The world of computing is slowly moving away from complex user interfaces into a more interactive user experience in the recent past. Personalised assistants like Amazon Echo and Google Home have made use of voice and natural language as a medium to get to what customer wants. This is accomplished using computational techniques like Voice Recognition, Natural Language Processing and Deep Learning algorithms.

FDA Submission deadlines followed by additional analysis and data requirements are probably some of the most stressful times for sponsors and statisticians. Requests could range from seeking information on specific areas or additional analysis against specific populations, questions on Safety and Efficacy, PK etc. For example consider the scenario where FDA would like to see how the laboratory/vital data are populated for the subjects with serious adverse events or wherein the FDA needs a list of subjects who have taken multiple distinct medications after treatment. This will translate to additional tables, listings or figures to be run on specific populations that needs to be created on the fly

Radical changes in Microbiome research in Clinical Trials has materialized with the widespread application of next-generation sequencing technologies. This is empowered by high-throughput profiling of the genetic contents of microbial communities. With the advent of big data technologies and high throughput computing resources, we are able to now analyze large complex microbiome data sets. Research is ongoing to identify new methods and models suitable for analyzing microbiome data. Some of the areas that needs attention include a. Analysis of microbiome data and tools to explore its compositionb. Longitudinal data analysisc. Causation Analysis Since data is extremely complex it remains a challenge to statisticians for developing tools required for analysis. We are exploring the possibilities of using SAS for putting together an analysis framework for microbiome data sets.