SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2201.13299 · 2022

Orientation-Aware Graph Neural Networks for Protein Structure Representation Learning

arXiv · PDF · Open in the Atlas

Code that ran

4 of 8 samples (functions and classes) lifted from this paper's linked repositories executed on a synthesized input in Syntology's jail (0 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 3 failures of our instrument; 4 no recorded run), measured 2026-11-22; repository links from the Papers with Code archive attributed under CC BY-SA, no affiliation; bodies inline only under a permissive licence as GitHub detects it. Not a reproduction of the paper's results.

"Ran" means the function executed on a synthesized input and returned a value. It is not a reproduction of the paper's results. This record, dated, as JSON: /api/ran/2201.13299.json · badge: /api/ran/2201.13299.svg

Each repository's role is a label: a classifier's output recorded on the link, or, where no role is recorded, what the Papers with Code archive marked. The line under it names its basis. Neither says who wrote the code.

RepositoryRoleRan
ced3-han/oagnn canonical (classifier label)
classifier basis not recorded on the link
4 ran · 4 no recorded run
FunctionStatusWhere it lives
construct_3d_basis Ran
ran; our contract draft was wrong, not the code
ced3-han/oagnn/modules/geometric.py
code served (permissive licence) · get_code("0e8cf361c5d81874")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 3, dtype family float, shape (2, 3, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# Create small 3D coordinate tensors
# Shape: (batch_size, 3) where batch_size=2
center = torch.randn(2, 3)
p1 = torch.randn(2, 3)
p2 = torch.randn(2, 3)

ARGS = {
    "center": center,
    "p1": p1,
    "p2": p2,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 3, dtype family float, shape (2, 3, 3) — shape (2, 3, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
normalize_vector Ran
ran on a synthesized input
ced3-han/oagnn/modules/geometric.py
code served (permissive licence) · get_code("29d5539ba153502d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 4) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch
import torch.linalg

torch.manual_seed(0)

# Create a small tensor for normalization
# Shape: (batch=2, features=4)
v = torch.randn(2, 4)

# Define the dimension along which to normalize
dim = 1

# Define epsilon for numerical stability
eps = 1e-8

ARGS = {
    "v": v,
    "dim": dim,
    "eps": eps
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 4) — shape (2, 4) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
project_v2v Ran
ran; our contract draft was wrong, not the code
ced3-han/oagnn/modules/geometric.py
code served (permissive licence) · get_code("06175d405523ab18")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API) and returned Tensor, ndim 2, dtype family float, shape (2, 3) as a later run recorded it. The image it ran in was not recorded. If your copy returns the same type, ndim and shape on these inputs, it matched what we observed; nothing here checks that. It does NOT mean the output is correct: nothing has compared it to the paper.

import torch

torch.manual_seed(0)

# The function takes three parameters:
# - v: a tensor of shape (*, 3)
# - e: a tensor of shape (*, 3)
# - dim: an integer specifying which dimension to sum over

# Create small tensors with batch size 2 and last dimension 3
v = torch.randn(2, 3)
e = torch.randn(2, 3)

# dim should be an integer; based on the keepdim=True usage,
# it's the dimension to sum over. For shape (2, 3), dim=1 makes sense
dim = 1

ARGS = {
    "v": v,
    "e": e,
    "dim": dim,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type Tensor, ndim 2, dtype family float, shape (2, 3) — shape (2, 3) as a later run recorded it
dtype family
int means an integer dtype; float means any other dtype the instrument saw, bool and complex included (fixture_check.py records only these two families)
Environment
image not recorded; re-verify against syntology-harvest-sandbox:v5-deps; not recorded for this sample: the harness installs a cuda-to-cpu shim (cuda_shim.py) before every sample and no run records whether a sample needed it; seed: none by the harness; any seed is in the setup block
safe_norm Ran
ran; our contract draft was wrong, not the code
ced3-han/oagnn/modules/common.py
pointer only (licence: MIT); the stored copy get_code serves, from smiles724/peptidedesign, is pointer only (licence: NONE) · get_code("e253039723a2f1f8")
How it ran

The body of this sample is withheld: this paper's link allows the body inline (MIT), but get_code serves the stored copy, first harvested from smiles724/peptidedesign, and GitHub detected no licence in that repository when it was checked. The setup block that called it is withheld with it, because it is written against that body. source_path and origin say where the code lives, to read under the repository's own terms. A run is recorded.

