SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2203.01884 · NeurIPS · 2022

Graph Neural Networks for Multimodal Single-Cell Data Integration

Jiliang Tang, Wei Jin, Yiqi Wang, Hongzhi Wen, Jiayuan Ding, Yuying Xie

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 (1 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; 2 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/2203.01884.json · badge: /api/ran/2203.01884.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
omicsml/dance canonical (classifier label)
classifier basis: classifier_2025
3 ran · 0 no recorded run
FunctionStatusWhere it lives
ScMoGCN Ran
ran on a synthesized input · constructed an object; no result was computed
omicsml/dance/dance/modules/multi_modality/joint_embedding/scmogcn.py
code served (permissive licence) · get_code("b0a963dc284b953a")
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 an instance of its own class, ScMoGCN: the run constructed the object and did not call it, so no result was computed. 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 torch.nn as nn

torch.manual_seed(0)

# Define parameters for ScMoGCN
nb_cell_types = 3
nb_batches = 2
nb_phases = 4
input_dimension = 9

ARGS = {
    "nb_cell_types": nb_cell_types,
    "nb_batches": nb_batches,
    "nb_phases": nb_phases,
    "input_dimension": input_dimension,
}
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 ScMoGCN — the run constructed an instance of its own class and did not call it; no shape is stated — the instrument coerces any output to an array; for a ScMoGCN 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
propagation_layer_combination Ran
ran; the contract check could not run (RAISES, DEP_MISSING or TIMEOUT)
omicsml/dance/dance/modules/multi_modality/joint_embedding/scmogcn.py
code served (permissive licence) · get_code("fde51da806b4cf18")
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 1, dtype family float, shape (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)

# X should be a list/sequence where each element is indexable by idx
# Each X[i] should support indexing with idx and return a tensor
# Based on the function: x += wt[i] * X[i][idx]
# So X[i] is a tensor that can be indexed, and the result should be broadcastable with wt[i]

# wt has shape (num_sources, ...) and is used as wt[i] in a loop
# The result of X[i][idx] should be compatible with wt[i] for multiplication

# Let's create:
# - wt: shape (3, 4) - 3 sources, 4-dimensional logits
# - idx: an index to select from X elements
# - X: list of 3 tensors, each can be indexed by idx

X = [
    torch.randn(5, 4),  # 5 samples, 4 features - will be indexed by idx
    torch.randn(5, 4),
    torch.randn(5, 4),
]

idx = 2  # index into the first dimension of each X[i]

wt = torch.randn(3, 4)  # 3 sources, 4-dimensional (logits)

ARGS = {
    "X": X,
    "idx": idx,
    "wt": wt,
    "from_logits": True,
}
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 float, shape (4,) — shape (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
read_gmt Ran
ran; our contract draft was wrong, not the code
omicsml/dance/dance/transforms/graph/scmogcn_graph.py
code served (permissive licence) · get_code("a4783d0331a8594d")
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 defaultdict. 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.

from collections import defaultdict

# Analyze the function:
# - read_gmt takes two string parameters: entrez_string and symbol_string
# - entrez_string is split by whitespace, processed to extract numeric IDs and gene set names
# - symbol_string is split by whitespace, processed similarly
# - The function builds gene_sets_symbols by matching elements and filtering

# Construct valid arguments
entrez_string = "GeneSet1 12345 67890 GeneSet2 11111 22222 GeneSet3 33333"
symbol_string = "GeneSet1 BRCA1 TP53 GeneSet2 EGFR MYC GeneSet3 KRAS"

ARGS = {
    "entrez_string": entrez_string,
    "symbol_string": symbol_string,
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1
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 defaultdict — a defaultdict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a defaultdict 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

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, 1 are also present in other papers whose code we hold (0 with at least one paper dated earlier, 0 the same month, 1 later) and 2 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
propagation_layer_combination 1 other paper
1 later
2210.12385 (2022-10)
Deep Learning in Single-Cell Analysis

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

Recent advances in multimodal single-cell technologies have enabled simultaneous acquisitions of multiple omics data from the same cell, providing deeper insights into cellular states and dynamics. However, it is challenging to learn the joint representations from the multimodal data, model the relationship between modalities, and, more importantly, incorporate the vast amount of single-modality datasets into the downstream analyses. To address these challenges and correspondingly facilitate multimodal singlecell data analyses, three key tasks have been introduced: Modality prediction, Modality matching and Joint embedding. In this work, we present a general Graph Neural Network framework scMoGNN to tackle these three tasks and show that scMoGNN demonstrates superior results in all three tasks compared with the state-of-theart and conventional approaches. Our method is an official winner in the overall ranking of Modality prediction from NeurIPS 2021 Competition 1 , and all implementations of our methods have been integrated into DANCE package 2 . • Applied computing → Computational biology.

For agents

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

get_harvested_code_for_paper("2203.01884")
get_code_for_paper("2203.01884")
have("2203.01884")

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

curl https://syntology.ai/api/ran/2203.01884.json

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

[![Syntology run record](https://syntology.ai/api/ran/2203.01884.svg)](https://syntology.ai/paper/2203.01884)

Connect an agent — have() is free.