SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.00735 · ICML · 2024

Full-Atom Peptide Design based on Multi-modal Flow Matching

Jian Peng, Zhizhou Ren, Shitong Luo, Ruihan Guo, Jianzhu Ma, Chaoran Cheng, Jiahan Li, Zuofan Wu

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 10 functions out of this paper's own repositories and ran 8 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
Ced3-han/PepFlowww canonical 8 of 9
ced3-han/pepflowww canonical 0 of 1
FunctionStatusWhere it lives
flatten_final_dims Ran Ced3-han/PepFlowww/models_con/ipa_pytorch.py
code served (permissive licence) · get_code("706bd906bbbd5b15")
get_index_embedding Ran Ced3-han/PepFlowww/models_con/utils.py
code served (permissive licence) · get_code("773151823a896982")
get_psi_angle Ran Ced3-han/PepFlowww/models_con/torsion.py
code served (permissive licence) · get_code("486297ae5c4a75aa")
permute_final_dims Ran Ced3-han/PepFlowww/models_con/ipa_pytorch.py
code served (permissive licence) · get_code("c653d7a1bb820cd6")
process_dic Ran Ced3-han/PepFlowww/models_con/utils.py
code served (permissive licence) · get_code("698ee74b983de664")
tor_expmap Ran Ced3-han/PepFlowww/models_con/torus.py
code served (permissive licence) · get_code("add0c7814f5e2106")
tor_logmap Ran Ced3-han/PepFlowww/models_con/torus.py
code served (permissive licence) · get_code("58c927320adf39f6")
tor_projx Ran Ced3-han/PepFlowww/models_con/torus.py
code served (permissive licence) · get_code("b0d0914094997395")
calc_distogram Not yet run Ced3-han/PepFlowww/models_con/utils.py
code served (permissive licence) · get_code("04218cc837a6fff9")
get_tm_score Not yet run ced3-han/pepflowww/eval/align.py
code served (permissive licence) · get_code("ba6bcbc1beb38837")

Repositories linked to this paper

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

Abstract

Peptides, short chains of amino acid residues, play a vital role in numerous biological processes by interacting with other target molecules, offering substantial potential in drug discovery. In this work, we present PepFlow, the first multimodal deep generative model grounded in the flow-matching framework for the design of fullatom peptides that target specific protein receptors. Drawing inspiration from the crucial roles of residue backbone orientations and side-chain dynamics in protein-peptide interactions, we characterize the peptide structure using rigid backbone frames within the SE(3) manifold and side-chain angles on high-dimensional tori. Furthermore, we represent discrete residue types in the peptide sequence as categorical distributions on the probability simplex. By learning the joint distributions of each modality using derived flows and vector fields on corresponding manifolds, our method excels in the fine-grained design of full-atom peptides. Harnessing the multi-modal paradigm, our approach adeptly tackles various tasks such as fixbackbone sequence design and side-chain packing through partial sampling. Through meticulously crafted experiments, we demonstrate that PepFlow exhibits superior performance in comprehensive benchmarks, highlighting its significant potential in computational peptide design and analysis. Recently, deep generative models, particularly diffusion probabilistic models (Sohl-Dickstein et al., 2015;Ho et al., 2020;Song & Ermon, 2019; Song et al., 2020b), have shown considerable promise in de novo protein design (Huang et al., 2016). These models mainly focus on generating protein backbones, represented as N rigid frames in the SE(3) manifold

For agents

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

get_harvested_code_for_paper("2406.00735")
get_code_for_paper("2406.00735")
have("2406.00735")

Connect an agent — have() is free.