Pan-chloroplast genomes for accession-specific marker development in Hibiscus syriacus.

Hibiscus syriacus L. is a renowned ornamental plant. We constructed 95 chloroplast genomes of H. syriacus L. cultivars using a short-read sequencing platform (Illumina) and a long-read sequencing platform (Oxford Nanopore Technology). The following genome assembly, we delineate quadripartite structures encompassing large single-copy, small single-copy, and inverted repeat (IRa and IRb) regions, from 160,231 bp to 161,041 bp. Our comprehensive analyses confirmed the presence of 79 protein-coding genes, 30 tRNA genes, and 4 rRNA genes in the pan-chloroplast genome, consistent with prior research on the H. syriacus chloroplast genome. Subsequent pangenome analysis unveiled widespread genome sequence conservation alongside unique cultivar-specific variant patterns consisting of 193 single-nucleotide polymorphisms and 61 insertions or deletions. The region containing intra-species variant patterns, as identified in this study, has the potential to develop accession-specific molecular markers, enhancing precision in cultivar classification. These findings are anticipated to drive advancements in breeding strategies, augment biodiversity, and unlock the agricultural potential inherent in H. syriacus.

Two long read-based genome assembly and annotation of polyploidy woody plants, Hibiscus syriacus L. using PacBio and Nanopore platforms.

Improvements in long read DNA sequencing and related techniques facilitated the generation of complex eukaryotic genomes. Despite these advances, the quality of constructed plant reference genomes remains relatively poor due to the large size of genomes, high content of repetitive sequences, and wide variety of ploidy. Here, we developed the de novo sequencing and assembly of high polyploid plant genome, Hibiscus syriacus, a flowering plant species of the Malvaceae family, using the Oxford Nanopore Technologies and Pacific Biosciences Sequel sequencing platforms. We investigated an efficient combination of high-quality and high-molecular-weight DNA isolation procedure and suitable assembler to achieve optimal results using long read sequencing data. We found that abundant ultra-long reads allow for large and complex polyploid plant genome assemblies with great recovery of repetitive sequences and error correction even at relatively low depth Nanopore sequencing data and polishing compared to previous studies. Collectively, our combination provides cost effective methods to improve genome continuity and quality compared to the previously reported reference genome by accessing highly repetitive regions. The application of this combination may enable genetic research and breeding of polyploid crops, thus leading to improvements in crop production.

Construction of deep learning-based disease detection model in plants.

Accurately detecting disease occurrences of crops in early stage is essential for quality and yield of crops through the decision of an appropriate treatments. However, detection of disease needs specialized knowledge and long-term experiences in plant pathology. Thus, an automated system for disease detecting in crops will play an important role in agriculture by constructing early detection system of disease. To develop this system, construction of a stepwise disease detection model using images of diseased-healthy plant pairs and a CNN algorithm consisting of five pre-trained models. The disease detection model consists of three step classification models, crop classification, disease detection, and disease classification. The 'unknown' is added into categories to generalize the model for wide application. In the validation test, the disease detection model classified crops and disease types with high accuracy (97.09%). The low accuracy of non-model crops was improved by adding these crops to the training dataset implicating expendability of the model. Our model has the potential to apply to smart farming of Solanaceae crops and will be widely used by adding more various crops as training dataset.

Deep Learning Algorithms Correctly Classify Brassica rapa Varieties Using Digital Images.

Efficient and accurate methods of analysis are needed for the huge amount of biological data that have accumulated in various research fields, including genomics, phenomics, and genetics. Artificial intelligence (AI)-based analysis is one promising method to manipulate biological data. To this end, various algorithms have been developed and applied in fields such as disease diagnosis, species classification, and object prediction. In the field of phenomics, classification of accessions and variants is important for basic science and industrial applications. To construct AI-based classification models, three types of phenotypic image data were generated from 156 Brassica rapa core collections, and classification analyses were carried out using four different convolutional neural network architectures. The results of lateral view data showed higher accuracy compared with top view data. Furthermore, the relatively low accuracy of ResNet50 architecture suggested that definition and estimation of similarity index of phenotypic data were required before the selection of deep learning architectures.