Intermolecular halogen bonds are ideally suited for designing new molecular assemblies because of their strong directionality and the possibility of tuning the interactions by using different types of halogens or molecular moieties. Due to these unique properties of the halogen bonds, numerous areas of application have recently been identified and are still emerging. Here, we present an approach for controlling the 2D self-assembly process of organic molecules by adsorption to reactive vs. inert metal surfaces. Therewith, the order of halogen bond strengths that is known from gas phase or liquids can be reversed. Our approach relies on adjusting the molecular charge distribution, i.e., the σ-hole, by molecule-substrate interactions. The polarizability of the halogen and the reactiveness of the metal substrate are serving as control parameters. Our results establish the surface as a control knob for tuning molecular assemblies by reversing the selectivity of bonding sites, which is interesting for future applications.
In spite of the unprecedented resolution provided by non-contact atomic force microscopy (AFM) with CO-functionalized and advances in the interpretation of the observed contrast, the unambiguous identification of molecular systems solely based on AFM images, without any prior information, remains an open problem. This work presents a first step towards the automatic classification of AFM experimental images by a deep learning model trained essentially with a theoretically generated dataset. We analyze the limitations of two standard models for pattern recognition when applied to AFM image classification and develop a model with the optimal depth to provide accurate results and to retain the ability to generalize. We show that a variational autoencoder (VAE) provides a very efficient way to incorporate, from very few experimental images, characteristic features into the training set that assure a high accuracy in the classification of both theoretical and experimental images.
Spectroscopic methods-like nuclear magnetic resonance, mass spectrometry, X-ray diffraction, and UV/visible spectroscopies-applied to molecular ensembles have so far been the workhorse for molecular identification. Here, we propose a radically different chemical characterization approach, based on the ability of noncontact atomic force microscopy with metal tips functionalized with a CO molecule at the tip apex (referred as HR-AFM) to resolve the internal structure of individual molecules. Our work demonstrates that a stack of constant-height HR-AFM images carries enough chemical information for a complete identification (structure and composition) of quasiplanar organic molecules, and that this information can be retrieved using machine learning techniques that are able to disentangle the contribution of chemical composition, bond topology, and internal torsion of the molecule to the HR-AFM contrast. In particular, we exploit multimodal recurrent neural networks (M-RNN) that combine convolutional neural networks for image analysis and recurrent neural networks to deal with language processing, to formulate the molecular identification as an imaging captioning problem. The algorithm is trained using a data set-which contains almost 700,000 molecules and 165 million theoretical AFM images-to produce as final output the IUPAC name of the imaged molecule. Our extensive test with theoretical images and a few experimental ones shows the potential of deep learning algorithms in the automatic identification of molecular compounds by AFM. This achievement supports the development of on-surface synthesis and overcomes some limitations of spectroscopic methods in traditional solution-based synthesis.
2 March 2022 in Journal of Chemical Information and Modeling
This paper introduces Quasar Science Resources–Autonomous University of Madrid atomic force microscopy image data set (QUAM-AFM), the largest data set of simulated atomic force microscopy (AFM) images generated from a selection of 685,513 molecules that span the most relevant bonding structures and chemical species in organic chemistry. QUAM-AFM contains, for each molecule, 24 3D image stacks, each consisting of constant-height images simulated for 10 tip–sample distances with a different combination of AFM operational parameters, resulting in a total of 165 million images with a resolution of 256 × 256 pixels. The 3D stacks are especially appropriate to tackle the goal of the chemical identification within AFM experiments by using deep learning techniques. The data provided for each molecule include, besides a set of AFM images, ball-and-stick depictions, IUPAC names, chemical formulas, atomic coordinates, and map of atom heights. In order to simplify the use of the collection as a source of information, we have developed a graphical user interface that allows the search for structures by CID number, IUPAC name, or chemical formula.
Frequency modulation (FM) atomic force microscopy (AFM) with metal tips functionalized with a CO molecule at the tip apex (referred as High-Resolution AFM, HR-AFM) has provided access to the internal structure of molecules with totally unprecedented resolution. We propose a model to extract the chemical information from those AFM images in order to achieve a complete identification of the imaged molecule. Our Conditional Generative Adversarial Network (CGAN) converts a stack of constant-height HR-AFM images at various tip-sample distances into a ball-and-stick depiction, where balls of different color and size represent the chemical species and sticks represent the bonds, providing complete information on the structure and chemical composition. The CGAN has been trained and tested with the QUAM-AFM data set, that contains simulated AFM images for a collection of 686000 organic molecules that include all the chemical species relevant in organic chemistry. Tests with a large set of theoretical images and few experimental examples demonstrate the accuracy and potential of our approach for molecular identification.