Have you ever wondered what it would be like if new planes were created through cycles of trial-and-error in which prototypes are built and tested "to see if it flies"? This is how drugs are developed today. I'm working with application, validation and development of computational methods that can contribute to a drug development process that is more data-driven and less dependent on trial-and-error cycles.  About 12 years ago I was presented to the fascinating problems that lie in the interfaces between biology, chemistry, physics and computation. Since then, I developed PhD and post-doctoral research projects that focus on drug discovery using computational methods. During this journey, I worked with dozens of biomolecular systems during collaborations that I established with several research groups. This experience allows me to adapt to changing environments and to promote effective communication in multidisciplinary teams, focusing on problem solving while balancing independent and collaborative work.  In addition to that, after delivering more than 30 presentations to diverse audiences, I can communicate complex concepts in a simple way according to the target audience.  I'm currently working in two main projects:    • Combining deep neural networks and molecular dynamics simulations to build models that can predict pharmacokinetic or toxicological properties of molecules that are candidates for new cosmetics or drugs. Such methods can reduce or even eliminate the necessity of animal testing in some instances.    • Planning, executing and analyzing virtual screening assays to discovery new drugs or to identify drugs that were approved against one disease that can potentially be used against other diseases. This approach, called "drug repositioning" or "drug repurposing", can lead to faster development of new therapies because the toxicological and pharmacokinetic profiles of approved drugs are already known.  I'm a specialist in learning and I'm always looking for new methods and tools to make my work better and more efficient, even if it requires learning subjects that I’m not familiar with. For now, these are my main technical skills:    • Machine learning and deep learning    • Data analysis    • Molecular dynamics simulations    • Docking-based virtual screening    • Structural bioinformatics    • Affinity/ΔG calculation