New method explains complex fuel compound classifications.
problem Understanding complex quantitative structure-activity relationship models.
method Locally Interpretable Machine-Agnostic Explanations (LIME) applied to 2-D chemical structures.
result Replicates chemical intuition, allowing direct acceptance/rejection of decisions.
Neural networks predict substructures from mass spectra to identify chemical threats.
problem Identifying unknown chemical threats from mass spectra and formulas.
method Data-driven approach using neural networks to rank and match substructures.
result Substructure classifiers achieve over 90% micro F1-score and correctly identify structures in 88-71% of cases.
DeepSIBA predicts biological effects of chemical structures using graph neural networks.
problem Predicting biological effects of chemical structures for drug discovery.
method Siamese Graph Convolutional Neural Networks for structure-biological effect mapping.
result Highly accurate predictions of biological effects for structurally dissimilar compounds.
Framework separates chemical and structural contributions to aqueous solubility.
problem Merging chemical and structural information in solubility models obscures their relative importance.
method Additive MLP-GNN framework with separate chemical and structural branches.
result Framework reveals distinct roles of chemical and structural information in solubility.
A framework separates chemical and structural contributions to aqueous solubility.
problem Merging chemical and structural information in solubility models obscures their relative contributions.
method Additive MLP-GNN framework with separate chemical and structural branches.
result Framework reveals distinct roles of chemical and structural information in solubility.
AI models struggle to generate diverse natural chemical structures.
problem Generating diverse chemical structures for drug discovery.
method Quantified internal chemical diversity; challenge with two models.
result AI models fail to reproduce natural chemical diversity.
ChemGrapher uses deep learning to automatically convert chemical compound images into accurate graphs.
problem Automatically converting chemical compound images into accurate graphs with correct bond multiplicity and stereochemical information.
method Developed a deep neural network model for optical compound recognition, including segmentation and classification models.
result Significant error reductions in bond multiplicity and stereochemical information compared to existing tools.
CASTER predicts drug interactions using chemical substructures.
problem Identifying potential drug-drug interactions during drug design.
method CASTER uses sequential pattern mining, auto-encoding, and dictionary learning to predict DDIs.
result CASTER outperformed state-of-the-art models and provided interpretable predictions.
MoleculeSTM learns from molecule structures and texts for better drug design.
problem Lack of integration between chemical structures and textual knowledge in AI drug discovery.
method Jointly learns chemical structures and texts via contrastive learning, using a large dataset.
result MoleculeSTM achieves state-of-the-art performance in zero-shot tasks like structure-text retrieval and molecule editing.
SMILES2Vec learns chemical properties from SMILES strings without feature engineering.
problem Predicting chemical properties from SMILES strings without manual feature engineering.
method Deep RNN (SMILES2Vec) learns features from SMILES strings, optimized using Bayesian optimization.
result Optimized SMILES2Vec outperforms MLP neural networks and achieves 88% accuracy in predicting solubility.
GraphAF generates chemically valid molecules efficiently and accurately.
problem Generating chemically valid molecular structures while optimizing chemical properties.
method Flow-based autoregressive model combining autoregressive and flow-based approaches.
result GraphAF generates 68% chemically valid molecules without chemical knowledge rules and 100% with rules, achieving state-of-the-art performance.
Neural networks learn molecule and material representations.
problem Learning efficient representations for molecules and materials.
method Continuous-filter convolutional network SchNet.
result SchNet accurately predicts chemical properties across various datasets.
Generative models accelerate chemical design from properties to structures.
problem Expensive and incremental strategies for optimizing chemical properties.
method Review of current deep generative models and their application to molecular systems.
result Generative models can expedite the design of novel useful compounds.
Generative models encode and decode 3D crystal structures from a large dataset.
problem Challenges in encoding and decoding 3D crystal structures from large datasets.
method Training two neural networks on a dataset of over 120,000 crystal structures to encode and decode 3D atom positions.
result Ability to generate compressed, continuous latent space representations and decode molecules accurately.
Generative neural network designs novel 3D molecules with specified properties.
problem Designing molecules with desired properties in chemistry.
method Conditional generative neural network for 3D molecular structures.
result Demonstrated utility in generating novel molecules with specified motifs or composition.
