Skip to content

Deep phenotyping

levrex edited this page Nov 17, 2020 · 7 revisions

Deep Phenotyping - Clustering Approach

Calculating Clinical Similarity

Plain Binary comparison

Calculate the clinical similarity / distance based on the boolean vectors (doesn't require the structure of the HPO DAG). Example metrics:
Hamming
Dice
Jaccard

Semantic Similarity

Calculate clinical similarity while taking semantic similarity into account (requires the HPO DAG). Example metrics:
HRSS

Prioritisation

Phenotypes were ranked on phenotypic specificity. (Inspired by Hanneke et al)

Pathophysiology

The annotated HPO file (HPOA) was used to infer the genes associated with the phenotypes. These genes were supplied to PHRANK. This tool outperforms Phevor, PhenIX and Phenomizer at ranking the causative genes & diseases.

Input: Pherank requires a list of ensemble ID's The python module mygene was used to convert the entrez gene IDs to ensemble IDs.

Training

We first explored the potential of clustering for deepphenotyping on the ACTG1 ACTB case study collection.

Validation

The Deep Phenotyping clustering algorithm is validated on the COG-CDG case study collection of Hanneke et al. Where we hope to acquire the same pathophysiological insights.

Clone this wiki locally