ENG
SITE MAP
About Us
R&D
Contact
Online Contact Us
R&D
- Technology
- R&D Pipeline
- Service
R&D 
R&D Pipeline
SYSBIOGEN
R&D Pipeline
Prostate cancer early detection system
- About prostate cancer
- Prostate cancer (PCa) is a common cancer in men. There are no specific symptoms in the early stages, and symptoms are similar to those of other prostate diseases such as benign prostatic hyperplasia, requiring an accurate diagnosis. If detected early, the survival rate is close to 95%, but if detected late, the survival rate is less than 50%. The current method of diagnosing prostate cancer is to check the level of prostate-specific antigen (PSA) through a blood test, and to confirm the diagnosis through additional tissue biopsy.
- The need for a new diagnostic system
- If the PSA level is high, it is necessary to diagnose cancer early through periodic tissue biopsies, etc. However, the accuracy of the PSA test is not high, which causes more than 60% of normal people to undergo unnecessary tissue biopsies and the biopsies cause unnecessary economic losses and side effects (pain, bleeding, infection, etc.). Therefore, this leads to the need for a diagnostic system that can replace it. In addition, there is a need for a system that can easily and periodically test without pain to the patient using urine, etc.
- Technology Development Process
- After registering a patent (No. 10-2550113) for a system that can diagnose prostate cancer early based on machine learning, we are developing related products.
-
STEP. 1 Sample (urine)
collection -
STEP. 2 RNA extraction
and cDNA synthesis -
STEP. 3 Real-time
polymerase chain
reaction (qPCR) -
STEP. 4 Data analysis
-
STEP. 5 Sending prostate
cancer risk
assessment form
-
STEP. 1 Sample (urine)
collection -
STEP. 2 RNA extraction
and cDNA
synthesis -
STEP. 4 Data analysis
-
STEP. 3 Real-time
polymerase chain
reaction (qPCR) -
STEP. 5 Sending prostate
cancer risk
assessment form -
A system for detection of drug-resistant mutations in chronic myeloid leukemia
- About Chronic Myeloid Leukemia
- Chronic myeloid leukemia (CML) is mostly caused by the formation of the Philadelphia chromosome, a BCR-ABL1 fusion chromosome in which the ends of chromosomes 9 and 22 are swapped and fused. The abnormal tyrosine kinase activity of the BCR-ABL1 fusion protein causes cancer cell proliferation. Therefore, it is currently being treated with TKI (Tyrosine Kinase Inhibitor) series anticancer drugs.
- Need for Drug Treatment Monitoring
- CML patients are administered TKI series anticancer drugs, and the concentration of BCR-ABL1 fusion transcript in the body is monitored to confirm the anticancer effect. In addition, it is necessary to monitor the occurrence of mutations showing resistance to anticancer drugs. If mutations showing resistance to existing anticancer drugs are confirmed, they should be replaced with new anticancer drugs. It is also very important to check whether there is minimal residual disease (MRD), which requires a technology that can detect very low concentrations of transcripts and mutations during the treatment of CML.
-
Failure to monitor minimal residual disease -
Monitored minimal residual disease
- Technology Development Process
- Currently, SYSBIOGEN is developing a product that can detect the occurrence of anticancer drug-resistant mutations among BCR-ABL1 fusion transcripts in blood with high sensitivity and specificity even at very low concentrations using BDA technology.
Research and development of radiogenomics, a convergence of artificial intelligence (AI) + genomic data + mammography
- SYSBIOGEN is developing a groundbreaking diagnostic service for individual cancer diagnosis through a radiogenomics system that analyzes mammography image data obtained from patients suspected of having breast cancer at hospitals/clinics using AI and additionally combines it with next-generation genetic sequencing (NGS) data from patient samples.
- Special Features of Radiogenomics
- By combining medical image data (radiomics) and genetic data (genomics), we analyze the correlation between the patient's genetic characteristics and image data. This allows us to determine whether specific genetic abnormalities are related to the formation of specific lesions.
- The big data analysis and machine learning technique interpret complex data interactions, improving diagnostic technology and increasing the accuracy of diagnosis even when medical image interpretation is difficult.
- It can be used to develop personalized treatment strategies.
Medical image data obtained to be used for interpretation decisions
Patient's clinical data
-
Tissue characterization
Genetic expression
Genetic variation
Epigenetic analysis
Exome characterization
Noncoding genome
-
Radiomics
MRI
CT
PET
-
Clinical data
-
Genomics
IHC
Microarray
DNA sequencing
NGS
Radiogenomics
Analysis of associations between image data
and genetic profile
Function selection
Integrated data analysis
(Correlation analysis, regression model,
LASSO regularization, cluster analysis)
Data normalization
Data interpretation
-
Application of radiomics technologyPatient-tailored treatment plans
Analyzing genetic characteristics
Personalized treatment based on correlation with analyzed genetic characteristics
-
Overcoming existing limitations
of personalized treatmentRisk stratification
Early diagnosis
Treatment selection
Treatment response
Accurate prediction