Generates natural product-like compounds using GPT models.
problem Challenges in generating and evaluating natural product-like compounds.
method Trained GPT-based chemical language models on natural product dataset.
result Generated compounds have similar distribution to natural products.
ChemBoost predicts protein-ligand binding affinity using SMILES syntax.
problem Predicting high affinity drug-target interactions from sequence similarity alone.
method ChemBoost uses SMILES syntax to represent ligands as documents and proteins as sequences or ligand-centric features. It learns chemical word embeddings and predicts affinities using eXtreme Gradient Boosting.
result ChemBoost outperforms state-of-the-art systems in predicting protein-ligand affinities.
Unified machine learning predicts molecular wavefunctions efficiently.
problem Lack of explicit electronic structure in machine learning models for chemistry.
method Deep neural network for quantum mechanical wavefunction prediction.
result Efficient prediction of molecular wavefunctions with full electronic structure access.
MolGAN generates valid small molecular graphs without graph matching.
problem Generating valid small molecular graphs efficiently.
method Adapts GANs to generate graph-structured data with reinforcement learning.
result MolGAN generates close to 100% valid compounds.
ReLeaSE uses deep reinforcement learning to design novel molecules.
problem Designing molecules with specific properties.
method ReLeaSE integrates generative and predictive deep neural networks trained separately but jointly to generate novel chemical structures.
result ReLeaSE can generate chemical libraries with desired properties.
A new drug embedding method using hierarchical drug relations and chemical structures.
problem Learning accurate drug representations from chemical structures and hierarchies.
method Semi-supervised drug embedding using VAE in hyperbolic space.
result The method accurately places drugs in a hierarchy and predicts side-effects.
Optimizes molecular generation for chemist preferences.
problem Models lack inherent preferences for chemist-desired structures.
method Fine-tuning with Direct Preference Optimization.
result Approach is simple, efficient, and highly effective.
ML-FFs use ML to bridge chem. accuracy and efficiency.
problem Narrowing the gap between ab initio and classical FFs.
method Learn potential energy from structure data without fixed bonds.
result ML-FFs can achieve accuracy of ab initio methods with classical efficiency.
Upper bound on CRN reaction rates derived using information geometry.
problem Challenging task of deriving an upper bound on reaction rates of nonlinear, discrete CRNs.
method Information geometric approach using natural gradient.
result Validated through numerical simulations, demonstrating faster convergence in specific CRNs.
CrystalGAN generates novel stable chemical compounds using GANs.
problem Generating novel multi-element stable chemical compounds efficiently.
method Cross-domain Generative Adversarial Networks (GANs) with novel architecture and loss functions.
result CrystalGAN generates reasonable data with increased complexity.
Automates molecule design with a novel variational autoencoder.
problem Designing molecules based on specific chemical properties.
method Junction tree variational autoencoder generating tree-structured scaffolds and combining them into molecules.
result Significantly outperforms previous models on molecular generation and optimization tasks.
Proposes a new model to predict polymer properties by integrating various data types.
problem Inaccurate polymer property prediction due to separate modeling of different data types.
method Multi-modal cascade feature transfer using GCN for chemical structure and molecular descriptors.
result Empirically evaluated model shows higher predictive performance than single-feature approaches.
Motivation: Analysis of relationships of drug structure to biological response is key to understanding off-target and unexpected drug effects, and for developing hypotheses on how to tailor drug thera-pies. New methods are required for integrated analyses of a large number of chemical features of drugs against the corr…
Bayesian optimization improves chemical design by avoiding invalid molecules.
problem Bayesian optimization over variational autoencoder latent space produces invalid molecular structures.
method Formulated constrained Bayesian optimization to avoid querying far from training data.
result Marked improvements in validity of generated molecules.
This review introduces methods for modeling and inferring stochastic biochemical kinetics.
problem Challenges in modeling and inferring stochastic biochemical kinetics due to complex dynamics and computational limitations.
method Introduction to modelling concepts, simulation, exact solution methods, approximation methods, and inference methods.
result Efficient approximation and inference methods have been developed to handle the complexity of stochastic biochemical kinetics.
The paper develops a Gaussian process model for predicting chemical efficacy.
problem Statistical methodologies for analyzing chemical databases are limited.
method Conditional Gaussian process models with Tanimoto distance and a scaling parameter.
result Predictive performance improves when accounting for chemical space correlation.
