I have a new paper out:
Luis Pedro Coelho, Joshua D. Kangas, Armaghan Naik, Elvira Osuna-Highley, Estelle Glory-Afshar, Margaret Fuhrman, Ramanuja Simha, Peter B. Berget, Jonathan W. Jarvik, and Robert F. Murphy, Determining the subcellular location of new proteins from microscope images using local features in Bioinformatics, 2013 [Advanced Access]
(It’s not open access, but feel free to email me for a preprint.)
As you can see, this was 10 months in review, so I am very happy that it is finally out. To be fair, the final version is much improved due to some reviewer comments (alas, not all reviewer comments were constructive).
There are two main ideas in this paper. We could perhaps have broken this up into two minimum publishable units, but the first idea immediately brings up a question. We went ahead and answered that too.
The is the main point of the paper is that:
1. The evaluation of bioimage classification systems (in the context of subcellular classification, but others too) has under-estimated the problem.
Almost all evaluations have used the following mode :
- Define the classes of interest, such as the organelles: nuclear, Golgi, mitochondria, …
- For each of these, select a representative marker (ie, DAPI for the nuclear class, &c).
- Collect multiple images of different cells tagged with the representative marker for each protein.
- Test whether a system trained on some images of that marker can recognise other images of the same marker.
- Use cross-validation over these images. Get good results. Publish!
Here is the point of this paper: By using a single marker (a tagged protein or other fluorescent marker) for each class, we are unable to distinguish between two hypothesis: (a) the system is good at distinguishing the classes and (b) the system is good at distinguishing the markers. We show empirically that, in many cases, you are distinguishing markers and not locations!
This is a complex idea, and I will have at least another post just on this idea.
The natural follow-up question is how can we get better results in this new problem?
I had pointed out in my review of Liscovitch et al. that we had similarly obtained good results with local features.
I will have a few posts on this paper, including at least one on things that we left out because they did not work very well.
|||All that I know. I may be biased towards the subcellular location literature (which I know very well), but other literatures may have been aware of this problem. Add a comment below if you know of something.|
- Paper Review: FuncISH: learning a functional representation of neural ISH images (metarabbit.wordpress.com)