The project is to develop a database of interacting protein (DIP) File Based on the content in chapter 4 of the identification of interactions between the two proteins Based on Support Vector Machines) obtain the interaction information from the given data and generate a vector that can be processed by the vector machine.
Operating System: Windows
Development Environment: Visual C ++ 2010 and Visual C ++ 6.0
Overall Plan:
(1) preparation stage (5 days)
Develop subprograms for each part
Subprograms include:
- Diptoamino -- Analysis of the Interaction file to obtain the amino acid sequence
- Transferamino -- determines the materialized properties based on parameters and processes the amino acid sequence into a sequence containing only three characters: L/m/h.
- Vectorconstructor-vector builder, which obtains feature vectors based on any L/m/h sequence.
- Error Management Program
- Gui
(2) integration stage (3 days)
Debugging is completed through the functions of various subprograms and projects in Visual Studio, and then the interface is added.
(3) test and modification phase (one week)