Data Access and Contribution

[Sally-designs]

@jonbrenas and @ahernank

I would like to contribute to GSoC project 3 "Exploring natural-language interfaces to increase the understanding malaria vector genomic data."

My proposal would include building a natural language interface that translates plain-English queries into executable malariagen_data API call.I would use

1. NL Input Layer — Users type questions in plain English
2. LLM Query Parser
3. Execution Layer
4. Results + Visualisation .

Integration with other open source tools like EMOD and Open Malaria and maybe intergartion with IP Mappers and GIS maps of vector like Ploty's Mapbox.

I have started working on issue #1029

In addition I am experiencing challenges in accessing that malaria gen data but I have sent the filled data Access form and would like advice on which datasets to work and how long the approval takes.with I have set up my local environment and I'm ready to work on this.