Published on May 18, 2015 by PMR
Basics of ContentMining presented to Synthetic Biologists. This was followed by a lively discussion of what components could be extracted from the literature
1. Mining Bioscience Literature
Peter Murray-Rust,
University of Cambridge and TheContentMine
SynBio, Cambridge UK, 2015-05-18
Much Scientific Data lies hidden in text and images, in articles, theses,
reports, patents, lab-books…
The ContentMine has Open collaborative tools that anyone can use to
find facts and re-use for their own research
2. http://www.nytimes.com/2015/04/08/opinion/yes-we-were-warned-about-
ebola.html
We were stunned recently when we stumbled across an article by European
researchers in Annals of Virology [1982]: “The results seem to indicate that
Liberia has to be included in the Ebola virus endemic zone.” In the future,
the authors asserted, “medical personnel in Liberian health centers should be
aware of the possibility that they may come across active cases and thus be
prepared to avoid nosocomial epidemics,” referring to hospital-acquired
infection.
Adage in public health: “The road to inaction is paved with research
papers.”
Bernice Dahn (chief medical officer of Liberia’s Ministry of Health)
Vera Mussah (director of county health services)
Cameron Nutt (Ebola response adviser to Partners in Health)
A System Failure of Scholarly Publishing
3. Scientific and Medical publication (STM)[+]
• World Citizens pay $400,000,000,000…
• … for research in 1,500,000 articles …
• … cost $300,000 each to create …
• … $7000 each to “publish” [*]…
• … $10,000,000,000 from academic libraries …
• … to “publishers” who forbid access to 99.9% of citizens of
the world …
• 85% of medical research is wasted (not published, badly
conceived, duplicated, …)
[+] Figures probably +- 50 %
[*] arXiV preprint server costs $7 USD per paper
4. The Right to Read is the Right to Mine
http://contentmine.org
5. Facts Marked by “non-scientists” in ContentMine workshops
With Wikipedia everyone can be a scientist
6. ContentMine Workshops and
Hackdays
Open Science Brazil, 2014-08
Easily distributed software
Get started in 30 mins
Build application
in a morning
Start simple: bagOfWords, Stemming, Regex, templates
8. OUR TEAM
@jenny_molloy
Ross Mounce
@rmounce
Richard Smith-
Unna
@blahah404
Stephanie Smith-
Unna
@treblesteph
Jenny Molloy
Mark
MacGillivray
@cottagelabs
Peter Murray-
Rust
@petermurrayrust
Charles Oppenheim
@CharlesOppenh
Graham
Steel
@McDawg
9. Workshops
(1-hour -> full day or more)
2014-May->Nov
• Budapest/Shuttleworth
• Leicester Univ
• Electronic Theses and Dissertations
• Austrian Science Fund AT
• OKFest DE
• Eur. Bioinformatics Institute
• Open Science Rio de Janeiro BR
• Sci DataCon , Delhi IN
• Univ of Chicago US
• OpenCon 2014, Wash DC. US
• JISC , London
2015
• LIBER
• Cochrane
• BL
• Wellcome Trust (April)
• WHO
Collaborators
• Wikimedia/Wikidata
• Mozilla
• Open Knowledge
• LIBER (European Research Libraries)
• British Library
• Wellcome Trust
• EBI (Eur. Bioinf. Inst.)
• JISC
• Open Access Button
• SPARC
• Creative Commons
• CORE
• EuropePubmedCentral
10. Content-Mining (TDM*)
• Now COMPLETELY LEGAL IN UK since 2014-06-01
(“Hargreaves”)…
• … Whatever the publishers tell you. Do NOT sign
their APIs
• UK can legally IGNORE contractual restrictions
• Movement to extend this to Europe (Julia Reda,
MEP proposal)
• And STM publishers are spending millions to stop
us
*Text and Data Mining
12. “nuggets” in a scientific paper
quantity
units
Value ranges
Humans aren’t designed to mine this …
chemical
project places
13. What is “Content”?
Emily Sena (neuroscience.ed.ac.uk) spends
half a day digitising a diagram like this
ContentMine will soon be able to do it in 1 second
14. • CRAWL the web for scientific documents
(articles, grey literature, repositories)
• quickSCRAPE pages (text, graphics, images, data)
• NORMA-lize page to semantic form
…Open semantic science …
• MINE pages with your methods and tools (AMI)
• CAT-alogue results in searchable index
• Automate daily process (CANARY)
contentmine.org Infrastructure
26. CLINICAL TRIALS
How to we find (mentions of) clinical trials?
Is a document a (clinical) trial?
What is the subject of the trial?
What is the methodology used? How many/long?
Does the design and practice conform to CONSORT?
What are the outcomes?
Can we extract specific re-usable information?
Who are involved? (researchers, sponsors, patients?)
Has a proposed trial been completed and reported?
31. Open Content Mining of FACTs
Machines can interpret chemical reactions
We have done 500,000 patents. There are >
3,000,000 reactions/year. Added value > 1B Eur.
32. Ln Bacterial load per fly
11.5
11.0
10.5
10.0
9.5
9.0
6.5
6.0
Days post—infection
0 1 2 3 4 5
Bitmap Image and Tesseract OCR
37. Problems
• Cannot do handwriting
• Scanned documents give poorer results
• The older the document the poorer the result
• Tables are a major problem
• Always try to get the original document
• XML better than > Word better than > PDF
• Vector images >> PNG > JPEG
• Maths, chemistry are specialist
38. POSSIBLE USES
• Indexing/searching the literature; G***** for science
• Current awareness; alerts and practices
• Extraction and re-use of facts; re-computation
• Multidisciplinary integration; co-occurrence
• Compliance with funder/institution policies
• Managing your Research Data!
• Finding similar and complementary colleagues
• Reproducibility, checking data and avoiding fraud
39. ContentMine Workshops and
Hackdays
Open Science Brazil, 2014-08
Easily distributed software
Get started in 30 mins
Build application
in a morning
Start simple: bagOfWords, Stemming, Regex, templates
Hi, I’m here to talk about AMI; a data extraction framework and tool. First, I just want highlight some of key contributors to the projects; Andy for his work on the ChemistryVisitor and Peter for the overall architecture.
In this talk, I’m going to impress the importance of data in a specific format and its utility to automated machine processing. Then I’m going to demonstrate AMI’s architecture and the transformation of data as it flows through the process. I’m going to dwell a little on a core format used, Scalable Vector Graphics (SVG) before introducing the concept of visitors, which are pluggable context specific data extractors. Next, I’m going to introduce Andy’s ChemVisitor, for extracting semantic chemistry data, along with a few other visitors that can process non-chemistry specific data. Finally, I will demonstrate some uses of the ChemVisitor, within the realm of validation and metabolism.
Because information is structured (some examples listed), we can aggregate similar objects and mine using a modular systematic approach.
Because information is structured (some examples listed), we can aggregate similar objects and mine using a modular systematic approach.
Can describe each collaboration, but keep this slide brief if the presentation is short.