Keeping up with AI for Science - Monthly Roundups by Iris
AI for Science news, once a month, in about five minutes: AI drug discovery, protein structure prediction and design, AI for materials and chemistry, autonomous and self-driving labs, AI research agents, scientific foundation models, and AI weather and climate models. Every story links to its sources.
Latest: October 2026
IPD and Nvidia release open-source RFD4-Proteina
- IPD and Nvidia released RFD4-Proteina, an open-source protein-design model reporting five- to 10-fold gains in generation speed and design success across four computational tasks:
- Pinal linked natural-language functional descriptions to protein sequences and structures, with experimental validation across four tasks and a 1.7-fold titre increase for one engineered H-protein:
- An AI-guided perovskite interface reached 27.2% efficiency and retained more than 95% after 2,000 hours at 65°C, while a separate data-driven study synthesised 18 multilayer MXene phases:
- October 20265 min listen
IPD and Nvidia release open-source RFD4-Proteina
In this report October's results put more weight behind function-directed protein design and experimentally tested materials discovery, while autonomous science moved into facility-scale construction. Funding and model work also focused on…
- September 20264 min listen
Stanford builds a 37,000-agent virtual biotech
In this report September added evidence at several layers of AI-enabled science: statistical signals from clinical data, experimentally tested molecular designs, and laboratories that can close the loop between hypothesis and physical…
Want this for your field?
Iris builds a briefing agent around your own profile: your field, your focus areas, your context. Delivered on your schedule.