literature mapping with pubatlas -- extending pubmed with a `blasting interface’
DESCRIPTION
Literature Mapping with PubAtlas -- extending PubMed with a `BLASTing interface’. D Stott Parker 1 , WW Chu 1 , FW Sabb 3 , AW Toga 2 , RM Bilder 3 1 UCLA Computer Science Dept, 2 Laboratory of Neuroimaging, 3 Dept of Psychiatry & Biobehavioral Sciences. Hypothesis Web Project - PowerPoint PPT PresentationTRANSCRIPT
Literature Mapping with PubAtlas -- extending PubMed
with a `BLASTing interface’D Stott Parker1, WW Chu1, FW Sabb3, AW Toga2, RM Bilder31UCLA Computer Science Dept, 2Laboratory of Neuroimaging, 3Dept of Psychiatry & Biobehavioral Sciences
Hypothesis Web ProjectNIH RL1LM009833
PubAtlas is a“PubMed BLAST-query”service for two term sets/lexica
PubAtlas Literature Map
result: contingency table for all queries (X AND Y) where X,Y are terms in the two lexica
www.pubatlas.org
PubAtlas Lexica:• term: definition pairs Term Name : PubMed Query• optional hierarchical structure
Lexicon as:• concept base • ontology• user-defined term hierarchy (personalized MeSH hierarchy)• domain-specific query language
Lexica
Concept BLASTing
Lexicon1 = X hierarchy
Literature Map: (X AND Y)
association table
Lexicon2 = Y hierarchy
MEDLINE / PubMed as a bioscience association base
PubAtlas
`Concept BLASTing’ seeks useful associations, much like microarray analysis
Previous Work -- as an example
AliBaba: "AliBaba" [TIAB] AND "PubMed" [TIAB]Anne O'Tate: "Anne O'Tate" [TIAB]BioIE: "BioIE" [TIAB]ClusterMed: "ClusterMed" [TIAB]ConceptLink: "ConceptLink" [TIAB]GoPubMed: "GoPubMed" [TIAB]HubMed: "HubMed" [TIAB]PubFocus: "PubFocus" [TIAB]PubGene: "PubGene" [TIAB]PubMatrix: "PubMatrix" [TIAB]PubMed Assistant: "PubMed Assistant" [TIAB]PubNet: "PubNet" [TIAB]PubReMiner: "PubReMiner" [TIAB]Relemed: "Relemed" [TIAB]SLIM: "Muin M" [au] AND "SLIM" [TIAB]VisualNet: "VisualNet" [TIAB] OR "Visual Net" [TIAB]XplorMed: "XplorMed" [TIAB]
graph: "PubMed" [TIAB] AND ("graph" [TIAB] OR "network" [TIAB] OR "diagram" [TIAB])visual: "PubMed" [TIAB] AND ("visual" [TIAB] OR "visualizing" [TIAB] OR "visualization" [TIAB] …)friendly: "PubMed" [TIAB] AND ("friendly" [TIAB] OR "flexible" [TIAB])better interface: "PubMed" [TIAB] AND ("interface" [TIAB] OR "interaction" [TIAB] OR "query" [TIAB]) …)exploration: "PubMed" [TIAB] AND ("exploration" [TIAB] OR "explore" [TIAB] OR "discovery" [TIAB] …)summarization: "PubMed" [TIAB] AND (summariz* [TIAB] OR digest* [TIAB])map: "PubMed" [TIAB] AND ("mapping" [TIAB] OR "map" [TIAB] OR "mapped" [TIAB])extraction: "PubMed" [TIAB] AND (extract* [TIAB] OR identif* [TIAB])relevance: "PubMed" [TIAB] AND ("relevance" [TIAB] OR "ranking" [TIAB] OR "ordering" [TIAB])powerful: "PubMed" [TIAB] AND ("powerful" [TIAB] OR "extended" [TIAB] OR "advanced" [TIAB])
Desirable extension features
previous PubMed extensions
semi-automatedgeneration of areview paper -- but thorough and remaining up-to-date
PubAtlas -- interesting aspects PubAtlas as a tool for concept “BLASTing”
Moving towards shared, user-defined query/concept languages
Visual literature search with concept maps / literature maps
Building on familiar association mining metaphor Extending PubMed with temporal indexing / concept
evolution Real uses: semi-automated reviews, knowledge mgmt, ...
Applications in Phenomics Phenotypes are often naturally represented as queries Promising applications in interdisciplinary collaboration
Knowledge Management
Who at UCLA works on Dopamine Receptors?
Many possibilities for interdisciplinary collaboration
People as ConceptsLori Altshuler: Altshuler Lori [FAU] OR Altshuler LL [AU]Stephen Marder: Marder Stephen [FAU] OR Marder SR [AU]Carrie Bearden: Bearden Carrie [FAU] OR Bearden CE [AU]Ty Cannon: Cannon Tyrone [FAU] OR Cannon TD [AU]Michael Phelps: Phelps Michael [FAU] OR Phelps ME [AU]John Mazziotta: Mazziotta John [FAU] OR Mazziotta J [AU]Paul Thompson: Thompson Paul M [FAU] OR Thompson PM [AU]Arthur Toga: Toga Arthur [FAU] OR Toga A [AU] Roger Woods: Woods Roger [FAU] OR Woods RP [AU] Bob Bilder: Bilder Robert [FAU] OR Bilder RM [AU]Nelson Freimer: Freimer Nelson [FAU] OR Freimer N [AU]...
