piwowar amia 2008: identifying data sharing in biomedical literature
DESCRIPTION
Many policies and projects now encourage investigators to share their raw research data with other scientists. Unfortunately, it is difficult to measure the effectiveness of these initiatives because data can be shared in such a variety of mechanisms and locations. We propose a novel approach to finding shared datasets: using NLP techniques to identify declarations of dataset sharing within the full text of primary research articles. Using regular expression patterns and machine learning algorithms on open access biomedical literature, our system was able to identify 61% of articles with shared datasets with 80% precision. A simpler version of our classifier achieved higher recall (86%), though lower precision (49%). We believe our results demonstrate the feasibility of this approach and hope to inspire further study of dataset retrieval techniques and policy evaluation.TRANSCRIPT
Identifying data sharingin the biomedical literature
Heather Piwowar and Wendy Chapman
Department of Biomedical Informatics, U of Pittsburgh
Visualized as a “Wordle” (font size ~ word frequency, location and orientation are random)
Our full paper:
Created at IBM’s data sharing and visualization site Many Eyes
Our aim:
Identify research articles for which the authors have shared their datasets
For this research:
sharing = submitted to centralized databases
Links between article and dataare important
The data provides detail for the results of the article
The article provides detail for the data
Specialized searching methods help us find articles OR data...
but what about when we want articles WITH data?
How can we find articles that have shared their datasets?
Sometimes the links are easy to discover
1. Through database citations:
When authors upload data to a database, they have the opportunity to cite the paper that describes the data collection
Text
Unfortunately, the citation is often left blankbecause the data is submitted before
the paper is published
2. Through hyperlink urls in the text
Authors often reference their datasets within their paper with a website url
But the meaning of the hyperlinks is ambiguous. Sometimes they point to datasets that have been
accessed, rather than submitted.
But the meaning of the hyperlinks is ambiguous. Sometimes they point to datasets that have been
accessed, rather than submitted.
And often the text contains no hyperlinks at all:
3. Through text mining
What if we could extract phrases like
“data of the experiment can be accessed at”
full-text phrases containing “... accessed”
“can be accessed” suggests data is shared
BUT “was/were accessed” suggests data reuse!
full-text phrases containing “... downloaded”
“was/were downloaded” suggests data reuse
while “can be downloaded” suggests data sharing
Our aim:
Identify research articles for which the authors have shared their raw datasets.
Proposed approach:
Develop a system to identify statements of shared data from an article’s full text.
Materials:
Full text from a subset of the open access literature
Database submission citations from five databases:
• Genbank
• Protein Data Bank
• Gene Expression Omnibus
• ArrayExpress
• Stanford Microarray Database
Our Gold standard:
An article was considered to have a “shared dataset” if the article was cited within the primary submission field of a database entry
(+ a small amount of manual screening to find additional positives based on full text)
Approach:
For those articles that mention database names,
• Extract a 300-character window around every mention of a database name
• Apply various mining algorithms to decide if there is evidence that the authors deposited data from this study in the database
Results:
• queried 24 000 articles across 27 journals
• 25% of all open access articles mentioned one of the database names (50% Genbank)
• development set of 4434 articlestraining set of 2000test set of 1028
True positives:
23% of the articles that mentioned a database were cited from within a database submission field
= evidence that article shared its data!
Three simple methods for identifying sharing
Does the excerpt surrounding the database name contain:
1. the word “accession”
2. an accession number
3. a URL
Two complex methods:
4. A manually-derived regular expression to match lexical cues that suggest sharing
5. An automatically-derived bag of words decision tree
Snippet of manually-developed regular expression
wehavehasisarewaswerebebeen
+
accessionedaddedarchivedassigneddepositedenteredimportedincludedinsertedloadedlodgedplacedpostedprovidedregisteredreported tostoredsubmitteduploaded to
How accurately were these methods able to identify papers with evidence of public database submissions?
Recall: % of papers cited in database submission fields that were found by our methods
Recall: % of papers cited in database submission fields that were found by our methods
Best method for
recall depends on
database
Recall: % of papers cited in database submission fields that were found by our methods
“accession”good for
some, <url> for others
Recall: % of papers cited in database submission fields that were found by our methods
lexical regular
expressions do well overall
Precision: % of papers found by our methods that were cited in database submissions fields
Precision: % of papers found by our methods that were cited in database submissions fields
lexical regular
expressions do well overall,
bag-of-words doeseven better
Precision: % of papers found by our methods that were cited in database submissions fields
Precision of simple
patterns depends on
database
Precision: % of papers found by our methods that were cited in database submissions fields
Simple patterns do poorly on the most popular
databases (those with the most
statements of reuse?)
Precision vs. Recall plot of all methods for each database.
Diverse!
<url>
bag of words
“accession”
<accession>
<lexical patterns>
Relative strength of methods for this taskacross databases
Limitations:
• bias due to manual screening of negatives
• database-centric classifier
• approach requires computational access to literature full text!
Impact:
• A recent version that runs in PubMed Central:
• could increase GEO article links by 2.6%
• by 5.5% annually when all NIH in PMC
• double the recall (to 80%), double these estimates
• 40 links already added by GEO staff!
Ongoing work:
1. Continue focusing on methods that use existing full-text query interfaces, like PubMed Central
2. Use this tool to evaluate the patterns and prevalence ofbiomedical research data sharing and reuse
Thanks to
the Dept of Biomedical Informatics at the U of Pittsburgh,
the NLM for funding through training grant 5 T15 LM007059-22,
and everyone who publishes “gold” open access, thereby facilitates reuse of article full text for studies like this.
My shared data: www.dbmi.pitt.edu/piwowarShare your research data too!
