matrix completion method can take into account these genes through their feature
vectors.
5 Conclusion
A variety of data repositories containing partially independent information about
human genes, proteins, diseases, and drugs is continuously increasing. Combining
these complementary views on the same data objects can be expected to enhance
the overall information about the biological problem at study. Many computational
approaches have been developed to improve our understanding of the complex
interplay between these diverse data objects.
This chapter highlights the three most commonly used, state-of-the-art, compu-
tational approaches for biological data integration. In addition, we also provide a
brief review of important biological problems, along with a review of data repos-
itories commonly used in addressing these problems. The power of the computa-
tional approaches in addressing these problems is increasingly suggesting data
integration as a way forward to understanding complex mechanisms of life.
However, an application of these integrative methods to personalized medicine
is still an open question. It faces the following challenges: (1) development of user-
friendly tools for domain scientists for fast integration of heterogeneous,
multidimensional biological data, along with clinical data; (2) interpretation of
the outputs of these analyses and their translation to medical practice; (3) training
the future generations of medical doctors in necessary programming and computa-
tional skills to enable them to use these tools.
Other research areas, such as climatology, neuroscience, and social science, are
facing the flood of high-dimensional diverse data that need to be analyzed in an
integrated way. We expect in the future that these areas will utilize data integration
techniques to adequately address current problems.
Acknowledgments This work was supported by the European Research Council (ERC) Starting
Independent Researcher Grant 278212, the National Science Foundation (NSF) Cyber-Enabled
Discovery and Innovation (CDI) OIA-1028394, the Serbian Ministry of Education and Science
Project III44006, and ARRS project J1-5454.
References
Aerts S, Lambrechts D, Maity S, Loo PV, Coessens B, Smet FD, Tranchevent LC, Moor BD,
Marynen P, Hassan B, Carmeliet P, Moreau Y (2006) Gene prioritization through genomic data
fusion. Nat Biotechnol 24(5):537–544. doi:10.1038/nbt1203
Aittokallio T, Schwikowski B (2006) Graph-based methods for analysing networks in cell biology.
Brief Bioinform 7(3). doi:10.1093/bib/bbl022
Computational Methods for Integration of Biological Data 171