whereismyai
Alphaprotein Novo
Alphaprotein Novo is a generative diffusion pipeline for de novo enzyme design via structural motif scaffolding.
AlphaProtein Novo is a generative diffusion pipeline for de novo enzyme design via structural motif scaffolding. It includes a diffusion model which co-generates protein structures and sequences conditioned on a catalytic motif and ligand context. To form an end-to-end pipeline, the diffusion model is combined with optional sequence redesign using LigandMPNN, structure prediction using AlphaFold 3, and evaluation metrics. Campaigns are configured using a JSON manifest describing the design problem, motif conditioning, and downstream processing. The software is intended for researchers working on enzyme design for new-to-nature chemistry and non-natural substrates.
Alphaprotein Novo at a glance
Key features
- Generates protein structures and sequences via diffusion
- Conditions generation on catalytic motifs and ligand context
- Performs sequence redesign using LigandMPNN
- Predicts structures using AlphaFold 3 or AlphaFold 3 Leaving Atom
- Runs end-to-end design campaigns using a JSON manifest
- Supports evaluation metrics for designed enzymes
Use it for
- Designing enzymes for new-to-nature chemistry
- Scaffolding structural motifs for non-natural substrates
- Running end-to-end protein design and folding pipelines
Alternatives to Alphaprotein Novo
- Biomni — Automates complex wet-lab experimental design with specialized tools and databases.
- Mol 1 — It handles complex biomolecular prediction tasks with customizable JSON inputs.
- DiscoveryRSI — Achieves high actionable-reference rates and supports multi-agent evolutionary research search.
- NanoJev — It runs parallel decisions and outputs probability distributions without output-token decoding.
- Paper2Agent — It enables direct interaction with research papers and automatic result reproduction.
- Hypoarena — Provides a fully offline environment to test scientific discovery pipeline logic.
- Ncm — Generates text significantly faster than diffusion baselines while maintaining high quality.
- Neuron Explorer — It keeps every rollout and maps model layers in perspective.
- Finetuning With Sampling — Official implementation of the Finetuning with Sampling research paper from Harvard.
- Arbor — It grows a hypothesis tree and tests changes on held-out data.
- Open Science — Local-first design with persistent Python and R kernels and traceable artifacts.
- Liatir App — Runs local analyses offline with managed AI models and scientific viewers.
All Alphaprotein Novo alternatives