Beyond Genes, Proteins, and Abstracts:

A Framework to Capture Scientific Claims

Catherine Blake

School of Information and Library Science

University of North Carolina at Chapel Hill

http://www.ils.unc.edu/~cablakecablake@email.unc.edu

2

Motivation• Relentless increase in electronically

available text– Life Sciences

• The NLM added the 17 millionth entry to PubMed in April 2007

• 5,200 journals indexed• 12,000 new articles each week !

– Chemistry – more than 110,000 articles in 1 year alone

• Consequences:– Hundreds of thousands of relevant articles– Implicit connections between literature go

unnoticed

Shift from Retrieval to Synthesis

Entity Extraction

• Newspaper genre– People, places, and organizations– Message Understanding Conference

(MUC)• Biomedical genre

– Genes and proteins – Diseases and treatments– Chemical compounds– Challenges: BioCreative , GENIA,

JNLPBA3

Relationship Extraction

• Newspaper genre– Person moving from one company to

another• Biomedicine genre

– genes and proteins e.g. binds, inhibits

– ARBITER (Rindflesch, Rajan, & Hunter, 2000)

– Geneways (Rzhetsky, et al, 2004)– relEx (Fundel, Kuffner, & Zimmer,

2007)– GENIA

www-tsujii.is.s.u-tokyo.ac.jp/GENIA

4

Causal Relationships

• Newspaper genre– Causal relationships (Khoo, Chan, &

Niu, 1998)• Biomedical genre

– Causes and treats (Price & Delcambre, 2005)

– Causal knowledge (Khoo, Chan, Niu, 2000)

• Universal Grammar – Causatives (Comrie, 1974, 1981)– Action verbs (Thomson, 1987)

5

Claim Definition

• “To assert in the face of possible contradiction”

• Example sentence reporting a claim– “This study showed that Tamoxifen

reduces the breast cancer risk”• Example Claim Framework

– Tamoxifenagent

– reduceschange

– [breast cancer risk] object6

Goals• Create a Framework that reflects

how claims made in biomedical literature

• The Framework should– generalize beyond biomedicine– differentiate between different

levels of confidence in the claim– consider claims made in the full text

• Populate the Framework automatically

7

The Claim Framework

• Information facets– concepts– change– basis of the claim

• Each information facet may have– modifiers– directionality

8

The Claim Framework

9

CategoryConcept

AConcept

B

Nature of

change

Claim Basis

1. Explicit Claim

Agent Object Required Optional

2. Implicit Claim

Agent Object Optional Optional

3. Correlation

Required Required Required Optional

4. Comparison

Required Required Required Required

5. Observation

N/A Required Required Optional

Explicit Claims

Indeed, glycine prevented Wy-14643-stimulated superoxide production by Kupffer cells.

Claim 1– glycineagent –

preventedchange – [Wy-14643-stimulated superoxide

production]object

Claim 2– [Kupffer cells]agent –

produceschange

– [Wy-14643-stimulated superoxide]object.

10

Implicit Claims

In liver the number of peroxisomes increases from about 500-600/cell to > 5000/cell after exposure to peroxisome proliferators.

Claim 1– [Peroxisomes proliferators] agent

– increaseschangeDirection

– Peroxisomesobject

– [In the liver]agentModifier – [number]agentModifier

11

Correlations

A weak but statistically significant correlation was observed between the plasma nm23-H1 level and the WBC count (Figure 1, n=102, r=0.437, P<0.0001)– [plasma nm23-H1 level] agent

– [WBC count] object

– correlation change

– [statistically significant] changeModifier12

Comparisons

The plasma concentration of nm23-H1 was higher in patients with AML than in normal controls (P = .0001)

Claim 1– [plasma concentration of nm23-H1]

basis of claim

– [Patients with AML]agent

– higher changeDirection

– [normal controls]object

13

Observations

However, the plasma nm21-H1 protein level was increased in SML-M3 patients (P=.0002)

