REVIEW 20 cited by
MolGAN: An implicit generative model for small molecular graphs
Not yet reviewed by Pith; the record is open.
This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.
SPECIMEN: schema-true, not a live event
T0 review · schema-true
One-sentence machine reading of the paper's core claim.
pith:XXXXXXXX · record.json · timestamp
read the original abstract
Deep generative models for graph-structured data offer a new angle on the problem of chemical synthesis: by optimizing differentiable models that directly generate molecular graphs, it is possible to side-step expensive search procedures in the discrete and vast space of chemical structures. We introduce MolGAN, an implicit, likelihood-free generative model for small molecular graphs that circumvents the need for expensive graph matching procedures or node ordering heuristics of previous likelihood-based methods. Our method adapts generative adversarial networks (GANs) to operate directly on graph-structured data. We combine our approach with a reinforcement learning objective to encourage the generation of molecules with specific desired chemical properties. In experiments on the QM9 chemical database, we demonstrate that our model is capable of generating close to 100% valid compounds. MolGAN compares favorably both to recent proposals that use string-based (SMILES) representations of molecules and to a likelihood-based method that directly generates graphs, albeit being susceptible to mode collapse. Code at https://github.com/nicola-decao/MolGAN
Forward citations
Cited by 20 Pith papers
-
A collaborative constrained graph diffusion model for the generation of realistic synthetic molecules
A valence-preserving double edge-swap diffusion model with a learned time estimator generates chemically valid molecules with property distributions closer to real molecules than JTVAE and DiGress on the GuacaMol benchmark.
-
Implementations of Quantum and Classical Topology-Aligned Architectures for Molecular Property Prediction
A quantum circuit and a classical network with identical topology-shaped 64-parameter design perform comparably on QM9 classification, indicating the inductive bias rather than quantum substrate drives parameter efficiency.
-
Quantum latent distributions in deep generative models
Quantum latent distributions from boson samplers are shown in theory to expand the output distribution class of invertible Lipschitz generators, and in GAN benchmarks on QM9 to beat Gaussian, Bernoulli, and distinguis...
-
NovoMolGen: Rethinking Molecular Language Model Pretraining
A 1.5-billion-molecule pretrained transformer family, NovoMolGen, sets new state-of-the-art results in de novo and goal-directed molecule generation, and shows pretraining loss correlates only weakly with downstream g...
-
Combining Graph Neural Networks and Mixed Integer Linear Programming for Molecular Inference under the Two-Layered Model
A GNN-based molecular inference framework simulates the trained GNN inside a MILP, enabling exact search for valid chemical graphs with desired predicted properties.
-
Vector Representations of Vessel Trees
VeTTA encodes a vascular tree into one vector and recursively decodes it into a geometrically accurate, topologically valid tree, outperforming voxel-based autoencoders on reconstruction metrics.
-
Bridging Quantum and Classical Computing in Drug Design: Architecture Principles for Improved Molecule Generation
Bayesian optimization of a hybrid quantum-classical GAN produced a model with higher drug candidate scores and fewer parameters than benchmark hybrid and classical GANs.
-
Generative Risk Minimization for Out-of-Distribution Generalization on Graphs
GRM replaces discrete subgraph extraction with a continuous generative model and reports state-of-the-art results on graph out-of-distribution benchmarks.
-
Rank-Refined Quantum-Behaved Particle Swarm Optimization for Quantum Molecular Generation
RR-QPSO raises the validity–uniqueness product of 9-heavy-atom quantum molecular generation from 0.902 (BO) to 0.942 by rank-refined mean-best and fitness-guided swarm updates.
-
MoDyGAN: Combining Molecular Dynamics With GANs to Investigate Protein Conformational Space
MoDyGAN trains a ProGAN on pairwise spherical-coordinate matrices derived from MD simulations and uses dual-discriminator Pix2Pix refinement to generate novel, physically plausible protein conformations.
-
NGTM: Substructure-based Neural Graph Topic Model for Interpretable Graph Generation
NGTM generates graphs by sampling substructures from learned topic-specific distributions and assembling them, achieving competitive quality with interpretable, controllable topics.
-
Phenotypic Profile-Informed Generation of Drug-Like Molecules via Dual-Channel Variational Autoencoders
SmilesGEN generates drug-like molecules from gene expression profiles by subtracting the molecule's latent code from the treated-cell code to reconstruct the untreated cell state.
-
MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning
MolEditRL uses structure-aware graph diffusion plus RL fine-tuning to edit molecules toward desired properties while preserving scaffold similarity, reporting SOTA on its own MolEdit-Instruct benchmark.
-
QCA-MolGAN: Quantum Circuit Associative Molecular GAN with Multi-Agent Reinforcement Learning
QCA-MolGAN couples a quantum circuit Born machine prior with a graph GAN and multi-agent RL to generate drug-like molecules on QM9, reporting property balances but no comparison to the classical baseline.
-
AI4Research: A Survey of Artificial Intelligence for Scientific Research
A survey that organizes AI-for-research work into five tasks, comprehension, survey, discovery, writing, and peer review, and compiles associated tools and benchmarks.
-
A Survey of Large Language Models for Text-Guided Molecular Discovery: from Molecule Generation to Optimization
A review that categorizes LLM-based molecule generation and optimization into four learning paradigms and summarizes datasets, evaluation metrics, and future research directions.
-
Beyond Prediction: Reinforcement Learning as the Defining Leap in Healthcare AI
A survey of reinforcement learning in healthcare that frames RL as a paradigm shift from prediction to agentive clinical intelligence.
-
Beyond Equilibrium: Non-Equilibrium Foundations Should Underpin Generative Processes in Complex Dynamical Systems
A position paper arguing that non-equilibrium-physics-inspired generative models (like diffusion models) are, and should be, the foundation for modeling time-varying complex systems, supported by one 2D simulation.
-
Unraveling the Potential of Diffusion Models in Small Molecule Generation
A survey and benchmark of 18 diffusion models for small molecule generation, reporting MiDi and KGDiff as category leaders while all models still require post-hoc relaxation.
-
Graph Neural Networks in Modern AI-aided Drug Discovery
A comprehensive model-centric review of graph neural network methods and applications in AI-aided drug discovery, from molecular representation to synthesis planning.
Discussion (0). Continue with ORCID to comment.