Aleksandar Poleksić

Overcoming sparseness of biomedical networks to identify drug repositioning candidates

The paper introduces a computational method to identify drug repositioning candidates by overcoming biomedical network sparseness using compressed sensing.

Hyperbolic matrix factorization reaffirms the negative curvature of the native biological space

The paper demonstrates that hyperbolic matrix factorization improves biological relationship inference and reduces latent dimensions compared to Euclidean methods.