Tal Korem

Out after peer-review: www.science.org/doi/full/10....

Our bottom line stayed: never use leave-one-out cross-validation as it has inherent train-test leakage. Consider our Rebalanced version instead!

We now also account for regression and nested cross-validation, with more extensive benchmarking.

Senator Kelly is correct.

Plus a Public Service Announcement:

KEY section of Department of Defense's Law of War Manual is 18.3.2.1.

The VERY rule on the "requirement" to refuse illegal orders gives as its paradigmatic example of what is "clearly illegal:
"orders to fire upon the shipwrecked."

Using leave-one-out cross-validation to calculate metrics such as AUC and R^2 creates bias! This can be fixed by removing one of each class in the meanwhile to maintain the training data distribution - great work by Tal and his team 🧪🧬🖥️

I found a flowchart which helps you navigate the IT landscape

Back when we hid beer in the cold room in a box labeled “yeast embryos.”

Out after peer-review: www.science.org/doi/full/10....

Our bottom line stayed: never use leave-one-out cross-validation as it has inherent train-test leakage. Consider our Rebalanced version instead!

We now also account for regression and nested cross-validation, with more extensive benchmarking.

As long as three reviewers keep reading each proposal, doesn't really address anything either

"This could take down Democrats, too."

I know. And I frankly wouldn't give even an itty bitty damn if it implicated every Democratic man in Congress, every Democratic hopeful for 2028 and every Democrat who has even thought about running for office.

Down with the sex predators, wherever they are.

Among the Schumer victimhood and his "opposition to the deal", this post really stuck with me. He was aware & grinning

White paper: github.com/aqlaboratory...
GitHub Repo: github.com/aqlaboratory...
Huggingface: huggingface.co/OpenFold/Ope...
Testimonials: openfold.ghost.io/openfold3-co...

OpenFold3-preview (OF3p) is out: a sneak peek of our AF3-based structure prediction model. Our aim for OF3 is full AF3-parity for every modality. We now believe we have a clear path towards this goal and are releasing OF3p to enable building in the OF3 ecosystem. More👇

Just to be super clear, if you’re phoning in your peer review to ai you should quit your job so someone else who actually likes science can have it.

No idea. Still working through this.

This is from the very paper you linked to - Figure S5. They claim that this has a p-value of 1. It's not here and there, this is what most results look like, and this is a large part of the basis for claiming that there are no robust associations with other tumors.

So you look at this figure and your interpretation is "no signal"?

I never knew I needed this thread

Korem Lab - Microbiome Systems Biology @ Columbia | New York, USA We apply systems biology approaches to decipher the metabolic interactions between the microbiome and its human host in diverse clinical settings, aiming towards personalized microbiome-based therapeu...

We are hiring a postdoc - come work with us (www.koremlab.science) at the intersection of #microbiome, data science, and women's health!
Message or email me if interested. 🖥️ 🧬

I am seeking a postdoc for my group at UCLA. We work at the intersection of population genetics x microbiome (garud.eeb.ucla.edu). If interested, please message me!

This will also likely reduce the number of study sections, firing SROs and making them less specialized.

Guidelines for preventing and reporting contamination in low-biomass microbiome studies Nature Microbiology - In this Consensus Statement, the authors outline strategies for processing, analysing and interpreting low-biomass microbiome samples, and provide recommendations to minimize...

Hope this is useful - consensus statement "Guidelines for preventing and reporting contamination in low-biomass microbiome studies" rdcu.be/er3Io

The trolley problem graphic where one side is several people tied to the train tracks except the other side has no one on the tracks. A man is standing holding a lever trying to decide which track the trolley should take. The text reads “You can pull the lever, but to do so you must wear a mask at the grocery store.”

Not getting much attention, except in a recent NYTimes story, is a provision to increase the tax on university endowments and those of other nonprofits.

Incorporating scale uncertainty in microbiome and gene expression analysis as an extension of normalization - Genome Biology Statistical normalizations are used in differential analyses to address sample-to-sample variation in sequencing depth. Yet normalizations make strong, implicit assumptions about the scale of biologic...

New paper in Genome Biology!

genomebiology.biomedcentral.com/articles/10....

We introduce scale models, a generalization of normalizations that explciitly account for uncertainty in biological system scale (e.g., microbial load).

as a resident of syracuse, ny, a rust belt town that used to be an economic epicenter for the nation: syracuse university is our largest local employer now and if it goes under, so does my town, which has the largest concentration of child poverty in the nation.

Antibiotic research at Harvard lab threatened by federal funding cuts Microbiologist Michael Baym studies antibiotic resistance at Harvard Medical School. He lost millions in federal funding this week.

"I'm still in shock. I know that there have been political issues around Harvard in recent weeks, but antibiotic resistance isn't one of them." My conversation with Harvard microbiologist @baym.lol, one of many researchers there who just lost millions in fed. grants. www.wbur.org/news/2025/05...

Our paper explaining why Gihawi et al. failed to prove an error in the normalization used by the 2020 cancer #microbiome analysis now out as a Matters Arising in @asm.org #mSystems (w/ @george-austin.bsky.social) 🖥️ 🧬

Thread explaining the key points below.

journals.asm.org/doi/10.1128/...

Our paper explaining why Gihawi et al. failed to prove an error in the normalization used by the 2020 cancer #microbiome analysis now out as a Matters Arising in @asm.org #mSystems (w/ @george-austin.bsky.social) 🖥️ 🧬

Thread explaining the key points below.

journals.asm.org/doi/10.1128/...

Come and work with me!

The Nature Micro team is expanding and we're looking for someone to champion microbial ecology, plant micro & related areas for the journal

Knowledge of microbial ecology/plant micro is desirable but we're open to applications from all microbiologists

Link below 👇

Congrats!

Processing-bias correction with DEBIAS-M improves cross-study generalization of microbiome-based prediction models - Nature Microbiology DEBIAS-M corrects technical variability in microbiome data in a manner both interpretable and suitable for machine learning. In extensive benchmarks, DEBIAS-M facilitates robust analyses that generali...

OUT NOW: Processing-bias correction with DEBIAS-M improves cross-study generalization of microbiome-based prediction models

@tkorem.bsky.social & co

#microsky #microbiomesky 🧪

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