Hadoop and Spark

We are experts in applying high-performance computing and big data analytics to solve healthcare big data challenges. In addition to applying SGE/LSF for bioinformatics questions, we have evolved our capacities to utilize Hadoop and Spark, which are more powerful for real-time healthcare applications such as fraud detection and precision medicine recommendations.

Below is an example of using Spark to predict disease status from genomic testing data:

PySpark SVM model for classifying tumor and normal samples