Framework for training-free guidance in discrete diffusion models for molecular generation.
problem No equivalent training-free guidance methods for discrete diffusion models.
method Framework using guidance functions for discrete data.
result Demonstrated utility on molecular graph generation tasks.
Transformer-M learns molecular data in 2D or 3D formats.
problem Learning models for molecules are limited to specific data formats.
method Developed a Transformer-based model that can handle 2D and 3D molecular data.
result Transformer-M achieves strong performance on both 2D and 3D molecular tasks.
GAGA accelerates 3D molecular generation by replacing long trajectories with Gaussian approximations.
problem High computational cost of long generative trajectories in 3D molecular generation.
method GAGA identifies a characteristic step where molecular data becomes sufficiently Gaussian, replacing the trajectory with a Gaussian approximation.
result Significant improvement in both generation quality and computational efficiency.
LSS learns molecular trajectories from MD data.
problem Limited integration time steps in MD simulations.
method Three deep learning networks for slow collective variables, dynamics, and configuration reconstruction.
result Generates ultra-long synthetic folding trajectories.
A new model designs molecular latent vectors for drug discovery.
problem Designing effective molecular descriptors from molecular structures.
method Proposes a denoising diffusion probabilistic model (DDPM) for variational autoencoding molecular graphs.
result Demonstrates superior prediction performance and robustness compared to existing approaches.
XIMP improves molecular property prediction by integrating multiple graph representations.
problem Graph neural networks struggle in data-scarce regimes and fail to surpass traditional methods.
method Cross-graph inter-message passing with multiple graph abstractions.
result XIMP outperforms state-of-the-art baselines across diverse molecular property tasks.
MoFlow generates chemically valid molecular graphs from latent representations.
problem Generating chemically valid molecular graphs from latent representations is challenging.
method MoFlow uses a flow-based approach with Glow for bond generation and a novel graph conditional flow for atom generation, ensuring chemical validity and efficiency.
result MoFlow achieves state-of-the-art performance in molecular graph generation and optimization.
In chemistry, deep neural network models have been increasingly utilized in a variety of applications such as molecular property predictions, novel molecule designs, and planning chemical reactions. Despite the rapid increase in the use of state-of-the-art models and algorithms, deep neural network models often produce…
FlowMO uses Gaussian Processes for molecular property prediction with uncertainty.
problem Predicting molecular properties with uncertainty for small datasets.
method Gaussian Processes implemented in FlowMO, built on GPflow and RDKit.
result Comparable predictive performance to deep learning but superior uncertainty calibration.
Study compares GNNs and classical molecular featurisations for molecular property and cliff prediction.
problem Comparing GNNs and classical featurisations for molecular property and cliff prediction.
method Systematic exploration and comparison of PDVs, ECFPs, and GNNs; introduction of substructure pooling.
result Sort & Slice outperforms hash-based folding in ECFP vectorization.
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…
ASGN uses active semi-supervised learning to predict molecular properties efficiently.
problem Predicting molecular properties with scarce labeled data and high computational cost.
method ASGN combines a teacher-student framework with active learning to handle joint representation and property learning.
result ASGN achieves remarkable performance in property prediction on public datasets.
BayReL learns molecular interactions across multi-omics data.
problem Inferring meaningful interactions across diverse molecular data types.
method BayReL uses Bayesian representation learning with graph models to integrate multi-omics data.
result BayReL outperforms existing methods in inferring molecular interactions.
Automates GNN design for molecular property prediction.
problem Designing and tuning GNN architectures for molecular property prediction is labor-intensive.
method Developed a NAS approach to automatically discover high-performing GNN architectures for MPNNs.
result Automatically discovered MPNNs outperform manually designed GNNs in molecular property prediction.
There is an increasing demand for computing the relevant structures, equilibria and long-timescale kinetics of biomolecular processes, such as protein-drug binding, from high-throughput molecular dynamics simulations. Current methods employ transformation of simulated coordinates into structural features, dimension red…
Machine learning predicts molecular crystal stability.
problem Predicting the stability of molecular crystals.
method Supervised and unsupervised machine learning techniques to classify and predict lattice energy.
result Data-driven assessment of chemical groups' contribution to crystal stability.
