SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2402.13555 · 2024

Full-Atom Peptide Design with Geometric Latent Diffusion

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 9 functions out of this paper's own repositories and ran 7 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.

RepositoryRoleRan
thunlp-mt/pepglad canonical 7 of 9
FunctionStatusWhere it lives
aar Ran thunlp-mt/pepglad/evaluation/seq_metric.py
code served (permissive licence) · get_code("99b400302703c232")
clamp_coord Ran thunlp-mt/pepglad/generate.py
code served (permissive licence) · get_code("f2916ae470191082")
compute_rmsd Ran thunlp-mt/pepglad/evaluation/rmsd.py
code served (permissive licence) · get_code("a1113bf1f4b79892")
get_best_ckpt Ran thunlp-mt/pepglad/generate.py
code served (permissive licence) · get_code("f7ef153bd4e8be1a")
slide_aar Ran thunlp-mt/pepglad/evaluation/seq_metric.py
code served (permissive licence) · get_code("e1b9a31622a34ae1")
struct_diversity Ran thunlp-mt/pepglad/evaluation/diversity.py
code served (permissive licence) · get_code("9ad6907b79ff7bd0")
to_device Ran thunlp-mt/pepglad/generate.py
code served (permissive licence) · get_code("8fb15b5e77827ed9")
create_encoder Not yet run thunlp-mt/pepglad/models/autoencoder/model.py
code served (permissive licence) · get_code("5bebb16ab75fb874")
url_get Not yet run thunlp-mt/pepglad/utils/network.py
code served (permissive licence) · get_code("2d15d2649443d0f6")

Repositories linked to this paper

Some links come from the archived Papers with Code dataset (CC BY-SA 4.0): attribution and licence.

Abstract

Peptide design plays a pivotal role in therapeutics, allowing brand new possibility to leverage target binding sites that are previously undruggable. Most existing methods are either inefficient or only concerned with the target-agnostic design of 1D sequences. In this paper, we propose a generative model for full-atom \textbf{Pep}tide design with \textbf{G}eometric \textbf{LA}tent \textbf{D}iffusion (PepGLAD) given the binding site. We first establish a benchmark consisting of both 1D sequences and 3D structures from Protein Data Bank (PDB) and literature for systematic evaluation. We then identify two major challenges of leveraging current diffusion-based models for peptide design: the full-atom geometry and the variable binding geometry. To tackle the first challenge, PepGLAD derives a variational autoencoder that first encodes full-atom residues of variable size into fixed-dimensional latent representations, and then decodes back to the residue space after conducting the diffusion process in the latent space. For the second issue, PepGLAD explores a receptor-specific affine transformation to convert the 3D coordinates into a shared standard space, enabling better generalization ability across different binding shapes. Experimental Results show that our method not only improves diversity and binding affinity significantly in the task of sequence-structure co-design, but also excels at recovering reference structures for binding conformation generation.

For agents

The same record, over MCP at https://syntology.ai/mcp:

get_harvested_code_for_paper("2402.13555")
get_code_for_paper("2402.13555")
have("2402.13555")

Connect an agent — have() is free.