~180 lines of code to win the in silico portion of the Adaptyv Nipah binding competition
Here's the script we used to get 1st place in the in silico portion of the Adaptyv Nipah competition: import modal def download_boltz2(): from mosaic.models.boltz2 import Boltz2 Boltz2() ### Build modal image: install mosaic + deps and download boltz2 model. image = ( modal.Image.debian_slim(python_version="3.12"
~180 lines of code to win the in silico portion of the Adaptyv Nipah binding competition Nick Boyd , Sam Guns - 08 Jan, 2026 Here's the script we used to get 1st place in the in silico portion of the Adaptyv Nipah competition: import modal def download_boltz2(): from mosaic.models.boltz2 import Boltz2 Boltz2() ### Build modal image: install mosaic + deps and download boltz2 model. image = ( modal.Image.debian_slim(python_version="3.12") .apt_install("git") .run_commands("git clone https://github.com/escalante-bio/mosaic.git") .workdir("mosaic") .run_commands("uv pip install --system -r pyproje
Explore this link on the map →saved by
related reading
- Ludovico Comitoludocomito.dev
- Minibinder design is just not that hardblog.escalante.bio
- AlphaProteo generates novel proteins for biology and health research — Google DeepMinddeepmind.google
- AlphaFold2 @ CASP14: “It feels like one’s child has left home.” << Some Thoughts on a Mysterious Universemoalquraishi.wordpress.com
- A Conversation With Navvye Anand (Bindwell) | Rowanrowansci.com
- Engineering Plastic-Degrading Enzymes and PCSK9 Binders with Protein AI Toolsblog.latch.bio
- Manifold Bio | Tissue-targeted medicines, designed in vivomanifold.bio
- Paving the way for agents in biology \ Anthropicanthropic.com
- Evo 2 Can Design Entire Genomesasimov.press
- Practical Cheminformatics Index - Practical Cheminformaticspatwalters.github.io
- DISCO — Teaching AI to Invent Enzymes Nature Never Imagineddisco-design.github.io
- Google DeepMind and Isomorphic Labs introduce AlphaFold 3 AI modelblog.google