Big (Bio)Chemical Data Mining Using Chemometric Methods: A Need for Chemists

Large and complex chemical data sets generated by modern analytical technologies have led to the so-called Big (Bio)Chemical Data (BBCD) era [1]. These data sets can be produced using modern analytical instruments such as multi-dimensional chromatography, high-resolution and multi-dimensional spectroscopy, hyperspectral imaging and DNA/RNA microarrays [2]. These huge data sets are difficult to manage and analyze using conventional statistical methodologies and software tools [3]. Chemometric methods have shown potential to analyze BBCD especially in omics sciences and chemical toxicology/drug discovery [4]. Therefore, this contribution aims to demonstrate abilities to analyze BBCD with multivariate chemometric methods and to show some of the more important challenges of modern analytical research. In this regard, the capabilities and versatility of chemometric methods will be discussed in light of the BBCD challenges that are being encountered in chromatographic, spectroscopic and hyperspectral imaging measurements, with an emphasis on their application to omics sciences. In addition, insights and perspectives on how to address the analysis of BBCD are provided along with a discussion of the procedures necessary to obtain more reliable qualitative and quantitative results. In this work, the importance of Big Data and of their relevance to (bio) chemistry is first discussed. Then, analytical tools which can produce BBCD are presented as well as some basics needed to understand prospects and limitations of chemometric techniques when they are applied to BBCD are given. Finally, the significance of the combination of chemometric approaches with BBCD analysis in different chemical disciplines is highlighted with some examples