Precision medicine is an emerging and novel approach for both disease treatment and prevention. Precision medicine allows to classify individuals into subpopulations that di er in their susceptibility to a particular disease with the aim to tailor the medical treatment to the individual characteristics of each patient. To provide precision medicine to patients researchers needs to analyze huge amounts of heterogeneous data from both biomedical research and healthcare systems. The growing amount of these data gives rise to the need for new research methods and analysis techniques. In this paper we present a infrastructure that exploits new strategies aimed at storing, accessing, and analyzing e ciently these heterogeneous data.
Nowadays, advances in technology has arisen in a huge amount of data in both
biomedical research and healthcare systems. This growing amount of data gives
rise to the need for new research methods and analysis techniques. Analysis of
these data o ers new opportunities to de ne novel diagnostic processes.
Therefore, a greater integration between healthcare and biomedical data is essential
to devise novel predictive models in the eld of biomedical diagnosis. In this
context, the digitalization of clinical exams and medical records is becoming
essential to collect heterogeneous information. Analysis of these data by means of
big data technologies will allow a more in depth understanding of the
mechanisms leading to diseases, and contextually it will facilitate the development of
novel diagnostics and personalized therapeutics. The recent application of big
data technologies in the medical elds will o er new opportunities to integrate
enormous amount of medical and clinical information from population studies.
Therefore, it is essential to devise new strategies aimed at storing, accessing, and
analyzing the data in a standardized way. Moreover, it is important to provide
suitable methods to manage these heterogeneous data.
relational databases does not lend to the nature of these data. In our opinion,
better results can be obtained using non-relational (NoSQL) databases. Starting
from these considerations, the infrastructure has been developed on a NoSQL
database with the aim to combine scalability and exibility performances. In
particular MongoDB [
With the aim to enable researchers to perform their analysis through dedicated computing resources, the infrastructure has been built on a hardware platform intended to enable big-data classes of applications which consists of: { a massive storage platform of 1.6 PB; { 2040 CPU cores; { 16 NVIDIA K20 GPUs; { 2 big memory nodes (i.e., 1 node equipped with 1TB and 1 node equipped with 512GB of memory).
It should be pointed out that the concept of precision medicine is about the
customization of healthcare, with decisions and practices tailored to an
individual patient based on their genome sequence, microbiome composition, lifestyle,
and diet in addition to medical and clinical data. Therefore, in addition to the
data about the patient collected by healthcare providers, researchers need to
incorporate many di erent types of data. To this end, a web-based platform
built upon the Galaxy technology [
The presented infrastructure exploits big data technologies in order to overcome
the limitations of relational databases when working with large and
heterogeneous data. The infrastructure implements a set of interface procedures aimed
at preparing the metadata for importing data in a NoSQL DB. Moreover, data
can also be represented as a graph using Neo4j [
Moreover, the robust hardware infrastructure together with the Galaxy webbased platform allow to easily integrate and analyze heterogeneous data from di erent biological sources.
Currently, the infrastructure is used in a project aimed at implementing techniques to infer the predisposition to some cancer diseases. The project is funded by the Fondazione Bracco. 4
This work has been supported by the Fondazione Bracco, the Italian Ministry of Education and Research Flagship (PB05) InterOmics project.