An expanded atlas of human cells maps the expression of nearly all human transcription factors across 701 cell-type/tissue combinations and uncovers the heterogeneous nature of senescence across tissu...

Prevailing binder design evaluations can overstate what these methods deliver. We propose a more stringent standard for reporting binders and affinities.

These models have learned grammar. They have not learned physics.

YouTube video by Sabine Hossenfelder

The authors present a molecular classification of acute leukemia using 5-methylcytosine signatures, together with a neural network-based classifier for clinical use.

As has been long and widely emphasized in various terms … frequentism and Bayesianism are incomplete both as learning theories and as philosophies of statistics, in the pragmatic sense that e…

In October 2024, I twote that “something is deeply wrong” with what we now call virtual cell models. A lot has happened since then: modelers are advancing new architectures and mining new sources of i...

In the world of taxicab geometry, even the Pythagorean theorem takes a back seat.

This manuscript gives a big-picture, up-to-date overview of the field of (deep) reinforcement learning and sequential decision making, covering value-based methods, policy-based methods, model-based m...

Youtube channel for the Machine Learning in Computational Biology conference: https://mlcb.github.io/

Scientists are using machine learning to find new treatments among thousands of old medicines.

One of the most important events in the history of life on Earth was the emergence of multicellularity. In this episode, Will Ratcliff discusses how his snowflake yeast models provide insight into wha...

Predicting morphological impacts of perturbations using computational methods can aid treatment discovery. Here, authors present IMPA, a generative model that predicts control cell responses to measur...

A language model predicts the effects of genetic variants in the human genome.

Complete blood count indices are tightly regulated around setpoints for decades in healthy adults, and represent a deep phenotype providing opportunities for investigating differential disease risks, ...

How the measurement tools have led us to falsely believe our T is low

YouTube video by PyData

<p>The parameters of a statistical model can sometimes be difficult to interpret substantively, especially when that model includes nonlinear components, interactions, or transformations. Analysts who...

A bereaved mother’s case against our grief-phobic culture.

Here, the authors present the Pantry framework, which extracts features from RNA sequencing data and performs multimodal genetic analyses. This type of analysis can increase gene-trait associations id...

Large language models show potential in suggesting common functions for a gene set.

Nature Communications - Multi-omics integration is often limited by data sparsity and heterogeneity. Here, the authors develop MOSA, a method designed to augment DepMap cell line data to...

Listen now | Does smoking prevent COVID? Is being obese actually healthy? Or is something funny going on?

Authors should be open about the limitations of their work and not overstate its importance.

This is a screencast of my UseR! 2015 presentation: Tiny Data, Approximate Bayesian Computation and the Socks of Karl Broman. Based on the original blog post it is a quick’n’dirty …

Contribute to ImagineAILab/ai-by-hand-excel development by creating an account on GitHub.

A brief tutorial with reusable code.

YouTube video by Jeremy Howard

Population genetics notes. Contribute to cooplab/popgen-notes development by creating an account on GitHub.