Difference between revisions of "Obvio"
(→Automatic Subgraph Creation) |
(→Demos) |
||
Line 453: | Line 453: | ||
'''Web Application:''' http://knoesis-hpco.cs.wright.edu/obvio/ <br /> | '''Web Application:''' http://knoesis-hpco.cs.wright.edu/obvio/ <br /> | ||
'''Video Demo:''' http://youtu.be/B-4gUelLJnc | '''Video Demo:''' http://youtu.be/B-4gUelLJnc | ||
+ | <br /> <br /> | ||
=Publications= | =Publications= |
Revision as of 17:51, 15 May 2014
Obvio (spanish for obvious) is a framework developed for leveraging structured knowledge representations and biomedical literature to facilitate Literature-Based Discovery (LBD). The broader goal of Obvio is to uncover hidden connections between concepts in biomedical texts, to support knowledge exploration and hypothesis generation from publicly available scientific literature. It utilizes several tools and resources developed at the National Library of Medicine (NIH-NLM), including MetaMap, SemRep, MEDLINE, SemMedDB, MeSH, UMLS, BKR and the UMLS Semantic Navigator.
Contents
People
Graduate Students: Delroy Cameron, Swapnil Soni, Nishita Jaykumar, Vishnu Bompally
External Collaborators: Thomas C. Rindflesch, Ramakanth Kavuluru, Olivier Bodenreider
Faculty: Krishnaprasad Thirunarayan, Amit P. Sheth (Advisor)
Past Members: Pablo N. Mendes, Tu Danh, Sreeram Vallabhaneni, Hima Yalamanchili, Drashti Dave
Overview
Obvio is driven by assertions extracted from biomedical literature (called semantic predications) as well as statements obtained from structured knowledge sources (such as the UMLS and MeSH). Semantic predications are extracted from MEDLINE using SemRep and made publicly available through the Semantic MEDLINE Database (SemMedDB). These semantic predications can be leveraged for various tasks, including: 1) Information Retrieval; 2) Question Answering (QA); 3) Document Summarization and 4) Literature-Based Discovery (LBD). They have been used in Obvio for Question Answering (QA) and LBD.
Applications
Reachability
We applied semantic predications to biomedical QA using data from the 2006 TREC Challenge. Our approach is based on the notion of reachability, which determines whether documents that answer complex biomedical questions could be connected. Semantic predications and structured background knowledge<ref>D. Cameron, R. Kavuluru, O. Bodenreider, P. N. Mendes, A. P. Sheth, K. Thirunarayan, Semantic Predications for Complex Information Needs in Biomedical Literature, 5th International Conference on Bioinformatics and Biomedicine (BIBM2011), Atlanta GA, November 12-15, 2011 (acceptance rate=19.4%)</ref> are key factors in establishing reachability. Our presentation from BIBM 2011 on applying predications and background knowledge for QA is shown below.
Rediscovery
The second application of semantic predications and structured background knowledge in Obvio is for Literature-based Discovery (LBD). Specifically, we applied these elements to first prove that they can be used successfully to rediscover existing knowledge. A graph-based approach for knowledge rediscovery was developed and successfully applied to recover and decompose Don R. Swanson's Raynaud Syndrome - Dietary Fish Oils Hypothesis from 1986.
RS-DFO Hypothesis
Much of the early research aimed at rediscovering Swanson's Hypotheses focused almost entirely on Information Retrieval (IR) techniques, such as term and concept co-occurrence. Only recently has significant attention been devoted to semantics-based techniques that exploit the meaning of associations between concepts. While generally more intuitive, the feasibility of such semantics-based approaches has not been fully established. It is reasonable to expect that if semantics-based techniques are adequate for discovering new knowledge, they ought to be sufficient for recovering existing knowledge.
In this work<ref>D. Cameron, O. Bodenreider, H. Yalamanchili, T. Danh, S. Vallabhaneni, K. Thirunarayan, A. P. Sheth, T. C. Rindflesch, A Graph-Based Recovery and Decomposition of Swanson’s Hypothesis using Semantic Predications, Journal of Biomedical Informatics 46(2) 238-251, (2013). ScienceDirect, PMID </ref> we investigate the applicability of semantics-based techniques for recovering and decomposing Swanson's Raynaud Syndrome--Fish Oil hypothesis using semantic predications, background knowledge and graph-based algorithms for path extraction and subgraph creation. Below is a presentation, and various datasets and experimental results for download and consumption based on our investigation.
