SchNet - A deep learning architecture for molecules and materials.
By Kristof T. Schütt, Huziel E. Sauceda, P. Kindermans, Alexandre Tkatchenko, K. Müller. 2017
2,154 citations recorded by the source corpus.
Deep learning has led to a paradigm shift in artificial intelligence, including web, text, and image search, speech recognition, as well as bioinformatics, with growing impact in chemical physics. Machine learning, in general, and deep learning, in particular, are ideally suitable for representing quantum-mechanical interactions, enabling us to model nonlinear potential-energy surfaces or enhancing the exploration of chemical compound space. Here we present the deep learning architecture SchNet that is specifically designed to model atomistic systems by making use of continuous-filter convolutional layers. We demonstrate the capabilities of SchNet by accurately predicting a range of properties across chemical space for molecules and materials, where our model learns chemically plausible embeddings of atom types across the periodic table. Finally, we employ SchNet to predict potential-energy surfaces and energy-conserving force fields for molecular dynamics simulations of small molecules and perform an exemplary study on the quantum-mechanical properties of C20-fullerene that would have been infeasible with regular ab initio molecular dynamics.
Subfields: Computational Theory and Mathematics, Materials Chemistry, Molecular Biology, Generative Models, Computational Chemistry & Drug Discovery
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Computational Theory and Mathematics
- Gisbert Schneider
- Francesca Grisoni
- Tommi S. Jaakkola
- Regina Barzilay
- Kenneth Atz
- K. Müller
- Tess E. Smidt
- Frank No'e
In Materials Chemistry
- Tommi S. Jaakkola
- Regina Barzilay
- Gisbert Schneider
- Tess E. Smidt
- Francesca Grisoni
- K. Müller
- Frank No'e
- Kenneth Atz
In Molecular Biology
- Frank No'e
- Tommi S. Jaakkola
- Regina Barzilay
- Tess E. Smidt
- K. Müller
- Gisbert Schneider
- Kenneth Atz
- Francesca Grisoni
In Generative Models
- Tommi S. Jaakkola
- Regina Barzilay
- Jian Tang
- Frank No'e
- Andrew Gordon Wilson
- Jimeng Sun
- Tianfan Fu
- Alán Aspuru-Guzik
In Computational Chemistry & Drug Discovery
- K. Müller
- Grgoire Montavon
- Tess E. Smidt
- Frank No'e
- Gisbert Schneider
- Shyue Ping Ong
- Chi Chen
- Chaopeng Shen
Citations in the corpus
- Relevance of Rotationally Equivariant Convolutions for Predicting Molecular Properties (2020, methodology): “The successes have been characterized by designing bespoke neural networks which have relevant properties “bakedin,” such as parameter sharing across calculations on individual atoms, continuous convolutions, invariance to atomic indexing, and invariance to rotation and translation [4, 5].”
- Generalizing Convolutional Neural Networks for Equivariance to Lie Groups on Arbitrary Continuous Data (2020, methodology): “We perform competitively with state-of-the-art methods (Gilmer et al., 2017; Schütt et al., 2018; Anderson et al., 2019), with lowest MAE on several of the tasks.”
- Graph Networks as a Universal Machine Learning Framework for Molecules and Crystals (2018, background): “36,37 However, this approach is extremely inefficient when multiple targets are related by a physical relationship and should share similar features.”
- Neural Message Passing with Edge Updates for Predicting Properties of Molecules and Materials (2018, methodology): “res. The functions M t, S t, E tand Rare all implemented as neural networks with trainable parameters and can be optimised using gradient descent. Some models, for example Deep Tensor Neural Network (Schütt et al., 2017a), use weight sharing across the interaction steps, thus M tM, S tSand E tEfor a”
- Higher-Order Explanations of Graph Neural Networks via Relevant Walks (2020, methodology): “Graph neural networks (GNNs) [1], [2] have been proposed as a method to learn from observations in general graph structures and have found use in an ever growing number of applications [3], [4], [5], [6], [7], [8].”
- Machine Learning for High-entropy Alloys: Progress, Challenges and Opportunities (2022, background): “However, the adoption of GCNN for the atomistic simulations of complex materials, particularly HEAs, has been rare.”
- Physically informed artificial neural networks for atomistic modeling of materials (2018, methodology): “The general idea is to forego the physical insights and reproduce the PES by interpolating between DFT data points using high-dimensional nonlinear regression methods such as the Gaussian process regression [19, 25–27], interpolating moving least squares [28], kernel ridge regression [12, 20, 21], c”