Prof Zoran Nikoloski
Prof. Zoran Nikoloski is the Chair of Bioinformatics at the Institute of Biochemistry and Biology of the University of Potsdam and also holds a collaborative research group leader position at the neighbouring Max Planck Institute of Molecular Plant Physiology. Zoran Nikoloski trained as a computer scientist at the University of Central Florida, Orlando, FL, USA and has worked as a postdoctoral fellow at the Department of Applied Mathematics of Charles University, Prague, Czech Republic, and the Bioinformatics Department at University of Potsdam. His research has made pioneering contributions to modeling and understanding how genomic variation leads to different metabolic phenotypes and growth-related traits in photosynthetic organisms. The metabolic modeling efforts and computational frameworks resulting from his research have contributed important insights to robustness and plasticity of metabolic phenotypes – properties that are tightly related to optimization of photosynthesis. In CAPITALISE, the Nikoloski team focuses on modeling natural variation in the context of the Calvin-Benson cycle as well as integration of large-scale data from high-throughput phenotyping for the purpose of predicting genotypes with improved photosynthesis.
Title: Insights from machine learning of photosynthesis-related traits using hyperspectral reflectance data
Webinar date: Tuesday 5th December 14.00 CET
Abstract: The experimental efforts in CAPITALISE have generated large data sets about photosynthesis-related traits as well as hyperspectral reflectance obtained from leaves of individuals from different species and populations. My talk will present our insights from machine learning models that make use of hyperspectral data to predict photosynthesis-related traits. Emphasis will be placed on identifying relevant predictors and investigating the generalizability of the models across species. We will also discuss the extent to which hyperspectral data can help in decreasing the experimental effort in quantifying photosynthesis-related traits.