Artificial Immune Systems Applications

UnivAIRRse introduces a unified framework to organize and compare AIRR-seq simulators, identifying limitations and providing a tool for dynamic comparison.

The paper shows that transformer attention and contrastive learning can be mathematically derived from immunological principles, highlighting computational convergence between adaptive immunity and AI.

This paper develops a mathematical model of adaptive immunity that integrates humoral and cellular responses, explaining immune memory, original antigenic sin, and cancer-immune interactions.

This paper develops a dynamical model of the immune system that supports the discontinuity theory by showing how immune responses depend on the rate of antigenic change, with implications for infections and vaccination.

This paper develops a novel representation of adaptive immune receptors to improve disease classification from blood samples, achieving higher accuracy for infectious disease, autoimmunity, and cancer.

The paper introduces a quantitative model of innate immune activation regulation using Bayesian inference, revealing tradeoffs between precision and adaptation.

Transformer attention is recast as the update rule of modern Hopfield networks, and the resulting DeepRC classifier handles immune repertoires with enormous instance counts and few informative sequences.

This paper introduces a comprehensive mechanistic model of the human immune system as a digital twin blueprint, integrating immune cells, secretory factors, and disease conditions to simulate immune responses.