16:02:46 <RRSAgent> RRSAgent has joined #hcls2
16:02:46 <RRSAgent> logging to http://www.w3.org/2011/05/05-hcls2-irc
16:02:46 <michel> zakim, this is tmo
16:02:50 <Bob> scribenick Bob
16:02:54 <Zakim> Zakim has joined #hcls2
16:04:34 <michel> https://docs.google.com/document/d/1lKdDSb2uBBIeTEQAv2CyTHN_aVW63k9si1hmmilOMi0/edit?hl=en&authkey=CJGUtcwF#
16:04:35 <AmitSheth> AmitSheth has joined #HCLS2
16:05:16 <AmitSheth> there is nothing at http://www.w3.org/wiki/HCLSIG/SWANSIOC/Actions/RhetoricalStructure/
16:05:25 <michel> https://docs.google.com/document/d/1lKdDSb2uBBIeTEQAv2CyTHN_aVW63k9si1hmmilOMi0/edit?hl=en&authkey=CJGUtcwF#
16:08:28 <epichler> epichler has joined #HCLS2
16:08:36 <Bob> Michel: Use case plus the data and the ontological discussions
16:08:43 <joanne> joanne has joined #hcls2
16:09:19 <Bob> ... paper is about SNPs pxgx, how SNP's might be recorded in patient records
16:09:19 <joanne> pls post link to paper again.  i see only a link to rhetorical structure
16:09:38 <Bob> https://docs.google.com/document/d/1lKdDSb2uBBIeTEQAv2CyTHN_aVW63k9si1hmmilOMi0/edit?hl=en&authkey=CJGUtcwF#
16:09:59 <bbalsa> bbalsa has joined #HCLS2
16:10:28 <Bob> ... breast cancer case: info still tied around gene expression as a biomarker
16:10:46 <Bob> ... a little bit further away from what we wanted to embark
16:10:54 <joanne> 12:09	Bob	https://docs.google.com/document/d/1lKdDSb2uBBIeTEQAv2CyTHN_aVW63k9si1hmmilOMi0/edit?hl=en&authkey=CJGUtcwF#
16:11:02 <joanne> for bo
16:12:12 <Bob> Michel: Breast cancer case suited for collab w BioRDF
16:12:42 <AmitSheth> +q
16:12:55 <Bob> ... maybe a separate paper. One paper for SNPs, one paper for pharmacogenomics
16:13:46 <Bob> Joanne: TMO to bridge;
16:14:21 <Bob> Michel: Introduction by Eiker(?), startup w breast cancer interest
16:15:05 <Bob> ... there is a front end that uses TMO; based on what we published
16:16:16 <Bob> Michel: Learned as much as there is about warfarin
16:16:54 <Bob> ... dosing, SNP ids; also prediciton algorithms, interesting to see lots of work
16:17:17 <AmitSheth> was this shared on this group? http://news.sciencemag.org/sciencenow/2011/04/computer-algorithm-may-speed-dru.html?ref=hp
16:17:36 <Bob> ... pharmGKB is interested. Wonder if we can look at semantic web services
16:17:45 <AmitSheth> +q
16:18:36 <Bob> ... would be well placed to do prediction for a speicific patient
16:19:05 <Bob> Elgar: What are predictions based on?
16:19:45 <Bob> Michel: Testing is done by int'l normalized ratio INR: how active is the pathway for coagulation
16:19:59 <Bob> ... amt of warfarin needs to be balanced
16:20:18 <Bob> ... there are home monitoring kits to manage dosing
16:20:46 <Bob> ... factors other than the two genes are diet, etc that can change
16:21:18 <Bob> ... this is already a nice patient-specific case
16:21:44 <Bob> Joanne: bc w BioRDF; warf w...
16:22:07 <Bob> ... Lib of Personalized Med has published on warfarin
16:22:44 <Bob> Michel: Also genetic tests for low $
16:23:00 <Bob> ... genetic component explains 40% of dosage variance
16:23:23 <Bob> ... FDA has published the table reproduced in the doc
16:23:48 <Bob> ... but the table is less effective than other research
16:25:17 <Bob> Elgar: We have two things that determine dosing
16:25:47 <Bob> ... so there is an input vector for the algorithms
16:26:01 <Bob> ... dosage recommendation is not great for accuracy
16:26:13 <joanne> what are the inputs?
16:26:37 <Bob> ... we would like to look at 1) can we find other features to consider? and 2) look at diff prediction algorithms
16:27:21 <Bob> Michel: There are papers that crit pgx approach; doesn't work for people >65
16:27:39 <Bob> ... reduced metabolism, loss of liver function, etc
16:27:55 <AmitSheth> Looks like being on the queue does not help: so here are questions/comments: (a) have you thought about the quality of data you are integrating? (b) quality of intergration?
16:28:03 <Bob> ... consider a range of factors beyond genetics, should be able to account for more variance
16:28:23 <Bob> (well, warfariin dosing is tough!)
