Abstract: A method is presented for analyzing interactions in a human genome. The method includes: receiving a biological sample of a cell from a subject; extracting read data from the biological sample, where the read data includes a set of reads; and constructing, by a computer processor, a hypergraph from the read data, where each node in the hypergraph represents a locus and hyperedges in the hypergraph represent interactions between two or more loci. The hypergraphs may be used for different applications including determining entropy, comparing different biological samples and reporting multi-way contacts in a set of transcription clusters.

Abstract: The lack of robustness of Deep Neural Networks (DNNs) against different types of attacks is problematic in adversarial environments. The long-standing and arguably most powerful natural defense system is the mammalian immune system, which has successfully defended the species against attacks by novel pathogens for millions of years. This disclosure proposes a Robust Adversarial Immune-inspired Learning System (RAILS) inspired by the mammalian immune system. The RAILS approach is demonstrated using adaptive immune system emulation to harden Deep k-Nearest Neighbor (DkNN) architectures against evasion attacks. Using evolutionary programming to simulate new B-cell generation that occurs in natural immune systems, e.g., B-cell flocking, clonal expansion, and affinity maturation, it is shown that the RAILS learning curve exhibits similar learning behavior as observed in in-vitro experiments on B-cell affinity maturation. The life-long learning mechanism allows RAILS to evolve and defend against diverse attacks.