Osteoarthritis improvement effect of Chrysanthemum zawadskii var. latilobum extract in relation to genotype.

Objectives: To determine whether SNPs of osteoarthritis (OA)-related genes predict the effect of Chrysanthemum zawadskii var. latilobum (CZ) extract in OA patients with OA. Subjects/methods: To analyze correlations between CZ extract effects in humans and their genotypes, 121 Korean patients with OA were recruited. Patients ingested 600 mg/day of the CZ extract GCWB106 (one tablet daily), including 250-mg CZ, or placebo (one tablet daily) for 12 weeks. Twenty SNPs were genotyped in 11 genes associated with OA pathogenesis, including tumor necrosis factor-alpha (TNF-α) and matrix metalloproteinases (MMPs), and 9 genes involved in OA-related dietary intervention. The Visual Analogue Scale (VAS) and Korean Western Ontario and McMaster Universities (K-WOMAC) were measured as indicators of GCWB106 effect. Statistical comparisons were performed using Kruskal-Wallis tests to identify associations between these scales and genotyped loci in patients with OA. Results: Three SNPs (PPARG rs3856806, MMP13 rs2252070, and ZIP2 rs2234632) were significantly associated with the degree of change in VAS pain score. Homozygous CC genotype carriers of rs3856806, G allele carriers (GA or GG) of rs2252070, and T allele carriers (GT or TT) of rs2234632 showed lower VAS score (i.e., less severe symptoms) in the GCWB106 group (n=53) than the placebo group (n=57) (p=0.026, p=0.009, and p=0.025, respectively). Gene-gene interaction effects on GCWB106-mediated pain relief were then examined, and it was found that the addition of each genotype resulted in a greater decrease in VAS pain score in the GCWB106 group (p=0.0024) but not the placebo group (p=0.7734). Conclusions: These novel predictive markers for the pain-relieving effects of GCWB106 may be used in the personalized treatment of patients with OA.

Genome-wide copy number alteration and VEGFA amplification of circulating cell-free DNA as a biomarker in advanced hepatocellular carcinoma patients treated with Sorafenib.

BACKGROUND: Although sorafenib is the global standard first-line systemic treatment for unresectable hepatocellular carcinoma (HCC), it does not have reliable predictive or prognostic biomarkers. Circulating cell-free DNA (cfDNA) has shown promise as a biomarker for various cancers. We investigated the use of cfDNA to predict clinical outcomes in HCC patients treated with sorafenib. METHODS: This prospective biomarker study analyzed plasma cfDNA from 151 HCC patients who received first-line sorafenib and 14 healthy controls. The concentration and VEGFA-to-EIF2C1 ratios (the VEGFA ratio) of cfDNA were measured. Low depth whole-genome sequencing of cfDNA was used to identify genome-wide copy number alteration (CNA), and the I-score was developed to express genomic instability. The I-score was defined as the sum of absolute Z-scores of sequenced reads on each chromosome. The primary aim of this study was to develop cfDNA biomarkers predicting treatment outcomes of sorafenib, and the primary study outcome was the association between biomarkers with treatment efficacy including disease control rate (DCR), time to progression (TTP) and overall survival (OS) in these patients. RESULTS: The cfDNA concentrations were significantly higher in HCC patients than in healthy controls (0.71 vs. 0.34 ng/µL; P < 0.0001). Patients who did not achieve disease control with sorafenib had significantly higher cfDNA levels (0.82 vs. 0.63 ng/µL; P = 0.006) and I-scores (3405 vs. 1024; P = 0.0017) than those achieving disease control. The cfDNA-high group had significantly worse TTP (2.2 vs. 4.1 months; HR = 1.71; P = 0.002) and OS (4.1 vs. 14.8 months; HR = 3.50; P < 0.0001) than the cfDNA-low group. The I-score-high group had poorer TTP (2.2 vs. 4.1 months; HR = 2.09; P < 0.0001) and OS (4.6 vs. 14.8 months; HR = 3.35; P < 0.0001). In the multivariable analyses, the cfDNA remained an independent prognostic factor for OS (P < 0.0001), and the I-score for both TTP (P = 0.011) and OS (P = 0.010). The VEGFA ratio was not significantly associated with treatment outcomes. CONCLUSION: Pretreatment cfDNA concentration and genome-wide CNA in cfDNA are potential biomarkers predicting outcomes in advanced HCC patients receiving first-line sorafenib.

