SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2310.03320 · ICLR · 2024

BioBridge: Bridging Biomedical Foundation Models via Knowledge Graphs

Zifeng Wang, Balasubramaniam Srinivasan, Zichen Wang, Vassilis Ioannidis, Huzefa Rangwala, Rishita Anubhai

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 (2 of them constructed an object rather than computing a result; 0 honoured the contract we drafted, 0 violated it and 2 have no contract verdict; 0 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/2310.03320.json · badge: /api/ran/2310.03320.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
RyanWangZf/BioBridge canonical (classifier label)
classifier basis: classifier_2025
0 ran · 1 no recorded run
ryanwangzf/biobridge marked official in Papers with Code
Papers with Code archive
2 ran · 1 no recorded run
FunctionStatusWhere it lives
BindingModelOutput Ran
ran on a synthesized input · constructed an object; no result was computed
ryanwangzf/biobridge/src/model.py
code served (permissive licence) · get_code("e18aaccab9b4935e")
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, BindingModelOutput: 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
from dataclasses import dataclass
from transformers.utils import ModelOutput
from typing import Optional

torch.manual_seed(0)

@dataclass
class BindingModelOutput(ModelOutput):
    """Class for the output of the binding model.
    """
    loss: Optional[torch.FloatTensor] = None
    embeddings: Optional[torch.FloatTensor] = None
    tail_embeddings: Optional[torch.FloatTensor] = None

ARGS = {
    "loss": torch.tensor([[0.5, 0.3], [0.2, 0.1]], dtype=torch.float32),
    "embeddings": torch.randn(2, 4),
    "tail_embeddings": torch.randn(2, 3),
}
Setup block drafted by
a language model, Claude Haiku 4.5, prompt python_fixture_v1, through the batch API
Imports
torch, transformers — import names as written, not package names to install; a name the repository itself provides is not a package
Returned
type BindingModelOutput — 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 BindingModelOutput 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
InfoNCE Ran
ran on a synthesized input · constructed an object; no result was computed
ryanwangzf/biobridge/src/model.py
code served (permissive licence) · get_code("eccecba9485b1bae")
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, InfoNCE: 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
import torch.nn.functional as F

torch.manual_seed(0)

# Setup: Create small tensors for testing
batch_size = 2
embedding_dim = 4
num_negatives = 3

# Test case 1: unpaired negative mode
query = torch.randn(batch_size, embedding_dim)
positive_key = torch.randn(batch_size, embedding_dim)
negative_keys_unpaired = torch.randn(num_negatives, embedding_dim)

# Test case 2: paired negative mode
negative_keys_paired = torch.randn(batch_size, num_negatives, embedding_dim)

# Define ARGS for the InfoNCE class initialization
ARGS = {
    'temperature': 0.1,
    'reduction': 'mean',
    'negative_mode': 'unpaired'
}
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 InfoNCE — 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 InfoNCE 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
BindingModel Not yet run
unverified (harvested, no recorded run)
ryanwangzf/biobridge/src/model.py
code served (permissive licence) · get_code("ac3bb81faa198022")
How it ran

no invocation recorded.

build_model_config Not yet run
unverified (harvested, no recorded run)
RyanWangZf/BioBridge/src/model.py
code served (permissive licence) · get_code("ca08cf9006c11129")
How it ran

no invocation recorded. this sample carries JSON test cases instead of a setup block; get_reference_implementation serves them with the level they back.

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, 1 are also present in other papers whose code we hold (1 with at least one paper dated earlier, 0 the same month, 0 later) and 3 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
InfoNCE
brick of this paper's assembly: loss
1 other paper
1 dated earlier
2306.10008 (2023-06)
CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search

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

Foundation models (FMs) learn from large volumes of unlabeled data to demonstrate superior performance across a wide range of tasks. However, FMs developed for biomedical domains have largely remained unimodal, i.e., independently trained and used for tasks on protein sequences alone, small molecule structures alone, or clinical data alone. To overcome this limitation, we present BioBRIDGE, a parameter-efficient learning framework, to bridge independently trained unimodal FMs to establish multimodal behavior. BioBRIDGE achieves it by utilizing Knowledge Graphs (KG) to learn transformations between one unimodal FM and another without fine-tuning any underlying unimodal FMs. Our results demonstrate that BioBRIDGE can beat the best baseline KG embedding methods (on average by ∼ 76.3%) in cross-modal retrieval tasks. We also identify BioBRIDGE demonstrates out-of-domain generalization ability by extrapolating to unseen modalities or relations. Additionally, we also show that BioBRIDGE presents itself as a general-purpose retriever that can aid biomedical multimodal question answering as well as enhance the guided generation of novel drugs. 1 * This work was completed while the author was an intern at Amazon.

For agents

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

get_harvested_code_for_paper("2310.03320")
get_code_for_paper("2310.03320")
have("2310.03320")

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

curl https://syntology.ai/api/ran/2310.03320.json

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

[![Syntology run record](https://syntology.ai/api/ran/2310.03320.svg)](https://syntology.ai/paper/2310.03320)

Connect an agent — have() is free.