Some nanoinformatics challenges
are, for instance, information
management and search, creation
of taxonomies and classifications
for nanomaterials, the construction
of nanomaterials databases,
infrastructures for R&D in nano-
technology, or new models and
simulations of nanoparticles,
among others. We have reported
the first reviews of the field and
carried out research on various
areas: (i) development of an
inventory of nano resources, (ii)
text mining-based research to
extract information of nanoparti-
cles from the scientific literature,
(
iii) a nanotoxicity searcher, (iv)
creation and definition of the area
“
Translational Nanoinformatics”,
and (v) a new scientific approach
to build visual, "morphospatial"
taxonomies of nanoparticles. We
led ACTION-Grid, the first EC
project on nanoinformatics.
References:
Maojo V, Martin-Sanchez F, Kulikowski C,
Rodriguez-Paton A, Fritts M. Nanoinfor-
matics and DNA-Based Computing:
Catalyzing Nanomedicine. Pediatric
Research 2010
García-Remesal M, García-Ruiz A, Pérez-
Rey D, de la Iglesia D, Maojo V. Using
nanoinformatics methods for automati-
cally identifying relevant nanotoxicology
entities from the literature. Biomed Res
Int 2013
Maojo V, Fritts M, Martin-Sanchez F, De la
Iglesia D, Cachau RE et al. Nanoinforma-
tics: developing new computing applica-
tions for nanomedicine. Comput Sci Eng
2012
de la Iglesia D, Maojo V, Chiesa S, Martin-
Sanchez F, Kern J, Potamias G, Crespo J,
Garcia-Remesal M, Keuchkerian S,
Kulikowski C, Mitchell JA.International
efforts in nanoinformatics research
applied to nanomedicine.Methods Inf
Med. 2011
Maojo V, Fritts M, de la Iglesia D, Cachau
RE, Garcia-Remesal M, Mitchell JA,
Kulikowski C. Nanoinformatics: A new
area of research in nanomedicine.
International Journal of Nanomedicine
2012
Mark D Hoover, Nathan A Ba-
ker, Frederick Klaessig, Stacey Har-
per, Juli Klemm and Victor Maojo.
Nanoinformatics: Principles and Practice.
Elsevier 2014 (in preparation)
We have used computational
ontologies in topics such as ontolo-
gy-based data integration, query
homogenization, data cleaning and
mining, clinical-genomic trials,
information extraction and retriev-
al, text mining, building biomedical
vocabulary servers, nanoinformat-
ics research, or developing cancer
ontologies. We have also intro-
duced a fundamental challenge,
proposing a new approach for
building “morphospatial” and visual
taxonomies of shapes, represent-
ing the kind of graphical, “visual”
information that is inherent to the
shapes of entities such as mole-
cules, organs, nanoparticles,
viruses, etc.
In 1997 the GIB decided to build a
system —the first in the world— to
access Pubmed using MeSH terms
in Spanish. Once the terms are
specified in Spanish they are
automatically translated to English
and the query is submitted via
Web to the NLM server.
References:
Alonso-Calvo R, Maojo V, Billhardt H,
Martin-Sanchez F, García-Remesal M,
Pérez-Rey D. An agent- and ontology-
based system for integrating public gene,
protein, and disease databases. J Biomed
Inform 2007
Pérez-Rey D, Maojo V, García-Remesal M,
Alonso-Calvo R, Billhardt H, Martin-
Sánchez F, Sousa A. ONTOFUSION:
ontology-based integration of genomic
and clinical databases. Comput Biol Med
2006
Maojo V, Crespo J, García-Remesal M, de
la Iglesia D, Perez-Rey D, Kulikowski C.
Biomedical ontologies: toward scientific
debate. Methods Inf Med 2011
Rodríguez, J, Maojo, V, Crespo, J.,
Fernandez.I. A Concept Model for the
Automatic Maintenance of Controlled
Medical Vocabularies. Proceedings of
Medinfo 1998
Rodriguez J, Maojo V, Crespo J, Fernan-
dez I. A concept model for the automatic
maintenance of controlled medical
vocabularies. Proceedings of Medinfo
1998
We created the BioInformatics
Resource Inventory (BIRI) for
automatically discovering and
indexing available public bioinfor-
matics, later expanded to medical
and nano resources using infor-
mation extracted from the scien-
tific literature. We also worked on
the identification and extraction of
DNA sequences and automated
database population. Data report-
ed in the biomedical literature are
an aid for primer and probe design
for microorganism identification,
genotyping and gene expression
studies. Unfortunately, there are
only a few online databases
established as repositories for
empirically validated primer and
probe sequences. Thus, we creat-
ed an original method for automat-
ically detecting and extracting
infectious disease-related primer
and probe sequences from scien-
tific papers, applied to all the
PubMed Central repository. The
data extracted from the manu-
scripts were then fed into the
PubDNA finder database, the first
public online resource linking
scientific papers to sequences of
nucleic acids.
