Explainable graph neural networks for organic cages

The development of accurate and explicable machine learning models to predict the properties of topologically complex systems is a challenge in materials science. Porous organic cages, a class of polycyclic molecular materials, have potential application in molecular separations, catalysis and encapsulation. For most applications of porous organic cages, having a permanent internal cavity in the absence of solvent, a property termed “shape persistence” is critical. Here, we report the development of Graph Neural Networks (GNNs) to predict the shape persistence of organic cages. Graph neural networks are a class of neural networks where the data, in our case that of organic cages, are represented by graphs. The performance of the GNN models was measured against a previously reported computational database of organic cages formed through a range of [4 + 6] reactions with a variety of reaction chemistries. The reported GNNs have an improved prediction accuracy and transferability compared to random forest predictions. Apart from the improvement in predictive power, we explored the explicability of the GNNs by computing the integrated gradient of the GNN input. The contribution of monomers and molecular fragments to the shape persistence of the organic cages could be quantitatively evaluated with integrated gradients. With the added explicability of the GNNs, it was possible not only to accurately predict the property of organic materials, but also to interpret the predictions of the deep learning models and provide structural insights for the discovery of future materials.

We report the development of explainable Graph Neural Networks to predict shape persistence of organic cages. Integrated gradient analysis identifies collapse-inducing molecular fragments and helps chemists design more shape persistent structures.

Materials Precursor Score: Modeling Chemists' Intuition for the Synthetic Accessibility of Porous Organic Cage Precursors

Computation is increasingly being used to try to accelerate the discovery of new materials. One specific example of this is porous molecular materials, specifically porous organic cages, where the porosity of the materials predominantly comes from the internal cavities of the molecules themselves. The computational discovery of novel structures with useful properties is currently hindered by the difficulty in transitioning from a computational prediction to synthetic realization. Attempts at experimental validation are often time-consuming, expensive, and frequently, the key bottleneck of material discovery. In this work, we developed a computational screening workflow for porous molecules that includes consideration of the synthetic difficulty of material precursors, aimed at easing the transition between computational prediction and experimental realization. We trained a machine learning model by first collecting data on 12,553 molecules categorized either as "easy-to-synthesize" or "difficult-to-synthesize" by expert chemists with years of experience in organic synthesis. We used an approach to address the class imbalance present in our data set, producing a binary classifier able to categorize easy-to-synthesize molecules with few false positives. We then used our model during computational screening for porous organic molecules to bias toward precursors whose easier synthesis requirements would make them promising candidates for experimental realization and material development. We found that even by limiting precursors to those that are easier-to-synthesize, we are still able to identify cages with favorable, and even some rare, properties.

stk: An extendable Python framework for automated molecular and supramolecular structure assembly and discovery

Computational software workflows are emerging as all-in-one solutions to speed up the discovery of new materials. Many computational approaches require the generation of realistic structural models for property prediction and candidate screening. However, molecular and supramolecular materials represent classes of materials with many potential applications for which there is no go-to database of existing structures or general protocol for generating structures. Here, we report a new version of the supramolecular toolkit, stk, an open-source, extendable, and modular Python framework for general structure generation of (supra)molecular structures. Our construction approach works on arbitrary building blocks and topologies and minimizes the input required from the user, making stk user-friendly and applicable to many material classes. This version of stk includes metal-containing structures and rotaxanes as well as general implementation and interface improvements. Additionally, this version includes built-in tools for exploring chemical space with an evolutionary algorithm and tools for database generation and visualization. The latest version of stk is freely available at github.com/lukasturcani/stk.

Can we predict materials that can be synthesised?

The discovery of materials is an important element in the development of new technologies and abilities that can help humanity tackle many challenges. Materials discovery is frustratingly slow, with the large time and resource cost often providing only small gains in property performance. Furthermore, researchers are unwilling to take large risks that they will only know the outcome of months or years later. Computation is playing an increasing role in allowing rapid screening of large numbers of materials from vast search space to identify promising candidates for laboratory synthesis and testing. However, there is a problem, in that many materials computationally predicted to have encouraging properties cannot be readily realised in the lab. This minireview looks at how we can tackle the problem of confirming that hypothetical materials are synthetically realisable, through consideration of all the stages of the materials discovery process, from obtaining the components, reacting them to a material in the correct structure, through to processing into a desired form. In an ideal world, a material prediction would come with an associated 'recipe' for the successful laboratory preparation of the material. We discuss the opportunity to thus prevent wasted effort in experimental discovery programmes, including those using automation, to accelerate the discovery of novel materials.

