# Discovery of structure-property relations for molecules via hypothesis-driven active learning over the chemical space

arXiv: https://arxiv.org/abs/2301.02665 · HTML: https://mlsanity.com/paper/2301.02665/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 106 references that are in the map.
- First posted on arXiv 6 Jan 2023.

## Builds on (most cited first, 19 of 19)

- [MoleculeNet: A Benchmark for Molecular Machine Learning](https://mlsanity.com/paper/1703.00564/) (2017)
- [Automatic chemical design using a data-driven continuous representation of molecules](https://mlsanity.com/paper/1610.02415/) (2016)
- [Junction Tree Variational Autoencoder for Molecular Graph Generation](https://mlsanity.com/paper/1802.04364/) (2018)
- [SchNet: A continuous-filter convolutional neural network for modeling quantum interactions](https://mlsanity.com/paper/1706.08566/) (2017)
- [Molecular De Novo Design through Deep Reinforcement Learning](https://mlsanity.com/paper/1704.07555/) (2017)
- [Gaussian Processes and Kernel Methods: A Review on Connections and Equivalences](https://mlsanity.com/paper/1807.02582/) (2018)
- [Learning to Plan Chemical Syntheses](https://mlsanity.com/paper/1708.04202/) (2017)
- [Kernel Interpolation for Scalable Structured Gaussian Processes (KISS-GP)](https://mlsanity.com/paper/1503.01057/) (2015)
- [Deep Reinforcement Learning for De-Novo Drug Design](https://mlsanity.com/paper/1711.10907/) (2017)
- [Gaussian Process Kernels for Pattern Discovery and Extrapolation](https://mlsanity.com/paper/1302.4245/) (2013)
- [Drug discovery with explainable artificial intelligence](https://mlsanity.com/paper/2007.00523/) (2020)
- [Machine learning for molecular simulation](https://mlsanity.com/paper/1911.02792/) (2019)
- [Less is more: sampling chemical space with active learning](https://mlsanity.com/paper/1801.09319/) (2018)
- [Molecular Mechanics-Driven Graph Neural Network with Multiplex Graph for Molecular Structures](https://mlsanity.com/paper/2011.07457/) (2020)
- [GAUCHE: A Library for Gaussian Processes in Chemistry](https://mlsanity.com/paper/2212.04450/) (2022)
- [Molecular Generation with Recurrent Neural Networks (RNNs)](https://mlsanity.com/paper/1705.04612/) (2017)
- [Heterogeneous Molecular Graph Neural Networks for Predicting Molecule Properties](https://mlsanity.com/paper/2009.12710/) (2020)
- [Bayesian Active Learning for Scanning Probe Microscopy: from Gaussian Processes to Hypothesis Learning](https://mlsanity.com/paper/2205.15458/) (2022)
- [Machine Learning Prediction of Accurate Atomization Energies of Organic Molecules from Low-Fidelity Quantum Chemical Calculations](https://mlsanity.com/paper/1906.03233/) (2019)

## Built on by (most cited first, 5 of 5)

- [Deep Kernel Methods Learn Better: From Cards to Process Optimization](https://mlsanity.com/paper/2303.14554/) (2023)
- [Data-driven discovery of governing differential equations across physical systems](https://mlsanity.com/paper/2606.09638/) (2026)
- [Large language models, physics-based modeling, experimental measurements: the trinity of data-scarce learning of polymer properties](https://mlsanity.com/paper/2407.02770/) (2024)
- [Active Causal Learning for Decoding Chemical Complexities with Targeted Interventions](https://mlsanity.com/paper/2404.04224/) (2024)
- [Detecting Atomic Scale Surface Defects in STM of TMDs with Ensemble Deep Learning](https://mlsanity.com/paper/2312.05160/) (2023)

## Abstract (arXiv)

Discovery of the molecular candidates for applications in drug targets, biomolecular systems, catalysts, photovoltaics, organic electronics, and batteries, necessitates development of machine learning algorithms capable of rapid exploration of the chemical spaces targeting the desired functionalities. Here we introduce a novel approach for the active learning over the chemical spaces based on hypothesis learning. We construct the hypotheses on the possible relationships between structures and functionalities of interest based on a small subset of data and introduce them as (probabilistic) mean functions for the Gaussian process. This approach combines the elements from the symbolic regression methods such as SISSO and active learning into a single framework. The primary focus of constructing this framework is to approximate physical laws in an active learning regime toward a more robust predictive performance, as traditional evaluation on hold-out sets in machine learning doesn't account for out-of-distribution effects and may lead to a complete failure on unseen chemical space. Here, we demonstrate it for the QM9 dataset, but it can be applied more broadly to datasets from both domains of molecular and solid-state materials sciences.