Arnaud Dhaene

@json_yim @HannesStaerk Looks cool! Is it as flexible as RFdiffusion in the sense of being able to do motif scaffolding, fold conditioning, and binder design?

Combining discrete and continuous data is an important capability for generative models. To address this for protein design, we introduce Multiflow, a generative model for structure and sequence generation. Preprint: arxiv.org/abs/2402.04997 Code: github.com/jasonkyuyim/mu… 1/8

@pwang I use Todoist, it integrates well with Fantastical

I'm almost afraid to ask, but... What is everyone's fave simple TODO app? It's for personal stuff, but want to be able to separate into work stuff and projects. Needs solid mobile support. I already use Joplin and Keep. Don't want to use either for this. Trello feels too heavy.

All you need to do is wrap your original list object in a FuncList object. gist.github.com/arnauddhaene/4…

This is why I decided to create a little wrapper around the emblematic Python list that allows calling {filter, map, reduce, flatmap} on the list element itself. It's definitely a WIP, but my lists are now unencumbered and my code (more) readable!

I always felt that some of the functional tools that come with standard Python were insufficient and awfully verbose.

Unpopular data science opinion: no body uses dashboards

@marty You can simply sign into an account for a Google Chrome session window and all Google links will follow that account

I'll pay $100000000 a month for a tool that makes Google Docs/Meet links open in the right Google account automatically

Give fewer choices, get more action.

@bindureddy Completely agree with you, despite it being a weird setting to use the word “crisply”

The skill most underrated by both data scientists and Ai researchers - verbal and written communication Writing is as important as coding. Given ML is an indeterministic science, which requires practitioners to articulate both the problem statement and solution crisply

For the sake of the calculation, let us assume a 95% true-positive and a 2.3% false-positive rate based on the paper below (UK). Let us use the current infection rate in the UK: 273 per 100k residents (7-day rolling average) means P(C) = 0.00273 👇 coronavirus.data.gov.uk

What's the probability that you are infected with COVID-19 given that your RT-PCR test came back positive? 🤔 Hint: it's lower than you think! Let's find out using Bayes' Theorem👇

People are not getting tested randomly! Most people who get swabbed have a reason, they might display symptoms, recent contact, etc. This increases the probability of getting tested, AND of being infected! Lesson learned: never forget confounders! 🕵️‍♂️

P(C | T) = 0.95 / (0.95 * 0.00273 + 0.023 * 0.99727) * 0.00273 P(C | T) = 0.1015 or 10.15% Putting all of this together, we find that the probability you are infected given a positive test result is only 10.15%! Wait, is this true? How can this be? 👇

@chrisalbon Looking forward to this!

@kareem_carr I think an (the most) important part that’s left out is the causality models humans use to make sense of the data, link them to domain expertise and define the ML tasks and relevant statistics.

really makes you think.

@Vuhlandes y so butthurt

Prime example of opinions being said when no one asked