Edi Prifti

3 Open #Postdoc positions in #MachineLearning and #Health at #UMMISCO (The International Unit of Mathematical and Computer Modeling of Complex Systems) of the French National Research Institute for Sustainable Development @ird_fr and @Sorbonne_Univ_

Sauvons le Palais de la découverte chng.it/D9W4LSjw via @ChangeFrance

MAGA is making the claim that if you watch the entire 50 minute video, Zelensky is the antagonist. This isn't true. At all. I was with Zelensky before this meeting and it's important to know his mindset heading in. 1/ A short 🧵on how the entire ambush went down.

Very happy to see our work out in preprint. Try it out, hope you'll like it

Happy to share our latest research with @rodendm @VUMChealth @sorbonne : Polygenic Predictor of Baseline QTc is Associated With Sotalol-Induced QT Prolongation | Circulation ahajournals.org/doi/10.1161/CI…

Visite à l’institut Imagine de Paris, centre dédié aux maladies génétiques, unique au monde, et discussions prometteuses sur projets de recherche communs franco-albanais 🇫🇷🤝🇦🇱 avec le directeur prof. Lyonnet et les chercheurs albanais réputés, dr. Edor Kabashi et dr. Edi Prifti

Wow remote controlled lifeguard!

Congratulations @amglazer and the team great work

Muhammad and coll. provide a comprehensive functional map of thousands of protein-coding KCNE1 variants involved in arrhythmic disorders @amglazer Work is out now on Genome Medicine: genomemedicine.biomedcentral.com/articles/10.11…

@gunsnrosesgirl3 Monstera fruit

Can you explain what this fruit is? twitter.com/tradingMaxiSL/…

Our new review paper titled “Deep learning methods in metagenomics: a review” - go.shr.lc/3QaVP4h is now out in Microbial Genomics

NEW 🧵: American politics is in the midst of a racial realignment. I think this is simultaneously one of the most important social trends in the US today, and one of the most poorly understood.

In the early 1990s, Brazilian photojournalist Sebastião Ribeiro Salgado was assigned to document the genocide in Rwanda, an assignment that profoundly affected him. Returning to his native Minas Gerais, Brazil, in 1994, Sebastião hoped to reconnect with the verdant forests of his youth. However, he was met with a starkly different reality – his once flourishing home had become a desolate, barren expanse, devoid of wildlife. It was then that his wife, Lélia Deluiz Wanick Salgado, suggested the ambitious project of reforesting the entire area. Embracing this vision, Sebastião and Lélia spent the next two decades planting over 2.7 million trees. Their efforts led to the restoration of 1,500 acres of rainforest, transforming the land into a biodiverse haven for 293 plant species, 172 bird species, and 33 animal species, including some that were nearing extinction.

UN should embrace Open-source to reach Sustainable Development Goals

@nsegata @UniTrento Congratulations

So happy and proud to receive the Early Career "Research Quality Award 2023" from @UniTrento Rector and Research Pro-Rector. Really touching for me after I spent all my student career and most of my academic career at UniTrento. Photo ©UniTrento ph. Pierluigi Cattani Faggion

Our last work just released in @NatureMedicine from the ICI-international registry on Thymus alterations and susceptibility to immune checkpoint inhibitor #myocarditis nature.com/articles/s4159… @CardioOncology @salimhayek @APHP @Sorbonne_Univ_ @Inserm @HopPitieSalpe @UMich @UCSF

Proud to have contributed to this thorough work with bright scientists from @GmtScience. We show the impact of simulation and common feature space analyses on the performance and the ranking. Best profilers: BiomeScope, MetaPhlan4 and mOTU3… This comes with 2TB of simulated data

R² is a widely used measure of fit, but for many analysts, it is just a number. They believe high R² ➡ Good predictions. This is not always true! Now I will clarify. 🔽 R-squared measures how well the regression model fits the observed data. To be more precise: It is the proportion of the variation in the dependent variable that is predictable from the independent variable. It usually ranges from 0 to 1: (In rare cases it can be negative, I will explain this in another tweet) R² = 0 The model does not explain any of the variability in the dependent variable ➡ No predictive power ➡ Bad model. R² = 1 The model perfectly explains all the variability in the dependent variable ➡ Perfect fit to the data ➡ Good model if not overfitted and has predictive power. A high R-squared value does not mean that the predictions made by the model will be correct. It doesn't measure predictability power, it measures how well the model fits! In the example below, we compare the mean of the data to a fitted line. Of course, the mean of values is not a good fit ➡ the errors are large. On the other hand, the fitted line has smaller errors ➡ The R² will be close to 1. To calculate R² we need: - The total sum of squares for the mean - Sum of squares for the residuals from the model - Finally, subtract the ratio from 1 ___ That's it for today. I hope you've found this Tweet helpful. Like/Retweet for support and follow @levikul09 for more Data Science content. Thanks 😉

A reinforcement learning model developed to adapt Artificial Intelligence (AI) predictions to human preferences showed better performance for skin cancer diagnoses and optimal management decisions compared to a supervised learning model @HaraldKittler nature.com/articles/s4159…

Are you annoyed by strange results in your metagenomics data? Your dataset may contains well2well contaminations. Our poster B162 explains how to detect this critical issue using CroCoDDeeL, a tool designed by my student Lindsay Goulet. We will not bite you 🐊. #ISMBECCB2023

There are over 510 million square kilometers of area on the surface of Earth, but less than 30% of this is covered by land. The rest is water, in the form of vast oceans. This visualization by visualcapitalist.com uses data from UNSD [read more: buff.ly/3iFnxUO]