SHER: Semantic Databases SHER: Semantic Databases using using - PowerPoint PPT Presentation

SHER: Semantic Databases SHER: Semantic Databases using using ontologies ontologies Julian Dolby, Achille Fokoue Julian Dolby, Achille Fokoue, , Aditya Kalyanpur, Aaron , Aaron Aditya Kalyanpur Kershenbaum, Li Ma, Edith , Li Ma, Edith Kershenbaum Schonberg, Kavitha Srinivas Kavitha Srinivas Schonberg, Watson/ Hawthorne, China Research Lab Watson/ Hawthorne, China Research Lab 1

SHER – – Semantic DB Semantic DB using using ontologies ontologies SHER Breakthrough technology that: Breakthrough technology that: � Is highly scalable Is highly scalable -- -- reasons on 7.7M triples reasons on 7.7M triples in 7.9 s on benchmarks, scales to 60M in 7.9 s on benchmarks, scales to 60M triples. triples. � Can cleanse inconsistencies in noisy data. Can cleanse inconsistencies in noisy data. Identifies thousands of logically inconsistent Identifies thousands of logically inconsistent patterns in minutes. patterns in minutes. � Provides explanations of the chain of Provides explanations of the chain of semantic reasoning for a result set. semantic reasoning for a result set. 2

Who is interested in SHER? Who is interested in SHER? Government: � • Ordnance survey, the British national mapping agency • NSA Healthcare and informatics: � • Mayo Clinic, Chris Chute, Chair of Biomedical Informatics • Vanderbilt Medical Center (Dan Masys, Director of Biomedical Informatics), • Ohio University Medical Center (Philip Payne) • Columbia University Medical Center (Clinical and Translational Award Center) Pharmaceutical industry: � • Pfizer Telecom: � • DoCoMo, a mobile services client. Software/ Services Vendors: � • Clark-Parsia, a semantic consulting services company, interest in licensing/ subcontracting to SHER. • RacerPro (Franz Inc.) interest in licensing SHER.

When are semantic DBs DBs When are semantic useful? useful? Complex knowledge domains, where there is a semantic gap between data and queries Example from healthcare domain -- matching patient records to clinical trials, clinical decision support: Patient data: Queries: Patient on methotrexate Patients on immunosuppresants Patient tested positive for Patients with tuberculosis mycobacterium tuberculosis meningitis. Example from pharmaceutical domain (semantic querying of the metadata on microarray gene expression data): Gene Expression data Queries GSE1402 is data about arthritis Gene expression data on disorders

Clinical trials matching case study Clinical trials matching case study (with Columbia Med) (with Columbia Med) SNOMED Standard clinical Ontology in Patient JS is on Cerner: 7 countries � � WarfarinSodium10mg Laboratory data 1 yr SHER Pharmacy data EMR Radiology data Clinical trial queries in SNOMED: Patients on drugs with active ingredient 5 of warfarin? JS

SHER Scalability Results vs. state of the SHER Scalability Results vs. state of the art art SHER versus KAON2 450 400 350 Time in seconds 300 250 SHER KAON2 200 150 100 50 0 240 2M 7M Dataset sizes (# assertions) Performance of SHER vs state of the art (KAON2) on OWL benchmark – KAON2 6 fails on 7M (112 queries) – AAAI 2007.