Insilico Medicine Cayman Topco has established a strategic research collaboration with Aska Pharmaceutical Co. Ltd. to identify novel therapeutic targets for challenging gynecological conditions, including endometriosis, uterine fibroids and adenomyosis.

Rybodyn Inc. has announced the initial close of a $10 million seed financing to support its work decoding the dark proteome using an AI-powered novel sequencing and discovery platform. The financing will accelerate the company’s transition from foundational discovery into scaled platform execution and progress early-stage programs into IND-enabling studies.

PerturbAI has emerged from stealth mode with the release of the world’s largest in vivo CRISPR atlas as described in a preprint on Biorxiv. The study profiled over 7.7 million cells from the brains of 74 mice with different cellular knockouts of 1,947 disease-associated genes. The San Francisco-based company’s Perturb-seq platform combines CRISPR perturbations with single nucleus RNA sequencing to look at gene expression.

Computational pathology, which assesses molecular-level features of diseases directly from tissue images (rather than testing the tissue via methods such as staining or sequencing) is making rapid strides.

A project that started as a bioreactor to assist astronauts in deep space to keep medications safe in a microgravity environment could help pharma companies model how drugs behave in the human body. Omnigeniq unveiled at the J.P. Morgan Healthcare conference the first computer model of a human protein as it exists in the body, confirming that native protein topology can be calculated directly from physics.

Galux closed a ₩42 billion (US$29 million) series B round Feb. 10, led by Yuanta Investment to bring AI-driven “rational design” to the protein drug development process, already heavily influenced by human engineering.

Google Deepmind is shedding light on the dark genome with its latest AI model, which is trained to decipher the 98% of DNA that does not code for proteins. Alphagenome is designed to predict how variants in the regulatory genome exert their effects on the expression of the genes they control.

Google Deepmind is shedding light on the dark genome with its latest AI model, which is trained to decipher the 98% of DNA that does not code for proteins. Alphagenome is designed to predict how variants in the regulatory genome exert their effects on the expression of the genes they control.

How much have AI applications learned, and how can one know their capabilities if they are being evaluated with an exam that is far too easy? In 2024, with the publication of the previous benchmark to measure AI performance, the field debated whether existing assessments would keep pace with the rapid progress of AI.