Part of a Rawgraphs.io Data Visualization Case Study
RapidMiner Data Visaulizaiton
SnapGene Protein Strand Sequence
SpanGene Strand Visualization
GitHub Org Page
Educational Course + Tutorials in Progress
Dataview Study GitHub Page
VxAfee-Visualization GitHub Page
Knowing about Covid19, I wanted to do what I can given the whole "disaster relief" effort going on. I also have experience in the past with data visualization and biostatistical computing, so thought now may be a good time.
What it does
So I decided to build ALOT OF STUFF. This includes raw data visualization case studies, genomics case studies, and even a course as well as a visualization related to a potential protein synthesis.
How I built it
While some of the repos are mirrors, and I have used some out of the box stuff, all the visualizations are my own and most of the data work and code is from scratch. Tools/Languages I used include: RapidMiner Studio, RawGraphs.io, Dillinger.io, ReadtheDocs, Datasette, SQL, R and Python.
Challenges I ran into
Access to enough non-corrupted data, marketing challenges (really helpful stuff I wish more people would see), lots of misinformation and saturated news online was a stepping stone in helping me find all the stuff I need.
Accomplishments that I'm proud of
I think I was able to basically build a Coronavirus toolbox that offers many researchers and users extremely helpful information. I also think with access to more data and if I were able to work with others, a crowdsourced vaccine with the FDA could be a potential possibility. The whole thing was really, let me build as much things as possible in as short of a time period as I can. I think organizing it all in a GitHub portfolio page was the best idea, because now it looks like a toolbox/collection/library that people may be able to utilize.
What I learned
I learned more about the Coronavirus in general and how it has many strands. I also think stuff like the World Economics Forum's Event 201, and work by the CDC did provide me with some valuable insights on the different ways we could respond to a pandemic. The fact is the Coronavirus been around for decades, this is just one of its stands, and just like Influenza, there are many. This is why we need to find a way to biostatistically analyze data much quicker, and simulate things faster so that things such as clinical trials and FDA approvals could happen swiftly.
What's next for Annihilate Covid19
If I can be connected to some valuable people with influence that can get my research further known that would be great. Also, looking for grant opportunities for my startup. That being said, I wanna further work on datasets, case studies, models and documentation. I might publish some whitepapers and a Hackernoon article as well, who knows.