Date of Award


Publication Type

Master Thesis

Degree Name



Computer Science

First Advisor

Rueda, Luis (Computer Science)


Computer science.



Creative Commons License

Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License
This work is licensed under a Creative Commons Attribution-Noncommercial-No Derivative Works 4.0 License.


Prediction and discrimination of Crystal Packing interactions and Biological interactions is a particular problem that has drawn the attention of the research community in recent years. In this thesis, we have studied the prediction problem of these two types of interactions as well as obligate and nonobligate interactions. We are proposing new features such as Number Based Amino Acid Composition and Area Based Amino Acid Composition to predict different types of interactions more efficiently. We have measured our newly proposed features' contribution to the classification by comparing them with already proposed model. Along with we are also proposing an efficient multi-stage classification strategy to successfully predict crystal packing, non-obligate and obligate interactions. In this thesis we are also proposing a modified singularity problem free linear dimensionality reduction's linear transformation matrix maximization criterion. We have also applied our proposed LDR-Singular Value Decompositions modified (LDR-SVD) to other protein-protein interaction problems.