Andrew L. Hufton

@alhufton
137 Followers
299 Following
188 Posts
Same ol' Andrew, but now on Mastodon. Open science advocate and scientific editor. Personal website: https://alhufton.com/. Editor-in-Chief of Patterns at Cell Press https://www.cell.com/patterns/

Our October issue is now live!
https://www.cell.com/patterns/issue?pii=S2666-3899(24)X0002-1

Featured on the cover this month is a paper presenting LigUnity, a foundation model for predicting small molecule binding affinity for drug discovery and optimization applications
https://www.cell.com/patterns/fulltext/S2666-3899(25)00219-3

In light of ongoing recent events, we have released an editorial affirming our commitment to diversity, equity, and inclusion
https://www.cell.com/patterns/fulltext/S2666-3899(25)00052-2

Register now for our seminar this Wednesday on federated learning in digital healthcare presented by
Guang Yang, Brandon Edwards, Sarthak Pati, Xiaoxiao Li

đź“… Wednesday 6th Nov 2024
⏰ 15.30 PM (London)
https://cassyni.com/events/8F2FuXndxa8YzF7Kcrjp8D

#machinelearning

Federated learning in digital healthcare: Introduction of the Federated learning in digital healthcare special collection | Privacy preservation for federated learning in health care | Discussion: Emerging trends in federated learning

In an era where data privacy and accessibility are paramount, federated learning emerges as a transformative paradigm, enabling collabora...

Cassyni
#PeerReviewTips: As a reviewer, you can help promote #openscience! If any code, data or models are missing that you feel are crucial to the paper, write to the journal and offer to submit your report *after* these are made available. #PeerReviewWeek
It’s #PeerReviewWeek and this year’s theme is the intersection of innovation & technology. In this month's Editorial, @alhufton argues that authors, editors & reviewers must be mindful of both the risks and benefits that technologies offer for peer review https://www.cell.com/patterns/fulltext/S2666-3899(24)00211-3

Our September issue is now live with a fabulous cover image by artist and biologist Mol Mir (https://molmir.com/)
https://www.cell.com/patterns/issue?pii=S2666-3899(23)X0010-5

Check out their related Creations paper https://www.cell.com/patterns/fulltext/S2666-3899(24)00182-X

Mol Mir

Work by Mol Mir

Mol Mir

Trying to up your #machinelearning learning game? Check out these three Patterns papers:

Avoid common pitfalls https://www.cell.com/patterns/fulltext/S2666-3899(24)00188-0

Examine your underlying values, assumptions and biases
https://www.cell.com/patterns/fulltext/S2666-3899(24)00160-0

Test your model design for leakage
https://www.cell.com/patterns/fulltext/S2666-3899(23)00159-9

The reporting in MIT Tech Review is such a mixed bag. Some good critical work, some "look shiny!" tech reporting that at best quotes a few "skeptics" towards the bottom before returning to boosterism. This one is an example of that:

https://www.technologyreview.com/2024/08/01/1095551/end-of-life-decisions-ai-help/

This is the same horrific idea that I wrote about in my MAIHT3k newsletter post on Monday, but @techreview goes for the "ooh shiny!" angle instead:

https://buttondown.email/maiht3k/archive/medical-science-shouldnt-platform-automating-end/

>>

End-of-life decisions are difficult and distressing. Could AI help?

Ethicists say a “digital psychological twin” could help doctors and family members make decisions for people who can’t speak themselves.

MIT Technology Review

Big model release today: Meta AI's Llama 3.1 series, including Llama 3.1 405B which appears to be the first openly licensed model that genuinely competes with current top proprietary models GPT-4o and Claude 3.5 Sonnet

My notes here: https://simonwillison.net/2024/Jul/23/introducing-llama-31/

Introducing Llama 3.1: Our most capable models to date

We've been waiting for the largest release of the Llama 3 model for a few months, and now we're getting a whole new model family instead. Meta are calling Llama …

In the @patterns July issue we launched a new special collection on Federated Learning in Healthcare. If you are interested in secure, privacy-protected techniques for using #AI and #machinelearning in healthcare do check it out!

July issue: https://www.cell.com/patterns/issue?pii=S2666-3899(23)X0008-7
Special collection: https://www.cell.com/patterns/collections/federated-learning-digital-healthcare