Reaction prediction remains one of the major challenges for organic chemistry, and is a pre-requisite for efficient synthetic planning. It is desirable to develop algorithms that, like humans, "learn" from being exposed to examples of the application of the rules of organic chemistry. We explore the use of neural netwo…
On-device research index
arXiv research
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.
169,181 papers · 148 categories
Trend · papers per month
48 results for “organic chemistry”
Graphs predict reaction conditions for organic chemistry.
problem Predicting specific reaction conditions in organic chemistry.
method Graph Neural Networks (GNNs) for modeling reaction graphs.
result GNNs can identify specific graph features affecting reaction conditions.
Neural model predicts organic reactions with high accuracy.
problem Predicting outcomes of complex organic chemistry reactions.
method Sequence-to-sequence model trained end-to-end, data-driven.
result Achieved 80.1% top-1 accuracy on a smaller dataset.
Retro* uses neural networks to efficiently find high-quality synthetic routes in organic chemistry.
problem Finding efficient synthetic routes in organic chemistry is challenging due to the vast search space.
method Retro* is a neural-based A*-like algorithm that learns a neural search bias to guide efficient best-first search.
result Retro* outperforms existing methods in both success rate and solution quality while being more efficient.
ChemCrow enhances LLMs for chemistry tasks, automating complex chemical processes.
problem Limited access to computational chemistry tools for large-language models.
method Integrating 18 expert-designed chemistry tools into an LLM (ChemCrow).
result ChemCrow autonomously plans and executes chemical syntheses and discoveries.
Alchemy dataset benchmarks AI models in chemistry.
problem Lack of diverse molecular datasets for AI models in chemistry.
method Developed a new molecular dataset with 119,487 organic molecules and benchmarked AI models on it.
result Demonstrated the usefulness of new data in validating and developing machine learning models for chemistry.
BERT learns molecular substructures for chemistry problems.
problem Predicting chemical properties and synthesizing molecules.
method Transformer-based BERT model on molecule string representations, attention visualization.
result BERT learns to represent functional groups and atoms for various chemical properties.
Simple and efficient algorithms for training machine learning potentials to force dataphysics.comp-ph
New algorithm efficiently trains machine learning models to atomic forces data.
problem Efficiently training machine learning models to large amounts of force data.
method Developed an efficient algorithm for training machine learning models to all available force data.
result Training to all available force data is only a few times more expensive than training to energies alone.
Kernelized PCovR reveals structure-property relations in chemistry and materials.
problem Understanding structure-property relations in complex systems.
method Kernel Principal Covariates Regression (kernel PCovR) with sparsification.
result Kernelized PCovR effectively reveals and predicts structure-property relations.
A deep neural network for molecular wave functions in quasi-atomic minimal basis representationphysics.comp-ph
Deep neural network predicts molecular wave functions in minimal basis.
problem Improving accuracy and efficiency in quantum chemistry calculations.
method Adapted SchNet for Orbitals (SchNOrb) model in quasi-atomic minimal basis.
result Model accurately predicts molecular orbital energies and wavefunctions for large molecules.
Machine Learning Prediction of Accurate Atomization Energies of Organic Molecules from Low-Fidelity Quantum Chemical Calculationsphysics.comp-ph
Machine learning predicts atomization energies accurately from low-fidelity calculations.
problem Predicting accurate atomization energies of organic molecules efficiently.
method Machine learning models trained on low-fidelity B3LYP energies to predict high-fidelity G4MP2 energies.
result Predicted G4MP2 atomization energies within 0.012 eV for molecules with 10-14 heavy atoms.
A new method predicts organic reactions faster and more accurately.
problem Predicting reaction outcomes in complex molecules is computationally challenging.
method Identifies reaction centers, enumerates candidate products, and scores them using a Weisfeiler-Lehman Difference Network.
result Framework outperforms template-based methods with a 10% margin and runs faster.
Transfer learning boosts chemically accurate neural network potentials for organic molecules.
problem Developing accurate interatomic potentials from ab-initio data.
method Discriminative fine-tuning of pre-trained neural networks.
result Fine-tuning with energy labels alone can achieve accurate atomic forces.
Transferable Generative Models Bridge Femtosecond to Nanosecond Time-Step Molecular Dynamicsphysics.chem-ph
Generative models accelerate molecular dynamics by four orders of magnitude.
problem Femtosecond time steps limit access to slow molecular processes.
method Deep generative modeling framework that accelerates sampling.
result Quantitative characterization of equilibrium ensembles and dynamical relaxation processes.
New model predicts chemical reactions with conditional graph logic networks.
problem Predicting chemical reactions for synthesizing molecules.
method Conditional Graph Logic Network (CGLN) based on graph neural networks.
result Significant improvement of 8.1% over state-of-the-art methods.
