Designing miRNA-Based Synthetic Cell Classifier Circuits Using Answer Set Programming

Abstract

Cell classifier circuits are synthetic biological circuits capable of distinguishing between different cell states depending on specific cellular markers and engendering a state-specific response. An example are classifiers for cancer cells that recognize whether a cell is healthy or diseased based on its miRNA fingerprint and trigger cell apoptosis in the latter case. Binarization of continuous miRNA expression levels allows to formalize a classifier as a Boolean function whose output codes for the cell condition. In this framework, the classifier design problem consists of finding a Boolean function capable of reproducing correct labelings of miRNA profiles. The specifications of such a function can then be used as a blueprint for constructing a corresponding circuit in the lab. To find an optimal classifier both in terms of performance and reliability, however, accuracy, design simplicity and constraints derived from availability of molcular building blocks for the classifiers all need to be taken into account. These complexities translate to computational difficulties, so currently available methods explore only part of the design space and consequently are only capable of calculating locally optimal designs. We present a computational approach for finding globally optimal classifier circuits based on binarized miRNA datasets using Answer Set Programming for efficient scanning of the entire search space. Additionally, the method is capable of computing all optimal solutions, allowing for comparison between optimal classifier designs and identification of key features. Several case studies illustrate the applicability of the approach and highlight the quality of results in comparison with a state of the art method. The method is fully implemented and a comprehensive performance analysis demonstrates its reliability and scalability.

Designing Distributed Cell Classifier Circuits using a Genetic Algorithm

“…While this research shows that theoretically single-circuit classifiers can perform such classification tasks [16,1], there is a number of challenges for the approach in application. Depending on the heterogeneity of the data, to obtain a clear-cut classification often a circuit of high complexity is needed.…”

“…Since cell classifiers must be feasible to implement in the lab, many constraints are posed on the building blocks of these circuits that need to be encoded in the design problem. So far, two different methods for single-circuit classifiers were described [16,1]. Mohammadi et al [16] proposed a heuristic approach that allows to optimize a classifier's topology using a mechanistic model of the circuit and a predefined set of biochemical parameters.…”

“…Mohammadi et al [16] proposed a heuristic approach that allows to optimize a classifier's topology using a mechanistic model of the circuit and a predefined set of biochemical parameters. Another approach was presented by Becker et al [1]. The authors propose a method for finding globally optimal classifiers represented by boolean functions based on binarized miRNA expression data.…”

“…To search through the entire space of solutions in a short time frame the authors apply logic solvers. Becker et al compare their results to the previously mentioned state-ofthe-art method demonstrating significant improvement in binary classification of presented classifiers [1].…”

“…Section 3 describes the architecture of the proposed genetic algorithm for the design and optimization of DCs. In Section 4 we present case studies performed on real-world breast cancer data and compare the results with a single-circuit design method proposed by Becker et al [1]. Finally, we discuss the distributed classifier performance and comment on potential future work.…”