Datasets and Experimental Results
- Dataset
- Baseline (B1)
- Original PDFs of the 65 articles cited by Swanson's RS-DFO paper (30.5MB)
- ASCII text with end-of-line text wrapping fixed
- Text in Medline format for parsing by SemRep
- SemRep Relations Output
- SemRep Relations Output (vascular reactivity)
- SemRep Extracted Predications
- Manually Identified Predications (vascular reactivity)
- Baseline (B2)
- Baseline (B1)
- Experimental Results
Automatic Subgraph Creation
We developed an approach to automatically generate subgraphs, which capture complex associations between two concepts<ref>D. Cameron, R. Kavuluru, T. C. Rindflesch, A. P. Sheth, K. Thirunarayan, O. Bodenreider Context-Driven Automatic Subgraph Creation for Literature-Based Discovery (under preparation)</ref> (called closed discovery). The method not only creates complex associations between concepts, but creates several subgraphs, along different thematic dimensions of association between the source and target concepts. The generated subgraphs facilitated the rediscovery of 8 out of 9 existing scientific discoveries. Each rediscovery scenario is covered in the following tables. The corresponding subgraphs for each association (in each rediscovery scenario) can be explored using our live web application: http://knoesis-hpco.cs.wright.edu/obvio/. A video demo is also available online.
Legend
Not Found | |
Found | |
subgraph x | x (subgraph number) |
singleton y | y (singleton number), where a singleton is a subgraph consisting of only one path |
zero rarity singleton | a single-path subgraph (or singleton) whose concepts never occur together in any article in MEDLINE |
Scenario 1 | Intermediate | Association | Status | |||
---|---|---|---|---|---|---|
Source | Target | Details | ||||
Dietary Fish Oils | Raynaud Syndrome | Cut-off Date: November 1985 By: Don R. Swanson |
Blood Viscosity | Dietary Fish Oils INHIBITS Blood Viscosity | Blood Viscosity CAUSES Raynaud Syndrome | zero rarity singleton15 |
Platelet Aggregation | Dietary Fish Oils INHIBITS Platelet Aggregation | Platelet Aggregation CAUSES Raynaud Syndrome | subgraph1 | |||
Vascular Reactivity | Dietary Fish Oils INHIBITS Vasoconstriction | Vasoconstriction CAUSES Raynaud Syndrome |
Scenario 2 | Intermediate | Association | Status | |||
---|---|---|---|---|---|---|
Source | Target | Details | ||||
Magnesium | Migraine | Cut-off Date: April 1987 By: Don R. Swanson | ||||
Calcium Channel Blockers | Magnesium ISA Calcium Channel Blocker | Calcium Channel Blockers TREATS Migraine | subgraph22 | |||
Epilepsy | Magnesium AFFECTS Epilepsy | Epilepsy COEXISTS_WITH Migraine | subgraph9 | |||
Hypoxia | Magnesium INHIBITS Hypoxia | Hypoxia ASSOCIATED_WITH Migraine | ||||
Inflammation (Brain Edema, Hydrocephalus) | Magnesium INHIBITS Inflammation | Inflammation CAUSES Migraine | zero rarity singleton3 | |||
Platelet Activity | Magnesium INHIBITS Platelet Aggregation | Platelet Aggregation CAUSES Migraine | subgraph1 | |||
Prostaglandins | Magnesium STIMULATES Prostaglandins | Prostaglandins DISRUPTS Migraine Disorders | subgraph4 | |||
Stress/Type A Personality | Stress INHIBITS Magnesium | Stress ASSOCIATED_WITH Migraine | ||||
Serotonin | Magnesium INHIBITS Serotonin | Serotonin CAUSES Migraine | subgraph1 | |||
Cortical Depression | Magnesium INHIBITS Spreading Cortical Depression | Spreading Cortical Depression CAUSES Migraine | ||||
Substance P | Magnesium INHIBITS Substance P | Substance P CAUSES Migraine | ||||
Vascular Mechanisms | Magnesium INHIBITS Vasoconstriction | Vasoconstriction CAUSES Migraine | subgraph9 |
Scenario 3 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Somatomedin C | Arginine | April 1989 | Don R. Swanson (Pubmed Central) | Growth Hormone | Arginine STIMULATES Growth Hormone | Growth Hormone STIMULATES Somatomedins | subgraph5 |
Body Weight (body mass) | Somatomedins (IGF1) STIMULATES Growth | Arginine STIMULATES Growth | subgraph7 | ||||
Malnutrition | Somatomedins TREATS Malnutrition | Arginine TREATS Malnutrition | subgraph7 | ||||
Wound Healing (NK activity) | Somatomedin STIMULATES Wound Healing | Arginine STIMULATES Wound Healing |
