SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · aaai_32074 · AAAI · 2025

Relation-Aware Equivariant Graph Networks for Epitope-Unknown Antibody Design and Specificity Optimization

Tailin Wu, Lirong Wu, Stan Li, Cheng Tan, Zhangyang Gao, Haitao Lin, Yunfan Liu, Yufei Huang

Open in the Atlas

Code that ran

8 of 10 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; 2 honoured the contract we drafted, 1 violated it and 0 have no contract verdict; 5 failures of our instrument; 2 no recorded run), measured 2026-11-22; 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/aaai_32074.json · badge: /api/ran/aaai_32074.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
LirongWu/RAAD canonical (classifier label)
classifier basis: census
8 ran · 2 no recorded run
FunctionStatusWhere it lives
compute_rmsd Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
LirongWu/RAAD/evaluation/rmsd.py
code served (permissive licence) · get_code("bc3dfc4da269ab70")
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 float, ndim 0, dtype family float, shape () 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 numpy as np

# Create two sets of paired points for testing
# P and Q should be (N, D) matrices where N is number of points and D is dimension
# Using distinct sizes: 5 points in 3D space

np.random.seed(0)

# Create point set 'a' - 5 points in 3D
a = np.random.randn(5, 3).astype(np.float32)

# Create point set 'b' - 5 points in 3D (slightly transformed version of a)
b = a + np.random.randn(5, 3) * 0.1

ARGS = {
    "a": a,
    "b": b,
    "aligned": False
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type float, ndim 0, dtype family float, shape () — shape () 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
get_prio Ran
ran, honoured the contract we drafted
LirongWu/RAAD/code/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from mansoor181/ConTact, is pointer only (licence: NONE) · get_code("b34ec54af3e6fffc")
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 mansoor181/ConTact, 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.

get_res_from_log Ran
ran; our contract draft was wrong, not the code
LirongWu/RAAD/evaluation/get_k_fold_res.py
code served (permissive licence) · get_code("90544e24e8b266c1")
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 dict. The image it ran in was not recorded. If your copy returns the same type 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 tempfile
import os

# Create a temporary log file with the expected format
temp_dir = tempfile.mkdtemp()
log_path = os.path.join(temp_dir, "test_log.txt")

# Write a log file with the expected patterns in the last 10 lines
log_content = """Some earlier log lines
More log content here
Line 3
Line 4
Line 5
PPL: mean 3.14, std 0.25
RMSD: mean 2.50, std 0.15
TMscore: mean 0.85, std 0.05
AAR: mean 0.92, std 0.03
Final line
"""

with open(log_path, 'w') as f:
    f.write(log_content)

ARGS = {
    'log_path': log_path
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
none outside the standard library — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict output the recorded ndim 0 and dtype family float describe that coercion, not the output, and are not stated
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
kabsch Ran
ran; our contract draft was wrong, not the code
LirongWu/RAAD/evaluation/rmsd.py
code served (permissive licence) · get_code("229d0977bd93c274")
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 tuple. The image it ran in was not recorded. If your copy returns the same type 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 numpy as np

# Create small sample point clouds
# P and Q should be (N, D) matrices where N is number of points and D is dimension
# Using N=2 points in D=3 dimensional space for minimal size

np.random.seed(0)

# Create two small point sets
a = np.array([[1.0, 2.0, 3.0],
              [4.0, 5.0, 6.0]], dtype=np.float64)

b = np.array([[1.1, 2.1, 3.1],
              [4.1, 5.1, 6.1]], dtype=np.float64)

ARGS = {
    "a": a,
    "b": b,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type tuple — a tuple output has no array shape of its own; none is stated
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
kabsch_rotation Ran
ran, honoured the contract we drafted
LirongWu/RAAD/evaluation/rmsd.py
code served (permissive licence) · get_code("de2a759aacf55c0c")
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 ndarray, ndim 2, dtype family float, shape (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 numpy as np

# Create two sets of paired points for the Kabsch algorithm
# P and Q should be (N, D) matrices where N is the number of points and D is the dimension
# Using N=5 points and D=3 dimensions

np.random.seed(42)

# Create point set P (5 points in 3D space)
P = np.random.randn(5, 3).astype(np.float64)

# Create point set Q by applying a rotation and some noise to P
# This ensures they are "paired" in a realistic way
rotation_matrix = np.array([
    [0.866, -0.5, 0.0],
    [0.5, 0.866, 0.0],
    [0.0, 0.0, 1.0]
])
Q = np.dot(P, rotation_matrix.T) + np.random.randn(5, 3) * 0.01

# Center both point sets around their centroids as mentioned in docstring
P = P - np.mean(P, axis=0)
Q = Q - np.mean(Q, axis=0)

