Semantic pipelines to molecular properties


Published on

In our quest to replace answers in molecular sciences by recipes to get answers, the semantic web technologies play the important role of giving meaning to numbers and characters. The Resource Description Framework (RDF) complements (and not replaces) earlier work with eXtensible Markup Language (XML) applications by providing a more clear separation between syntax and meaning. This creates an environment where multiple serialization formats can be used, that grows and shrinks in complexity where needed, and, for example, that can be easily embedded in document formats like HTML. We here present recent work in the dissemination and prediction of molecular properties, where data is shared in RDF, read into statistical and life science software including Bioclipse and R, and where molecular properties are predicted.

1 Like
  • Be the first to comment

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Semantic pipelines to molecular properties

  1. 1. semantic pipelines to Molecular Properties Egon Willighagen (@egonwillighagen) Dept. of Bioinformatics – BiGCaT, Maastricht University #ACSPhilly 2012Department of Bioinformatics - BiGCaT 1
  2. 2. Properties: Physical, chemical, biological• From experiment – with experimental error: interlab differences, method differences, …• No experiment? Predict – with prediction error, originating from experimental error, modeling error, incorrect interpretation, …• Where does the prediction error come from? Predicted BPs →Department of Bioinformatics - BiGCaT 2
  3. 3. Richer Property Prediction1. Select training data (x,y) ● experimental data with errors, detailed description of what the data is2. Find f(x) = y, minimizing error(y) ● use as much as possible information from 1.3. Validation ● not just validate (and quantify) the statistics against a test set, also compare with other data How? → Semantic pipelines E.L. Willighagen, et al. Molecular Chemometrics. Crit. Rev. Anal. Chem. 2006.Department of Bioinformatics - BiGCaT 3
  4. 4. Semantic pipelinesBe clear in what you mean ● Use (open) look-up lists, dictionaries, ontologies ● Be flexible and remove format limitation ● Link to other data → from other domains ● Calculation provenanceM. Samwald, et al. Linked open drug data for pharmaceuticalresearch and development. J. Cheminf. 2011. 3:19Department of Bioinformatics - BiGCaT 4
  5. 5. Semantic pipelines: what technology? CML: semantic, flexible, embeddable in HTML, RSS, … but only in XML RDF: ~10yrs before adopted! But JSON, XML, Turtle, … Also: linked data.Department of Bioinformatics - BiGCaT 5
  6. 6. RDF and friends ... • format independent (JSON, XML, ...) • db technology independent (RDB2RDF) • embeddable in HTML (e.g. RDFa) • Open Standard → widely supportedQuerying • SPARQL: like SQL → access • Federated SPARQL link multiple SPARQL endpoints and other RDF sources Department of Bioinformatics - BiGCaT 6
  7. 7. App #1: Bioclipse speaks RDF andOpenToxDepartment of Bioinformatics - BiGCaT 7
  8. 8. App #2: NanotoxicityDepartment of Bioinformatics - BiGCaT 8
  9. 9. Whats next?Department of Bioinformatics - BiGCaT 9
  10. 10. Collaborations / Thanx CDK community Christoph Steinbeck, Rajarshi Guha, many moreUppsala UniversityOla Spjuth et al. OpenTox community Nina Jeliazkova, Barry HardyKarolinska InstitutetRoland Grafström, Bengt CHEMINF communityFadeel, Hanna Karlsson Nico Adams, Michel Dumontier, Janna HastingsW3C Heath Care and LifeScience interest group CML community (you know :)Department of Bioinformatics - BiGCaT 10
  11. 11. Take home tweetImprove yourproperty predictiontraining andvalidation byadopting semanticpipelines! Further examples: blog: chem-bla-ics twitter: @egonwillighagen CiteULike: egonw Mendeley: egon-willighagen Blue Obelisk GScholar: u8SjMZ0AAAAJDepartment of Bioinformatics - BiGCaT 11