nodalpoint.org - Techniques - Comments

Application for Milano

ranrub — Tue, 16 Nov 2004 05:50:21 -0500

Let me give you an example. When performing a microarray experiment in which you test expression response to p53 (a DNA damage-related transcription factor and Very Important Protein), you get a list of 150 genes that were significantly up- or down-regulated. Now you want to find information about these genes. Milano enables you to perform automatic searches in the literature for these genes and cross them with experiment-specific search terms.
For example, searching these genes with the term 'p53', will give you positive hits on genes that co-appeared in articles with their putative regulator (as detected in the microarray experiment). This enables you to find known p53 targets, or even regulatory feed-back loops - if you find regulators of p53. Other intersting applications can be thought of.

Further development

ranrub — Tue, 16 Nov 2004 05:20:36 -0500

Currently Milano is in 'alpha'. I plan to release the source (with a proper open-source license) once I clean it up .

Further advancements will include accepting different types of accession numbers, such as Affymetrix probeset IDs. Currently I use Locuslink/Gene Id's because I feel they have the most meaning for this type of search, and because GeneRIF is based on these genes. Also, most microarray vendors supply LocusLink IDs in their annotations.

Feature suggestions will be gladly accepted!

duplicate

Neil — Tue, 16 Nov 2004 00:38:17 -0500

This story appeared recently then disappeared - I promoted it back to the front page. Don't know if that caused any problems.

I have little/no microarray knowledge, but a problem I have with this kind of approach is that it's not clear what the service is meant to do or what I should be typing in as search terms. Perhaps I would have a better idea if I did microarray experiments. I assume the idea is to correlate gene annotation data with expression data? In which case I can think of better ways than small, limited searches - but then I am a proponent of "all against all" approaches.

Admin

Greg — Mon, 15 Nov 2004 06:31:03 -0500

I haven't done a word for word comparison, but I assume this story is a duplicate of the story in the queue ? I will delete the one in the queue if that is okay, if not let me know.

Milano looks interesting, but unfortunately I don't have much expertise in this area to comment seriously. Do you plan on developing it further ?

On second thoughts

Greg — Fri, 10 Sep 2004 05:24:41 -0400

I was originally inclined to agree with Neil on this, but on second thougths this would make an excellent web service. Give it an http link and have it return the XML markup directly.

Alternatively let me have an option to conver the data to RDF. Then link it in with other RDF formatted data. Lots of possibilies...

text mining

jaws — Wed, 08 Sep 2004 08:01:13 -0400

Quite right, textmining technology is still in its infancy, but the overall goal (what I understood from this talk I attended last week) is to be able to parse large quantities of text (PubMed) for example, and be able to extract interesting bits of information. This does not mean searching fulltext for particular keywords etc, but more in the nature of using a well indexed enclycopaedia. So for example, if you were interested in p52 interactions, this sort of technology would pick out not only p52, but its synonyms, binding studies, microarray experiments etc. So you would end up with a set of references which are likely to be very specific and yet offer a wide coverage.

Will there ever be AI?

Neil — Wed, 08 Sep 2004 01:47:58 -0400

I tried this with the pasted text (straight off a web page) from a paper entitled "Adenovirus protein VII condenses DNA, represses transcription, and associates with transcriptional activator E1A", available in J. Virol. at this link and got it to look for protein interactions.

It's quite interesting. There are basically 2 kinds of highlights: (1) links to an SRS search at the EBI for named proteins and (2) what the software has picked as interactions. Some are useful:

"...interaction between protein VII and E1A..."

Others less so:

"...GST protein bound to glutathione-agarose beads..."

Now, I can say "useful or not" because my brain recognises instantly that the first one is a biological process, the second refers to the methodology that they were using. In fact, I can scan the abstract in about the same time as Whatizit takes and extract more useful information from it.

I regard these things as interesting curiosities, but they don't improve my research. Until a computer thinks like me, they never will.

Interesting

Greg — Wed, 08 Sep 2004 00:44:39 -0400

I tried the utility, but unfortunately I got an XML error on the output. I can see the point though, it looks interesting.

I sent you a gmail invite, however the email that you registered with was not working. Can you please email me at greg[at]nodalpoint[dot]org and I'll send anther invite, thanks.