As the positive pairs in the training set share a common GO term, we expect our method to classify the protein pairs as positive whose GO terms are the same or the next one in the GO hierarchy and as negative if their respective GO terms are far away.
For a query protein with domains A and B and its neighbors AC1, AC2, …, and AC n, the more C n domains share a common GO term, the higher the possibility that domain B or protein AB will associate with the same GO term.
More specifically, for each network, we count how often directly connected genes share a common Gene Ontology term.
This contrasts with BHI, which just assigns a score of 0 or 1 to gene pairs depending on whether or not they share a common GO term.
The work [ 20] is based on the assumption that if two genes are related in the information dataset they should share a common GO term.
To simplify the classification, similar InterPro domains sharing a common "parent" term were collapsed into the parent term.
Students also share a common history in terms of going to the same school and being taught in the same classrooms by the same teachers.
Pathologists and researchers share a common goal in terms of scientific research and the advancement of scientific knowledge [ 1], but hold a variety of views relating to the use of biological specimens [ 5- 7, 21].
According to SCOP, protein sequences that have sequence identity of over 30% or that share a common ancestor in terms of structures and functions are grouped into FFs [ 10, 18].
Multiple individuals sharing a common TCR, termed public T cell response, has been observed during viral infections, tumorigenesis, and in autoimmune diseases such as multiple sclerosis, rheumatoid arthritis, aplastic anemia, and sarcoidosis (reviewed in [ 48]).
