phosphoinositide-3-kinase regulatory subunit 1 (PIK3R1) : Machine learning discoveries of 2nd order synergy in Meningiomas

Background : Meningiomas are the most common intracranial primary neoplasm in adults. Patel et al. [1] analyzed 160 tumors from all 3 World Health Organization (WHO) grades (I through III) using clinical, gene expression, and sequencing data and using unsupervised clustering analysis identified 3 molecular types (A, B, and C) that reliably predicted recurrence. Further, these groups did not directly correlate with the WHO grading system, which classifies more than half of the tumors in the most aggressive molecular type as benign. Issue : Increasing evidence point to the fact that meningioma classification and grading, that is based on histopathology does not always accurately predict tumor aggressiveness and recurrence behaviour and knowledge of the underlying biology of the treatment resistant meningiomas and the impact of genetic alterations in these tumors, is lacking. At the current stage more genomic studies are required to unravel the role of other genes and their interations with other genetic factors. Resolution : In a recently published work Sinha [2], a frame work of a search engine was developed which can rank combinations of factors (genes/proteins) in a signaling pathway. Adapting this search engine to the Meningioma dataset, i present here 2nd order combinations of PIK3R1, some of which have been known to exist via wet lab experiments, but many are yet to be tested. The reveals combinations might help oncologists/biologists test possible hypotheses that might be the causing factors in meningioma. Further, in my limited grasp, if proven true, the combinations revealed by the search engine might pave way for development of gene based therapies aimed at resolving pathological issues related to meningiomas.