Scenario 4 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Indomethacin | Alzheimer’s Disease | July 1995 | Neil R. Smalheiser/Don R. Swanson (J. Neurol) | Acetylcholine | Indomethacin INHIBITS Acetylcholine | Acetylcholine CAUSES Alzheimer's Disease | subgraph4 |
Lipid peroxidation | Indomethacin INHIBITS Lipid peroxidation | Lipid peroxidation CAUSES Alzheimer's Disease | subgraph2 | ||||
M2-muscarinic | Indomethacin INHIBITS M2-muscarinic | M2-muscarinic CAUSES Alzheimer's Disease | |||||
Membrane Fluidity | Indomethacin INHIBITS Membrane Fluidity | Membrane Fluidity CAUSES Alzheimer's Disease | |||||
Lymphocytes | Indomethacin STIMULATES natural killer T-Cell Activity | T-Cell Activity INHIBITS Alzheimer's Disease | subgraph14 | ||||
Thyrotropin | Indomethacin STIMULATES Thyrotropin | Thyrotropin AFFECTS Alzheimer's Disease | zero rarity singleton20 | ||||
T-lymphocytes (T-Cells) | Indomethacin STIMULATES T-lymphocytes | T-lymphocytes Activity INHIBITS Alzheimer's Disease | subgraph3 |
Scenario 5 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Estrogen | Alzheimer’s Disease | July 1995 | Neil R. Smalheiser/Don R. Swanson (Pubmed) | Antioxidant activity | Estrogen INHIBITS Antioxidant activity | Antioxidant activity CAUSES Alzheimer's Disease | subgraph4 |
Alipoprotein E (ApoE) | Estrogen INHIBITS ApoE | ApoE CAUSES Alzheimer's Disease | subgraph3 | ||||
Calbindin D28k | Estrogen REGULATES Calbindin D28k | Calbindin D28k AFFECTS Alzheimer's Disease | subgraph4 | ||||
Cathepsin D | Estrogen STIMULATES Cathepsin D | Cathepsin D PREVENTS Alzheimer's Disease | |||||
Cytochrome C oxidase subunit III | Estrogen STIMULATES Cytochrome Coxidase subunit III | Cytochrome Coxidase subunit III AFFECTS Alzheimer's Disease | |||||
Glutamate | Estrogen STIMULATES Glutamate | Glutamate AFFECTS Alzheimer's Disease | |||||
Receptor Polymorphism | Estrogen EXHIBITS Receptor Polymorphism | Receptor Polymorphism AFFECTS Alzheimer's Disease |
Scenario 6 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Calcium-Independent PLA2 | Schizophrenia | 1997 | Neil R. Smalheiser/Don R. Swanson (Pubmed) | Oxidative stress | Oxidative Stress INHIBITS Calcium-Independent PLA2 | Oxidative stress CAUSES Schizophrenia | singleton2 |
Selenium | Selenium INHIBITS Calcium-Independent PLA2 | Selenium PREVENTS Schizophrenia | singleton2 | ||||
Vitamin E | Vitamin E STIMULATES Calcium-Independent PLA2 | Vitamin E PREVENTS Schizophrenia | singleton2 |
Scenario 7 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Chlorpromazine | Cardiac Hypertrophy (Cardiomegaly) | 2002 | Jonathan D. Wren (PubMed) | Calcineurin | Chlorpromazine INHIBITS Calcineurin | Calcineurin CAUSES Cardiac Hypertrophy | subgraph5 |
Isoproterenol | Chlorpromazine INHIBITS Isoproterenol | Isoproterenol CAUSES Cardiomegaly | subgraph12 |
Scenario 8 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Testosterone | Sleep | 2011 | Christopher M. Miller/Thomas C. Rindflesch (PubMed) | Cortisol/Hydrocortisone | Testosterone INHIBITS Hydrocortisone | Hydrocortisone DISRUPTS Sleep | subgraph7 |
Scenario 9 | Intermediate | Association | Status | ||||
---|---|---|---|---|---|---|---|
Source | Target | Details | |||||
Diethylhexyl phthalate (DEHP) | Sepsis | 2013 | Michael J. Cairelli/Thomas C. Rindflesch (PubMed Central) | PParGamma | DEHP STIMULATES PParGamma | PParGamma INHIBITS Sepsis |
Demos
Web Application: http://knoesis-hpco.cs.wright.edu/obvio/
Video Demo: http://youtu.be/B-4gUelLJnc
Publications
<references/>
SWLBD Workshop
Kno.e.sis and the National Library of Medicine (NLM) organized The First International Workshop on the role of Semantic Web in Literature-Based Discovery (SWLBD2012) in conjunction with The IEEE Conference on Bioinformatics and Biomedicine (BIBM2012) in Philadelphia PA, USA.
- Due date for full workshop papers submission: Aug 6, 2012
- Notification of paper acceptance to authors: August 28, 2012
- Camera-ready version of accepted papers: September 4, 2012
- Workshop: October 4, 2012
Internal
Obvio Web App
Automatic Subgraph Creation
Recovery and Decomposition
Reachability
Contact: Delroy Cameron