Regina Barzilay, Tommi Jaakkola, Jason Yim, John Yang
We lifted 2 functions out of this paper's own repositories and ran 2 of them in a sandbox. "Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results.
| Repository | Role | Ran |
|---|---|---|
| johnyang101/pmpnndiff | canonical | 2 of 2 |
| Function | Status | Where it lives |
|---|---|---|
| pmpnn_sample | Ran | johnyang101/pmpnndiff/experiments/inference.py code served (permissive licence) · get_code("4499a1c5a50594c5") |
| sampling_fn | Ran | johnyang101/pmpnndiff/experiments/inference.py code served (permissive licence) · get_code("686a6e46697bf230") |
Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.
Generating protein sequences that fold into a intended 3D structure is a fundamental step in de novo protein design. De facto methods utilize autoregressive generation, but this eschews higher order interactions that could be exploited to improve inference speed. We describe a non-autoregressive alternative that performs inference using a constant number of calls resulting in a 23 times speed up without a loss in performance on the CATH benchmark. Conditioned on the 3D structure, we fine-tune ProteinMPNN to perform discrete diffusion with a purity prior over the index sampling order. Our approach gives the flexibility in trading off inference speed and accuracy by modulating the diffusion speed.
The same record, over MCP at https://syntology.ai/mcp:
get_harvested_code_for_paper("2312.02447")
get_code_for_paper("2312.02447")
have("2312.02447")
Connect an agent — have() is free.