Claim 1– [nm21-H1 protein level]object

– IncreasedchangeDirection

– [SML-M3 patients]objectModifier

14

Working Hypothesis 1

The Claim Framework reflects how a scientist communicates her findings

– Full text documents randomly selected from biomedical literature will report findings using constructs within the Claim Framework

– Human annotators will agree on facets within the Claim Framework

– The Claim Framework will generalize to a variety of scientific literatures

15

Working Hypothesis 2

Facets within the Claim Framework can be populated automatically

– The system will detect all claims identified by the human annotators (i.e. recall)

– The system will only identify claims that were identified by the human annotators (i.e. precision)

– The system design will generalize to new literatures by avoiding domain specific constructs

16

Validating the Claim Framework

• Draft Claim Framework given to two annotators

• Pilot Study: Identify every claim– Include claims that don’t conform to the

framework– Don’t consider how this will be

automated

17

Validating the Claim Framework

• Main study– 25 articles

• Verification– Random set

of sentences annotated twice

– Feedback provided daily

18

Results• All documents

– Total number of sentences: 5535 – Sentences with >=1 claim: 1250

(22.6%)– Total number of claims: 3228– Average claims per sentence: 2.51 – Claims that did not fit in the

Framework: 31• Per document

– Average number of sentences: 191 – Average number of sentences with

>=1 claim:43

19

Distribution of Claim Categories

20

Category Total (%) Pilot(%) Main(%)

Explicit 2489 77.11 332 83.42 215776.6

3

Implicit 87 2.70 3 0.75 84 2.98Observation 298 9.23 24 6.03 274 9.73Correlation 174 5.39 12 3.02 162 5.75Comparison 165 5.11 27 6.85 138 4.9

Total 3228 100 398 100 2830 100

21

All DocumentsAnnotation Total (%) Words (Avg)Agent 2894 89.65 5221 1.80Agent Direction 285 8.83 291 1.02Agent Modifier 1246 38.60 4448 3.57Object 3197 99.04 6849 2.14Object Direction 271 8.40 283 1.04Object Modifier 1561 48.36 5383 3.44Change 1897 58.77 1953 1.03Change Direction 1337 41.42 1358 1.02Change Modifier 1147 35.53 1618 1.41Claim Basis 165 5.11 394 2.39Claim Basis Dir. 42 1.30 43 1.02Claim Basis Mod. 86 2.66 266 3.09

Total 3228   28107 8.70

Inter Annotator Agreement

Information Facet KappaAgreement

Agent 0.71 substantial

Object 0.77 substantial

Change 0.57 moderate

Change+ChangeDir 0.88 almost perfect

22

Location of Claims

23

Total Sentences  With % %

SectionClaim

Total

section

claim

Abstract 98 309 31.72 7.84

Introduction 357 979 36.4728.5

6Method 6 1121 0.54 0.48

Result 293 1829 16.0223.4

4

Discussion 539 1406 38.3443.1

2

Total 1250 5535 22.58100.

00

Findings thus far

• 99% of the claims made in these articles could be captured in the Claim Framework

• 22% of sentences report at least 1 claim

• 77% of the claims identified were explicit

• 8% of claims are made in the abstract

• Agreement– substantial between agents and

objects – almost perfect for change and change

direction

24

Acknowledgements– This project supported in part by

– Renaissance Computing Institute (RENCI) Faculty Fellowship Program

– NSF Center for Environmentally Responsible Solvents and Processes (CERSP CHE-9876674)

– This project used resources provided by – the OSG, which is supported by the

NSF & the U.S. Department of Energy's Office of Science

• The speaker thanks• Nassib Nassar and Mats Rynge

(RENCI)• Amol Bapat and Ryan Jones (SILS)

Questions and Comments Welcome

Catherine Blakecablake@email.unc.edu

http://www.ils.unc.edu/~cablakeSchool of Information and Library

ScienceUniversity of North Carolina at Chapel

Hill