16:28:52 <Bob> Elgar: No idea at moment how data analysis and prediction would sound
16:29:21 <Bob> Michel: Have touched the surface; maybe take closer look at prediction aspect
16:30:02 <Bob> Joanne: Interested in prediction, along w Elgar
16:30:23 <Bob> Michel: We need a better understanding of what they use to train
16:30:55 <Bob> ... one of papers in section on prediction; performance of the different approaches
16:31:13 <Bob> ... are there some elements that are being missed, even in state-of-the-art
16:31:39 <Bob> ... could we add more features to explain more variance?
16:31:44 <joanne> here's one tonellato warfarin avatar paper: http://www.google.com/url?sa=t&source=web&cd=4&sqi=2&ved=0CDAQFjAD&url=http%3A%2F%2Fpeople.dbmi.columbia.edu%2F~rip7002%2FSite%2FHome_files%2FSimulated%2520Comparison%2520of%2520Warfarin%2520Treatment%2520Protocols%2520Chi%25202010.pdf&ei=itDCTeG-K9PqgQeMlJHaBg&usg=AFQjCNGRNZdX7CCrLw3Mh5YJK3pIHkV7Yg&sig2=GmqL31HAsPP
16:32:27 <Bob> What is quality of data that you are going to use?
16:33:16 <Bob> Michel: Reduce dimensionality of data; can analytically find strong correlates in the input
16:33:44 <Bob> ... we would complement what they already use w new contributions
16:33:59 <joanne> Look at page 17 and 18 of this (at least!)  http://docs.google.com/viewer?a=v&q=cache:gaOqmO8SKj4J:online.law.asu.edu/events/Personalized_Medicine/ppts/Monday/Afternoon/Session_III/Tonellato.pdf+tonellato+warfarin+filetype:PDF&hl=en&gl=us&pid=bl&srcid=ADGEESi-OP2QSvCcWEh-8WEj1Ukq0ApfCCv3_xqKfTNFBWbTdKlZ3_TzyCVp475MFh1xs1qbV8YTcHVXGWnfxpXHSE8HXiak2sH59WHNMhSzd
16:35:07 <Bob> Amit(?): question about correlates and alignment
16:35:23 <Bob> Michel: Can't comment on even their quality of data
16:35:41 <Bob> ... won't build a new algorithm for paper
16:36:18 <Bob> ... how do we represent facts; mostly focus on rep of knowledge
16:36:37 <Bob> ... we might build a better predictor later :-)
16:37:08 <Bob> Michel: Looked at pathways from pharmGKB; basically a diagram
16:37:29 <Bob> ... don't know how well maps out to Reactome or Kegg
16:39:10 <Bob> Michel: There was a GWAS on pharmGKB; want to convert patient data wrt outcomes
16:39:15 <michel> http://www.pharmgkb.org/do/serve?objId=PA135603152#tabview=tab2
16:39:36 <Bob> that's not the right link!
16:39:45 <Bob> here's another one:
16:40:15 <michel> http://www.pharmgkb.org/do/serve?objId=PA165291561&objCls=PhenotypeDataset#tabview=tab1
16:40:53 <Bob> Michel: Based on clinical and other demo factors
16:42:31 <Bob> ... this is the most important dataset for us; need to convert to semantic set for individual
16:43:12 <Bob> ... convert to RDF; ensure that our representation has all the fields, and in ontologies
16:43:38 <Bob> ... ontological nature of the representations
16:43:59 <Bob> Joanne: will do tab-to-RDF
16:44:30 <Bob> Michel: Are there other datasets that we might consider?
16:45:30 <Bob> Joanne: emailing warfarin paper to everyone
16:47:33 <Bob> ... can set parameters flexibility in the avatars
16:47:54 <Bob> Michel: Which field; does our ont have the slots?
16:48:37 <Bob> ... vis-a-vis predictive stuff that Russ did? Which fields might be missing, overlap of these.
16:48:56 <Bob> Joanne: Probably have captured all the important ones
16:50:41 <Bob> Michel: Warfarin case: enough for good investigation
16:52:10 <Bob> Bosse: Would like to see link to pharam co
16:52:37 <Bob> Michel: Label has been updated twice; gene but no dosing
16:52:56 <Bob> ... 2009 updated w table, w variance accounted for
16:54:17 <Bob> ... What kind of data are required to make decision? expensive to do trials
16:55:23 <Bob> Bosse: Clinical trial could be the angle here.
16:55:51 <Bob> Michel: Also what data the FDA requires so that becomes part of the label?
16:57:47 <Bob> Amit: Interested to see how this is realized. Issues of data access, quality etc
16:59:31 <Bob> ... have developed tools to produce RDF
17:00:17 <Bob> ... capturing data is what I would like
17:00:45 <Bob> Matthias: Interested in clinical decision support; how pgx data can be used for alerts etc
17:01:04 <Bob> ... seamless integration into clincial workloads
17:02:58 <Bob> Michel: Adrian Coulet and I will work on representations
17:12:10 <iker> iker has joined #hcls2
17:14:08 <michel> michel has joined #hcls2
17:14:12 <michel> rrsagent, draft minutes
17:14:12 <RRSAgent> I have made the request to generate http://www.w3.org/2011/05/05-hcls2-minutes.html michel
17:14:20 <michel> rrsagent, make log world-visible
18:46:54 <Zakim> Zakim has left #hcls2