Abstract: Systems and methods are described relating to a Poisson Boltzmann machine learning model, which may be executed to predict electrostatic solvation free energy for molecular compounds, such as proteins. Feature data input to the Poisson Boltzmann machine learning model may include multi-weighted colored subgraph centralities, which may be calculated based on edge definitions of pairwise atomic interactions between atoms of a given protein using a generalized exponential function and/or a generalized Lorentz function, either or both of which may be weighted based on atomic rigidity or atomic charge. Predictions of electrostatic solvation free energy performed by the Poisson Boltzmann machine learning model may be used as a basis for ranking candidate compounds for a defined target clinical application.

Abstract: Characteristics of molecules and/or biomolecular complexes may be predicted using differential geometry based methods in combination with trained machine learning models. Element specific and element interactive manifolds may be constructed using element interactive number density and/or element interactive charge density to represent the atoms or the charges in selected element sets. Feature data may include element interactive curvatures of various types derived from element specific and element interactive manifolds at various scales. Element interactive curvatures computed from various element interactive manifolds may be input to trained machine learning models, which may be derived from corresponding machine learning algorithms.

Abstract: Various characteristics of molecules and/or biomolecular complexes may be predicted using persistent homology and graph theory based methods in combination with trained machine learning algorithms. Feature data derived from one or more of element specific persistent homology barcodes, atom specific persistent homology barcodes, binned barcodes, multiscale weighted colored graphs, and/or evolutionary homology barcodes may be input to one or more trained machine learning models, which may be derived from one or more trained machine learning algorithms, such as gradient-boosted regression trees, deep neural networks, and/or convolutional neural networks.