• Corpus ID: 102206622

Machine Learning, Quantum Mechanics, and Chemical Compound Space

  title={Machine Learning, Quantum Mechanics, and Chemical Compound Space},
  author={Raghunathan Ramakrishnan and O. Anatole von Lilienfeld},
  journal={arXiv: Chemical Physics},
We review recent studies dealing with the generation of machine learning models of molecular and solid properties. The models are trained and validated using standard quantum chemistry results obtained for organic molecules and materials selected from chemical space at random. 

Figures and Tables from this paper

Machine Learning of Partial Charges Derived from High-Quality Quantum-Mechanical Calculations
A machine learning (ML) based approach for predicting partial charges extracted from density functional theory (DFT) electron densities and the training set was chosen with the goal to provide a broad coverage of the known chemical space of druglike molecules.
Deep Molecular Representation in Cheminformatics
Results on a benchmark dataset show that the deep encoded molecular representation outperforms Bag-of-Bond representations in predicting electronic quantum-chemical descriptors.
Machine learning of molecular properties: Locality and active learning.
A new machine learning algorithm for predicting molecular properties that is based on a local model of interatomic interactions providing high accuracy when trained on relatively small training sets and an active learning algorithm of optimally choosing the training set that significantly reduces the errors for the outliers is proposed.
A deep learning approach to the structural analysis of proteins
A DL architecture capable of predicting non-trivial and intrinsically global quantities, that is, the eigenvalues of a protein’s lowest-energy fluctuation modes is built, and demonstrates unexpected use in the identification of mechanically relevant regions of the molecule.
Modelling Chemical Reasoning to Predict Reactions
A model that mimics chemical reasoning, and formalises reaction prediction as finding missing links in a knowledge graph that outperforms a rule-based expert system in the reaction prediction task for 180 000 randomly selected binary reactions.
Challenges in Simulating Light-Induced Processes in DNA
In this contribution, we give a perspective on the main challenges in performing theoretical simulations of photoinduced phenomena within DNA and its molecular building blocks. We distinguish the
Enabling Large Scale DFT Simulation with GPU Acceleration and Machine Learning
Two complementary approaches were developed to boost the performance of large scale DFT calculations of CP2K, with the predominant operation, sparse matrix-matrix multiplication, ported to GPU accelerators and further increased employing geometry adapted basis sets obtained with machine learning.


Machine learning for many-body physics: efficient solution of dynamical mean-field theory
The results indicate that with modest further development, machine learning approach may be an attractive computational efficient option for real materials predictions for strongly correlated systems.
Fourier series of atomic radial distribution functions: A molecular fingerprint for machine learning models of quantum chemical properties
We introduce a fingerprint representation of molecules based on a Fourier series of atomic radial distribution functions. This fingerprint is unique (except for chirality), continuous, and
Gaussian approximation potentials: the accuracy of quantum mechanics, without the electrons.
We introduce a class of interatomic potential models that can be automatically generated from data consisting of the energies and forces experienced by atoms, as derived from quantum mechanical
Quantum Energy Regression using Scattering Transforms
This new framework removes fundamental limitations of Coulomb matrix based energy regressions, and numerical experiments give state-of-the-art accu- racy over planar molecules.
Interatomic potentials for ionic systems with density functional accuracy based on charge densities obtained by a neural network
By allowing the electronic charge to distribute itself in an optimal way over the system, the approach can describe not only neutral but also ionized systems with unprecedented accuracy and is able to obtain chemical accuracy, i.e. errors of less than a milli Hartree per atom.
Quantum chemistry structures and properties of 134 kilo molecules
This data set provides quantum chemical properties for a relevant, consistent, and comprehensive chemical space of small organic molecules that may serve the benchmarking of existing methods, development of new methods, such as hybrid quantum mechanics/machine learning, and systematic identification of structure-property relationships.
Molecular electronic-structure theory
Second Quantization Spin in Second Quantization Orbital Rotations Exact and Approximate Wave Functions The Standard Models Atomic Basis Functions Short-Range Interactions and Orbital Expansions
Introduction to Computational Chemistry
An energy optimized basis set which gives a good description of the outer part of the wave function.
Statistical Mechanics: Theory and Molecular Simulation
1. Introduction 2. Classical Mechanics 3. Theoretical Foundations of Classical Statistical Mechanics 4. The Microcanonical Ensemble and Introduction to Molecular Dynamics 5. The Canonical Ensemble 6.