Molecular Identification from AFM images using the IUPAC Nomenclature and Attribute Multimodal Recurrent Neural Networks

Abstract

Despite being the main tool to visualize molecules at the atomic scale, AFM with CO-functionalized metal tips is unable to chemically identify the observed molecules. Here we present a strategy to address this challenging task using deep learning techniques. Instead of identifying a finite number of molecules following a traditional classification approach, we define the molecular identification as an image captioning problem. We design an architecture, composed of two multimodal recurrent neural networks, capable of identifying the structure and composition of an unknown molecule using a 3D-AFM image stack as input. The neural network is trained to provide the name of each molecule according to the IUPAC nomenclature rules. To train and test this algorithm we use the novel QUAM-AFM dataset, which contains almost 700,000 molecules and 165 million AFM images. The accuracy of the predictions is remarkable, achieving a high score quantified by the cumulative BLEU 4-gram, a common metric in language recognition studies.

arXiv comment30 pages, 4 figures, 2 tables, includes supplementary information (with additional 21 pages, 9 figures, 1 table)

References in corpus (9)

• Advances in atomic force microscopy
• Long Short-Term Memory Based Recurrent Neural Network Architectures for Large Vocabulary Speech Recognition
• Self-Referencing Embedded Strings (SELFIES): A 100% robust molecular string representation
• The mechanism of high-resolution STM/AFM imaging with functionalized tips
• Deep Learning Based Text Classification: A Comprehensive Review
• The origin of high-resolution IETS-STM images of organic molecules with functionalized tips
• Automated Structure Discovery in Atomic Force Microscopy
• Machine learning aided atomic structure identification of interfacial ionic hydrates from atomic force microscopy images
• Integrating Bayesian Inference with Scanning Probe Experiments for Robust Identification of Surface Adsorbate Configurations

Cited by in corpus (2)

• Unveiling the amorphous ice layer during premelting using AFM integrating machine learning
• IUPAC-Induced Computational Approaches for Identifying Boosters of Small Biomolecule Functionality: A Case Study of Human Tyrosyl-DNA Phosphodiesterase 1 (TDP1) Inhibitors