Machine learning in Biofabrication
Data mining is a process of finding patterns commonly applied to large datasets.
Thus, it uses a set of statistics, machine learning algorithms and mathematical models to identify patterns and trends that can not be easily discovered using "traditional" methods. Such an approach is extremely important in post-genomic molecular biology, which generates a large amount of omic data.
Omic data - data from the genome, transcriptome, miRnoma, proteome, metabolome, toponome, among others (omics data), present complex interactions difficult to analyze, and the use of artificial intelligence are opportune.
Although data mining techniques have been used by several fields studied in genetics and molecular biology, its application to the discovery of biomarkers and functional networks for tissue biofabrication purposes remains little explored.
The cellular and tissue phenotype is essential for the understanding of tissue regeneration. Understanding the networks of molecular interaction of tissues and cell lines are crucial for the development of therapies, such as biofabrication of tissues and organs.
Specific molecular networks can predict cell-specific responses to a stimulus, and reveal the functional roles of genes and their interactions.
Thus, integrated approaches with artificial intelligence methods can provide new insights and information on signaling networks of cell differentiation during the development or regeneration of a tissue.