SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2406.11906 · NeurIPS · 2024

NovoBench: Benchmarking Deep Learning-based De Novo Peptide Sequencing Methods in Proteomics

Yue Liu, Jun Xia, Stan Li, Jianwei Yin, Jingbo Zhou, Shaorong Chen, Sizhe Liu, Tianze Ling, Wenjie Du

arXiv · PDF · Open in the Atlas

Code that ran

3 of 3 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 0 have no contract verdict; 3 failures of our instrument; 0 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/2406.11906.json · badge: /api/ran/2406.11906.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
Westlake-OmicsAI/NovoBench canonical (classifier label)
classifier basis: census
3 ran · 0 no recorded run
FunctionStatusWhere it lives
collate_batch Ran
ran; our contract draft was wrong, not the code
Westlake-OmicsAI/NovoBench/novobench/models/adanovo/adanovo_dataloader.py
code served (permissive licence) · get_code("046e71c75d9ba9b1")
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
import numpy as np

torch.manual_seed(0)

# Create sample spectra tensors with m/z and intensity values
# Each spectrum is a 2D tensor: (num_peaks, 2) where columns are m/z and intensity
spectrum_1 = torch.tensor([
    [100.5, 0.8],
    [200.3, 0.5],
    [300.1, 0.9]
], dtype=torch.float32)

spectrum_2 = torch.tensor([
    [150.2, 0.7],
    [250.6, 0.4]
], dtype=torch.float32)

# Create batch data
batch_data = [
    (spectrum_1, 500.25, 2, "PEPTIDE_001"),
    (spectrum_2, 600.75, 3, "PEPTIDE_002"),
]

ARGS = {
    "batch": batch_data,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, 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
process_spectrum Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
Westlake-OmicsAI/NovoBench/novobench/models/deepnovo/deepnovo_dataloader.py
code served (permissive licence) · get_code("1d4cd40b55e04c9d")
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 numpy as np

# Create a mock deepnovo_config module
class DeepNovoConfig:
    mass_H = 1.00783
    mass_N_terminus = 1.99491
    mass_C_terminus = 17.00265
    SPECTRUM_RESOLUTION = 10  # peaks per Dalton
    MZ_SIZE = 150000  # size of spectrum array

deepnovo_config = DeepNovoConfig()

# Inject the mock config into the module namespace where the function expects it
import sys
module = sys.modules[__name__]
module.deepnovo_config = deepnovo_config

# Create small test data
spectrum_mz_list = [100.5, 150.3, 200.7, 250.2]
spectrum_intensity_list = [0.5, 1.0, 0.8, 0.3]
peptide_mass = 400.5

ARGS = {
    "spectrum_mz_list": spectrum_mz_list,
    "spectrum_intensity_list": spectrum_intensity_list,
    "peptide_mass": peptide_mass
}
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, 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
split_peptide Ran
ran; our contract draft was wrong, not the code
Westlake-OmicsAI/NovoBench/novobench/metrics/evaluate.py
code served (permissive licence) · get_code("39e1f2d7cabeb996")
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 list, 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 re

def split_peptide(peptide, aa_dict):
    aa_list = aa_dict.keys()
    regex_pattern = '|'.join(map(re.escape, sorted(aa_list, key=len, reverse=True)))
    parts = re.findall(regex_pattern, peptide)
    parts = [part for part in parts if part]
    if ''.join(parts) != peptide:
        raise ValueError(f"Input string '{peptide}' contains unmatched characters in aa_dict: {aa_list}.")
    else:
        return parts

# Setup code for split_peptide
peptide = "MVHLTPEEKS"
aa_dict = {
    'M': 'Met',
    'V': 'Val',
    'H': 'His',
    'L': 'Leu',
    'T': 'Thr',
    'P': 'Pro',
    'E': 'Glu',
    'K': 'Lys',
    'S': 'Ser'
}

ARGS = {
    'peptide': peptide,
    'aa_dict': aa_dict
}
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 list, ndim 1, dtype family float — a list 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 3 samples lifted from this paper's linked repositories, 3 carry a function identity and 0 do not. Of the 3 distinct functions with an identity, 2 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 2 later) and 1 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
collate_batch 1 other paper
1 later
2505.17524 (2025-05)
Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing
split_peptide 1 other paper
1 later
2505.17524 (2025-05)
Latent Imputation before Prediction: A New Computational Paradigm for De Novo Peptide Sequencing

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

Tandem mass spectrometry has played a pivotal role in advancing proteomics, enabling the high-throughput analysis of protein composition in biological tissues. Many deep learning methods have been developed for de novo peptide sequencing task, i.e., predicting the peptide sequence for the observed mass spectrum. However, two key challenges seriously hinder the further advancement of this important task. Firstly, since there is no consensus for the evaluation datasets, the empirical results in different research papers are often not comparable, leading to unfair comparison. Secondly, the current methods are usually limited to amino acid-level or peptide-level precision and recall metrics. In this work, we present the first unified benchmark NovoBench for de novo peptide sequencing, which comprises diverse mass spectrum data, integrated models, and comprehensive evaluation metrics. Recent impressive methods, including DeepNovo, PointNovo, Casanovo, InstaNovo, AdaNovo and π-HelixNovo are integrated into our framework. In addition to amino acid-level and peptide-level precision and recall, we evaluate the models' performance in terms of identifying post-tranlational modifications (PTMs), efficiency and robustness to peptide length, noise peaks and missing fragment ratio, which are important influencing factors while seldom be considered. Leveraging this benchmark, we conduct a large-scale study of current methods, report many insightful findings that open up new possibilities for future development. The code is available at https://github.com/Westlake-OmicsAI/NovoBench.

For agents

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

get_harvested_code_for_paper("2406.11906")
get_code_for_paper("2406.11906")
have("2406.11906")

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

curl https://syntology.ai/api/ran/2406.11906.json

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

[![Syntology run record](https://syntology.ai/api/ran/2406.11906.svg)](https://syntology.ai/paper/2406.11906)

Connect an agent — have() is free.