Clinically significant maternal X chromosomal copy number variation detected by noninvasive prenatal test.

Maternal copy number variation (CNV), especially at the X chromosome is an important cause of false positive noninvasive prenatal test (NIPT) results for sex chromosomal aneuploidy. In addition, some maternal CNV can cause significant anomalies if the male fetus was inherited the X chromosome with CNV. During 1000 high risk Korean NIPT, we incidentally detected two cases of maternal X chromosomal CNV which can cause abnormal phenotype in a male fetus. The first false-positive NIPT case (47, XXY) was due to a maternal 0.5 Mb duplication at Xq28, including the MECP2 gene. The second is a case of an 8-Mb deletion on maternal Xq24q25, including GRIA3 and XIAP genes.

Exposure amount and timing of solar irradiation during pregnancy and the risk of sensitization in children.

BACKGROUND: Solar irradiation affects sensitization to aeroallergens and the prevalence of allergic diseases. Little is known, however, about how the time and amount of solar irradiation during pregnancy affects such risks in children. We aimed to find out how solar irradiation during pregnancy affects sensitization to aero-allergens and the prevalence of allergic diseases in children. METHODS: This population-based cross-sectional study involved 7301 aged 6 years and aged 12 years children. Maternal exposure to solar irradiation during pregnancy was evaluated using data from weather stations closest to each child's birthplace. Monthly average solar irradiation during the second and third trimesters was calculated with rank by quartiles. Risks of allergic sensitization and allergic disease were estimated. RESULTS: Relative to the first (lowest) quartile, the adjusted odds ratio (aOR) for allergic sensitization in the fourth (highest) quartile was lowest within solar irradiation during pregnancy months 5-6 (aOR = 0.823, 95% CI 0.720-0.942, p < 0.05). During months 9-10, the aOR for allergic sensitization for the fourth was higher than the first quartile of solar irradiation (aOR = 1.167, 95% CI 1.022-1.333, p < 0.05). Similar results were observed when solar irradiation was analyzed as a continuous variable during months 5 (aOR = 0.975, 95% CI 0.962-0.989, p < 0.001) and month 9 (aOR = 1.018, 95% CI 1.004-1.031, p = 0.003). Increased solar irradiation during months 7-8 increased the risk of asthma (aOR = 1.309, 95% CI 1.024-1.674, p = 0.032). CONCLUSIONS: Maternal exposure to solar irradiation during the second trimester of pregnancy associated with reduced aeroallergen sensitization, whereas solar irradiation during the third trimester was related to increased sensitization to aeroallergens.

Carrier frequency of Wilson's disease in the Korean population: a DNA-based approach.

Wilson's disease (WD) is an autosomal recessive disorder caused by ATP7B gene mutation. The frequency of WD is about 1 in 30 000 worldwide. In the present study, we screened 14 835 dried blood spots (DBSs) from asymptomatic Korean neonates and retrospectively reviewed massively parallel sequencing of 1090 control individuals to estimate carrier frequency. TaqMan real-time PCR assays were conducted to detect six mutations that account for 58.3% of mutations in Korean WD patients: c.2333G>T (p.Arg778Leu), c.2621C>T (p.Ala874Val), c.3086C>T (p.Thr1029Ile), c.3247C>T (p.Leu1083Phe), c.3556G>A (p.Gly1186Ser) and c.3809A>G (p.Asn1270Ser). We also retrospectively reviewed data from 1090 individuals with various indications other than WD for whom whole-exome or panel sequencing data were available. Mutant allele frequency based on the six most common mutations was 0.0067 among the total of 14 835 DBSs screened. Given that these six mutations account for 58.3% of mutations in Korean WD patients, the corrected mutant allele frequency is 0.0115 (95% confidence interval (CI): 0.0103-0.0128). Corresponding incidence (q2) and carrier frequency (2pq) were estimated to be 1:7561 and 1:44, respectively. In retrospective data analysis of 1090 control individuals, allele frequency of pathogenic or likely pathogenic variants was 0.0096 (95% CI: 0.0063-0.0146). Corresponding carrier frequency was estimated to be 1:53. Estimated allele and carrier frequencies based on DNA screening were relatively higher than those reported previously based on clinical ascertainment.

