Summary

In this chapter, we went into the basics of genomics. We defined key terminology related to genetics and understood how genomes influence our day-to-day functions. We also learned about genomic sequencing, the process of decoding genomic information from our DNA. We then learned about the challenges that organizations face when processing genomic data at scale and some techniques they can use to mitigate those challenges. Lastly, we learned about the inference options of SageMaker and hosted a pre-trained model on a SageMaker real-time endpoint. We combined this model with clinical entity recognition from Comprehend Medical to extract genetic and clinical entities from a genomic testing report.

In Chapter 8, Applying Machine Learning to Molecular Data, we will look at how ML is transforming the world of molecular property prediction. We will see how ML-based approaches are allowing scientists to discover unique drugs faster and with better outcomes for patients.