References:
de la Calle G, García-Remesal M, Chiesa
S, de la Iglesia D, Maojo V. BIRI: a new
approach for automatically discovering
and indexing available public bioinformat-
ics resources from the literature. BMC
Bioinformatics 2009
García-Remesal M, Cuevas A, Pérez-Rey
D, Martín L, Anguita A, de la Iglesia D, de
la Calle G, Crespo J, Maojo V. PubDNA
Finder: a web database linking full-text
articles to sequences of nucleic acids.
Bioinformatics 2010
García-Remesal M, Cuevas A, López-
Alonso V, López-Campos G, de la Calle G,
de la Iglesia D, Pérez-Rey D, Crespo J,
Martín-Sánchez F, Maojo V. A method for
automatically extracting infectious
disease-related primers and probes from
the literature. BMC Bioinformatics 2010
Maojo V, Martin-Sanchez F. Bioinforma-
tics: towards new directions for public
health. Methods Inf Med. 2004
In 1995 we carried out a perfor-
mance comparative analysis
between traditional rule-induction
algorithms and clustering-based
constructive rule induction algo-
rithms. As a benchmark, a data-
base of rheumatoid arthritis (RA)
from the Hospital 12 de Octubre
was used. A set of clinical predic-
tion rules for prognosis in RA was
obtained by applying the most
successful methods, selected
according to the study outcomes.
A panel of medical specialists in RA
chose 21 predictive variables and
the outcomes. By comparing
artificial neural networks, induction
and clustering techniques, we
were available to extract clinical
prediction rules that were success-
fully tested in clinical practice.
Later we have used data mining
techniques for extracting infor-
mation from heterogeneous
databases, using a federated
approach. Members of the GIB
were also involved in various data
mining projects, chairing various
data mining international confer-
ences.
References:
Maojo, V.; Crespo, J.; Sanandrés, J. y
Billhardt, H. Computational Intelligence
Techniques in Medical Decision Making.
The Data Mining Perspective. In Jain, L.
et al (Ed). Computational Intelligence
Processing in Medical Diagnosis 2002
David Pérez-Rey, D. and Maojo, V: An
Ontology-Based Method to Link Database
Integration and Data Mining within a
Biomedical Distributed KDD. Proceedings
of AIME 2009
Sanandrés, J.; Maojo, V.;Crespo, J. and
Gómez, A. A Clustering-Based Construc-
tive Induction Method and Its Application
to Rheumatoid Arthritis. Lecture Notes in
Artificial Intelligence 2101, 2001
Crespo, J.; Maojo, V. y Martín, F. (Eds).
Medical Data Analysis. Lecture Notes in
Computer Science 2199, 2001
Sanandres-Ledesma, JA, Maojo, V.,
Crespo, J., García-Remesal, M. and
Gómez de la Cámara, A: A Performance
Comparative Analysis Between Rule-
Induction Algorithms and Clustering-
Based Constructive Rule-Induction
Algorithms. Application to Rheumatoid
Arthritis. ISBMDA 2004
Nanoinformatics
Biomedical
Ontologies and
Vocabularies
Text Mining
&
Information
Retrieval
Data Mining
Over the last decade, the GIB has
been involved in a large number of
text mining and information
extraction/retrieval projects. We
have been particularly active in
accessing and extracting
knowledge from various unstruc-
tured sources, and particularly
from the biomedical literature —
available in Pubmed. Bringing
together structured and text-based
sources is an exciting challenge for
biomedical informaticians, since
most relevant biomedical sources
belong to one of these categories.
Unfortunately, the methods and
tools provided by state-of-the-art
database integration tools cannot
be reused to bridge together
structured and non-structured
(
text-based) sources, since all of
them require the individual
sources to be equipped with a
logical schema.
To address this issue, we created
various approaches based on text
mining techniques to automatically
create a logical schema for non-
structured sources. As seen in
other sections, we have widely
used text mining techniques in a
large number of areas.
References:
de la Calle G, García-Remesal M, Nkumu-
Mbomio N, Kulikowski C, Maojo V. e-
MIR2: a public online inventory of medical
informatics resources. BMC Med Inform
Decis Mak 2012
García-Remesal M, Maojo V, Crespo J,
Billhardt H. Logical schema acquisition
from text-based sources for structured
and non-structured biomedical sources
integration. AMIA AnnuSymp 2007
Billhardt H, Borrajo D, Maojo V. A context
vector model for informations retrieval.
JASIST 2002
Maojo V, García-Remesal M, Crespo J.
"
Detectors could spot plagiarism in
research proposals". Nature 2008
Bioinformatics
and the
“
Resourceome”
