Lab of the Future

Course Overview

The Lab of the Future short course is designed to provide the framework, skills and knowledge to assist participating organizations in the design and implementation of automated laboratory workflows that are tightly integrated with modern AI machine learning strategies.

Under the guidance of a skilled instructor, participants will learn topics ranging from analyzing laboratory layouts to selecting optimal machine learning strategies to achieve their goals.

Completion of this course will grant participants the ability to:

  • Evaluate the potential benefits of automation
  • Utilize the best automation approach for a successful implementation plan
  • Monitor and improve the automation setup
  • Determine the best application of machine learning for an experimental procedure
  • Determine the appropriate hardware for their experimentation processes
  • Identify the potential strengths and weaknesses of a proposed automation solution

Cost: $10,000
Price includes travel and lodging costs for the course instructor.

This course can be conducted onsite at a host institution or it can be conducted virtually.

Note: Course scheduling is dependent on the instructors’ availability. Please request the Lab of the Future short course on demand at your earliest convenience so that we may best accommodate your requested date(s).

If you would like to conduct this course at your institution, please email SLAS Scientific Director, Lesley Matthews, Ph.D.

Hear more from course creaters Mario Richter, Ph.D. (AbbVie), and Joshua Kangas, Ph.D. (Carnegie Mellon University) on a special episode of the New Matter: Inside the Mind of SLAS Scientists podcast.


Mario Richter, Ph.D., and Joshua Kangas, Ph.D., are two of the content creators behind the Lab of the Future short course.

Mario Richter: Mario Richter, Ph.D., acquired his Ph.D. in epigenetics from the University of Vienna where he also studied biochemistry. Richter is currently a director in the DMPK-BA department of AbbVie where he leads a global team in conducting biomarker analytical work for the company’s pipeline. In his 12 years working for Abbott/AbbVie, Richter has helped transform the fully manual process in regulated bioanalysis into a completely automated workflow. Optimizing and automating laboratory workflows is a primary interest of Ritcher in the pursuit of identifying solutions in making research more efficient to grant more time for innovative thinking. Additionally, he is a passionate supporter of precision medicine approaches that use biomarkers that possess the potential to identify the best treatment for a patient and monitor efficacy.

Joshua Kangas: Joshua Kangas, Ph.D., is an Assistant Teaching Professor at Carnegie Mellon University in the Computational Biology Department in the School of Computer Science. The laboratory courses Kangas teaches focus on the interface of computation (including machine learning and modeling), biological data generation (sequencing, microscopy, cytometry, etc.) and artificial intelligence-directed laboratory automation. Kangas’ approach to teaching focuses on providing students experience in experimental design and execution at the interface between lab experimentation (data generation) and computation (data analysis and modeling).

Aside from the Lab of the Future short course, Kangas played a role in the founding of two academic programs. Kangas and his colleague, Phillip Compeau, Ph.D., Carnegie Mellon University, founded the first high school program focused on computational biology with an emphasis on laboratory techniques and the implementation of algorithms for the analysis of DNA sequence data. Kangas also was involved in starting the first M.S. Automated Science Biological Experimentation program in the world at Carnegie Mellon University.

Learn more about the Lab of the Future short course from the content creators themselves in this special episode of the SLAS New Matter Podcast!


Our team of instructors is comprised of industry experts skilled in AI/ML, laboratory automation, data pipelines and other areas of laboratory expertise, as well as teaching and educational experience

Paul Jensen, Ph.D. (Massachusetts, USA): Paul Jensen, Ph.D., has spent the last five years teaching undergraduate and graduate-level courses in machine learning, artificial intelligence and automation at the University of Illinois and the University of Michigan. Jensen is the author of the textbook "Linear Algebra: Foundations of Machine Learning," and is currently writing a second book on automated science.

Jensen’s primary research focus is automated science – using AI to plan, execute and interpret scientific experiments in a closed loop. Since 2020, his lab’s AI systems have performed more than 920,000 phenotypic experiments and distilled the results into human-interpretable models. The AI systems have developed algorithms that learn "from scratch" without any prior human knowledge. Also, Jensen’s lab heavily uses next-generation sequencing, primarily for prokaryotic RNA-seq. In 2021, they processed more than 600 sequencing libraries using custom assays and liquid handling robots.

Donat Elsener (Switzerland): Donat Elsener, Director Sales and Marketing at Hamilton Storage, has served as a business process analyst and project manager for multi-million laboratory automation projects around the globe. Past projects include high-throughput screening (HTS) systems for major pharmaceutical and biotech companies and development projects for laboratory automation vendors. Elsener is an experienced presenter having delivered hundreds of presentations for laboratory automation projects around the globe.

Ian Kerman, M.S. (California, USA): Ian Kerman, (M.S. in Biology and M.S. in Computer Science) possesses a comprehensive knowledge of data pipelines stemming from his experience building, maintaining, and using data pipelines, primarily in the life and material sciences. Kerman has extensively assisted customers on how use and leverage machine learning in their high throughput and virtual screening workflows. His understanding includes data engineering and cleanup, model training and evaluation and deployment and maintenance of chosen models.

Gleb Konotop, Ph.D. (Germany): Gleb Konotop, Ph.D., is currently the head of automation at AbbVie in Germany. Konotop’s primary focus is on fully automated ligand-binding assays (ELISA, ECL), formulation, cell-based assays and NGS. He is an experienced instructor who has previously led a global in-house programming training course for Hamilton systems at AbbVie. Konotop also has experience working in device connectivity and Internet of Things.