ARGS = {
    "P": P,
    "Q": Q,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type ndarray, ndim 2, dtype family float, shape (3, 3) — shape (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
unsorted_segment_mean Ran
ran; our contract draft was wrong, not the code
LirongWu/RAAD/code/modules.py
pointer only (licence: MIT); the stored copy get_code serves, from ManlioWu/ESTAG, is pointer only (licence: NONE) · get_code("4a152e58abf0c317")
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 ManlioWu/ESTAG, 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.

unsorted_segment_sum Ran
ran; our contract draft was wrong, not the code
LirongWu/RAAD/code/modules.py
pointer only (licence: MIT); the stored copy get_code serves, from ManlioWu/ESTAG, is pointer only (licence: NONE) · get_code("7a39c2530c1f1d13")
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 ManlioWu/ESTAG, 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.

valid_check Ran
ran, violated the contract we drafted
LirongWu/RAAD/code/utils.py
pointer only (licence: MIT); the stored copy get_code serves, from mansoor181/ConTact, is pointer only (licence: NONE) · get_code("4bc134986fb637f3")
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 mansoor181/ConTact, 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.

coord2radial Not yet run
unverified (harvested, no recorded run)
LirongWu/RAAD/code/modules.py
pointer only (licence: MIT); the stored copy get_code serves, from mansoor181/ConTact, is pointer only (licence: NONE) · get_code("da995abbf5622788")
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 mansoor181/ConTact, 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. No invocation recorded.

url_get Not yet run
unverified (harvested, no recorded run)
LirongWu/RAAD/utils/network.py
code served (permissive licence) · get_code("2d15d2649443d0f6")
How it ran

no invocation recorded.

Also present in other papers' code

Of 10 samples lifted from this paper's linked repositories, 10 carry a function identity and 0 do not. Of the 10 distinct functions with an identity, 10 are also present in other papers whose code we hold (9 with at least one paper dated earlier, 0 the same month, 5 later) and 0 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
unsorted_segment_mean 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
2302.00203 (2023-02)
End-to-End Full-Atom Antibody Design
2405.12868 (2024-05)
Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
and 2 more not named here
unsorted_segment_sum 5 other papers
3 dated earlier, 1 later, 1 same year, order not determinable
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
2302.00203 (2023-02)
End-to-End Full-Atom Antibody Design
2405.12868 (2024-05)
Equivariant Spatio-Temporal Attentive Graph Networks to Simulate Physical Dynamics
and 2 more not named here
url_get 3 other papers
3 dated earlier
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
2302.00203 (2023-02)
End-to-End Full-Atom Antibody Design
2402.13555 (2024-02)
Full-Atom Peptide Design with Geometric Latent Diffusion
coord2radial 2 other papers
1 dated earlier, 1 later
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
2605.21600 (2026-05)
ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning
valid_check 2 other papers
1 dated earlier, 1 later
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
2605.21600 (2026-05)
ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning
compute_rmsd 1 other paper
1 dated earlier
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
get_prio 1 other paper
1 later
2605.21600 (2026-05)
ConTact: Contact-First Antibody CDR Design via Explicit Interface Reasoning
get_res_from_log 1 other paper
1 dated earlier
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
kabsch 1 other paper
1 dated earlier
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation
kabsch_rotation 1 other paper
1 dated earlier
2208.06073 (2022-08)
Conditional Antibody Design as 3D Equivariant Graph Translation

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

Antibodies are Y-shaped proteins that protect the host by binding to specific antigens, and their binding is mainly determined by the Complementary Determining Regions (CDRs) in the antibody. Despite the great progress made in CDR design, existing computational methods still encounter several challenges: 1) poor capability of modeling complex CDRs with long sequences due to insufficient contextual information; 2) conditioned on pre-given antigenic epitopes and their static interaction with the target antibody; 3) neglect of specificity during antibody optimization leads to non-specific antibodies. In this paper, we take into account a variety of node features, edge features, and edge relations to include more contextual and geometric information. We propose a novel Relation-Aware Antibody Design (RAAD) framework, which dynamically models antigen-antibody interactions for co-designing the sequences and structures of antigen-specific CDRs. Furthermore, we propose a new evaluation metric to better measure antibody specificity and develop a contrasting specificity-enhancing constraint to optimize the specificity of antibodies. Extensive experiments have demonstrated the superior capability of RAAD in terms of antibody modeling, generation, and optimization across different CDR types, sequence lengths, pre-training strategies, and input contexts.

For agents

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

get_harvested_code_for_paper("aaai_32074")
get_code_for_paper("aaai_32074")
have("aaai_32074")

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

curl https://syntology.ai/api/ran/aaai_32074.json

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

[![Syntology run record](https://syntology.ai/api/ran/aaai_32074.svg)](https://syntology.ai/paper/aaai_32074)

Connect an agent — have() is free.