« Back
Deep Phenotyping - Harnessing Data Richness for Unsupervised High-Content Analysis
Poster Title: Deep Phenotyping - Harnessing Data Richness for Unsupervised High-Content Analysis
Submitted on 05 May 2016
Author(s): Huang Dong, Wang Yi, Maciej Hermanowicz, Ke Yiping, Maja Choma, Lee Kee Khoon, Frederic Bard
Affiliations: Institute of high performance Computing, Astar
This poster was presented at High Content & Phenotypic Screening 2016
Poster Views: 1,550
View poster »

Poster Information
Abstract: High-content analysis (HCA) has recently arisen as a novel systematic approach to cell biology research. Due to the intrinsically high variability and noise level of the assay, it has been primarily applied to supervised analysis, where the phenotypes are known beforehand and manual labels are provided to guide the analysis. Furthermore, most existing research uses only a few parameters, failing to exploit the richness of the raw images.

In this work, we develop an end-to-end computational framework focused on unsupervised HCA. The framework can identify unknown subtle phenotypes from massive multi-parametric data, thus dubbed “Deep Phenotyping”, and correlate them with gene perturbations. It consists of a series of modules: high-dimensional parameter extraction for each cell from raw images, multi-level quality control using both supervised and unsupervised methods with minimal labeling effort, a novelty detection algorithm to automatically retrieve cells that differ from the control, and an unsupervised clustering algorithm to identify unknown phenotypes in the multi-parametric space.

The framework is modularized and applicable to a variety of HCA tasks. We demonstrate its use on the phenotypic analysis of the Golgi apparatus. Novel Golgi phenotypes beyond the three known ones are identified, and potential protein-protein interactions regulating Golgi functions are revealed.
Summary: Recognising the key challenges, we develop an end-to-end computational framework for HCA dubbed “Deep Phenotyping” that perform unsupervised analysis to leverage on the data richness for the discovery of unknown sub-phenotypes with minimal labeling cost.Report abuse »
Ask the author a question about this poster.
Ask a Question »

Creative Commons

Related Posters

Etiological diagnostics of cardiomyopathies in the cardiology unit of the HUEH internal medicine department during the period from 8 January 2014 to 14 June 2014
*Axler JEAN PAUL; **Lesly Ed. ARCHER; *Raema Mimrod JEAN; *Gerald VERNELUS; *Rodolph MALEBRANCHE

Medical Student: Move over Stem Cells – Exosomes are Here! What are Exosomes & their role in Regenerative Medicine?
Amartej Singh Deol MD4 & Advisor: Shivinder S. Deol MD

Briand Bounkeu MD; Ravi Shekarappa MD; La Toya Jackson DO, FAAFP; Chinedu Ivonye MD, FACP; Cristal Kudiwu MD

Striving for Equity in Surgical, Anesthesia, and Obstetric Research in Haiti: A Multi-Partner, International Research Training Collaboration
Dr. Jean Alouidor*, Dr. Frédéric Barau Déjean*, Dr. Louis-Franck Télémaque, Dr. Ronald Eveillard, Dr. Laëlle Mangurat, Dr. Isaac Martineau, Dr. Chartelin Jean Isaac, Dr. Darlène Rochelin Paultre, Carine Réveil Jean-Baptiste, Dr. Lucile Louis Riché, Dr. Jordan Pyda, Rolvix Patterson III, Dr. Blake Alkire, Dr. Eunice Dérivois-Mérisier (*Co-First Authors)

Projektstatus: Entwicklung einer konsensbasierten Therapieempfehlung für die PADOVAN-METHODE® in der Neurorehabilitation
Eisenmeier, Dimitri1; Ostermann, Thomas1; Vogel, Hannah1; Fetz, Katharina1