Embedded Files
Journal Club
Journal Club
Recall holiday next Wed
Welcome Inês - and Ana, and Arlindo
VCF paper published: https://pubmed.ncbi.nlm.nih.gov/38827109
https://link.springer.com/article/10.1007/s10676-024-09775-5#Sec3 "ChatGPT is bullshit" --> Lee?
Is this about a fork in the road between semantics and embeddings?
or is it closer to the explanatory ODE model vs stat mechanics forecasting?
_______
A whole-slide foundation model for digital pathology from real-world data
Xu, H., Usuyama, N., Bagga, J. et al. A whole-slide foundation model for digital pathology from real-world data. Nature 630, 181–188 (2024). https://doi.org/10.1038/s41586-024-07441-w
_______
See also Mark's Bioinformatics journal club at 11:00 (see below)
Hackathon
Hackathon
Heatmap clusters update [Lorena]
Heatmap clusters update [Lorena]
... the embeddings visualizer ?...
Dynamic force-graph: https://vasturiano.github.io/force-graph/example/dynamic/
How to Operate WSI foundation model
How to Operate WSI foundation model
... intro ... https://huggingface.co/prov-gigapath/prov-gigapath
... real-world genAI tooling ...
Loose Notes on Connect Governance
Loose Notes on Connect Governance
Start with unrestricted data - it will help shape governance as a type of public (to those authorized). This allows security to be addressed at the API level, not at the perimeter.
Security at the perimeter vs at the oauth token remains un-understood by domain experts. For example, the incompatibility between FAIR and enclaves or the perception of not being able to detect use patterns such as downloads. On the other end of this conversation, security at the API offers full provence - who did what when is typically offered by Cloud middle layers such as Box.com, Google Drive, etc
Hard fact: Security at the perimeter is obsolete.
George Zaki
George Zaki
Posit gives you a lot ... all the way down to what packages a given client can use
ok, he just went through the whole suite, recall from log of at the end :-)
The next DCEG Bioinformatics Virtual Core Exchange/Journal Club meeting (https://nci-dceg.github.io/bioinformatics_journal_club/meetings/24-06-12) is scheduled for 11:00-12:00pm, June 12, 2024. The hybrid meeting will take place at Rm 6E032/34 and via Teams (meeting details below).
We're pleased to have Dr. Mark Little leading the discussion. He will be discussing two recently published papers in Scientific Reports , also the work of an NCRP Committee which he has been involved with and which has been very recently published. The papers can be found on the BVC journal club folder here.
Little, M. P., Hamada, N., & Zablotska, L. B. (2023). A generalisation of the method of regression calibration. Scientific Reports, 13(1), 15127. https://doi.org/10.1038/s41598-023-42283-y
Little, M. P., Hamada, N., & Zablotska, L. B. (2024). A generalisation of the method of regression calibration and comparison with Bayesian and frequentist model averaging methods. Scientific Reports, 14(1), 6613. https://doi.org/10.1038/s41598-024-56967-6
NCRP Commentary No 34 2024 Recommendations on statistical approaches to account for dose uncertainties in radiation epidemiologic risk models.
11:00 - 12:00 CBIIT Data Science Seminar Series: The Current State of Transparency for AI Models and Datasets by Aaron Y. Lee, M.D., M.S.C.I
11:00 - 12:00 CBIIT Data Science Seminar Series: The Current State of Transparency for AI Models and Datasets by Aaron Y. Lee, M.D., M.S.C.I
Report abuse