Retro Drug Design: From Target Properties to Molecular Structures.

To deliver more therapeutics to more patients more quickly and economically is the ultimate goal of pharmaceutical researchers. The advent and rapid development of artificial intelligence (AI), in combination with other powerful computational methods in drug discovery, makes this goal more practical than ever before. Here, we describe a new strategy, retro drug design, or RDD, to create novel small-molecule drugs from scratch to meet multiple predefined requirements, including biological activity against a drug target and optimal range of physicochemical and ADMET properties. The molecular structure was represented by an atom typing based molecular descriptor system, optATP, which was further transformed to the space of loading vectors from principal component analysis. Traditional predictive models were trained over experimental data for the target properties using optATP and shallow machine learning methods. The Monte Carlo sampling algorithm was then utilized to find the solutions in the space of loading vectors that have the target properties. Finally, a deep learning model was employed to decode molecular structures from the solutions. To test the feasibility of the algorithm, we challenged RDD to generate novel kinase inhibitors from random numbers with five different ADMET properties optimized at the same time. The best Tanimoto similarity score between the generated valid structures and the available 4,314 kinase inhibitors was < 0.50, indicating a high extent of novelty of the generated compounds. From the 3,040 structures that met all six target properties, 20 were selected for synthesis and experimental measurement of inhibition activity over 97 representative kinases and the ADMET properties. Fifteen and eight compounds were determined to be hits or strong hits, respectively. Five of the six strong kinase inhibitors have excellent experimental ADMET properties. The results presented in this paper illustrate that RDD has the potential to significantly improve the current drug discovery process.

A high-throughput imaging and nuclear segmentation analysis protocol for cleared 3D culture models.

Imaging and subsequent segmentation analysis in three-dimensional (3D) culture models are complicated by the light scattering that occurs when collecting fluorescent signal through multiple cell and extracellular matrix layers. For 3D cell culture models to be usable for drug discovery, effective and efficient imaging and analysis protocols need to be developed that enable high-throughput data acquisition and quantitative analysis of fluorescent signal. Here we report the first high-throughput protocol for optical clearing of spheroids, fluorescent high-content confocal imaging, 3D nuclear segmentation, and post-segmentation analysis. We demonstrate nuclear segmentation in multiple cell types, with accurate identification of fluorescently-labeled subpopulations, and develop a metric to assess the ability of clearing to improve nuclear segmentation deep within the tissue. Ultimately this analysis pipeline allows for previously unattainable segmentation throughput of 3D culture models due to increased sample clarity and optimized batch-processing analysis.