Model predicts stable molecules with AI and physics constraints.
problem Designing stable molecules with limited data.
method Graph Scattering Variational Autoencoder with physical constraints.
result Model generates stable molecules with desired properties.
Paper improves molecular property prediction using denoising autoencoders.
problem Limited data for molecular property prediction from 3D structures.
method Pre-training via denoising for learning molecular force fields.
result Achieves new state-of-the-art performance on QM9 dataset.
MACE architecture outperforms alternatives in various molecular and materials science tasks.
problem Improving machine learning force fields for diverse molecular and materials science applications.
method Evaluation of MACE architecture on various datasets and tasks, demonstrating data efficiency and excellent performance.
result MACE architecture generally outperforms alternatives across a wide range of systems, including amorphous carbon, universal materials modelling, and organic chemistry.
Molecular dynamics simulations are an important tool for describing the evolution of a chemical system with time. However, these simulations are inherently held back either by the prohibitive cost of accurate electronic structure theory computations or the limited accuracy of classical empirical force fields. Machine l…
Generative models in molecular design tend to be richly parameterized, data-hungry neural models, as they must create complex structured objects as outputs. Estimating such models from data may be challenging due to the lack of sufficient training data. In this paper, we propose a surprisingly effective self-training a…
Improved CG force-field learning from all-atom data.
problem Training accurate coarse-grained models from all-atom simulations is challenging.
method Optimized force mapping to improve statistical efficiency of force-field learning.
result Substantially improved CG force-fields can be learned from the same simulation data.
RC flow learns molecular kinetics in low dimensions.
problem Discovering interpretable low-dimensional models of molecular kinetics.
method Normalizing flow for coordinate transformation and Brownian dynamics for kinetics approximation.
result Tractable and trainable model of reduced kinetics in continuous time and space.
Molecular structure-property relationships are key to molecular engineering for materials and drug discovery. The rise of deep learning offers a new viable solution to elucidate the structure-property relationships directly from chemical data. Here we show that the performance of graph convolutional networks (GCNs) for…
In drug-discovery-related tasks such as virtual screening, machine learning is emerging as a promising way to predict molecular properties. Conventionally, molecular fingerprints (numerical representations of molecules) are calculated through rule-based algorithms that map molecules to a sparse discrete space. However,…
Paper tackles multi-task learning for molecular property prediction with limited data.
problem Limited labeled data for each molecular property task in drug discovery.
method Proposes SGNN-EBM method to utilize relation graph between tasks and improve multi-task learning performance.
result Empirical results show the effectiveness of SGNN-EBM.
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…
Quantum machine learning boosts drug discovery efficiency.
problem Enhancing drug discovery through quantum computing.
method Quantum neural networks on gate-based quantum computers.
result Significant advancements in molecular property prediction and generation.
New method calibrates uncertainty in molecular property predictions.
problem Uncalibrated uncertainty estimates in molecular property predictions.
method Message Passing Neural Networks with calibrated probabilistic predictive distribution.
result Accurate molecular formation energy predictions with well-calibrated uncertainty.
Multitask Gaussian process regression reduces data generation costs for molecular property prediction.
problem Data bottleneck in training surrogate models for molecular properties.
method Multitask Gaussian process regression over heterogeneous data sources (CC and DFT).
result Predicts at CC-level accuracy with over an order of magnitude reduction in data generation cost.
GeoPhy uses geometric gradients to efficiently infer phylogenetic trees from molecular data.
problem Challenges in accurately inferring species relationships from molecular data due to combinatorially vast tree topologies.
method Introduces a novel, fully differentiable formulation of phylogenetic inference using geometric spaces and variational Bayesian methods.
result Significantly outperforms other approximate Bayesian methods in inferring phylogenetic trees.
