Abstract: Methods and systems for generating drug repurposing predictions for a disease caused by a pathogen, such as a novel pathogen, are provided. A multi-modal system includes a protein-protein interaction network (PPI), a graph neural network (GNN), a diffusion module, a proximity module, and an aggregation module. The GNN is configured to predict new edges between candidate drug nodes and disease nodes in an embedded representation of the PPI to produce a decoded embedding space. The diffusion module is configured to determine a proximity distance for pairs of nodes in the PPI, and the proximity module is configured to determine a proximity distance for pairs of nodes in the PPI, each pair comprising a pathogen-protein node and a drug-protein node. A ranked list of candidate drugs predicted to be effective in treatment of the disease based on candidate drug lists generated by the other modules is generated by the aggregation module.

Abstract: Systems and methods are disclosed for predicting a product's (e.g., a book's) performance prior to its availability. An example embodiment is a system for machine learning classification that includes representations of characteristics of products, a pre-processor, and a machine learning classifier. The pre-processor can determine (i) representations of comparative intrinsic characteristics of the products based on the representations of characteristics of products and (ii) representations of corresponding comparative extrinsic characteristics of the products. The pre-processor can generate a data structure representing relationships between the comparative intrinsic characteristics and the comparative extrinsic characteristics. The machine learning classifier is trained with the data structure. The classifier can return representations of comparative extrinsic characteristics in response to given comparative intrinsic characteristics.