SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2408.05196 · 2024

Cell Morphology-Guided Small Molecule Generation with GFlowNets

arXiv · PDF · Open in the Atlas

Code that ran

3 of 13 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; 1 honoured the contract we drafted, 0 violated it and 0 have no contract verdict; 2 failures of our instrument; 10 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/2408.05196.json · badge: /api/ran/2408.05196.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
thematrixmaster/omics-guided-gfn canonical (classifier label)
classifier basis: census
3 ran · 10 no recorded run
FunctionStatusWhere it lives
get_active_assay_cols Ran
ran, honoured the contract we drafted
thematrixmaster/omics-guided-gfn/vis/utils.py
code served (permissive licence) · get_code("54936394beb9f240")
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 1, dtype family int, shape (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 torch
import numpy as np

torch.manual_seed(0)

class MockDataset:
    def __init__(self):
        self.ids = ["CCCO", "CC(C)O", "CCO"]
        self.y = torch.tensor([
            [1, 0, 1, 0],
            [0, 0, 0, 0],
            [1, 1, 0, 1]
        ], dtype=torch.float32)

dataset = MockDataset()
smi = "CCCO"

ARGS = {
    "dataset": dataset,
    "smi": smi
}
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 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
load_run Ran
ran; our contract draft was wrong, not the code
thematrixmaster/omics-guided-gfn/vis/plot_num_modes_over_trajs.py
code served (permissive licence) · get_code("29b3d9a2a4428f17")
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 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 torch
import numpy as np
from unittest.mock import Mock, patch

torch.manual_seed(0)

# Mock the load_datum_from_run function since it's called inside load_run
def mock_load_datum_from_run(rundir, run_id, remove_duplicates=False, fps_from_file=False, 
                             save_fps=False, last_k=None, every_k=None):
    """Mock function that returns fps, rewards, smis"""
    num_samples = 100
    fps = np.random.rand(num_samples, 4).astype(np.float32)
    rewards = np.random.rand(num_samples).astype(np.float32)
    smis = [f"smile_{i}" for i in range(num_samples)]
    return fps, rewards, smis

# Create a mock RUNDIR
RUNDIR = "/mock/run/dir"

# Patch the load_datum_from_run in the module namespace
import sys
current_module = sys.modules[__name__]
current_module.load_datum_from_run = mock_load_datum_from_run
current_module.RUNDIR = RUNDIR

# Construct the run argument
run = {
    'run_paths': {
        'run_1': 'run_id_1',
        'run_2': 'run_id_2'
    }
}

# Define ARGS with all parameters
ARGS = {
    'run': run,
    'num_samples': None,
    'every_k': None,
    'check_len': False
}
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, ndim 1, 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
load_sm_run Ran
ran; our contract draft was wrong, not the code
thematrixmaster/omics-guided-gfn/vis/plot_oracle_hist.py
code served (permissive licence) · get_code("b6e0ab7839b75db7")
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 dict. 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
from unittest.mock import Mock, patch

torch.manual_seed(0)

# Mock the load_datum_from_run function since it's imported
def mock_load_datum_from_run(rundir, run_id, remove_duplicates=False, fps_from_file=False, save_fps=False, last_k=None, every_k=None):
    """Mock function that returns dummy data"""
    num_samples = 5 if last_k is None else min(last_k, 5)
    if every_k is not None:
        num_samples = num_samples // every_k if num_samples // every_k > 0 else 1
    
    full_fps = [torch.randn(2048) for _ in range(num_samples)]
    full_rewards = [float(i) * 0.1 for i in range(num_samples)]
    full_smis = [f"SMILES_{i}" for i in range(num_samples)]
    
    return full_fps, full_rewards, full_smis

# Create run dict structure
run = {
    'run_paths': {
        'experiment_1': 'run_id_001',
        'experiment_2': 'run_id_002'
    }
}

# Patch the external dependencies
import sys
current_module = sys.modules[__name__]
current_module.RUNDIR = '/mock/rundir'
current_module.load_datum_from_run = mock_load_datum_from_run

ARGS = {
    'run': run,
    'num_samples': None,
    'every_k': None
}
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 dict — a dict output has no array shape of its own; none is stated — the instrument coerces any output to an array; for a dict 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
compute_num_modes Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_num_modes_over_trajs.py
code served (permissive licence) · get_code("8c3564ce41ecc062")
How it ran

no invocation recorded.

compute_rew_thresh Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_num_modes_over_trajs.py
code served (permissive licence) · get_code("84b1f70fe2f28daa")
How it ran

no invocation recorded.

compute_rew_thresh Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_oracle_hist.py
code served (permissive licence) · get_code("14c5f28b5c28ecbb")
How it ran

no invocation recorded.

load_run Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/compute_max_tanimoto_sim.py
code served (permissive licence) · get_code("d257b6ddb4daf66e")
How it ran

no invocation recorded.

load_run Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_main.py
code served (permissive licence) · get_code("79a72ec80eecdf67")
How it ran

no invocation recorded.

load_run Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_oracle_hist.py
code served (permissive licence) · get_code("e5f14c7ec00729a6")
How it ran

no invocation recorded.

load_run Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_umap.py
code served (permissive licence) · get_code("a223c9ddde2baeee")
How it ran

no invocation recorded.

merge Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plot_main.py
code served (permissive licence) · get_code("1147f62a9cb2ddd4")
How it ran

no invocation recorded.

smooth Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plotting.py
code served (permissive licence) · get_code("db648b3524c8c8b4")
How it ran

no invocation recorded.

smooth_ci Not yet run
unverified (harvested, no recorded run)
thematrixmaster/omics-guided-gfn/vis/plotting.py
code served (permissive licence) · get_code("d99d5b1c131f02db")
How it ran

no invocation recorded.

Also present in other papers' code

Of 13 samples lifted from this paper's linked repositories, 13 carry a function identity and 0 do not. Of the 13 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 13 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

High-content phenotypic screening, including high-content imaging (HCI), has gained popularity in the last few years for its ability to characterize novel therapeutics without prior knowledge of the protein target. When combined with deep learning techniques to predict and represent molecular-phenotype interactions, these advancements hold the potential to significantly accelerate and enhance drug discovery applications. This work focuses on the novel task of HCI-guided molecular design. Generative models for molecule design could be guided by HCI data, for example with a supervised model that links molecules to phenotypes of interest as a reward function. However, limited labeled data, combined with the high-dimensional readouts, can make training these methods challenging and impractical. We consider an alternative approach in which we leverage an unsupervised multimodal joint embedding to define a latent similarity as a reward for GFlowNets. The proposed model learns to generate new molecules that could produce phenotypic effects similar to those of the given image target, without relying on pre-annotated phenotypic labels. We demonstrate that the proposed method generates molecules with high morphological and structural similarity to the target, increasing the likelihood of similar biological activity, as confirmed by an independent oracle model.

For agents

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

get_harvested_code_for_paper("2408.05196")
get_code_for_paper("2408.05196")
have("2408.05196")

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

curl https://syntology.ai/api/ran/2408.05196.json

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

[![Syntology run record](https://syntology.ai/api/ran/2408.05196.svg)](https://syntology.ai/paper/2408.05196)

Connect an agent — have() is free.