Computer immunology

Abstract

This review describes a body of work on computational immune systems that behave analogously to the natural immune system. These artificial immune systems (AIS) simulate the behavior of the natural immune system and in some cases have been used to solve practical engineering problems such as computer security. AIS have several strengths that can complement wet lab immunology. It is easier to conduct simulation experiments and to vary experimental conditions, for example, to rule out hypotheses; it is easier to isolate a single mechanism to test hypotheses about how it functions; agent-based models of the immune system can integrate data from several different experiments into a single in silico experimental system.

Weka Machine Learning for Predicting the Phospholipidosis Inducing Potential

“…Several examples of such algorithms are artificial neural networks, genetic algorithms, artificial immune systems, ant colony optimization, DNA computing, and particle swarm optimization. Artificial immune systems (AIS) are computational tools that emulate processes and mechanism of the biological immune system [77][78][79][80]. AIS use the learning, memory, and optimization capabilities of the immune system to develop computational algorithms for classification, function optimization, pattern recognition, novelty detection, and process control [81][82][83].…”

Simulating antigenic drift and shift in influenza A

“…There are several approaches to immune system (IS) and pathogen modeling [23], among which models based on differential equations are probably the most common [16]. This methodology is mostly used for modeling particular aspects of the IS and pathogens, among which is its use on the study of influenza dynamics [2,8,20] and treatment [5].…”

Immuno-engineering

“…These investigations sparked a host of attempts to apply aspects of immunology to a wider range of engineering problems, and the reader is referred to the International Conference on Artificial Immune Systems (ICARIS) for a comprehensive collection of papers [7,8,9,10,11,12]. Over recent years there have been a number of review papers written on AIS with the first being [13] followed by a series of others that either review AIS in general, for example, [14,15,16,17,18], or more specific aspects of AIS such as data mining [19], network security [20], applications of AIS [21], theoretical aspects [22] and modelling in AIS [23].…”

“…Modelling affords us the opportunity to investigate a complex system from different perspectives: from the level of individual components (molecules and cells), to the level of populations of cells, to an overall systems level. For the modelling, a wide variety of options are open, all with their own advantages and disadvantages [23] such as dynamical systems, optimal control theory, information and coding, probability, stochastic π-calculus and complex network theory. 10 immune systems, capturing the essentials of immuno-ecology (the interaction between which itself acts as the bridge between experimental immunology and engineering Fig.…”

“…It is pointed out, however, by Garrett [17] that the immune system has more to offer than this, with the mechanisms of the innate immune system and the view that the immune system is a homeostatic control system, being highlighted as future areas for AIS to exploit, and indeed this call seems to be taken up in a small part in recent times [42,43,44]. Concurring with the above, Bersini [45] argues that the immune system is much more than a simple classifier and performs much more than "pattern matching" and urges people in AIS to think about applications that are far removed from such applications which are the dominant force in AIS [23]. This challenges the community to find that niche application that AIS alone can tackle.…”