Evaluation of the MACE Force Field Architecture: from Medicinal Chemistry to Materials Sciencephysics.chem-ph
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.
Bayesian algorithm discovers synthetic routes from target molecules.
problem Identifying synthetic routes from desired products.
method Bayesian inference and combinatorial optimization.
result Algorithm rediscovered 80.3% and 50.0% of known synthetic routes.
Gryffin optimizes categorical variables in materials design, leveraging expert knowledge.
problem Optimizing categorical variables in complex design choices like molecule selection.
method Bayesian optimization with smooth approximations to categorical distributions, incorporating expert knowledge.
result Gryffin accelerates discovery of promising molecules and materials, highlighting relevant correlations.
Optimized DMD for fast atmospheric chemistry forecasting.
problem Forecasting global atmospheric chemistry dynamics efficiently.
method Optimized Dynamic Mode Decomposition (DMD) for reduced order modeling.
result Significant improvement in computational speed and interpretability.
Deep QMC methods use neural networks to solve quantum chemistry problems.
problem Solving the electronic Schrödinger equation from first principles.
method Quantum Monte Carlo with neural network wavefunctions.
result Highly accurate solutions at reduced computational cost.
METRO predicts reactions using minimal templates, reducing computational overhead and achieving state-of-the-art results.
problem Predicting possible reaction substrates for complex molecules from simpler precursors.
method METRO (Molecule-Edit Templates for RetrOsynthesis) uses minimal templates to predict reactions efficiently and accurately.
result METRO achieves state-of-the-art results on standard benchmarks, reducing computational overhead.
Unifying machine learning and quantum chemistry -- a deep neural network for molecular wavefunctionsphysics.chem-ph
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.
ML4Chem offers a user-friendly platform for developing and deploying machine learning models in chemistry.
problem Developing and deploying machine learning models in chemistry and materials science.
method User-experience design, six core building blocks: data, featurization, models, model optimization, inference, and visualization.
result Ease of use and functionality of the atomistic module for neural networks and kernel ridge regression.
The Effects of Taxes on Wealth Inequality in Artificial Chemistry Models of Economic Activityq-fin.GN
Study examines how taxes affect wealth inequality in economic models.
problem Reducing economic inequality in models of economic activity.
method Examined Artificial Chemistry models and various tax measures.
result Effective tax measures can reduce economic inequality.
Symmetric and antisymmetric kernels for machine learning problems in quantum physics and chemistryquant-ph
Derives symmetric and antisymmetric kernels for quantum physics and chemistry applications.
problem Efficiently handling symmetries and antisymmetries in machine learning for quantum physics and chemistry.
method Symmetrizing and antisymmetrizing conventional kernels, analyzing feature space dimensions, proving kernel properties, proposing Slater determinant representation.
result Efficient evaluation of antisymmetric Gaussian kernels even in high-dimensional state spaces, significant reduction in training data size.
BoFire optimizes chemistry experiments using Bayesian Optimization.
problem Effective deployment of Bayesian Optimization in the chemical industry.
method Combines Bayesian Optimization with DoE strategies, providing a rich feature-set.
result BoFire enables seamless integration into RESTful APIs for real-world use.
MetaMD outperforms other sampling methods in training neural network model chemistries.
problem Improving neural network model chemistries for accurate chemical space exploration.
method Competitive evaluation of molecular dynamics, normal-mode sampling, and Metadynamics for preparing training geometries.
result MetaMD is an efficient and scalable method for training neural network model chemistries.
Atomistic structure learningcond-mat.mtrl-sci
ASLA learns atomic structures using neural networks and reinforcement learning.
problem Designing materials and drugs with desired properties.
method Atomistic structure learning algorithm (ASLA) using a convolutional neural network and reinforcement learning.
result ASLA can predict optimal structural arrangements of atoms for various target properties.
Sparse molecular representations improve interpretability in graph neural networks.
problem Difficulty in understanding which molecular graph aspects drive deep learning predictions.
method Constrain weights in a graph convolutional neural network using the Gini index to maximize representation inequality.
result The Gini-constrained approach does not degrade evaluation metrics and allows for interpretable representation combination.
Towards Run Time Estimation of the Gaussian Chemistry Code for SEAGrid Science Gatewayphysics.comp-ph
The paper predicts run times for Gaussian chemistry code.
problem Accurate run time prediction for complex scientific codes.
method Characterized data set, explored regression methods.
result Promising future directions for run time prediction.
This work improves chemistry modeling by jointly learning reaction progress variables and look-up models.
problem Jointly modeling turbulent combustion requires solving both chemistry and flow systems simultaneously, which is computationally expensive.
method Developed a deep neural network architecture that jointly learns reaction progress variables and look-up models, improving accuracy.
result Joint learning yields more accurate results in chemistry modeling.
