SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2106.13058 · ICML · 2021

Fold2Seq: A Joint Sequence(1D)-Fold(3D) Embedding-based Generative Model for Protein Design

Pin-Yu Chen, Payel Das, Yang Shen, Igor Melnyk, Vijil Chenthamarakshan, Yue Cao

arXiv · PDF · Open in the Atlas

Code that ran

2 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; 0 honoured the contract we drafted, 0 violated it and 1 has no contract verdict; 1 failure of our instrument; 2 no recorded run); 1 of them was also run on the host, not in the jail, by the peer-agreement lane that set its level, 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/2106.13058.json · badge: /api/ran/2106.13058.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
IBM/fold2seq canonical (classifier label)
classifier basis: classifier_2025
2 ran · 2 no recorded run
FunctionStatusWhere it lives
greedy_sampling Ran
ran; our contract draft was wrong, not the code
IBM/fold2seq/src/inference.py
code served (permissive licence) · get_code("89c01911e1df4415")
How it ran

Ran in Syntology's jail on this synthesized input (drafted by a language model, Claude Haiku 4.5, prompt python_fixture_v1) and returned Tensor, ndim 1, dtype family int, shape (2,) as a later run recorded it. The image it ran in was not recorded. The comparison behind this sample's level is a different run: the peer-agreement lane ran it again on the host, not in the jail (report dated 2026-09-05T00:49:48Z). 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)

# token_preds should be a 2D tensor where:
# - dimension 0 is batch size
# - dimension 1 is vocabulary/token dimension
# The function calls torch.max(token_preds, 1).indices
# which finds the argmax along dimension 1

token_preds = torch.randn(2, 4)

ARGS = {
    "token_preds": token_preds
}
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 1, dtype family int, shape (2,) — shape (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
ProteinSeqTransformer Ran
ran on a synthesized input
IBM/fold2seq/src/generator.py
code served (permissive licence) · get_code("8fdc852733d7bd8d")
How it ran

Ran in Syntology's sandbox on this synthesized input (drafted by a language model, class construct-then-call prompt, model not recorded) and returned Tensor, ndim 3, 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 torch.nn as nn
from torch.nn import TransformerEncoder, TransformerEncoderLayer

class ProteinSeqTransformer(nn.Module):

    def __init__(self, args):
        super(ProteinSeqTransformer, self).__init__()
        self.model_type = 'ProteinSeqTransformer'
        encoder_layers = TransformerEncoderLayer(args.nhidden, args.nhead, args.seq_encoder_feedforward, args.dropout)
        self.transformer_encoder = TransformerEncoder(encoder_layers, args.nlayers)

    def forward(self, src, padding_masking=None):
        output = self.transformer_encoder(src, src_key_padding_mask=padding_masking)
        return output


class Args:
    def __init__(self, nhidden, nhead, seq_encoder_feedforward, dropout, nlayers):
        self.nhidden = nhidden
        self.nhead = nhead
        self.seq_encoder_feedforward = seq_encoder_feedforward
        self.dropout = dropout
        self.nlayers = nlayers


INIT_ARGS = {
    'args': Args(
        nhidden=8,
        nhead=2,
        seq_encoder_feedforward=16,
        dropout=0.1,
        nlayers=2
    )
}

ARGS = {
    'src': torch.randn(5, 2, 8),
    'padding_masking': None
}

if __name__ == '__main__':
    model = ProteinSeqTransformer(**INIT_ARGS)
    output = model(**ARGS)
    print(f"Output shape: {output.shape}")
    print(f"Output: {output}")
Setup block drafted by
a language model, class construct-then-call prompt, model not recorded
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 — no output shape is stated: observe_signature.py observed this class with its constructor sizes canonicalised where it could, which the node does not record, so its shape is not stated as this setup block's
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: torch and numpy seeded to 0 by the harness immediately before the class was constructed from INIT_ARGS (fixture_check.py)
inference Not yet run
unverified (harvested, no recorded run)
IBM/fold2seq/src/inference.py
code served (permissive licence) · get_code("3bfd5a6f57425739")
How it ran

no invocation recorded.

top_k_sampling Not yet run
unverified (harvested, no recorded run)
IBM/fold2seq/src/inference.py
code served (permissive licence) · get_code("cdb4cb372e3f547e")
How it ran

no invocation recorded.

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

Designing novel protein sequences for a desired 3D topological fold is a fundamental yet nontrivial task in protein engineering. Challenges exist due to the complex sequence-fold relationship, as well as the difficulties to capture the diversity of the sequences (therefore structures and functions) within a fold. To overcome these challenges, we propose Fold2Seq, a novel transformer-based generative framework for designing protein sequences conditioned on a specific target fold. To model the complex sequence-structure relationship, Fold2Seq jointly learns a sequence embedding using a transformer and a fold embedding from the density of secondary structural elements in 3D voxels. On test sets with single, high-resolution and complete structure inputs for individual folds, our experiments demonstrate improved or comparable performance of Fold2Seq in terms of speed, coverage, and reliability for sequence design, when compared to existing state-of-the-art methods that include datadriven deep generative models and physics-based RosettaDesign. The unique advantages of foldbased Fold2Seq, in comparison to a structurebased deep model and RosettaDesign, become more evident on three additional real-world challenges originating from low-quality, incomplete, or ambiguous input structures. Source code and data are available at https://github.com/ IBM/fold2seq.

For agents

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

get_harvested_code_for_paper("2106.13058")
get_code_for_paper("2106.13058")
have("2106.13058")

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

curl https://syntology.ai/api/ran/2106.13058.json

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

[![Syntology run record](https://syntology.ai/api/ran/2106.13058.svg)](https://syntology.ai/paper/2106.13058)

Connect an agent — have() is free.