Precision and Personalized Medicine in the age of Big Data and Machine Learning

Personalized medicine has become a popular buzzword and is used across the board to describe many different ideas about healthcare innovation. Healthcare, bioinformatics and pharmaceutical researchers agree that somewhere in the overlap between big data (structured and non-structured personal information), systems biology modeling and machine learning lies the promise of innovative precision for diagnostics and therapeutics that will redefine healthcare of the future.

At the center of this innovation is technology that produces new high-throughput data and the ability to mine this data to interpret it’s meaning. New tools are being developed to analyze, mine, integrate and help researchers interpret this continuously growing avalanche of big data. As the tools become more precise by eliminating errors and artifacts, a deeper understanding of biological meaning will result in reliable targets for diagnosis and intervention.

One of the challenges to better biological understanding of cellular mechanisms is integration of big heterogeneous datasets. While separate genomic, transcriptomic, proteomic and metabolomic studies can contribute to a model over time, multiple “omics” and phenotypic sources of information together could enhance our understanding of complex host-pathogen circuitry models of interaction in a new way.

Yet, the idea of data integration is not new, as there are thousands of articles via Pubmed that mention data integration in relation to omics, yet this is still a significant challenge, both theoretically and practically. In [1] a survey found that researches needed user-friendly data tools for their integrations of heterogeneous data.

T-BioInfo Platform, a bioinformatics platform that is being developed at the Tauber Bioinformatics Research Center at the University of Haifa is being expanded to include a new section on virology. This is in collaboration with researchers at UCSF and Stanford, where a new method for precision sequencing of viral RNA (doi:10.1038/nature12861) was developed, the virology section is built to integrate CirSeq, NGS, and proteomics data.

Integration of both the genomic and proteomic data from these complex systems can allow for better understandings of viral function, adaptation, and potentially identify possible targets for intervention.

Our goal is to expand integration and data mining capabilities of the platform to help researchers gain better understanding with insight into intervention for viral diseases. If you could be interested in trying out the virology pipeline on T-Bioinfo, please contact us at

Gomez-Cabrero D, Abugessaisa I, Maier D, et al. Data integration in the era of omics: current and future challenges. BMC Systems Biology. 2014;8(Suppl 2):I1. doi:10.1186/1752-0509-8-S2-I1.


Commenting is Disabled on Precision and Personalized Medicine in the age of Big Data and Machine Learning