SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2206.06583 · 2022

Exploring evolution-aware & -free protein language models as protein function predictors

arXiv · PDF · Open in the Atlas

Code that ran

7 of 9 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, 1 violated it and 4 have no contract verdict; 2 failures of our instrument; 2 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/2206.06583.json · badge: /api/ran/2206.06583.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
elttaes/revisiting-plms canonical (classifier label)
classifier basis not recorded on the link
7 ran · 2 no recorded run
FunctionStatusWhere it lives
apc Ran
ran; our contract draft was wrong, not the code
elttaes/revisiting-plms/ESM-1b_Pretrain/esm/modules.py
code served (permissive licence) · get_code("f6701ae421cbe0d4")
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 4, dtype family float, shape (2, 3, 4, 5) 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 apc performs average product correction on a tensor
# It expects a tensor x with at least 2 dimensions
# The operations use sum on dimensions -1 and -2, so we need at least 2D
# Let's create a small 4D tensor (batch, sequence, dimension, dimension)
# to make the contact prediction use case clear

x = torch.randn(2, 3, 4, 5)

ARGS = {
    "x": x
}
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 4, dtype family float, shape (2, 3, 4, 5) — shape (2, 3, 4, 5) 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
calc_neff Ran
ran on a synthesized input
elttaes/revisiting-plms/ESM-MSA/af2_eval.py
code served (permissive licence) · get_code("95cfb6fa75b827cc")
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 float64, ndim 0, 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
import tempfile
import os

# Create a temporary file with the expected format for calc_neff
# The function expects:
# - Line 0: header (skipped)
# - Line 1: sequence data (odd indices)
# - Line 2: header (skipped)
# - Line 3: sequence data (odd indices)
# etc.

temp_file = tempfile.NamedTemporaryFile(mode='w', delete=False, suffix='.txt')
temp_path = temp_file.name

# Write sample data in the expected format
# The function reads lines at indices 1, 3, 5, ... (every other line starting from index 1)
# Each sequence line contains characters that will be converted to ASCII codes
sequences = [
    "ACGT-ACG",  # First sequence with one gap
    "ACGT-ACA",  # Second sequence with one gap
]

for seq in sequences:
    temp_file.write("header\n")
    temp_file.write(seq + "\n")

temp_file.close()

ARGS = {
    "path": temp_path
}
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 float64, ndim 0, dtype family float — no output shape is stated: observe_signature.py recorded float ndim 0, which disagrees with the fixture run
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
filt_gaps Ran
ran on a synthesized input
elttaes/revisiting-plms/ESM-MSA/GREMLIN_tensorflow.py
code served (permissive licence) · get_code("4ef9ac2f182847f2")
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

alphabet = 'ARNDCQEGHILKMFPSTWYV-'
states = len(alphabet)

# Create a small MSA (Multiple Sequence Alignment) matrix
# Shape: (num_sequences, num_positions)
# Values should be integers in range [0, states-1]
# where states-1 (20) represents a gap
msa = np.array([
    [0, 1, 2, 3, 20, 5, 6, 7],
    [1, 2, 3, 4, 20, 6, 7, 8],
    [2, 3, 4, 5, 20, 7, 8, 9],
    [3, 4, 5, 6, 20, 8, 9, 10],
], dtype=np.int64)

gap_cutoff = 0.5

ARGS = {
    'msa': msa,
    'gap_cutoff': gap_cutoff
}
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
gelu Ran
ran; our contract draft was wrong, not the code
elttaes/revisiting-plms/ESM-1b_Pretrain/esm/modules.py
code served (permissive licence) · get_code("2e7bd6c4ccd1ed68")
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 math
import torch

torch.manual_seed(0)

# The gelu function takes a single parameter 'x' which is used in:
# - x * 0.5 * (1.0 + torch.erf(x / math.sqrt(2.0)))
# So x must be a tensor that supports arithmetic operations and torch.erf

# Create a small tensor for testing
x = torch.randn(2, 4)

ARGS = {
    'x': x
}
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
generate_coordinates Ran
ran on a synthesized input
elttaes/revisiting-plms/ESM-MSA/draw.py
code served (permissive licence) · get_code("32b11da71f634b4a")
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 (4, 2) 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 pandas as pd
import numpy as np
import tempfile
import os

# Create temporary CSV files for testing
temp_dir = tempfile.mkdtemp()

# Create path CSV - contains query, target, E-value columns
path_csv = os.path.join(temp_dir, "results.tsv")
path_data = """query\ttarget\tE-value
seq1\tseq2\t1e-5
seq1\tseq3\t1e-10
seq2\tseq1\t1e-8
seq2\tseq4\t1e-3
"""
with open(path_csv, 'w') as f:
    f.write(path_data)

