Garbage in, garbage out? Solve data preprocessing with Gabe Musso | Podcast #14
Welcome to the Talking Precision Medicine podcast. In this series, we sit down with experts on the application of AI and big data analytics in the drug discovery space. Our guests are innovators, business decision makers and thought leaders at the intersection of data and therapeutics. We discuss the promise, practice, challenges, and myths of AI in precision medicine. This show is brought to you by Genialis, and Rafael, our CEO, is your host.
Genialis is focused on data integration and predictive modeling of disease biology to help accelerate the discovery and de-risk the development of novel therapeutics.
Today our guest is Gabe Musso. Gabe is Chief Scientific Officer of BioSymetrics, a Toronto-based biomedical AI company empowering healthcare and R&D innovation.
In this episode, Gabe tells us how BioSymetrics is working to clean up data clean up, by applying a rigorous product framework to data preprocessing.
- Drug discovery is an expensive endeavor. So how can we use machine learning effectively to reduce the costs in terms of generating better early clinical leads, better understanding and partitioning patients into disease categories and definitions, and then ultimately how do we understand the full consequence of each of those diseases and diagnosis
- When you look at why machine learning will tend to fail, it’s not an algorithmic problem, the algorithms are sufficiently advanced, it’s a data problem. So how can we improve that data processing or have more transparency over that data process so we can refine it a little bit more easily and quickly
- The blessing curse of the machine learning is that it doesn’t care what inputs you give it, it will always try to run the algorithm and give you the result.
- Data are the new currency, this is what builds value, not only for companies but for anybody.