Use supervised machine learning and hidden markov model to automatically analysis mitosis and cytokinesis in genome scale

The paper finally is out~~
When I was listening this work in a seminar down stair last year, I feel it would be big. Yes, it is in Nature.
The approach they used to study mitosis is very powerful, state of the art!

Comment on Nature by Jason, Cecilia and Stephen

The paper in brief
* The research assessed the activity of some 21,000 protein-coding genes in the human genome.
* Each gene was silenced by small interfering (si) RNA sequences.
* The effects — the 'phenotypic profiles' — were monitored by time-lapse microscopy and analysed by image processing.
* The emphasis is on genes that function in mitotic cell division — the process by which a (non-germ) cell divides to produce two identical daughter cells.
* 190,000 time-lapse movies of 19 million cell divisions were generated.
* The resulting data set is publicly available at http://www.mitocheck.org.

For one, the present work1 assembles all these techniques into a pipeline to systematically screen the entire human genome. As outlined in 'The paper in brief', the sheer scale of the data generated and the associated annotations are a notable achievement, freely available to the research community.

...

One concern about the authors' work is that it was performed in only one cell line, potentially missing — or overemphasizing — certain pathways. It would be beneficial to complete the same analysis using cancer cell lines and normal cells to see if different cell types show different hierarchical clusters of gene expression.

We believe that, as more such genome-wide screens are performed, a future challenge will be not only the creation of new data sets and the amplification of existing ones, but also the establishment of a flexible platform that will cross-reference and integrate different screens to facilitate the collection of information and to create an overall picture of protein function.

Nature. 2010 Apr 1;464(7289):721-7.

Phenotypic profiling of the human genome by time-lapse microscopy reveals cell division genes.

Neumann B, Walter T, Hériché JK, Bulkescher J, Erfle H, Conrad C, Rogers P, Poser I, Held M, Liebel U, Cetin C, Sieckmann F, Pau G, Kabbe R, Wünsche A, Satagopam V, Schmitz MH, Chapuis C, Gerlich DW, Schneider R, Eils R, Huber W, Peters JM, Hyman AA, Durbin R, Pepperkok R, Ellenberg J.

MitoCheck Project Group, European Molecular Biology Laboratory (EMBL), Meyerhofstrasse 1, D-69117 Heidelberg, Germany.

Despite our rapidly growing knowledge about the human genome, we do not know all of the genes required for some of the most basic functions of life. To start to fill this gap we developed a high-throughput phenotypic screening platform combining potent gene silencing by RNA interference, time-lapse microscopy and computational image processing. We carried out a genome-wide phenotypic profiling of each of the approximately 21,000 human protein-coding genes by two-day live imaging of fluorescently labelled chromosomes. Phenotypes were scored quantitatively by computational image processing, which allowed us to identify hundreds of human genes involved in diverse biological functions including cell division, migration and survival. As part of the Mitocheck consortium, this study provides an in-depth analysis of cell division phenotypes and makes the entire high-content data set available as a resource to the community.

PMID: 20360735 [PubMed - in process]

Talk given by Daniel Gerlich (ETH Zurich) record on Oct 7, 2009
[video vid_image=http://en.dogeno.us/wp-content/video/VID00130.png filename=/wp-content/video/VID00130.mp4 /]