Multi-input distributed classifiers for synthetic genetic circuits

TL;DR

This paper introduces a novel synthetic genetic classifier capable of handling multi-input data with complex shapes, enhancing the design of genetic circuits with learning abilities for advanced biological computation.

Contribution

It presents a new design for multi-input distributed classifiers in synthetic biology, enabling complex data separation and learning in genetic networks.

Findings

The classifier can separate multi-input data that are inseparable for single input classifiers.

Both hard and soft classification schemes are analytically and numerically validated.

The approach allows for flexible data class shapes in input space.

Abstract

For practical construction of complex synthetic genetic networks able to perform elaborate functions it is important to have a pool of relatively simple "bio-bricks" with different functionality which can be compounded together. To complement engineering of very different existing synthetic genetic devices such as switches, oscillators or logical gates, we propose and develop here a design of synthetic multiple input distributed classifier with learning ability. Proposed classifier will be able to separate multi-input data, which are inseparable for single input classifiers. Additionally, the data classes could potentially occupy the area of any shape in the space of inputs. We study two approaches to classification, including hard and soft classification and confirm the schemes of genetic networks by analytical and numerical results.