The inverse design of tailored organic molecules for specific optoelectronic devices of high complexity holds an enormous potential but has not yet been realized. Current models rely on large data sets that generally do not exist for specialized research fields. We demonstrate a closed-loop workflow that combines high-throughput synthesis of organic semiconductors to create large datasets and Bayesian optimization to discover new hole-transporting materials with tailored properties for solar cell applications. The predictive models were based on molecular descriptors that allowed us to link the structure of these materials to their performance. A series of high-performance molecules were identified from minimal suggestions and achieved up to 26.2% (certified 25.9%) power conversion efficiency in perovskite solar cells.

By comparison and combination of two strategies, extending π-conjugation and tuning Intramolecular Charge Transfer (ICT) effect, new long-wavelength BODIPY dyes have been efficiently synthesized. The new chromophores exhibit good optical properties: high fluorescence quantum yields, exceptionally large molar extinction coefficients, narrow red-emission bands, and relatively large Stokes shifts etc., in polar or apolar solvents. Besides, the new dyes, under transversal pumping at 532 nm, exhibit highly efficient and stable laser emission tunable from the green to NIR spectral region (570–725 nm). Moreover, one of these new BODIPY derivatives shows cell membrane permeability and bright intracellular red fluorescence. These advantageous characteristics assure the potential of these dyes for biophotonic applications.