Raphael Gottardo@rgottardo.bsky.social · 2y ago

Thank you for this incredible honor! 🙏 A huge shoutout to the trainees in my lab—this achievement is thanks to you. Excited for what’s ahead from our Biomedical #DataScience Center at UNIL/CHUV 🚀 #Teamwork #Innovation #AI #HighlyCited2024 clarivate.com/highly-cited... @unil.bsky.social

Highly Cited Researchers | Clarivate

The Highly Cited Researchers 2024 list identifies and celebrates individuals who have demonstrated significant and broad influence in their fields of research. Through rigorous selection criteria and ...

clarivate.com