Determining microRNA differences
The researchers determined that ovarian cancer cells and normal cells had different microRNA profiles. Since microRNAs move around in the blood, the team gathered microRNAs from the blood samples of 135 women and created a sample set. They aimed to look at the differences in the microRNA profiles between ovarian cancer and benign tumors using a computer program. Using this type of computerized approach, the team could create different predictive models in order to accurately distinguish ovarian cancer from benign tissue, also known as a neural network model. “When we train a computer to find the best microRNA model, it's a bit like identifying constellations in the night sky. At first, there are just lots of bright dots, but once you find a pattern, wherever you are in the world, you can pick it out,” said Elias.