SYNTOLOGY HomeExplorerAtlasCodeMethodologyAboutDevelopersFeedPricing
Paper · 2006.10137 · 2020

MoFlow: An Invertible Flow Model for Generating Molecular Graphs

arXiv · PDF · Open in the Atlas

Code that ran

1 of 2 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 0 have no contract verdict; 1 failure of our instrument; 1 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/2006.10137.json · badge: /api/ran/2006.10137.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
calvin-zcx/moflow canonical (classifier label)
classifier basis: classifier_2025
1 ran · 1 no recorded run
FunctionStatusWhere it lives
generate_mols_interpolation_grid Ran
ran; our contract draft was wrong, not the code
calvin-zcx/moflow/mflow/generate.py
code served (permissive licence) · get_code("6668d08e9432ab49")
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 torch
import numpy as np

torch.manual_seed(0)

# Create a minimal model that has the required attributes and methods
class MinimalMoleculeModel(torch.nn.Module):
    def __init__(self, b_size=5, a_size=7):
        super().__init__()
        self.b_size = b_size
        self.a_size = a_size
        # Dummy parameters to make it a valid nn.Module
        self.dummy = torch.nn.Linear(1, 1)
    
    def reverse(self, z_array, true_adj=None):
        # z_array shape: (batch_size, latent_size)
        batch_size = z_array.shape[0]
        latent_size = z_array.shape[1]
        
        # Return dummy outputs matching expected shapes
        # adj: adjacency matrix, xf: node features
        adj = torch.randn(batch_size, 9, 9)  # Small adjacency matrices
        xf = torch.randn(batch_size, 9, 4)   # Node features (9 nodes, 4 features)
        
        return adj, xf

# Instantiate model
model = MinimalMoleculeModel(b_size=5, a_size=7)

# Create optional z0 (starting point in latent space)
z0 = np.random.randn(12).astype(np.float32)

# Create optional true_adj (true adjacency matrix)
true_adj = torch.randn(13, 9, 9)  # Batch of 13 adjacency matrices

# Build the ARGS dictionary
ARGS = {
    'model': model,
    'z0': z0,
    'true_adj': true_adj,
    'seed': 0,
    'mols_per_row': 13,
    'device': None,
    'delta': 1.0
}
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 — 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
generate_mols Not yet run
unverified (harvested, no recorded run)
calvin-zcx/moflow/mflow/generate.py
code served (permissive licence) · get_code("54e7398c07a02f5c")
How it ran

no invocation recorded.

Also present in other papers' code

Of 2 samples lifted from this paper's linked repositories, 2 carry a function identity and 0 do not. Of the 2 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 1 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
generate_mols 1 other paper
1 later
2209.05481 (2022-09)
A Molecular Multimodal Foundation Model Associating Molecule Graphs with Natural Language

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

Generating molecular graphs with desired chemical properties driven by deep graph generative models provides a very promising way to accelerate drug discovery process. Such graph generative models usually consist of two steps: learning latent representations and generation of molecular graphs. However, to generate novel and chemically-valid molecular graphs from latent representations is very challenging because of the chemical constraints and combinatorial complexity of molecular graphs. In this paper, we propose MoFlow, a flow-based graph generative model to learn invertible mappings between molecular graphs and their latent representations. To generate molecular graphs, our MoFlow first generates bonds (edges) through a Glow based model, then generates atoms (nodes) given bonds by a novel graph conditional flow, and finally assembles them into a chemically valid molecular graph with a posthoc validity correction. Our MoFlow has merits including exact and tractable likelihood training, efficient one-pass embedding and generation, chemical validity guarantees, 100\% reconstruction of training data, and good generalization ability. We validate our model by four tasks: molecular graph generation and reconstruction, visualization of the continuous latent space, property optimization, and constrained property optimization. Our MoFlow achieves state-of-the-art performance, which implies its potential efficiency and effectiveness to explore large chemical space for drug discovery.

For agents

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

get_harvested_code_for_paper("2006.10137")
get_code_for_paper("2006.10137")
have("2006.10137")

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

curl https://syntology.ai/api/ran/2006.10137.json

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

[![Syntology run record](https://syntology.ai/api/ran/2006.10137.svg)](https://syntology.ai/paper/2006.10137)

Connect an agent — have() is free.