Familial aplasia cutis congenita associated with mega-cisterna magna.

Aplasia cutis congenita (ACC; MIM 107600) is a congenital skin disorder that manifests as localized absence of skin. Here we report a case of familial ACC and mega-cisterna magna. A female neonate was born with skin defects on the scalp. Brain magnetic resonance imaging demonstrated retrocerebellar space widening suggesting mega-cisterna magna. Her father also had a skin defect on the scalp at birth, and brain computed tomography of the father showed a cystic lesion over the right occipital lobe, similar to the patient's brain imaging. Karyotype 46,XX, t(6;18)(q23.2;q11.2) was identified on G-banded karyotype analysis of the patient and her father, after which whole exome sequencing was carried out, but this was thought to be a coincidental finding. This indicates that ACC may be associated with brain anomaly, although it is very rare.

Effect of solar irradiation on serum specific immunoglobulin E to house-dust mite.

BACKGROUND: The relationship between sensitization to Dermatophagoides species and solar irradiation, as reflected by vitamin D, remains elusive. OBJECTIVE: We investigated the lag time and the cumulative and maximum effects of exposure to solar irradiation on sensitization to house-dust mites. METHODS: A time series study design was applied to solar irradiation (MJ/m(2)) and relative humidity (%) for specific immunoglobulin E (IgE) levels against Dermatophagoides pteronyssinus (n = 20,451) and Dermatophagoides farinae (n = 22,824). We used the distributed lag nonlinear model to assess the difference of log IgE to house-dust mites in relation to climate variables. RESULTS: Compared with specific IgE levels of those exposed to 18 MJ/m(2), the maximum increase in sensitization to D. pteronyssinus was observed at a solar irradiation of 10 MJ/m(2) at peak 0 week (difference of log IgE 0.368 [95% confidence interval (CI), 0.209-0.529], p < 0.001), and this increase continued for 3 weeks. The IgE level was significantly affected by the relative humidity of the 3rd- to 12th-lag week, and the effect reached its peak at 75% on the 8th week (difference of log IgE 0.394 [95% CI, 0.221-0.566], p < 0.001). The logistic regression analysis showed that solar irradiation was associated with a decreased risk to sensitization to D. pteronyssinus (odds ratio 0.988 per 1 MJ/m(2) [95% CI, 0.979-0.997], p < 0.013) on the testing week after controlling for humidity and temperature. CONCLUSION: This study demonstrated that low solar irradiation immediately increased the risk of sensitization to two house-dust mite species. Further research is warranted to delineate the underlying mechanism of the effect of solar irradiation on aeroallergen sensitization.

The first Korean patient with Potocki-Shaffer syndrome: a rare cause of multiple exostoses.

Potocki-Shaffer syndrome (PSS, OMIM #601224) is a rare contiguous gene deletion syndrome caused by haploinsufficiency of genes located on the 11p11.2p12. Affected individuals have a number of characteristic features including multiple exostoses, biparietal foramina, abnormalities of genitourinary system, hypotonia, developmental delay, and intellectual disability. We report here on the first Korean case of an 8-yr-old boy with PSS diagnosed by high resolution microarray. Initial evaluation was done at age 6 months because of a history of developmental delay, hypotonia, and dysmorphic face. Coronal craniosynostosis and enlarged parietal foramina were found on skull radiographs. At age 6 yr, he had severe global developmental delay. Multiple exostoses of long bones were detected during a radiological check-up. Based on the clinical and radiological features, PSS was highly suspected. Subsequently, chromosomal microarray analysis identified an 8.6 Mb deletion at 11p11.2 [arr 11p12p11.2 (Chr11:39,204,770-47,791,278)×1]. The patient continued rehabilitation therapy for profound developmental delay. The progression of multiple exostosis has being monitored. This case confirms and extends data on the genetic basis of PSS. In clinical and radiologic aspect, a patient with multiple exostoses accompanying with syndromic features, including craniofacial abnormalities and mental retardation, the diagnosis of PSS should be considered.