New neural networks explain quantum chemistry predictions atomically.
problem Need for interpretable quantum chemical models.
method Atomistic neural networks and aggregation of atom-wise contributions.
result Atom-wise explanations reveal chemical insights.
A Novel Mathematical Model of Protein Interactions from the Perspective of Electron Delocalizationq-bio.BM
A new model explains protein interactions via electron delocalization.
problem Understanding how protein interactions affect each other.
method Quantized discrete differential geometry of n-simplices.
result Allosteric regulation follows from the model of interactions.
Orders-of-magnitude speedup in atmospheric chemistry modeling through neural network-based emulationphysics.ao-ph
Neural network speeds up atmospheric chemistry modeling 4250x.
problem Computational expense of simulating atmospheric chemistry.
method Created a neural network to emulate a complex chemical mechanism.
result Achieved a 250x computational speedup.
Review of automation's role in chemical discoveries.
problem Improving autonomous discovery in chemistry.
method Classification of discovery types, assessment of autonomy, case studies.
result Rapid advancements in automation and machine learning are transforming experimentation and modeling.
DFT: A Universal Quantum Chemistry Dataset of Drug-Like Molecules and a Benchmark for Neural Network Potentialsphysics.chem-ph
New dataset DFT for drug-like molecules benchmarks neural network potentials.
problem Lack of large, diverse datasets for training neural network potentials in quantum chemistry.
method Developed a new dataset DFT containing energies, forces, and molecular properties for drug-like molecules.
result First dataset with relaxation trajectories for drug-like molecules.
Study explains Graph Convolutional Networks decisions.
problem Difficulty in understanding Graph Network decisions.
method Gradient-based and decomposition-based techniques.
result Sets groundwork for future explainability development.
The rise and fall of artificial neural networks is well documented in the scientific literature of both computer science and computational chemistry. Yet almost two decades later, we are now seeing a resurgence of interest in deep learning, a machine learning algorithm based on multilayer neural networks. Within the la…
Olympus benchmarks optimization algorithms for noisy experiments.
problem Benchmarking optimization algorithms on realistic experimental scenarios is challenging.
method Introduces Olympus, a software package for benchmarking optimization algorithms on synthetic experiments.
result Mitigates barriers in benchmarking optimization algorithms on realistic experimental scenarios.
We present chemlambda (or the chemical concrete machine), an artificial chemistry with the following properties: (a) is Turing complete, (b) has a model of decentralized, distributed computing associated to it, (c) works at the level of individual (artificial) molecules, subject of reversible, but otherwise determinist…
Accelerated RPCholesky speeds up kernel matrix approximations.
problem Efficiently approximating large kernel matrices.
method Accelerated randomly pivoted Cholesky (RPCholesky) with block matrix computations and rejection sampling.
result Approximates kernel matrices up to 40 times faster.
Machine learning and excited-state molecular dynamicsphysics.chem-ph
Machine learning aids excited-state molecular dynamics studies.
problem Challenges in studying electronically excited states of molecules.
method Employing machine learning techniques for excited-state molecular dynamics.
result Highlight successes and challenges in machine learning for excited-state processes.
Automatically detects and down-weights noisy samples in machine learning training.
problem Numerical noise in reference data hampers the accuracy of machine learning models.
method On-the-fly outlier detection using exponential moving average to identify and down-weight noisy samples.
result The method prevents overfitting and matches the performance of iterative refinement with reduced overhead.
Deep learning improves OFDFT for molecular systems.
problem Limited accuracy of OFDFT for non-periodic molecular systems.
method M-OFDFT using deep learning to approximate kinetic energy density.
result Achieves comparable accuracy to Kohn-Sham DFT on large molecules.
Steerable E(3) Graph Neural Networks incorporate geometric and physical covariant information.
problem Incorporating covariant information like position, force, velocity, or spin in graph neural networks.
method Steerable E(3) Equivariant Graph Neural Networks (SEGNNs) that use steerable MLPs to incorporate geometric and physical covariant information.
result SEGNNs improve upon classic linear point convolutions and recent equivariant graph networks that send invariant messages.
In the last few years, we have seen the transformative impact of deep learning in many applications, particularly in speech recognition and computer vision. Inspired by Google's Inception-ResNet deep convolutional neural network (CNN) for image classification, we have developed "Chemception", a deep CNN for the predict…
An ab initio foundation model of wavefunctions that accurately describes chemical bond breakingphysics.chem-ph
New model accurately predicts chemical bond breaking.
problem Challenges in describing bond breaking in quantum chemistry.
method Pretrained deep neural network wavefunction model Orbformer.
result Consistently converges to chemical accuracy (1 kcal/mol).
Zipper logicmath.CO
Zipper logic is a graph rewrite system, consisting in only local rewrites on a class of zipper graphs. Connections with the chemlambda artificial chemistry and with knot diagrammatics based computation are explored in the article.