Computer methods for visualization chromosome-specific DNA sequences in FISH images

Poster (download) Video (download) Bogomolov A.G.1, Karamysheva T.V.2, Rubtsov N.B.31Institute of Cytology and Genetics SB RAS, Novosibirsk, Russia; Novosibirsk State University Novosibirsk, Russia, mantis_anton@bionet.nsc.ru2Institute of Cytology and Genetics SB RAS, Novosibirsk, Russia, kary@bionet.nsc.ru3Institute of Cytology and Genetics SB RAS, Novosibirsk, Russia; Novosibirsk State University Novosibirsk, Russia, rubt@bionet.nsc.ru A great number of interspersed repetitive sequences in chromosomes make it difficult to identify chromosomal material via fluorescence in situ hybridization (FISH). The traditional approach to solve this problem is chromosome in situ suppression hybridization (CISS- hybridization). Unfortunately, it is impossible to be performed or fails with chromosomes of many eukaryote species. The aim of this study was to consider the image enhance procedure [1] and the in silico method of chromosome specific signal visualization (method VISSIS) [2] as alternatives to CISS-hybridization. The effectiveness of approaches for identification of specific signals was estimated by signal-to-background ratio (SNR). The computer methods were applied to images of human chromosomes, obtained with FISH of the whole chromosome painting DNA probes. Results showed that effectiveness of image processing methods depends on ratio of short and line interspersed elements (SINEs/LINEs) in DNA probes. The closer chromosomes in ratio of SINEs/LINEs, the higher specific signal intensities and signal-to-background ratios could be achieved. This suggests that computer methods can be efficient only with application of DNA probes derived from chromosomes characterized with similar ratio of SINE and LINE contents.

Read More

Application of neural networks to image recognition of wheat rust diseases

Poster (download) Mikhail Genaev11Mikhail Genaev ICG SB RAS, Kurchatov Genomic Center, Novosibirsk, Russia NSU, Novosibirsk, Russia, mag@bionet.nsc.ru Rust diseases of cereals are caused by pathogenic fungi and can significantly reduce plant productivity. Many cultures are subject to them. The disease is difficult to control on a large scale, so one of the most relevant approaches is crop monitoring, which helps to identify the disease at an early stage and make efforts to prevent its spread. One of the most effective methods of control is the identification of the disease from digital images that obtained by a smartphone camera. In this paper, we present a deep learning algorithm that uses a digital image of wheat plants to determine whether they are affected by a disease and, if so, what type: leaf rust or stem rust. The algorithm based on the convolution neural network of the densenet architecture. The resulting model demonstrates high accuracy of classification: the measure of accuracy F1 on the validation sample is 0.9, the AUC averaged over 3 classes is 0.98.

Read More