Map of publications in which people X, Y both occur as authors
Exploring Associations over Time
Extending PubMed with Time
199820002002200420062008
Historical map of interdisciplinary collaboration at UCLA over 10 yrs
Deeper ExplorationVisualization and interaction along with standard mining of association data
For term sets of size M, N, PubAtlas submits M+N PubMed queries
This can scale to hundreds or thousands of terms
Larger Lexica
CNP_peo ple.t erms CNP investigators, ordered alphabe tical ly CNP. terms freque ntly-used terms in the CNP Mem oryMec hanisms.terms freque ntly-used terms: CNP Mem ory Mec hanisms projec t ResponseInhi biti on.t erms freque ntly-used terms: CNP Response Inhibition proje ct CNP_tea ms.terms CNP investigators, ordered by fiel d CNP_groups.terms CNP investigators, ordered by fiel d, with field names ADHD_gen es.terms a l ist of abou t 50 gen es possibly linked wit h ADHD BP_gen es.terms a l ist of abou t 25 gen es possibly linked wit h BP SZ_gen es.terms a l ist of abou t 50 gen es possibly linked wit h SZ CNP_gen es.terms a l ist of abou t 100 gen es possibly linked wit h ADHD/BP/SZ Pub Brain.t erms Pub Brain vocab ulary: 330 anatomica l regio ns of the brain UCLANeuroscie nceFaculty.terms UCLA Neuroscie nc e faculty, ordered alphabe tical ly MeSH_Amines.terms MeSH hierarchy for Amines MeSH_Aza_Compoun ds.terms MeSH hierarchy for Aza Compounds MeSH_Beh avior. terms MeSH hierarchy for Beh avior MeSH_Brain_Anat om ica l_Regions.terms MeSH hierarchy for Brain Regions MeSH_Brain _Diseases.terms MeSH hierarchy for Brain Diseases MeSH_Catecholami nes.terms MeSH hierarchy for Catec holamines MeSH_Cytoskeleto n.terms MeSH hierarchy for Cytoskeleto n MeSH_dopa mine.t erms MeSH dop amine-relate d terms MeSH_Heterocycl ic_Compoun ds_with_3 _rin gs.terms MeSH hierarchy for Heterocycl ic Compounds (3 ring s) MeSH_Heterocycl ic_Compoun ds_with_4 _rin gs.terms MeSH hierarchy for Heterocycl ic Compounds (4 ring s) MeSH_Heterocycl ic_Compoun ds_with_ bridged _rin gs MeSH hierarchy for Heterocycl ic Compounds (bridge d rin gs) MeSH_Hormon es.terms MeSH hierarchy for Hormones MeSH_Ment al_Disorders.terms MeSH hierarchy for Mental Disorders MeSH_Ment al_Processes.terms MeSH hierarchy for Mental Processes MeSH_Metab ol ic_Brain_Diseases.terms MeSH hierarchy for Metabol ic Pathways MeSH_Neural_Pat hways.terms MeSH hierarchy for Neural Pathw ays MeSH_Neurobeh avioral_Manifestatio ns.terms MeSH hierarchy for Neurobeh avioral Manifestations MeSH_ne urobeh avior. terms MeSH hierarchy for neurobeh avior MeSH_Neurodegen erative_Diseases.terms MeSH hierarchy for Neurodegen erative Diseases MeSH_Neurons.terms MeSH hierarchy for Neurons MeSH_Neurotoxicity_Disorders.terms MeSH hierarchy for Neurotoxici ty Disorders MeSH_Neurotransmitt er_Age nts.terms MeSH hierarchy for Neurotransmitter Age nts MeSH_Neurotransmitt er_Recept ors.terms MeSH hierarchy for Neurotransmitter Receptors MeSH_Neurotransmitt ers.terms MeSH hierarchy for Neurotransmitters MeSH_ne urotransmitt er.terms MeSH hierarchy for neurotransmitter MeSH_Neurotransmitt er_Transport_Proteins.terms MeSH hierarchy for Neurotransmitter Transort Proteins MeSH_Personal ity. terms MeSH hierarchy for Personal ity MeSH_Primat es.terms MeSH hierarchy for Primates MeSH_Rode ntia.t erms MeSH hierarchy for Rodentia MeSH_Sleep _Disorders.terms MeSH hierarchy for Slee p MeSH_Su bstance_Related _Disorders.terms MeSH hierarchy for Substance-relate d Disorders
Diverse, complex phenotypes can be represented as queries (predicates)-- denoting the set of all relevant documents
Phenomic Vocabularies as Lexica
PubMed / MEDLINE = central phenomics database
Query Expansion -- for Phenotypes
Queries (like “n-back test”) can be expanded with terms related to their target concept (like working memory), using statistical models to identify better expansions.
Expansion can improve precision and recall of queries that are being used as models of concepts/phenotypes
N-backWisconsin card sorting
Sternberg
Stroopchoice reaction time
…
paced auditory serial addition
("nback" OR “n-back” OR "wisconsin card sorting" OR "sternberg" OR "working memory capacity" OR "stroop" OR "choice reaction time" OR "paced auditory serial addition" OR "pasat" OR "digit span" OR "delayed match to sample")
"nback"
Summary PubAtlas as a tool for concept “BLASTing”
Lexica are concept bases / user-defined query languages PubAtlas constructs concept maps / literature maps Extends PubMed with temporal indexing Multiple features for exploration, visualization Real uses: semi-automated reviews, who is doing what, ... Many interesting directions for further work
Applications in Phenomics Phenotypes are often naturally represented as queries Promising applications in interdisciplinary collaboration
Thank you!