1.Convolutional Neural Network Technology in Endoscopic Imaging: Artificial Intelligence for Endoscopy
Joonmyeong CHOI ; Keewon SHIN ; Jinhoon JUNG ; Hyun-Jin BAE ; Do Hoon KIM ; Jeong-Sik BYEON ; Namku KIM
Clinical Endoscopy 2020;53(2):117-126
Recently, significant improvements have been made in artificial intelligence. The artificial neural network was introduced in the 1950s. However, because of the low computing power and insufficient datasets available at that time, artificial neural networks suffered from overfitting and vanishing gradient problems for training deep networks. This concept has become more promising owing to the enhanced big data processing capability, improvement in computing power with parallel processing units, and new algorithms for deep neural networks, which are becoming increasingly successful and attracting interest in many domains, including computer vision, speech recognition, and natural language processing. Recent studies in this technology augur well for medical and healthcare applications, especially in endoscopic imaging. This paper provides perspectives on the history, development, applications, and challenges of deep-learning technology.
2.Development of a Mycobacterial Gene Knock-out System using Sequence-specific Recombinase FLP/FRT and its Application to the Construction of a Rhamnose Biosynthetic Gene rmlD Deletion Mutant.
Kwang Chul LEE ; Jong Seok LEE ; Sang Ji LEE ; Kwan Ho LEE ; Tae Jin LEE ; Hyun Jung SHIN ; Ji Eun CHOI ; Ho Sun PARK ; Sung Kwang KIM ; Tae Yoon LEE
Journal of Bacteriology and Virology 2002;32(3):221-230
Development of a new and effecient tuberculosis vaccine is very important since the efficacy of the only available vaccine against tuberculosis, BCG, is variable among races and different ages. Attempts to develop attenuated vaccines by disrupting virulence gene(s) specifically in Mycobacterium tuberculosis are now actively being tried after the release of whole genome sequence of M. tuberculosis in 1998. However, disruption of specific genes in M. tuberculosis is still very difficult due to the lack of effective gene knock-out system(s) in mycobacteria. In this study, we developed a novel method to delete specific genes in both Escherichia coli and mycobacteria. This knock-out system is operated by a sequence-specific recombinase FLP and its recognition sequence FRT (FLP/FRT system). Two shuttle vectors (an FLP expressing vector and a gene targeting vector) between Escherichia coli and Mycobacteria were developed. The gene targeting vector contains a kanamycin resistance gene (KmR) flanked by two neighboring genes and two FRTs (FLPrecognition targets). We applied this system to knock-out the rhamnose biosynthetic gene rmlD of Escherichia coli. The upstream and downstream genes of rmlD, rmlB and rmlA, were cloned into the gene targeting vector. After and allelic exchange of E. coli chromosomal rmlB, rmlD, rmlA with vectoral rmlB, FRT-KmR-FRT, rmlA by homologous recombination, FLP-expressing plasmid was introduced to induce the excision of KmR cassette remaining one FRT sequence between rmlB and rmlA. We also demonstrated our shuttle vector could disrupt a target gene (kanamycin resistance gene) in M. smegmatis. These results suggest that our gene knock-out system can be used for the development of an attenuated tuberculosis vaccines and for the functional genomic study of mycobacteria.
Clone Cells
;
Continental Population Groups
;
Escherichia coli
;
Gene Targeting
;
Genes, vif
;
Genetic Vectors
;
Genome
;
Homologous Recombination
;
Humans
;
Kanamycin Resistance
;
Mycobacterium bovis
;
Mycobacterium tuberculosis
;
Plasmids
;
Recombinases*
;
Rhamnose*
;
Tuberculosis
;
Tuberculosis Vaccines
;
Vaccines, Attenuated
;
Virulence