We found a match
Your institution may have rights to this item. Sign in to continue.
- Title
KCML: a machine‐learning framework for inference of multi‐scale gene functions from genetic perturbation screens.
- Authors
Sailem, Heba Z; Rittscher, Jens; Pelkmans, Lucas
- Abstract
Characterising context‐dependent gene functions is crucial for understanding the genetic bases of health and disease. To date, inference of gene functions from large‐scale genetic perturbation screens is based on ad hoc analysis pipelines involving unsupervised clustering and functional enrichment. We present Knowledge‐ and Context‐driven Machine Learning (KCML), a framework that systematically predicts multiple context‐specific functions for a given gene based on the similarity of its perturbation phenotype to those with known function. As a proof of concept, we test KCML on three datasets describing phenotypes at the molecular, cellular and population levels and show that it outperforms traditional analysis pipelines. In particular, KCML identified an abnormal multicellular organisation phenotype associated with the depletion of olfactory receptors, and TGFβ and WNT signalling genes in colorectal cancer cells. We validate these predictions in colorectal cancer patients and show that olfactory receptors expression is predictive of worse patient outcomes. These results highlight KCML as a systematic framework for discovering novel scale‐crossing and context‐dependent gene functions. KCML is highly generalisable and applicable to various large‐scale genetic perturbation screens. Synopsis: KCML is a Knowledge‐ and Context‐driven Machine Learning framework that systematically analyses large‐scale genetic screens. KCML utilises gene ontology to identify phenotypes associated with a particular gene function in a given cellular context. KCML is a novel approach for inferring context‐specific gene functions.KCML predicts multiple functions per gene based on phenotypic similarity along the confidence in these predictions.KCML allows generating a data‐driven map of functions represented in a certain dataset.Measurements of nuclear morphology and multicellular organisation can be predictive of many biological functions.KCML revealed a novel role for olfactory receptors in multicellular organisation of colorectal cancer cells.
- Subjects
GENETIC testing; WNT genes; CANCER genes; WNT signal transduction; GENES
- Publication
Molecular Systems Biology, 2020, Vol 16, Issue 3, p1
- ISSN
1744-4292
- Publication type
Article
- DOI
10.15252/msb.20199083