1 / 10

OpenDMAP :

OpenDMAP :. An open source, ontology-driven concept analysis engine, with applications to capturing knowledge regarding protein transport, protein interactions and cell-type-specific gene expressions by Hunter, et al. OpenDMAP. Ontology-driven: An ontology is the backbone of the system.

gianna
Download Presentation

OpenDMAP :

An Image/Link below is provided (as is) to download presentation Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author. Content is provided to you AS IS for your information and personal use only. Download presentation by click this link. While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server. During download, if you can't get a presentation, the file might be deleted by the publisher.

E N D

Presentation Transcript


  1. OpenDMAP: An open source, ontology-driven concept analysis engine, with applications to capturing knowledge regarding protein transport, protein interactions and cell-type-specific gene expressions by Hunter, et al.

  2. OpenDMAP • Ontology-driven: An ontology is the backbone of the system. • Concept-analysis engine • Each concept in the ontology has an associated recognizer. • A recognizer is a text pattern. • “A pattern describes the words, phrases, parts of speech, syntactic structures or concepts that should cause an instance of the associated concept to be recognized.”

  3. Simple Pattern • Concept: NUCLEUS • Pattern recognizer: NUCLEUS := nucleus, nuclei, nuclear;

  4. Sample ontology

  5. Complex Pattern Regular Expression References to non-terminals (other concepts) Recognizes: “… Bax translocation to mitochondria …”

  6. Another Complex Pattern Fails to recognize: “… Bax translocation to mitochondria from the cytosol …” But the following succeeds: Any order markers

  7. Another Complex Pattern • Fails to recognize: “… H1F-1alpha which is present in glomus cells translocates to the nucleus …” because of the intervening “which” clause. • wild-cards (here, too promiscuous) • syntactic constraints (here, a counter-balance to promiscuity) • The following succeeds:

  8. “Powerful” Patterns Experiments run with just patterns 5–9 augmented with 119 cellular component patterns.

  9. Results* • Run over all abstracts in Medline • Produced 72,460 transport instances • F-measure • 0.29, 10% higher than next best • Recall similar to others, but precision ~20% better (0.39) • Manual check on a small subset • Partial recognition counted • Corrected for protein identification • F-measure raised to 0.81 *Caution: See paper for details.

  10. Discussion Messages • Ontology/Language connection • “[Ensures] that the knowledge representation is grounded [wrt] a carefully constructed model of reality” • “[Recognizers] … structured by the ontology ...” which “… finesses many difficult ambiguity resolution problems” • The architecture makes it easy to exploit better gene/protein recognition systems as they are developed. better any-kind-of recognition systems

More Related