Session: Trends in Analytical & Bioanalytical Chemistry: Make, Measure, and Smart Machines

Session Chair: Prof. Dr. Ulrich Panne, Prof. Dr. Günter Gauglitz, Dr. Jens Riedel

Opening the random forest black box by variable selection and relational analysis

Prof. Dr. Stephan Seifert, Uni Hamburg
In order to comprehensively exploit the complex data generated by analytical techniques for the classification and characterization of biological samples, multivariate chemometric methods are applied. These methods are divided into unsupervised approaches, which are applied without further information, and supervised approaches, by which classification models are trained using samples with known class memberships. The latter, machine learning approaches, are often applied as black boxes meaning that only the class assignment is reported, while the background that led to this decision remains unknown. Random forest (RF) is a non-parametric machine learning approach that consist of a large number of individual binary decision and has many advantages, such as flexibility in terms of input and output variables and the possibility of internal validation. [1] Another advantage is the ability to generate variable importance measures that are used to select relevant features. However, the relationships between the predictor variables are usually not examined. We developed a novel RF based variable selection method called Surrogate Minimal Depth (SMD) that incorporates relations into the selection process of important variables. [2] This is achieved by the exploitation of surrogate variables that have originally been introduced to deal with missing predictor variables. In addition to improving variable selection, surrogate variables and their relationship to the primary split variables can also be utilized as proxy for the relations between the different variables. This relation analysis goes beyond the investigation of ordinary correlation coefficients because it is based on the mutual impact on the outcome. This talk will introduce chemometric classification methods and the SMD approach to open the black box for classification of various analytical data.
21-Jun-2022 15:00 (30 Minutes) ICM/Hall 4b

Smart Machines, New Materials, Automated Future

Dr. Tomasz Stawski, BAM

21-Jun-2022 15:30 (30 Minutes) ICM/Hall 4b

Automating the analytical laboratory – What’s next

Prof. Dr. Kerstin Thurow, Universität Rostock
21-Jun-2022 16:00 (30 Minutes) ICM/Hall 4b

3D Printer in the Lab, not only a Toy

Dr. Vittorio Saggiomo, Wageningen University
Although 3D printers have been in the consumer market for a while, they are still underrepresented in many laboratories. In this talk, I will show the potential of having a 3D printer in the lab and show the four stages of 3D printing: 3D printing, designing, materials, and electronics. Having a 3D printer in the lab is not only beneficial for rapid prototyping and producing personalized objects but also for making new materials and directly testing them without the need for external companies. I will show how to make microfluidics1 and 3D printing nanocomposite materials with unique optical properties. 2,3 As the last point, I will show how 3D printers are very cheap XYZ robots that can be used to automate laboratory procedures. For example, we have used a 3D printer electronics and mechanics to build a set of three programmable syringe pumps4 and used a 3D printer for making automatic histological procedures
21-Jun-2022 16:30 (30 Minutes) ICM/Hall 4b