Quantum Computing Based Inference of GRNs

Abstract

The accurate reconstruction of gene regulatory networks from temporal gene expression data is crucial for the identification of genetic inter-regulations at the cellular level. This will help us to comprehend the working of living entities properly. Here, we have proposed a novel quantum computing based technique for the reverse engineering of gene regulatory networks from time-series genetic expression datasets. The dynamics of the temporal expression profiles have been modelled using the recurrent neural network formalism. The corresponding training of model parameters has been realised with the help of the proposed quantum computing methodology based concepts. This is based on entanglement and decoherence concepts. The application of quantum computing technique in this domain of research is comparatively new. The results obtained using this technique is highly satisfactory. We have applied it to a 4-gene artificial genetic network model, which was previously studied by other researchers. Also, a 10-gene and a 20-gene genetic network have been studied using the proposed technique. The obtained results suggest that quantum computing technique significantly reduces the computational time, retaining the accuracy of the inferred gene regulatory networks to a comparatively satisfactory level.