ARD-PRED: an in silico tool for predicting age-related-disorder-associated proteins
Interactions among various proteins largely govern cellular processes, and this leads to numerous efforts toward extraction of information related to the proteins, their interactions and the function which is determined by these interactions. The main concern of the study is to present interface analysis of age-related-disorder (ARD)-related proteins to shed light on details of the interactions. It also emphasizes on the importance of using structures in network studies. A major goal in the post-genomic era is to identify and characterize disease susceptibility of genes and to apply this knowledge to disease prevention and treatment. Attempts have been made to integrate biological knowledge of Gene Ontology and Kyoto Encyclopedia of Genes and Genomes pathways into the genomics field. Many gene set analysis methods have been used to detect disease-related risk pathways. The present study combines the network-centered approach with three-dimensional structures to comprehend the biology behind ARDs. Interface properties of the interacting complexes have been used as descriptors to classify age-related associated proteins and non-age-related associated proteins. Machine learning has been used to generate a classifier which is used to predict potential age-related proteins. The ARD-PRED tool achieved an overall accuracy in terms of precision score 81.5, recall score 81.2, accuracy value 79 and ROC Area score 89.6, F-measure 81.1. The tool has been made online at http://genomeinformatics.dtu.ac.in/ARD-PRED/. The present work would comprehend ongoing research in the field of ARDs and would also significantly improvise the understanding of the molecular mechanism of age-related diseases.
KeywordsInterface properties Age-related disorder Machine learning 3-Dimensional structure Network analysis
Authors acknowledge Pooja Khurana, Nitin Thukral, Lokesh Kumar Gahlot and Isha Srivastava for their scientific contributions.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
This article does not contain any studies with human participants or animals performed by any of the authors.
- Aung Z (2006) Computational analysis of 3D protein structures. Doctoral dissertation, School of Computing, National Institute of SingaporeGoogle Scholar
- Davis J, Goadrich M (2006) The relationship between precision-recall and ROC curves. In: Proceedings of the 23rd international conference on machine learning, Pennsylvania, USA, 2006. ACM, New York, NYGoogle Scholar
- Magrane M, The UniProt consortium (2011) UniProt knowledgebase: a hub of integrated protein data. Database (Oxford) 2011:bar009. https://doi.org/10.1093/database/bar009
- Srivastava I, Khurana P, Yadav M, Hasija Y (2017) An integrative system biology approach to unravel potential drug candidates for multiple age related disorders. Biochimica et Biophys Acta (BBA) Proteins Proteomics 1865(12):1729–1738. doi: 10.1016/j.bbapap.2017.07.016Google Scholar