Deep learning model integrating cfDNA methylation and fragment size profiles for lung cancer diagnosis.

Detecting aberrant cell-free DNA (cfDNA) methylation is a promising strategy for lung cancer diagnosis. In this study, our aim is to identify methylation markers to distinguish patients with lung cancer from healthy individuals. Additionally, we sought to develop a deep learning model incorporating cfDNA methylation and fragment size profiles. To achieve this, we utilized methylation data collected from The Cancer Genome Atlas and Gene Expression Omnibus databases. Then we generated methylated DNA immunoprecipitation sequencing and genome-wide Enzymatic Methyl-seq (EM-seq) form lung cancer tissue and plasma. Using these data, we selected 366 methylation markers. A targeted EM-seq panel was designed using the selected markers, and 142 lung cancer and 56 healthy samples were produced with the panel. Additionally, cfDNA samples from healthy individuals and lung cancer patients were diluted to evaluate sensitivity. Its lung cancer detection performance reached an accuracy of 81.5% and an area under the receiver operating characteristic curve of 0.87. In the serial dilution experiment, we achieved tumor fraction detection of 1% at 98% specificity and 0.1% at 80% specificity. In conclusion, we successfully developed and validated a combination of methylation panel and a deep learning model that can distinguish between patients with lung cancer and healthy individuals.

Plasma Circulating Cell-free DNA in Advanced Hepatocellular Carcinoma Patients Treated With Radiation Therapy.

BACKGROUND/AIM: Although radiation therapy (RT) is an effective and safe treatment when administered locally for various stages of hepatocellular carcinoma (HCC), adequate biomarkers that are predictive of therapeutic efficacy have not been identified. We evaluated the clinical utility of circulating cell-free DNA (cfDNA) to predict treatment response of patients with HCC treated with RT. PATIENTS AND METHODS: We prospectively recruited 37 patients diagnosed with HCC between March 2019 and May 2020. All patients were treated with RT as salvage therapy. Whole peripheral blood was collected twice, one before RT (baseline; V1) and another aliquot one week after the end of RT (V2). We determined whether cfDNA genomic copy number variations (CNVs) could predict treatment outcome. An I-score was calculated from the plasma cfDNA that reflected CNVs of cfDNA, which is evidence of genomic instability. RESULTS: The I-score at V1 exhibited a strong correlation with the planning target volume (PTV) (coefficient=0.65) and was a predictive marker for progression-free survival (PFS). In particular, a mean I-score value at V1 of ≥6.3 had a significant positive correlation with PFS (p=0.017). Compared with patients who had a complete response (CR) following RT, non-CR patients had a higher mean I-score value at V2 ≥6.2 (p=0.034). Furthermore, I-score values at V1 and V2 and the delta I-score ratio were significantly associated with a pre-RT alpha-fetoprotein level ≥200 among non-CR patients. CONCLUSION: I-score values calculated from plasma cfDNA represent a potential biomarker for predicting treatment outcomes in patients with advanced HCC receiving RT.

Narcolepsy is associated with an increased risk of HLA-related autoimmune diseases: Evidence from a nationwide healthcare system data in South Korea.

STUDY OBJECTIVES: To determine the incidence rate of narcolepsy in South Korea and closely examine the relationship between narcolepsy, which is believed to be an autoimmune response, and other systemic autoimmune diseases. METHODS: We examined data from the South Korean nationwide health insurance claims database from 2010 to 2019. Our study included patients with narcolepsy as well as age- and sex-matched controls without narcolepsy. We estimated the incidence of narcolepsy and the odds ratio of narcolepsy and associated autoimmune comorbidities in South Korea. RESULTS: We identified 8710 patients with narcolepsy (59.8% men and 40.2% women). The incidence of narcolepsy was 0.05%. Patients with narcolepsy were at a significantly high risk of ankylosing spondylitis, rheumatoid arthritis, and Sjögren's syndrome, which diseases are known to be related to human leukocyte antigen (HLA) genes. CONCLUSIONS: Narcolepsy is closely related to systemic autoimmune diseases, particularly those related to HLA genes.

