The Arrowsmith Project: 2005 Status Report
(invited lecture for DS 2005)
Author: Neil R. Smalheiser
Affiliation: The Department of Psychiatry,
University of Illinois at Chicago, Chicago, U.S.A.
Source: Discovery Science, 8th International Conference,
DS 2005, Singapore, October 2005, Proceedings,
(Achim Hoffmann, Hiroshi Motada, Tobias Scheffer, Eds.),
Lecture Notes in Artificial Intelligence 3735, pp. 26 - 43, Springer 2005.
In the 1980s, Don Swanson proposed the concept of
“undiscovered public knowledge.” He
published several examples in which two disparate literatures (i.e., sets of articles
having no papers in common, no authors in common, and few cross-citations)
nevertheless held complementary pieces of knowledge that, when brought together, made
compelling and testable predictions about potential therapies for human disorders.
Joining Swanson in the 1990s, we published more predictions together and created a
computer-assisted search strategy (“Arrowsmith”).
At first, the so-called one-node
search was emphasized, in which one begins with a single literature (e.g., that
dealing with a disease) and searches for a second unknown literature having
complementary knowledge (e.g. that dealing with potential therapies). However, we soon
realized that the two node search is better aligned to the information practices of
most biomedical investigators: in this case, the user chooses two literatures and then
seeks to identify meaningful links between them.
Could typical biomedical investigators learn to carry out Arrowsmith analyses? Would
they find routine occasions for using such a sophisticated tool? Would they uncover
significant links that affect their experiments? Four years ago, with the support of
the Human Brain Project, we initiated a project to answer these questions, working
with several neuroscience field testers. Initially we expected that investigators
would spend several days learning how to carry out searches, and would spend several
days analyzing each search. Instead, we completely re-designed the user interface, the
back-end databases, and the methods of processing linking terms, so that investigators
could use Arrowsmith without any tutorial at all, and requiring only minutes to carry
out a search. The Arrowsmith Project now hosts a suite of free, public tools. It has
launched new research spanning medical informatics, genomics and social informatics,
and has, indeed, assisted investigators in formulating new experiments, with direct
impact on basic science and neurological diseases.
©Copyright 2005 Author