Deep learning model classifies drug effects based on structure and cell responses.
problem Limited ability to classify chemicals based on their modes of action.
method Integrative deep learning architecture combining molecular structures and cell responses.
result Improved classification performance, reducing error by 4.6%.
Automates molecule design with simpler SMILES generation and reinforcement learning.
problem Designing molecules with specific chemical properties.
method Combines context-free grammar for SMILES strings and reinforcement learning with a Transformer model.
result Significantly reduces model steps per atom and beats previous baselines.
Proposes SGCN for spatially structured data.
problem Lack of node neighbor ordering in GCNs.
method Uses spatial features to learn from graphs with spatial positions.
result Empirically outperforms state-of-the-art methods.
This paper characterizes stable polynomial mappings in a specific set.
problem Characterizing stable polynomial mappings in a given set.
method Analyzing polynomial mappings with specific degrees and determining topological equivalence.
result Effective determination of mappings with generic topology.
This review discusses challenges and solutions for AI in chemical engineering.
problem Challenges in applying classical machine learning to chemical engineering data.
method Identifying four data characteristics and discussing their applications and solutions.
result Current research extends data science and machine learning to handle chemical engineering data challenges.
Novel multigraph network improves chemical classification tasks.
problem Learning from variable graphs with multiple relationships.
method Proposed a multigraph network using Chebyshev GCNs to handle variable graphs and learned edges.
result Achieved competitive results on chemical classification benchmarks.
EAGCN learns attention weights and node features for multi-relational graphs.
problem Learning molecular properties from complex graph structures.
method Edge attention-based multi-relational GCN (EAGCN) that learns attention weights and node features.
result EAGCN predicts compound properties from molecular graphs efficiently and interprets attention weights.
For each integer d at least two, we construct non-spin closed oriented flat manifolds with holonomy group Z2d and with the property that all of their finite proper covers have a spin structure. Moreover, all such covers have trivial Stiefel-Whitney classes.
Rank-based Bayesian Optimization improves molecule selection in chemical systems.
problem Optimizing chemical compounds using traditional regression models.
method Introducing Rank-based Bayesian Optimization (RBO) using ranking models.
result RBO outperforms regression-based BO, especially for rough landscapes and activity cliffs.
Recent uses of differential geometry in materials science are reviewed here, in particular the September issue of the Phil. Trans. Royal Soc., entitled ``Curvature and chemical Structure.''
Study on stability in discretized hydrodynamics model.
problem Stability analysis of discretized hydrodynamics model.
method Geometric structure of Euler equations, convergence of sectional curvature and Jacobi equations.
result Geometric insights from discretized model transfer to Euler equations.
Automates key steps in NMR protein structure elucidation.
problem Laborious data analysis limits NMR spectroscopy potential.
method Combination of deep learning, non-parametric models, and combinatorial optimization.
result Automated detection and assignment of signals in NMR data.
GLAMOUR learns from macromolecules, overcoming diversity challenges.
problem Challenges in machine learning with macromolecules due to their vast diversity.
method Developed GLAMOUR, a framework for chemistry-informed graph representation of macromolecules.
result Quantifies structural similarity and enables supervised learning for macromolecules.
Analyzes Indian chemical industry post-Covid.
problem Global uncertainty impacts chemical industry performance.
method Fundamental analysis of key players and trends.
result Various geopolitical and macroeconomic trends shape industry performance.
Capsule Neural Networks classify graphs from categorical features and relationships.
problem Graph classification in scientific domains, especially with varying graph sizes and features.
method Explicit tensor representations, Capsule Network for classification.
result Capsule Network model performs competitively with state-of-the-art models.
MEGAN models chemical reactions as graph edits, improving synthesis planning.
problem Generating and predicting chemical reactions under constraints.
method End-to-end encoder-decoder neural model inspired by arrow pushing formalism.
result State-of-the-art accuracy in standard benchmarks for retrosynthesis prediction.
The formal structure of geometrical thermodynamics is reviewed with particular emphasis on the geometry of equilibria submanifolds. On these submanifolds thermodynamic metrics are defined as the Hessian of thermodynamic potentials. Links between geometry and thermodynamics are explored for single and multiple component…