Molecular machine learning has been maturing rapidly over the last few years. Improved methods and the presence of larger datasets have enabled machine learning algorithms to make increasingly accurate predictions about molecular properties. However, algorithmic progress has been limited due to the lack of a standard b…
This paper reviews deep learning and knowledge-based methods for molecular design.
problem Optimizing molecular properties for scientific advances and process performance.
method Survey of deep learning and knowledge-based methods for molecular design.
result Deep learning models show promise in overcoming computational challenges.
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…
In the majority of molecular optimization tasks, predictive machine learning (ML) models are limited due to the unavailability and cost of generating big experimental datasets on the specific task. To circumvent this limitation, ML models are trained on big theoretical datasets or experimental indicators of molecular s…
MD-GAN learns long-time molecular behavior from short-time data with multi-particle input.
problem Accurately predicting long-time molecular dynamics from short-time data.
method Machine learning method (MD-GAN) that incorporates dynamics of multiple particles of molecules.
result Predicting diffusion with one-third of the training data length using multi-particle input.
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…
New method uses cohomology to quantify molecular similarity.
problem Quantifying structural dissimilarity in molecular data.
method Gromov-Hausdorff ultrametric based on simplicial complexes and cohomology.
result Demonstrates effectiveness in clustering organic-inorganic halide perovskite structures.
Rotationally equivariant convolutions improve molecular property prediction.
problem Predicting molecular properties using graph neural networks.
method Ablation study with rotationally equivariant and invariant convolutions on QM9 data set.
result Rotationally equivariant layers decrease test error by an average of 23%.
New method uses geometric moments for accurate machine learning potentials.
problem Creating high-dimensional potential energy surfaces efficiently.
method Feed-forward neural networks with invariant local molecular descriptors based on geometric moments.
result Accuracy comparable to established models, high efficiency.
The success of enhanced sampling molecular simulations that accelerate along collective variables (CVs) is predicated on the availability of variables coincident with the slow collective motions governing the long-time conformational dynamics of a system. It is challenging to intuit these slow CVs for all but the simpl…
MolHF generates complex molecules with hierarchical flow-based model.
problem Designing novel molecular structures with desired properties.
method MolHF is a hierarchical normalizing flow model that generates molecular graphs in a coarse-to-fine manner.
result MolHF achieves state-of-the-art performance in random generation and property optimization.
Develops methods to simulate rare transitions in molecular systems.
problem Rare transitions between metastable states in molecular systems are difficult to study due to limited data.
method Two novel methods: chain-based and midpoint-based approaches.
result Demonstrates effectiveness of methods in both data-rich and data-scarce scenarios.
Single-cell RNA sequencing (scRNA-seq) is a fast growing approach to measure the genome-wide transcriptome of many individual cells in parallel, but results in noisy data with many dropout events. Existing methods to learn molecular signatures from bulk transcriptomic data may therefore not be adapted to scRNA-seq data…
MoReL models multi-omics data to find hidden molecular interactions.
problem Heterogeneous multi-omics data with varying quality and structure.
method Fused Gromov-Wasserstein (FGW) regularization in a deep Bayesian generative model.
result Enhanced performance in inferring meaningful interactions from real-world datasets.
Enhances diffusion-based sampling for molecular systems.
problem Inefficiency and thermodynamic mode miss in diffusion-based samplers for molecular systems.
method Introduces a sequential bias along collective variables (CVs) to encourage exploration and increase temperature in the projected space.
result Improves efficiency, mode discovery, and free energy estimation; first to demonstrate reactive sampling.
Due to its high computational speed and accuracy compared to ab-initio quantum chemistry and forcefield modeling, the prediction of molecular properties using machine learning has received great attention in the fields of materials design and drug discovery. A main ingredient required for machine learning is a training…
We propose a molecular generative model based on the conditional variational autoencoder for de novo molecular design. It is specialized to control multiple molecular properties simultaneously by imposing them on a latent space. As a proof of concept, we demonstrate that it can be used to generate drug-like molecules w…