# Create db_path CSV - contains class and sequence columns
db_path_csv = os.path.join(temp_dir, "database.tsv")
db_data = """class\tseq
classA\tseq1
classA\tseq2
classB\tseq3
classB\tseq4
"""
with open(db_path_csv, 'w') as f:
    f.write(db_data)

ARGS = {
    "path": path_csv,
    "db_path": db_path_csv,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
numpy, pandas — 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 (4, 2) — shape (4, 2) 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
parse_fasta Ran
ran on a synthesized input
elttaes/revisiting-plms/ESM-MSA/GREMLIN_tensorflow.py
code served (permissive licence) · get_code("be03e131ebf978b6")
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 tempfile
import os
import numpy as np

# Create a temporary FASTA file for testing
temp_fasta = tempfile.NamedTemporaryFile(mode='w', suffix='.fasta', delete=False)
temp_fasta.write('>sequence1\n')
temp_fasta.write('ATCGATCG\n')
temp_fasta.write('>sequence2\n')
temp_fasta.write('GCTAGCTA\n')
temp_fasta.write('>sequence3\n')
temp_fasta.write('AAATTTCCC\n')
temp_fasta.close()

ARGS = {
    'filename': temp_fasta.name,
    'limit': -1
}
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
symmetrize Ran
ran, violated the contract we drafted
elttaes/revisiting-plms/ESM-1b_Pretrain/esm/modules.py
code served (permissive licence) · get_code("b385be9826c4a8b3")
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) and returned Tensor, ndim 3, dtype family float, shape (2, 4, 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

torch.manual_seed(0)

# Create a small tensor with shape (2, 4, 4) for the final two dimensions to be square
# (required for transpose and addition to work meaningfully)
x = torch.randn(2, 4, 4)

ARGS = {
    "x": x
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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, 4, 4) — shape (2, 4, 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
aa2num Not yet run
unverified (harvested, no recorded run)
elttaes/revisiting-plms/ESM-MSA/GREMLIN_tensorflow.py
code served (permissive licence) · get_code("b5f6e8201d45514b")
How it ran

no invocation recorded.

reduce_loss Not yet run
unverified (harvested, no recorded run)
elttaes/revisiting-plms/ESM-1b_Pretrain/DDP_train_1b.py
code served (permissive licence) · get_code("7bbb1a6e077ff43b")
How it ran

no invocation recorded.

Also present in other papers' code

Of 9 samples lifted from this paper's linked repositories, 9 carry a function identity and 0 do not. Of the 9 distinct functions with an identity, 3 are also present in other papers whose code we hold (3 with at least one paper dated earlier, 0 the same month, 3 later) and 6 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
gelu 198 other papers
115 dated earlier, 79 later, 4 same year, order not determinable · 32 only as an assembly brick
1408.5882 (2014-08)
Convolutional Neural Networks for Sentence Classification
1810.04805 (2018-10)
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
1901.10125 (2019-01)
Glyce: Glyph-vectors for Chinese Character Representations
and 195 more not named here
symmetrize 5 other papers
1 dated earlier, 4 later
2106.02584 (2021-06)
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
2406.10391 (2024-06)
BEACON: Benchmark for Comprehensive RNA Tasks and Language Models
2408.11363 (2024-08)
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
and 2 more not named here
apc 4 other papers
1 dated earlier, 3 later
2106.02584 (2021-06)
Self-Attention Between Datapoints: Going Beyond Individual Input-Output Pairs in Deep Learning
2408.11363 (2024-08)
ProteinGPT: Multimodal LLM for Protein Property Prediction and Structure Understanding
2605.11189 (2026-05)
Deep Learning for Protein Complex Prediction and Design by
and 1 more not named here

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

Large-scale Protein Language Models (PLMs) have improved performance in protein prediction tasks, ranging from 3D structure prediction to various function predictions. In particular, AlphaFold, a ground-breaking AI system, could potentially reshape structural biology. However, the utility of the PLM module in AlphaFold, Evoformer, has not been explored beyond structure prediction. In this paper, we investigate the representation ability of three popular PLMs: ESM-1b (single sequence), MSA-Transformer (multiple sequence alignment) and Evoformer (structural), with a special focus on Evoformer. Specifically, we aim to answer the following key questions: (i) Does the Evoformer trained as part of AlphaFold produce representations amenable to predicting protein function? (ii) If yes, can Evoformer replace ESM-1b and MSA-Transformer? (ii) How much do these PLMs rely on evolution-related protein data? In this regard, are they complementary to each other? We compare these models by empirical study along with new insights and conclusions. All code and datasets for reproducibility are available at https://github.com/elttaes/Revisiting-PLMs.

For agents

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

get_harvested_code_for_paper("2206.06583")
get_code_for_paper("2206.06583")
have("2206.06583")

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

curl https://syntology.ai/api/ran/2206.06583.json

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

[![Syntology run record](https://syntology.ai/api/ran/2206.06583.svg)](https://syntology.ai/paper/2206.06583)

Connect an agent — have() is free.