Resources & FAQ

Q: What does the Genomics Tertiary Analysis and Machine Learning Using Amazon SageMaker solution do?

A: The solution creates a scalable environment in AWS, setting up a platform that allows users to build machine learning models on genomic datasets using AWS managed services. You can build and deploy updates to both the genomics workflows and the infrastructure that supports their execution.

Q: Can I modify the solution to run my own genomics analysis?

A: Yes, you can modify the solution to fit your particular needs. For example, you can add new genomics model generation pipelines to the solution. Each change is tracked by the CI/CD pipeline, facilitating change control management, rollbacks, and auditing.

Q: What bioinformatics tools are used for data preparation?

A: This solution uses AWS Glue jobs to transforms the ClinVar dataset with variant effect predictors. These predictors are added into ClinVar datasets and include features that are used for model training. In addition, an Amazon SageMaker notebook instance is provided that demonstrates how to use AWS Glue and Amazon SageMaker Autopilot to create a machine learning model generation pipeline.

Q: What bioinformatics datasets are used in the solution?

A: This solution includes ClinVar, a publicly available dataset that aggregates information about genomic variation and its relationship to human health. In addition, Ensemble Variant Effect Predictor (VEP) is used to determine the effect of your variants (Single Nucleotide Polymorphisms (SNPs), insertions, deletions, Copy Number Variations (CNVs), or structural variants) on genes, transcripts, protein sequence, and regulatory regions.

Q: Can I deploy the solution in any AWS Region?

A: No, this solution uses the AWS CodePipeline service, which is currently available in specific AWS Regions only. Therefore, you must launch this solution in an AWS Region where this service is available. For the most current availability by Region, see AWS service offerings by Region.