Liquid biopsy using cfDNA to predict radiation therapy response in solid tumors.

PURPOSE: This study explored the potential feasibility of cell-free DNA (cfDNA) in monitoring treatment response through the measurement of chromosomal instabilities using I-scores in the context of radiation therapy (RT) for other solid tumors. MATERIALS AND METHODS: This study enrolled 23 patients treated with RT for lung, esophageal, and head and neck cancer. Serial cfDNA monitoring was performed before RT, 1 week after RT, and 1 month after RT. Low-depth whole-genome sequencing was done using Nano kit and NextSeq 500 (Illumina Inc.). To measure the extent of genome-wide copy number instability, I-score was calculated. RESULTS: Pretreatment I-score was elevated to more than 5.09 in 17 patients (73.9%). There was a significant positive correlation between the gross tumor volume and the baseline I-score (Spearman rho = 0.419, p = 0.047). The median I-scores at baseline, post-RT 1 week (P1W), and post-RT 1 month (P1M) were 5.27, 5.13, and 4.79, respectively. The I-score at P1M was significantly lower than that at baseline (p = 0.002), while the difference between baseline and P1W was not significant (p = 0.244). CONCLUSION: We have shown the feasibility of cfDNA I-score to detect minimal residual disease after RT in patients with lung cancer, esophageal cancer, and head and neck cancer. Additional studies are ongoing to optimize the measurement and analysis of I-scores to predict the radiation response in cancer patients.

Chromosomal Instability in Cell-free DNA as a Prognostic Biomarker of Metastatic Hormone-sensitive Prostate Cancer Treated with Androgen Deprivation Therapy.

BACKGROUND: Although patients with metastatic hormone-sensitive prostate cancer (mHSPC) undergo androgen deprivation therapy (ADT), the disease can progress to metastatic castration-resistant prostate cancer (mCRPC). There are no reliable biomarkers for predicting this progression. Chromosomal instability resulting in copy number alterations (CNAs) is characteristically observed in patients with various cancers. OBJECTIVE: To investigate the role of chromosomal instability in patients with mHSPC. DESIGN, SETTING, AND PARTICIPANTS: This prospective study analyzed cell-free DNA (cfDNA) in pretreatment plasma samples from 75 patients with elevated prostate-specific antigen. Low-depth whole-genome sequencing of cfDNA was performed to identify CNAs. OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The I score (sum of the product of the absolute Z score and the corresponding chromosome length) was used as a measure of chromosomal instability. Kaplan-Meier and Cox proportional-hazard regression analyses were performed to evaluate the association between the I score and time to progression (TTP) and the prognostic value of chromosomal instability in predicting castration resistance, respectively. RESULTS AND LIMITATIONS: Of 22 patients with a positive I score, 86.4% (19/22) had metastatic prostate cancer. Of these 19 cases, 94.7% (18/19) were mHSPC, which was high-volume mHSPC in 83.3% (15/18). None of the patients with localized prostate cancer had a positive I score. TTP in patients with mHSPC was significantly shorter in the positive than in the negative I-score group (16.4 vs 36.9 mo; p = 0.001). Only the I score could independently predict mCRPC development (hazard ratio 10.315, 95% confidence interval 1.141-93.208; p = 0.038). CONCLUSIONS: The I score could be a biomarker for ADT response and progression to mCRPC in patients with mHSPC. PATIENT SUMMARY: We investigated whether genetic changes in cell-free DNA can predict outcomes for patients with metastatic prostate cancer that still responds to hormone therapy. We found that chromosomal instability could be a potential predictor of the development of metastatic castration-resistant prostate cancer.

Shallow Whole-Genome Sequencing of Cell-Free DNA (cfDNA) Detects Epithelial Ovarian Cancer and Predicts Patient Prognosis.