Inducing Social Self-Sorting in Organic Cages To Tune The Shape of The Internal Cavity

Many interesting target guest molecules have low symmetry, yet most methods for synthesising hosts result in highly symmetrical capsules. Methods of generating lower symmetry pores are thus required to maximise the binding affinity in host-guest complexes. Herein, we use mixtures of tetraaldehyde building blocks with cyclohexanediamine to access low-symmetry imine cages. Whether a low-energy cage is isolated can be correctly predicted from the thermodynamic preference observed in computational models. The stability of the observed structures depends on the geometrical match of the aldehyde building blocks. One bent aldehyde stands out as unable to assemble into high-symmetry cages-and the same aldehyde generates low-symmetry socially self-sorted cages when combined with a linear aldehyde. We exploit this finding to synthesise a family of low-symmetry cages containing heteroatoms, illustrating that pores of varying geometries and surface chemistries may be reliably accessed through computational prediction and self-sorting.

Organic Cage Dumbbells

Molecular dumbbells with organic cage capping units were synthesised via a multi-component imine condensation between a tri-topic amine and di- and tetra-topic aldehydes. This is an example of self-sorting, which can be rationalised by computational modelling.

Building blocks for recognition-encoded oligoesters that form H-bonded duplexes

A long-short base-pairing scheme hinders intramolecular folding and allows the use of flexible backbones in duplex-forming oligomers.

Competition from intramolecular folding is a major challenge in the design of synthetic oligomers that form intermolecular duplexes in a sequence-selective manner. One strategy is to use very rigid backbones that prevent folding, but this design can prejudice duplex formation if the geometry is not exactly right. The alternative approach found in nucleic acids is to use bases (or recognition units) that have different dimensions. A long-short base-pairing scheme makes folding geometrically difficult and is compatible with the flexible backbones that are required to guarantee duplex formation. A monomer building block equipped with a long hydrogen bond donor (phenol, D) recognition unit and a monomer building block equipped with a short hydrogen bond acceptor (phosphine oxide, A) recognition unit were prepared with differentially protected alcohol and carboxylic acid groups. These compounds were used to synthesise the homo and hetero-sequence 2-mers AA, DD and AD. ¹⁹F and ³¹P NMR experiments were used to characterize the assembly properties of these compounds in toluene solution. AA and DD form a stable doubly-hydrogen-bonded duplex with an effective molarity of 20 mM for formation of the second intramolecular hydrogen bond. AD forms a duplex of similar stability. There is no evidence of intramolecular folding in the monomeric state of this compound, which shows that the long-short base-pairing scheme is effective. The ester coupling chemistry used here is an attractive method for the synthesis of long oligomers, and the properties of the 2-mers indicate that this molecular architecture should give longer mixed sequence oligomers that show high fidelity sequence-selective duplex formation.

Emergent supramolecular assembly properties of a recognition-encoded oligoester

An oligoester containing an alternating sequence of hydrogen bonding donor and acceptor side-chains forms a supramolecular architecture that resembles the kissing stem-loops motif found in folded RNA.

A platform for the discovery of new macrolide antibiotics

The chemical modification of structurally complex fermentation products, a process known as semisynthesis, has been an important tool in the discovery and manufacture of antibiotics for the treatment of various infectious diseases. However, many of the therapeutics obtained in this way are no longer effective, because bacterial resistance to these compounds has developed. Here we present a practical, fully synthetic route to macrolide antibiotics by the convergent assembly of simple chemical building blocks, enabling the synthesis of diverse structures not accessible by traditional semisynthetic approaches. More than 300 new macrolide antibiotic candidates, as well as the clinical candidate solithromycin, have been synthesized using our convergent approach. Evaluation of these compounds against a panel of pathogenic bacteria revealed that the majority of these structures had antibiotic activity, some efficacious against strains resistant to macrolides in current use. The chemistry we describe here provides a platform for the discovery of new macrolide antibiotics and may also serve as the basis for their manufacture.