With software becoming more prevalent in fields where it previously did not exist, more people must learn how to write programs to accomplish their work. One example is bioinformatics. At Iowa State, COM S 444: Bioinformatic Analysis is cross listed with Biology and Genetics, among other majors. Students in these majors do not necessarily have to become top programmers to do their work, but their work involves programming nonetheless. A lack of experience in programming can become an unnecessary hindrance to getting the work done, especially when trying to figure out the syntax of a programming language. Our goal is to provide a method for users to type what they want to accomplish in natural language and convert that natural language to the software code. This would allow someone who doesn’t know how to write a particular statement in a programming language to type an approximation of that statement in English and have the editor convert the English to executable code.

The primary deliverable is a plugin to an existing integrated development environment (IDE) or text editor through which the user will interact with to translate natural language to code. Behind the scenes will be a classification engine that handles the actual conversion of English to code. Also produced will be a data set of possible natural language inputs that someone might type and the expected result, which will allow us to test the accuracy of our final product.