A locally-built, LLM-digested index of recent arXiv papers in quant finance, geometry/topology, and statistical ML — keyword search served straight from SQLite on this machine.
MoFlow generates chemically valid molecular graphs from latent representations.
We seek to automate the design of molecules based on specific chemical properties. In computational terms, this task involves continuous embedding and generation of molecular graphs. Our primary contribution is the direct realization of molecular graphs, a task previously approached by generating linear SMILES strings …
We present RL-VAE, a graph-to-graph variational autoencoder that uses reinforcement learning to decode molecular graphs from latent embeddings. Methods have been described previously for graph-to-graph autoencoding, but these approaches require sophisticated decoders that increase the complexity of training and evaluat…
A Graph Neural Network model for generating molecular graphs.
Advanced GNNs improve molecular generation models.
MolHF generates complex molecules with hierarchical flow-based model.
XIMP improves molecular property prediction by integrating multiple graph representations.
We propose GraphNVP, the first invertible, normalizing flow-based molecular graph generation model. We decompose the generation of a graph into two steps: generation of (i) an adjacency tensor and (ii) node attributes. This decomposition yields the exact likelihood maximization on graph-structured data, combined with t…
Model predicts stable molecules with AI and physics constraints.
Graph Polish optimizes molecular structures by minimizing changes and maximizing preservation.
Molecular "fingerprints" encoding structural information are the workhorse of cheminformatics and machine learning in drug discovery applications. However, fingerprint representations necessarily emphasize particular aspects of the molecular structure while ignoring others, rather than allowing the model to make data-d…
A new unpooling layer enhances graph generation in molecular models.
Recent work in graph neural networks (GNNs) has led to improvements in molecular activity and property prediction tasks. Unfortunately, GNNs often fail to capture the relative importance of interactions between molecular substructures, in part due to the absence of efficient intermediate pooling steps. To address these…
DeepGG generates graph distributions for drug discovery and molecular design.
Framework for training-free guidance in discrete diffusion models for molecular generation.
Study compares GNNs and classical molecular featurisations for molecular property and cliff prediction.
Tiered latent representations and latent spaces for molecular graphs provide a simple but effective way to explicitly represent and utilize groups (e.g., functional groups), which consist of the atom (node) tier, the group tier and the molecule (graph) tier. They can be learned using the tiered graph autoencoder archit…
Statistical generative models for molecular graphs attract attention from many researchers from the fields of bio- and chemo-informatics. Among these models, invertible flow-based approaches are not fully explored yet. In this paper, we propose a powerful invertible flow for molecular graphs, called graph residual flow…
A new neural network model for molecular graphs that learns efficiently and accurately.
A new model designs molecular latent vectors for drug discovery.
HiGraphDTI learns drug and target representations from molecular graphs to predict DTIs.
Graph neural network have achieved impressive results in predicting molecular properties, but they do not directly account for local and hidden structures in the graph such as functional groups and molecular geometry. At each propagation step, GNNs aggregate only over first order neighbours, ignoring important informat…
GraphBSI generates graphs by refining a belief in continuous space, outperforming existing models.
Graph Energy Matching improves generation quality for molecular graphs.
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 imp…
We view molecular optimization as a graph-to-graph translation problem. The goal is to learn to map from one molecular graph to another with better properties based on an available corpus of paired molecules. Since molecules can be optimized in different ways, there are multiple viable translations for each input graph…
New method generates molecular conformations efficiently.
We introduce a convolutional neural network that operates directly on graphs. These networks allow end-to-end learning of prediction pipelines whose inputs are graphs of arbitrary size and shape. The architecture we present generalizes standard molecular feature extraction methods based on circular fingerprints. We sho…
Deep learning predicts drug side-effects from molecular graphs.
ConfFlow uses transformer networks to generate molecular conformations efficiently.
ASGN uses active semi-supervised learning to predict molecular properties efficiently.
MV-GNN improves molecular property prediction by integrating atom and bond information.
Searching new molecules in areas like drug discovery often starts from the core structures of candidate molecules to optimize the properties of interest. The way as such has called for a strategy of designing molecules retaining a particular scaffold as a substructure. On this account, our present work proposes a scaff…
Molecule property prediction is a fundamental problem for computer-aided drug discovery and materials science. Quantum-chemical simulations such as density functional theory (DFT) have been widely used for calculating the molecule properties, however, because of the heavy computational cost, it is difficult to search a…
Advancements in neural machinery have led to a wide range of algorithmic solutions for molecular property prediction. Two classes of models in particular have yielded promising results: neural networks applied to computed molecular fingerprints or expert-crafted descriptors, and graph convolutional neural networks that…
Molecule generation is a challenging open problem in cheminformatics. Currently, deep generative approaches addressing the challenge belong to two broad categories, differing in how molecules are represented. One approach encodes molecular graphs as strings of text, and learns their corresponding character-based langua…
Much of the recent work on learning molecular representations has been based on Graph Convolution Networks (GCN). These models rely on local aggregation operations and can therefore miss higher-order graph properties. To remedy this, we propose Path-Augmented Graph Transformer Networks (PAGTN) that are explicitly built…
Study compares atom representations in graph neural networks for molecular properties.
Two new minor minimal intrinsically chiral graphs identified.
A new autoregressive model learns the order of graph generation tasks.
Two regularization techniques improve GCNN explainability and preference from chemists.
GCPNet improves molecular graph learning for protein structure and binding.
G2Gs transforms target molecules into reactants without templates, improving accuracy.
The problem of accelerating drug discovery relies heavily on automatic tools to optimize precursor molecules to afford them with better biochemical properties. Our work in this paper substantially extends prior state-of-the-art on graph-to-graph translation methods for molecular optimization. In particular, we realize …
Great computational effort is invested in generating equilibrium states for molecular systems using, for example, Markov chain Monte Carlo. We present a probabilistic model that generates statistically independent samples for molecules from their graph representations. Our model learns a low-dimensional manifold that p…
Machine learning generates coarse-grained force fields for molecular dynamics.
Discriminator guidance improves autoregressive diffusion models for generating molecular graphs.
A new graph model HMG and neural network HMGNN improve molecule property predictions.