Start date: Week 40 (1st October 2024)
Speaker 1: Cemal Erdem (DDLS Fellow; Tuesday 1st October 9:00-10:00 CEST)
This module will focus on combining machine learning, mechanistic models, and patient data to develop predictive computational models for cancer and other diseases. Topics will include mathematical modeling of signaling cascades, systems biology, quantitative systems pharmacology (QSP), and precision medicine.
Speaker 2: Gabriel Reder (Research associate at Cambridge University & KTH; Tuesday 1st October 10:00-11:00 CEST)
Gabriel Reder is a research associate in automated laboratory discovery and informatics. He has focused especially on applications to mass spectrometry metabolomics and self-driving robotic laboratories.
Titel: Accelerating Scientific Discovery with Large Language Models
Discovery in the biological laboratory is a difficult and time-consuming process. At every step, practitioners are faced with repetitive, complex, and labor-intensive tasks. Generative AI, especially large language models, can allow scientists to automate many of these tasks including experimentation, compilation, and data analysis. In this lecture, we will explore some examples of how researchers can utilize modern AI tools to aid their discovery research in the lab and at the desk.
Computer Lab: The lab will feature examples of cell modeling and using GPT models to enable automation. Participants will gain hands-on experience with computational modeling techniques and explore how large language models can be utilized to streamline and automate laboratory processes. This session will provide practical insights into the integration of AI tools for enhancing research efficiency and innovation.