When it comes to the treatment of complex diseases, such as cancer, Alzheimer’s, and autism, doctors need to understand the molecular basis of the disease before they can develop a treatment. By tracking multiple genes and finding out how they interact with each other and by finding out how they interact with other biomolecules in the complex network that are specific to tissues and cell types where those molecules are located, doctors can come to a better understanding on the condition and, as a result, identify the best approach towards a treatment.

By using a sophisticated machine learning approach, Olga Troyanskay, Professor of Computer Science at the Lewis-Singler Institute for Integrative Genomics at Princeton University, has found an efficient way to sift through large collections of big data, for the more precise identification of genes that are related to dangerous diseases. The use of big data provides doctors with an unbiased way of investigating the mutations as they happen at a cellular level. Big data has become critical to understanding just how genomes can be decoded, especially the non-coding areas of the human genome.

While traditional law experiments compare normal cells with tumors to reveal differences; by using this new method, doctors cannot only tell how the cancer cells are different from normal cells, but also how they differ in relation to the cancer cells in other tumors. This allows doctors to find genes and pathways that are unique to specific diseases. The new technology has enabled doctors to identify a number of genes that are more likely to underlie the molecular basis for autism. Using the same technology, doctors are able to identify the specific genes that are related to other diseases, such as kidney disease. The new technology is being used not only to identify the off-target effects of a drug, but also crucial drug targets, when looking to treat a disease. The successful sequencing of the whole genome is going to make it easier for researchers to develop more efficient and targeted drugs for specific chronic medical conditions. The goal of using this new method is to get a better understanding of the basic biology behind the genomes that are related to certain diseases and their impact on the physiology of an organism.