Enhancing interacting residue prediction with integrated contact matrix prediction in protein-protein interaction.

Identifying the residues in a protein that are involved in protein-protein interaction and identifying the contact matrix for a pair of interacting proteins are two computational tasks at different levels of an in-depth analysis of protein-protein interaction. Various methods for solving these two problems have been reported in the literature. However, the interacting residue prediction and contact matrix prediction were handled by and large independently in those existing methods, though intuitively good prediction of interacting residues will help with predicting the contact matrix. In this work, we developed a novel protein interacting residue prediction system, contact matrix-interaction profile hidden Markov model (CM-ipHMM), with the integration of contact matrix prediction and the ipHMM interaction residue prediction. We propose to leverage what is learned from the contact matrix prediction and utilize the predicted contact matrix as "feedback" to enhance the interaction residue prediction. The CM-ipHMM model showed significant improvement over the previous method that uses the ipHMM for predicting interaction residues only. It indicates that the downstream contact matrix prediction could help the interaction site prediction.

Prediction of residue-residue contact matrix for protein-protein interaction with Fisher score features and deep learning.

Protein-protein interactions play essential roles in many biological processes. Acquiring knowledge of the residue-residue contact information of two interacting proteins is not only helpful in annotating functions for proteins, but also critical for structure-based drug design. The prediction of the protein residue-residue contact matrix of the interfacial regions is challenging. In this work, we introduced deep learning techniques (specifically, stacked autoencoders) to build deep neural network models to tackled the residue-residue contact prediction problem. In tandem with interaction profile Hidden Markov Models, which was used first to extract Fisher score features from protein sequences, stacked autoencoders were deployed to extract and learn hidden abstract features. The deep learning model showed significant improvement over the traditional machine learning model, Support Vector Machines (SVM), with the overall accuracy increased by 15% from 65.40% to 80.82%. We showed that the stacked autoencoders could extract novel features, which can be utilized by deep neural networks and other classifiers to enhance learning, out of the Fisher score features. It is further shown that deep neural networks have significant advantages over SVM in making use of the newly extracted features.

Applying internal coordinate mechanics to model the interactions between 8R-lipoxygenase and its substrate.

BACKGROUND: Lipoxygenases (LOX) play pivotal roles in the biosynthesis of leukotrienes and other biologically active potent signalling compounds. Developing inhibitors for LOX is of high interest to researchers. Modelling the interactions between LOX and its substrate arachidonic acid is critical for developing LOX specific inhibitors. Currently, there are no LOX-substrate structures. Recently, the structure of a coral LOX, 8R-LOX, which is 41% sequence identical to the human 5-LOX was solved to 1.85Å resolution. This structure provides a foundation for modelling enzyme-substrate interactions. METHODS: In this research, we applied a computational method, Internal Coordinate Mechanics (ICM), to model the interactions between 8R-LOX and its substrate arachidonic acid. Docking arachidonic acid to 8R-LOX was performed. The most favoured docked ligand conformations were retained. We compared the results of our simulation with a proposed model and concluded that the binding pocket identified in this study agrees with the proposed model partially. RESULTS: The results showed that the conformation of arachidonic acid docked into the ICM-identified docking site has less energy than that docked into the manually defined docking site for pseudo wild type 8R-LOX. The mutation at I805 resulted in no docking pocket found near Fe atom. The energy of the arachidonic acid conformation docked into the manually defined docking site is higher in mutant 8R-LOX than in wild type 8R-LOX. The arachidonic acid conformations are not productive conformations. CONCLUSIONS: We concluded that, for the wild type 8R-LOX, the conformation of arachidonic acid docked into the ICM-identified docking site is more stable than that docked into the manually defined docking site. Mutation affects the structure of the putative active site pocket of 8R-LOX, and leads no docking pockets around the catalytic Fe atom. The docking simulation in a mutant 8R-LOX demonstrated that the structural change due to the mutation impacts the enzyme activity. Further research and analysis is required to obtain the 8R-LOX-substrate model.