Dry Lab Overview
Having found the perfect idea and scientific field that we were going to deal with, a new question was born. What should we do to upgrade our project further?
Considering that healthcare professionals and physicians are not very familiar with Pharmacogenomics’ scientific field, we decided to develop a “tool” that would help them personalize each patient’s dosage.
Thus, we thought it would be very beneficial for the user if there were a system assisting him/her by directly translating the genetic analysis results into clinically useful information; the proposed administered dosage.
To achieve that, our Dry Lab team suggested using AI software since it provides high reliability. Artificial Intelligence is on the verge of penetrating every major industry, from healthcare to advertising, transportation, finance, legal, education, and now inside the workplace.
Our task was to locate and classify different objects of interest (OoI) in images of the electrophoresis gels. Each image consists of 6 sample columns, with each consecutive pair representing a sample of a person, 2 blank sample columns, and the ladder. To perform multiple object detection, a modification of the state-of-the-art algorithm Yolo is implemented.
After completing the previous step, we started building a web-based application to make our system easily accessible by health professionals. The idea behind this is very simple, as the only thing that a user needs is a smartphone. All someone has to do is take a photo of the electrophoresis gel after completing the genetic analysis and upload it to the aforementioned web-based app. The system will then do the job for him/her, understanding what clinically useful information is displayed in the picture.
To conclude, the BentoLab-AI system makes Pharmacogenomics’ implementation into clinical practice easier than ever before. Through this, personalized medicine can be achieved even by health professionals who have never performed a genetic analysis.