SAttention Not yet run
unverified (harvested, no recorded run)
ced3-han/oagnn/modules/gconv.py
code served (permissive licence) · get_code("560b5284810a1afe")
How it ran

no invocation recorded.

VAttention Not yet run
unverified (harvested, no recorded run)
ced3-han/oagnn/modules/gconv.py
code served (permissive licence) · get_code("3b3af6533cb10a54")
How it ran

no invocation recorded.

rotate_apply Not yet run
unverified (harvested, no recorded run)
ced3-han/oagnn/modules/linear.py
code served (permissive licence) · get_code("b0cf6793b32580c7")
How it ran

no invocation recorded.

vector_input_scalar_linear Not yet run
unverified (harvested, no recorded run)
ced3-han/oagnn/modules/linear.py
code served (permissive licence) · get_code("64ba6b751168bfbe")
How it ran

no invocation recorded.

Also present in other papers' code

Of 8 samples lifted from this paper's linked repositories, 8 carry a function identity and 0 do not. Of the 8 distinct functions with an identity, 3 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 3 later) and 5 are only here among the 52,977 papers whose code Syntology holds (as of 2026-09-26).

Only here means: among the 52,977 papers whose code Syntology holds (51,887 with lifted samples, 1,090 through their assemblies only), as of 2026-09-26, no other paper's lifted samples or current assembly bricks contain an identical function body after normalisation.

FunctionAlso present inEarliest-datedOthers named
project_v2v 2 other papers
2 later
2203.14486 (2022-03)
Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
2411.18463 (2024-11)
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension
safe_norm 2 other papers
2 later
2203.14486 (2022-03)
Equivariant Point Cloud Analysis via Learning Orientations for Message Passing
2411.10618 (2024-11)
D-Flow: Multi-modality Flow Matching for D-peptide Design
construct_3d_basis 1 other paper
1 later
2411.18463 (2024-11)
Hotspot-Driven Peptide Design via Multi-Fragment Autoregressive Extension

Presence, not direction: an identical function body in two papers' repositories does not say who wrote it, which came from which, or that either paper's method rests on it. Matching is exact after normalisation, so a renamed or edited function is not matched. Dates are when papers appeared, not when code was written. Only .py files the harvester lifted are covered; notebooks are not read. A new-style arXiv id YYMM.NNNN dates a paper to the month 20YY-MM; otherwise Paper.year dates it to the year; otherwise it is undated. Dates are when the paper appeared, not when the code was written. Read 2026-11-22.

Repositories linked to this paper

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

Abstract

By folding into particular 3D structures, proteins play a key role in living beings. To learn meaningful representation from a protein structure for downstream tasks, not only the global backbone topology but the local fine-grained orientational relations between amino acids should also be considered. In this work, we propose the Orientation-Aware Graph Neural Networks (OAGNNs) to better sense the geometric characteristics in protein structure (e.g. inner-residue torsion angles, inter-residue orientations). Extending a single weight from a scalar to a 3D vector, we construct a rich set of geometric-meaningful operations to process both the classical and SO(3) representations of a given structure. To plug our designed perceptron unit into existing Graph Neural Networks, we further introduce an equivariant message passing paradigm, showing superior versatility in maintaining SO(3)-equivariance at the global scale. Experiments have shown that our OAGNNs have a remarkable ability to sense geometric orientational features compared to classical networks. OAGNNs have also achieved state-of-the-art performance on various computational biology applications related to protein 3D structures. The code is available at https://github.com/Ced3-han/OAGNN/tree/main.

For agents

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

get_harvested_code_for_paper("2201.13299")
get_code_for_paper("2201.13299")
have("2201.13299")

The run record, dated, one paper per request, free:

curl https://syntology.ai/api/ran/2201.13299.json

A badge for a README (the split and the date, never a ratio):

[![Syntology run record](https://syntology.ai/api/ran/2201.13299.svg)](https://syntology.ai/paper/2201.13299)

Connect an agent — have() is free.