Despite the progress in diagnostics and therapeutics, epithelial ovarian cancer (EOC) remains a fatal disease. Using shallow whole-genome sequencing of plasma cell-free DNA (cfDNA), we investigated biomarkers that could detect EOC and predict survival. Plasma cfDNA from 40 EOC patients and 20 healthy subjects were analyzed by shallow whole-genome sequencing (WGS) to identify copy number variations (CNVs) and determine the Z-scores of genes. In addition, we also calculated the genome-wide scores (Gi scores) to quantify chromosomal instability. We found that the Gi scores could distinguish EOC patients from healthy subjects and identify various EOC histological subtypes (e.g., high-grade serous carcinoma). In addition, we characterized EOC CNVs and demonstrated a relationship between RAB25 amplification (alone or with CA125), and disease-free survival and overall survival. This study identified RAB25 amplification as a predictor of EOC patient survival. Moreover, we showed that Gi scores could detect EOC. These data demonstrated that cfDNA, detected by shallow WGS, represented a potential tool for diagnosing EOC and predicting its prognosis.

Prevalence and Risk Factors of Germline Pathogenic Variants in Pancreatic Ductal Adenocarcinoma.

PURPOSE: The genetic attribution for pancreatic ductal adenocarcinoma (PDAC) has been reported as 5%-10%. However, the incidence of germline pathogenic variants (PVs) in Korean PDAC patients has not been thoroughly investigated. Therefore, we studied to identify the risk factors and prevalence of PV for future treatment strategies in PDAC. MATERIALS AND METHODS: Total of 300 (155 male) patients with a median age of 65 years (range, 33 to 90 years) were enrolled in National Cancer Center in Korea. Cancer predisposition genes, clinicopathologic characteristics, and family history of cancer were analyzed. RESULTS: PVs were detected in 20 patients (6.7%, median age 65) in ATM (n=7, 31.8%), BRCA1 (n=3, 13.6%), BRCA2 (n=3), and RAD51D (n=3). Each one patient showed TP53, PALB2, PMS2, RAD50, MSH3, and SPINK1 PV. Among them, two likely PVs were in ATM and RAD51D, respectively. Family history of various types of cancer including pancreatic cancer (n=4) were found in 12 patients. Three patients with ATM PVs and a patient with three germline PVs (BRCA2, MSH3, and RAD51D) had first-degree relatives with pancreatic cancer. Familial pancreatic cancer history and PVs detection had a significant association (4/20, 20% vs. 16/264, 5.7%; p=0.035). CONCLUSION: Our study demonstrated that germline PVs in ATM, BRCA1, BRCA2, and RAD51D are most frequent in Korean PDAC patients and it is comparable to those of different ethnic groups. Although this study did not show guidelines for germline predisposition gene testing in patients with PDAC in Korea, it would be emphasized the need for germline testing for all PDAC patients.

Integrative modeling of tumor genomes and epigenomes for enhanced cancer diagnosis by cell-free DNA.

Multi-cancer early detection remains a key challenge in cell-free DNA (cfDNA)-based liquid biopsy. Here, we perform cfDNA whole-genome sequencing to generate two test datasets covering 2125 patient samples of 9 cancer types and 1241 normal control samples, and also a reference dataset for background variant filtering based on 20,529 low-depth healthy samples. An external cfDNA dataset consisting of 208 cancer and 214 normal control samples is used for additional evaluation. Accuracy for cancer detection and tissue-of-origin localization is achieved using our algorithm, which incorporates cancer type-specific profiles of mutation distribution and chromatin organization in tumor tissues as model references. Our integrative model detects early-stage cancers, including those of pancreatic origin, with high sensitivity that is comparable to that of late-stage detection. Model interpretation reveals the contribution of cancer type-specific genomic and epigenomic features. Our methodologies may lay the groundwork for accurate cfDNA-based cancer diagnosis, especially at early stages.

A case of 9.7 Mb terminal Xp deletion including OA1 locus associated with contiguous gene syndrome.

Terminal or interstitial deletions of Xp (Xp22.2→Xpter) in males have been recognized as a cause of contiguous gene syndromes showing variable association of apparently unrelated clinical manifestations such as Leri-Weill dyschondrosteosis (SHOX), chondrodysplasia punctata (CDPX1), mental retardation (NLGN4), ichthyosis (STS), Kallmann syndrome (KAL1), and ocular albinism (GPR143). Here we present a case of a 13.5 yr old boy and sister with a same terminal deletion of Xp22.2 resulting in the absence of genes from the telomere of Xp to GPR143 of Xp22. The boy manifested the findings of all of the disorders mentioned above. We began a testosterone enanthate monthly replacement therapy. His sister, 11 yr old, manifested only Leri-Weill dyschondrosteosis, and had engaged in growth hormone therapy for 3 yr. To the best of our knowledge, this is the first report of a male with a 9.7 Mb terminal Xp deletion including the OA1 locus in Korea.

