Francesco Strozzi's Avatar

Francesco Strozzi

@fstrozzi

Passionate about Science, Bioinformatics, Healthcare and Data. I’m an Elder Millennial

93
Followers
495
Following
1
Posts
13.11.2024
Joined
Posts Following

Latest posts by Francesco Strozzi @fstrozzi

Post image

New Journal for ImmunoTherapy of Cancer ( #JITC ) article: Mimicry-based strategy between human and commensal antigens for the development of a new family of immune therapies for cancer bit.ly/3ET6xtD @fstrozzi.bsky.social @wickwolfgang.bsky.social

25.02.2025 14:40 👍 3 🔁 1 💬 0 📌 0

This is an amazing technology, we are already using it ourselves and it is transformative. Kudus to @caleblareau.bsky.social and @ronanchaligne.bsky.social and their teams.

09.01.2025 18:56 👍 39 🔁 9 💬 1 📌 1

Some thoughts about what I am looking forward this year from my vantage point of computational molecular biology. One mega-trend for me; we will definitely see more AI methods of all sorts emerge.

03.01.2025 18:46 👍 65 🔁 25 💬 1 📌 3

CASSIA allows for robust, automated cell annotation in single-cell RNA-sequencing data https://www.biorxiv.org/content/10.1101/2024.12.04.626476v1

09.12.2024 04:01 👍 1 🔁 1 💬 0 📌 0
Preview
Benchmarking second-generation methods for cell-type deconvolution of transcriptomic data In silico cell-type deconvolution from bulk transcriptomics data is a powerful technique to gain insights into the cellular composition of complex tissues. While first-generation methods used precompu...

Great collaboration with @itisalist.bsky.social ✨

We hope our study and set of tools and resources can be helpful to the scientific community 💫

📝 preprint: doi.org/10.1101/2024...
🛠️ omnideconv ecosystem: omnideconv.org

Please repost and help us spread the word!

6/6

12.11.2024 13:40 👍 13 🔁 6 💬 0 📌 1
Preview
Digital profiling of gene expression from histology images with linearized attention - Nature Communications Predicting gene alterations and expression from whole-slide images (WSIs) can be a cost-efficient solution for cancer profiling. Here, the authors develop SEQUOIA, a transformer model with linearised ...

Digital profiling of gene expression from histology images with linearized attention.

Codes for data pre-processing, model training and evaluation are available on GitHub: github.com/gevaertlab/s...

www.nature.com/articles/s41...

25.11.2024 05:55 👍 1 🔁 0 💬 0 📌 0
Preview
Atlas of the plasma proteome in health and disease in 53,026 adults A large-scale proteomics study involving 53,026 individuals maps 2,920 plasma proteins to 406 prevalent diseases, 660 incident diseases, and 986 health-related traits, identifying promising biomarkers...

Atlas of the plasma proteome in health and disease in 53,026 adults 👩‍🔬🥼👨‍🔬🧪. #proteomics #proteome #plasma #MedSky 👇👇

www.cell.com/cell/fulltex...

23.11.2024 07:49 👍 127 🔁 56 💬 11 📌 5