SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2410.02847 · ICLR · 2025

Deep Signature: Characterization of Large-Scale Molecular Dynamics

Terry Lyons, Haoliang Li, Tiexin Qin, Chunyang Li, Mengxu Zhu, Hong Yan

arXiv · PDF · Open in the Atlas

Code that ran

We lifted 8 functions out of this paper's own repositories and ran 5 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
WonderSeven/Deep-Signature canonical 3 of 5
patrick-kidger/signatory reimplementation 2 of 3
FunctionStatusWhere it lives
dense_mincut_pool Ran WonderSeven/Deep-Signature/models/modules.py
code served (permissive licence) · get_code("0ac0e65c26a98173")
interpret_basepoint Ran patrick-kidger/signatory/src/signatory/signature_module.py
code served (permissive licence) · get_code("05d34e6628f185c5")
interpret_initial Ran patrick-kidger/signatory/src/signatory/signature_module.py
code served (permissive licence) · get_code("c1154b1a79258c50")
process_each_file Ran WonderSeven/Deep-Signature/collect_new_results.py
code served (permissive licence) · get_code("ae1af563b524f920")
process_each_test_file Ran WonderSeven/Deep-Signature/collect_new_results.py
code served (permissive licence) · get_code("0cfb2a89c3da4fd2")
get_dataloader Not yet run WonderSeven/Deep-Signature/engine/inits.py
code served (permissive licence) · get_code("5019fe8bb6458335")
get_dataset Not yet run WonderSeven/Deep-Signature/engine/inits.py
code served (permissive licence) · get_code("3ff3fa2ecdecd93b")
signature Not yet run patrick-kidger/signatory/src/signatory/signature_module.py
code served (permissive licence) · get_code("b7f24a317d8a0910")

Repositories linked to this paper

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

Abstract

Understanding protein dynamics are essential for deciphering protein functional mechanisms and developing molecular therapies. However, the complex highdimensional dynamics and interatomic interactions of biological processes pose significant challenge for existing computational techniques. In this paper, we approach this problem for the first time by introducing Deep Signature, a novel computationally tractable framework that characterizes complex dynamics and interatomic interactions based on their evolving trajectories. Specifically, our approach incorporates soft spectral clustering that locally aggregates cooperative dynamics to reduce the size of the system, as well as signature transform that collects iterated integrals to provide a global characterization of the nonsmooth interactive dynamics. Theoretical analysis demonstrates that Deep Signature exhibits several desirable properties, including invariance to translation, near invariance to rotation, equivariance to permutation of atomic coordinates, and invariance under time reparameterization. Furthermore, experimental results on three benchmarks of biological processes verify that our approach can achieve superior performance compared to baseline methods. Our code is available at https://github.com/WonderSeven/Deep-Signature.

For agents

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

get_harvested_code_for_paper("2410.02847")
get_code_for_paper("2410.02847")
have("2410.02847")

Connect an agent — have() is free.