SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.13659 · 2024

ReactZyme: A Benchmark for Enzyme-Reaction Prediction

arXiv · PDF · Open in the Atlas

Code that ran

4 of 4 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 3 failures of our instrument; 0 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/2408.13659.json · badge: /api/ran/2408.13659.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
willhua127/reactzyme canonical (classifier label)
classifier basis: classifier_2025
4 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_fn Ran
ran; our contract draft was wrong, not the code
willhua127/reactzyme/data_utils.py
code served (permissive licence) · get_code("cf0c0ac0d19b0983")
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 torch
from torch.nn.utils.rnn import pad_sequence

torch.manual_seed(0)

# Create sample batch data
# Each item in batch is a tuple of (mol, seq, label)
# mols and seqs are sequences that will be padded, so they should be 1D or 2D tensors of varying lengths
# labels are tensors to be stacked

mol1 = torch.tensor([1, 2, 3], dtype=torch.long)
mol2 = torch.tensor([4, 5], dtype=torch.long)

seq1 = torch.tensor([10, 11, 12, 13], dtype=torch.long)
seq2 = torch.tensor([14, 15], dtype=torch.long)

label1 = torch.tensor([0.5, 0.3], dtype=torch.float)
label2 = torch.tensor([0.7, 0.2], dtype=torch.float)

# Create batch as list of tuples
batch = [
    (mol1, seq1, label1),
    (mol2, seq2, label2)
]

ARGS = {
    "batch": batch
}
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 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
collate_fn_pretrained Ran
ran; our contract draft was wrong, not the code
willhua127/reactzyme/data_utils.py
code served (permissive licence) · get_code("fc09fe92d0a51a4e")
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 torch

torch.manual_seed(0)

# The function expects a batch which is an iterable of tuples (mol, seq, label)
# where mol, seq, and label are all tensors that can be stacked

# Create sample data items
mol_1 = torch.randn(4, 3)  # molecule tensor with shape (4, 3)
seq_1 = torch.randn(5, 6)  # sequence tensor with shape (5, 6)
label_1 = torch.tensor([1.0, 0.0, 1.0, 1.0])  # label tensor

mol_2 = torch.randn(4, 3)  # molecule tensor with shape (4, 3)
seq_2 = torch.randn(5, 6)  # sequence tensor with shape (5, 6)
label_2 = torch.tensor([0.0, 1.0, 0.0, 1.0])  # label tensor

# Create batch as list of tuples
batch = [
    (mol_1, seq_1, label_1),
    (mol_2, seq_2, label_2)
]

ARGS = {
    "batch": batch
}
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 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
get_samples Ran
ran; our contract draft was wrong, not the code
willhua127/reactzyme/data_utils.py
code served (permissive licence) · get_code("9c4e721069783c6b")
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, ndim 2, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 tempfile
import os

torch.manual_seed(0)

# Create temporary directory for test files
temp_dir = tempfile.mkdtemp()

# Create positive samples dictionary
pos_samples = {
    'uni_id_1': ['C*CC', 'ACDEFG'],
    'uni_id_2': ['CC*C', 'GHIJKL'],
}

# Create negative samples dictionary
neg_samples = {
    'uni_id_3': ['*CCC', 'MNOPQR'],
    'uni_id_4': ['CC*CC', 'STUVWX'],
}

# Save to temporary files
pos_path = os.path.join(temp_dir, 'pos_samples.pt')
neg_path = os.path.join(temp_dir, 'neg_samples.pt')

torch.save(pos_samples, pos_path)
torch.save(neg_samples, neg_path)

ARGS = {
    'pos_path': pos_path,
    'neg_path': neg_path,
}
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 tuple, ndim 2, dtype family float — a tuple output has no array shape of its own; none is stated
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
topk_accuracy Ran
ran, honoured the contract we drafted
willhua127/reactzyme/retrieval.py
code served (permissive licence) · get_code("5a414eca5eaf8645")
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, ndim 1, dtype family float; no output shape is stated. The image it ran in was not recorded. If your copy returns the same type and ndim 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 logits tensor: batch_size=2, num_classes=4
logits = torch.randn(2, 4)

# Create labels tensor: batch_size=2, num_classes=4
# Multi-hot encoding where each row can have multiple 1s
labels = torch.tensor([
    [1, 0, 1, 0],
    [0, 1, 0, 1]
], dtype=torch.float32)

ARGS = {
    "logits": logits,
    "labels": labels,
    "k": 1
}
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 tuple, ndim 1, dtype family float — a tuple output has no array shape of its own; none is stated
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

Also present in other papers' code

Of 4 samples lifted from this paper's linked repositories, 4 carry a function identity and 0 do not. Of the 4 distinct functions with an identity, 0 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 0 later) and 4 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.

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

Enzymes, with their specific catalyzed reactions, are necessary for all aspects of life, enabling diverse biological processes and adaptations. Predicting enzyme functions is essential for understanding biological pathways, guiding drug development, enhancing bioproduct yields, and facilitating evolutionary studies. Addressing the inherent complexities, we introduce a new approach to annotating enzymes based on their catalyzed reactions. This method provides detailed insights into specific reactions and is adaptable to newly discovered reactions, diverging from traditional classifications by protein family or expert-derived reaction classes. We employ machine learning algorithms to analyze enzyme reaction datasets, delivering a much more refined view on the functionality of enzymes. Our evaluation leverages the largest enzyme-reaction dataset to date, derived from the SwissProt and Rhea databases with entries up to January 8, 2024. We frame the enzyme-reaction prediction as a retrieval problem, aiming to rank enzymes by their catalytic ability for specific reactions. With our model, we can recruit proteins for novel reactions and predict reactions in novel proteins, facilitating enzyme discovery and function annotation (https://github.com/WillHua127/ReactZyme).

For agents

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

get_harvested_code_for_paper("2408.13659")
get_code_for_paper("2408.13659")
have("2408.13659")

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

curl https://syntology.ai/api/ran/2408.13659.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.13659.svg)](https://syntology.ai/paper/2408.13659)

Connect an agent — have() is free.