• Proceedings of the Plant Resources Society of Korea Conference
• /
• 2018.04a
• /
• pp.5-5
• /
• 2018

Ginseng (Panax ginseng C.A. Meyer), one of the most widely used medicinal plants in traditional oriental medicine, is used for the treatment of various diseases. It has been classified according to its cultivation environment, such as field cultivated ginseng (FCG) and mountain cultivated ginseng (MCG). However, little is known about differences in gene expression in ginseng roots between field cultivated and mountain cultivated ginseng. In order to investigate the whole transcriptome landscape of ginseng, we employed High-Throughput sequencing technologies using the Illumina HiSeqTM2500 system, and generated a large amount of sequenced transcriptome from ginseng roots. Approximately 77 million and 87 million high-quality reads were produced in the FCG and MCG roots transcriptome analyses, respectively, and we obtained 256,032 assembled unigenes with an average length of 1,171 bp by de novo assembly methods. Functional annotations of the unigenes were performed using sequence similarity comparisons against the following databases: the non-redundant nucleotide database, the InterPro domains database, the Gene Ontology Consortium database, and the Kyoto Encyclopedia of Genes and Genomes pathway database. A total of 4,207 unigenes were assigned to specific metabolic pathways, and all of the known enzymes involved in starch and sucrose metabolism pathways were also identified in the KEGG library. This study indicated that alpha-glucan phosphorylase 1, putative pectinesterase/pectinesterase inhibitor 17, beta-amylase, and alpha-glucan phosphorylase isozyme H might be important factors involved in starch and sucrose metabolism between FCG and MCG in different environments.

• Journal of Information Processing Systems
• /
• v.13 no.2
• /
• pp.204-214
• /
• 2017

Artificial intelligence, especially deep learning technology, is penetrating the majority of research areas, including the field of bioinformatics. However, deep learning has some limitations, such as the complexity of parameter tuning, architecture design, and so forth. In this study, we analyze these issues and challenges in regards to its applications in bioinformatics, particularly genomic analysis and medical image analytics, and give the corresponding approaches and solutions. Although these solutions are mostly rule of thumb, they can effectively handle the issues connected to training learning machines. As such, we explore the tendency of deep learning technology by examining several directions, such as automation, scalability, individuality, mobility, integration, and intelligence warehousing.