Polygenic Risk Score

Gastric Cancer

Gastric Cancer is one of the most predominant types of cancer in the world, and its genomic links are currently being studied at great depth. In this study, we work towards using Genomic Wide Association Studies (GWAS) data for identifying the Single Nucleotide Polymorphisms (SNPs) which have the strongest correlation with the occurrence of gastric cancer through statistical tests and to leverage them to build a predictive machine learning model. Polygenic Scores are used to express the relative risk in comparison to people with a different genetic composition. They are calculated by summing risk alleles, which are weighted by effect sizes derived from GWAS results.
Sample data - GSE58356
Polygenic Risk Score


Expression data (GSE30589) from SARS-CoV with (WT) or without the envelope (DeltaE) gene were compared. We scored 54675 probes (genes) using a dissimilarity function. Nine out of the top ten genes are all upregulated in SARS-CoV-DeltaE compared to SARS-CoV (WT). PPP2R5E gene is the only downregulated gene. All the top 10 genes are directly or indirectly related to heat stress proteins (HSPs) and stress response pathways. Using RGD genes-compounds interactions database we found that Cyclosporin A upregulates all nine upregulated genes and downregulates the only downregulated gene. Moreover, Cyclosporin A inhibits the replication of diverse coronaviruses.
Sample data - GSE30589
Polygenic Risk Score

Alzheimer's Disease

Alzheimer’s disease (AD) is the most common subtype of dementia. Recently, microRNAs (miRNAs) have received a lot of attention as the novel biomarkers for dementia. Here, using serum miRNA expression of 1,601 Japanese individuals, we investigated potential miRNA biomarkers and constructed risk prediction models. This study demonstrates that predictive models are effective in prospective disease risk prediction; and with further improvement may contribute to practical clinical use in dementia.
Sample data - GSE120584
Polygenic Risk Score

Pancreatic Cancer

It is difficult to detect pancreatic cancer or biliary-tract cancer at an early stage using current diagnostic technology. Utilizing microRNA (miRNA) markers that are stably present in peripheral blood, this study aimed to identify pancreatic and biliary-tract cancers in patients. Prospective miRNA markers for pancreatic/biliary tract cancer were selected in the training cohort. Using these miRNAs, discriminant analysis was performed, and the diagnostic accuracy, sensitivity and specificity were calculated in the test cohort.
Sample data - GSE59856