Tag
Google DeepMind has open-sourced Science Skills, a collection of agent skills for scientific research tasks including genomics, structural biology, and cheminformatics, to accelerate agentic workflows with scientific grounding and higher token efficiency.
A new preprint from the Arc Institute introduces PerturbSpace, a method for spatially resolved, multimodal whole-transcriptome CRISPR screens compatible with standard single-cell workflows.
A researcher sequenced a human genome to 30× coverage entirely at home using an Oxford Nanopore P2 Solo, marking the first time this has been done outside a lab. He attributed his success to AI helping solve technical problems across software, hardware, and molecular biology.
Marc Andreessen on the Joe Rogan podcast shares 17 provocative takes on AI, including claims that AGI has arrived, top models surpass human experts, and AI is transforming medicine, therapy, coding, and science.
AgentCo-op is a retrieval-based synthesis framework for composing interoperable multi-agent workflows from reusable skills, tools, and external agents. It uses typed artifact handoffs and bounded self-guided local repair, achieving strong results on benchmarks and enabling collaborative discovery in open-world genomics tasks.
Rosalind is a deterministic genomics engine in Rust designed to run whole-genome pipelines with O(√t) memory, enabling bioinformatics on laptops and edge devices.
AttnGen is an attention-guided training framework that embeds interpretability into the optimization of deep neural networks for genomic sequence classification, achieving improved accuracy and encouraging models to focus on informative nucleotide positions.
DeepMind highlights the expanded impact of AlphaEvolve, a Gemini-powered coding agent, demonstrating its ability to optimize algorithms for genomics, grid optimization, earth sciences, quantum physics, and mathematics.
Google DeepMind highlights the broad impact of its Gemini-powered coding agent, AlphaEvolve, demonstrating significant advancements in genomics, grid optimization, earth sciences, and quantum physics research.
A user with no lab experience used Claude to guide them through building a home wetlab and sequencing their own genome, highlighting the democratization of DIY biology through AI assistance.
This paper introduces Shesha, a geometric stability metric that quantifies directional coherence of single-cell CRISPR perturbation responses using mean cosine similarity, revealing regulatory architecture and predicting cellular stress across 2,200+ perturbations in five CRISPR datasets.
OpenAI releases GPT-Rosalind, a specialized life sciences model optimized for protein reasoning, chemical analysis, genomics, and scientific workflows.
The paper introduces RGxEStat, a lightweight interactive tool that applies mixed-effect models to analyze gene-environment interactions, offering breeders a user-friendly alternative to complex SAS/R programming.
AI tools such as AlphaFold help Ugandan researchers conduct local cancer genetic research, narrowing breast cancer vaccine candidate targets from 15,000 to 15. This significantly lowers the research threshold and demonstrates the potential for democratizing science.