RESUMEN
Accelerating the development of π-conjugated molecules for applications such as energy generation and storage, catalysis, sensing, pharmaceuticals, and (semi)conducting technologies requires rapid and accurate evaluation of the electronic, redox, or optical properties. While high-throughput computational screening has proven to be a tremendous aid in this regard, machine learning (ML) and other data-driven methods can further enable orders of magnitude reduction in time while at the same time providing dramatic increases in the chemical space that is explored. However, the lack of benchmark datasets containing the electronic, redox, and optical properties that characterize the diverse, known chemical space of organic π-conjugated molecules limits ML model development. Here, we present a curated dataset containing 25k molecules with density functional theory (DFT) and time-dependent DFT (TDDFT) evaluated properties that include frontier molecular orbitals, ionization energies, relaxation energies, and low-lying optical excitation energies. Using the dataset, we train a hierarchy of ML models, ranging from classical models such as ridge regression to sophisticated graph neural networks, with molecular SMILES representation as input. We observe that graph neural networks augmented with contextual information allow for significantly better predictions across a wide array of properties. Our best-performing models also provide an uncertainty quantification for the predictions. To democratize access to the data and trained models, an interactive web platform has been developed and deployed.
RESUMEN
Materials design and discovery are often hampered by the slow pace and materials and human costs associated with Edisonian trial-and-error screening approaches. Recent advances in computational power, theoretical methods, and data science techniques, however, are being manifest in a convergence of these tools to enable in silico materials discovery. Here, we present the development and deployment of computational materials data and data analytic approaches for crystalline organic semiconductors. The OCELOT (Organic Crystals in Electronic and Light-Oriented Technologies) infrastructure, consisting of a Python-based OCELOT application programming interface and OCELOT database, is designed to enable rapid materials exploration. The database contains a descriptor-based schema for high-throughput calculations that have been implemented on more than 56 000 experimental crystal structures derived from 47 000 distinct molecular structures. OCELOT is open-access and accessible via a web-user interface at https://oscar.as.uky.edu.