Early detection of norovirus outbreak using machine learning methods in South Korea.

BACKGROUND: The norovirus is a major cause of acute gastroenteritis at all ages but particularly has a high chance of affecting children under the age of five. Given that the outbreak of norovirus in Korea is seasonal, it is important to try and predict the start and end of norovirus outbreaks. METHODS: We predicted weekly norovirus warnings using six machine learning algorithms using test data from 2017 to 2018 and training data from 2009 to 2016. In addition, we proposed a novel method for the early detection of norovirus using a calculated norovirus risk index. Further, feature importance was calculated to evaluate the contribution of the estimated weekly norovirus warnings. RESULTS: The long short-term memory machine learning (LSTM) algorithm proved to be the best algorithm for predicting weekly norovirus warnings, with 97.2% and 92.5% accuracy in the training and test data, respectively. The LSTM algorithm predicted the observed start and end weeks of the early detection of norovirus within a 3-week range. CONCLUSIONS: The results of this study show that early detection can provide important insights for the preparation and control of norovirus outbreaks by the government. Our method provides indicators of high-risk weeks. In particular, last norovirus detection rate, minimum temperature, and day length, play critical roles in estimating weekly norovirus warnings.

Development and performance evaluation of an artificial intelligence algorithm using cell-free DNA fragment distance for non-invasive prenatal testing (aiD-NIPT).

With advances in next-generation sequencing technology, non-invasive prenatal testing (NIPT) has been widely implemented to detect fetal aneuploidies, including trisomy 21, 18, and 13 (T21, T18, and T13). Most NIPT methods use cell-free DNA (cfDNA) fragment count (FC) in maternal blood. In this study, we developed a novel NIPT method using cfDNA fragment distance (FD) and convolutional neural network-based artificial intelligence algorithm (aiD-NIPT). Four types of aiD-NIPT algorithm (mean, median, interquartile range, and its ensemble) were developed using 2,215 samples. In an analysis of 17,678 clinical samples, all algorithms showed >99.40% accuracy for T21/T18/T13, and the ensemble algorithm showed the best performance (sensitivity: 99.07%, positive predictive value (PPV): 88.43%); the FC-based conventional Z-score and normalized chromosomal value showed 98.15% sensitivity, with 40.77% and 36.81% PPV, respectively. In conclusion, FD-based aiD-NIPT was successfully developed, and it showed better performance than FC-based NIPT methods.

Aberrant Transcript Usage Is Associated with Homologous Recombination Deficiency and Predicts Therapeutic Response.

BRCA1/2 mutations account for only a small fraction of homologous recombination (HR) deficiency (HRD) cases. Recently developed genomic HRD (gHRD) tests suffer confounding factors that cause low precision in predicting samples that will respond to PARP inhibitors and DNA damaging agents. Here we present molecular and clinical evidence of transcriptional HRD (tHRD) that is based on aberrant transcript usage (aTU) of minor isoforms. Specifically, increased TU of nonfunctional isoforms of DNA repair genes was prevalent in breast and ovarian cancer with gHRD. Functional assays validated the association of aTU with impaired HR activity. Machine learning-based tHRD detection by the transcript usage (TU) pattern of key genes was superior to directly screening for gHRD or BRCA1/2 mutations in accurately predicting responses of cell lines and patients with cancer to PARP inhibitors and genotoxic drugs. This approach demonstrated the capability of tHRD status to reflect functional HR status, including in a cohort of olaparib-treated ovarian cancer with acquired platinum resistance. Diagnostic tests based on tHRD are expected to broaden the clinical utility of PARP inhibitors. SIGNIFICANCE: A novel but widespread transcriptional mechanism by which homologous recombination deficiency arises independently of BRCA1/2 mutations can be utilized as a companion diagnostic for PARP inhibitors.