Our manual filter for additional positive classifications identified more cases in some databases than others: we
reclassified 19% of [article,database] cases from ArrayExpress as positive despite an omitted literature
link, compared to 11%, 7%, 2%, and 1% for GEO, Genbank, PDB, and SMD respectively (see Table 2 for raw number of cases). The most common situations included: the
database entry listed a citation for another paper by the same authors, the entry listed an erroneous PubMed ID,
the entry included a citation without a PubMed ID, or the entry had a blank citation field.
Usage?
• scientists looking for datasets for reuse
• curators looking for primary citations
• researchers studying data sharing behaviour
Regular expression
• Precise one +
• "(\b(accession.{0,20}(for|at).{0,100}(is|are)))",
• r"(\b(raw|original|our|complete|detailed).{0,20}data)",
• r"(\b(we|have|is|was|were|is|are|be|have|has|been).(exported|gave|given|listed|provided|reported))"
• ]) + ")"
Precise Regular expression
• wehavehasisarewaswerebebeen
accessioned|added|archived|assigned|deposited|entered|imported|included|inserted|loaded|lodged|placed|posted|provided|registered|reported.to|stored|submitted|uploaded.to))",
is|are|will.be|made).{0,20}(available|accessible)
(be).(accessed|browsed|downloaded|found|obtained|queried|retrieved|searched|viewed)
(through|under|as).{0,20}accession
(given)|new|received|assigned).{0,20}(accession)
(data.{0,20}availability|for public distribution|for.{0,20}release upon publication|for the.{0,20}data.{0,20}generated|from this study have.{0,20}accession|data.{0,10}from this study|access to.{0,20}data.
Stopwords are important!
Recall
Precision
• queried 24 000 articles across 27 journals
• 25% mentioned one of the database names
• development set of 4434 training set of 2000test set of 1028
Evaluation
Research data
http://upload.wikimedia.org/wikipedia/commons/7/76/PeptideMSMS.jpg; http://en.wikipedia.org/wiki/Image:Helices.png; http://en.wikipedia.org/wiki/Image:Heatmap.png; http://en.wikipedia.org/wiki/Image:Microarray2.gif;
http://zellig.cpmc.columbia.edu/medlee/demo/; htp://www.plosone.org/article/fetchArticle.action?articleURI=info:doi/10.1371/journal.pone.0000441
Research data
http://upload.wikimedia.org/wikipedia/commons/7/76/PeptideMSMS.jpg; http://en.wikipedia.org/wiki/Image:Helices.png; http://en.wikipedia.org/wiki/Image:Heatmap.png; http://en.wikipedia.org/wiki/Image:Microarray2.gif;
http://zellig.cpmc.columbia.edu/medlee/demo/; htp://www.plosone.org/article/fetchArticle.action?articleURI=info:doi/10.1371/journal.pone.0000441
PAST MEDICAL HISTORY:Past medical history showed she had superficial phlebitis times two in the past, had non-insulin
dependent diabetes mellitus for four years.She had been hypothyroid for three years.
HISTORY OF PRESENT ILLNESS:The patient is a 58-year-old female, …
Research data
http://upload.wikimedia.org/wikipedia/commons/7/76/PeptideMSMS.jpg; http://en.wikipedia.org/wiki/Image:Helices.png; http://en.wikipedia.org/wiki/Image:Heatmap.png; http://en.wikipedia.org/wiki/Image:Microarray2.gif;
http://zellig.cpmc.columbia.edu/medlee/demo/; htp://www.plosone.org/article/fetchArticle.action?articleURI=info:doi/10.1371/journal.pone.0000441
PAST MEDICAL HISTORY:Past medical history showed she had superficial phlebitis times two in the past, had non-insulin
dependent diabetes mellitus for four years.She had been hypothyroid for three years.
HISTORY OF PRESENT ILLNESS:The patient is a 58-year-old female, …
Research data
http://upload.wikimedia.org/wikipedia/commons/7/76/PeptideMSMS.jpg; http://en.wikipedia.org/wiki/Image:Helices.png; http://en.wikipedia.org/wiki/Image:Heatmap.png; http://en.wikipedia.org/wiki/Image:Microarray2.gif;
http://zellig.cpmc.columbia.edu/medlee/demo/; htp://www.plosone.org/article/fetchArticle.action?articleURI=info:doi/10.1371/journal.pone.0000441
PAST MEDICAL HISTORY:Past medical history showed she had superficial phlebitis times two in the past, had non-insulin
dependent diabetes mellitus for four years.She had been hypothyroid for three years.
HISTORY OF PRESENT ILLNESS:The patient is a 58-year-old female, …
Research data
http://upload.wikimedia.org/wikipedia/commons/7/76/PeptideMSMS.jpg; http://en.wikipedia.org/wiki/Image:Helices.png; http://en.wikipedia.org/wiki/Image:Heatmap.png; http://en.wikipedia.org/wiki/Image:Microarray2.gif;
http://zellig.cpmc.columbia.edu/medlee/demo/; htp://www.plosone.org/article/fetchArticle.action?articleURI=info:doi/10.1371/journal.pone.0000441
PAST MEDICAL HISTORY:Past medical history showed she had superficial phlebitis times two in the past, had non-insulin
dependent diabetes mellitus for four years.She had been hypothyroid for three years.
HISTORY OF PRESENT ILLNESS:The patient is a 58-year-old female, …
Research data
http://upload.wikimedia.org/wikipedia/commons/7/76/PeptideMSMS.jpg; http://en.wikipedia.org/wiki/Image:Helices.png; http://en.wikipedia.org/wiki/Image:Heatmap.png; http://en.wikipedia.org/wiki/Image:Microarray2.gif;
http://zellig.cpmc.columbia.edu/medlee/demo/; htp://www.plosone.org/article/fetchArticle.action?articleURI=info:doi/10.1371/journal.pone.0000441