DS-MAR22-PG45_Layout 1 17/03/2022 12:13 Page 1


MEDICAL & PHARMACEUTICAL INDUSTRY FOCUS AI AND AUTOMATION COMBINE


Artificial intelligence (AI) and automation have been built into a


laboratory automation system designed to speed up the diagnosis of SARS-CoV-2


significantly speed up the diagnosis of SARS-CoV-2. It can, in fact, test 15,000 individual samples per day. Developed at the Institute of Bioorganic Chemistry of the Polish Academy of Sciences, alongside Mitsubishi Electric, Labomatica and Perlan Technologies, the AGAMEDE robotic system features state-of-the- art automation technology combined with artificial intelligence (AI). Combining AI and automation in a high-throughput system is a breakthrough, the company explains. With the system, automation and AI are


A


combined to form a ‘closed loop’ setup. Here, the robots prepare experiments, read the results at a specified time and interpret the data using Labomatica’s Gene Game software to independently prepare the next experimental cycle. Operators therefore simply need to define the question, design the experimental system, and then monitor the correct sequence and operation of the system. AGAMEDE can then conduct experiments 24 hours a day and deliver the results.


THE PROJECT’S AIM The system wasn’t originally developed to carry out Covid tests. Work on AGAMEDE began at the IBCH PAS in 2015, with the system originally developed for the EPICELL project, which was funded by the National Centre for Research and Development (NCBiR) as part of the STRATEGMED programme ‘Prevention and Treatment of Civilisation Diseases’. The aim of the project was to develop optimised media for the culture of induced pluripotent stem cell-derived (iPSC) cardiomyocytes. The EPICELL consortium consists of the


IBCH PAS, the Institute of Human Genetics PAS, as well as three hospitals from Poznañ. Combining expertise in small molecule epigenetic modulators and experience in cell reprogramming, it conducted studies leading to the future development of methods for transforming induced iPSCs for the purposes of regenerative medicine. In particular, they looked at targeted implantation in the hearts of patients


laboratory automation system has been designed to


after heart attacks. The idea was to restore cardiac output to its pre- infarction state. However, the


number of experiments required to design a suitable mix of small molecule epigenetic modulators was a challenge. For example, a recipe with ten components and ten different concentrations requires 10,000,000 experiments. “AGAMEDE was used to search for the


right combination of compounds in a multidimensional system of solutions. From this, the composition of the reprogramming medium ‘EPICELL One’ was developed,” explains Prof. Wojciech T. Markiewicz, head of the EPICELL project. “Thanks to the AI module, AGAMEDE


interprets the experiments without human involvement, based on mathematical models,” explains Radosław Pilarski, PhD, the inventor and chief engineer of the system. “The system can be used by central diagnostic laboratories, pharmaceutical companies in drug development, oncology laboratories in search of personalised therapies for patients, but also in R&D departments of chemical and biotechnology companies to optimise bioprocesses.” The situation, however, changed in March 2020. IBCH PAS director, Prof. Marek Figlerowicz, said: “Our institute was the first in Poland to develop a test to detect SARS-CoV-2. We soon decided to combine AGAMEDE’s automation capabilities with our tests and developed a high-throughput diagnostic protocol that allows us to test 15,000 samples in one day. At least this is the potential, because IBCH PAS as a scientific entity does not have an accredited diagnostic laboratory. This is an outstanding result, because when analysing samples manually, one person can at most process a few hundred samples a day.”


ROBOTICS & PLCS For the project, Mitsubishi Electric provided a


6-axis industrial robot, PLC controls and its MELFA Basic software. Using an integrated set of robotic tools, it can perform microscale experiments on 96- and 384-well microassay plates, reproducing the work of a laboratory technician who continuously operates the analytical equipment. It does this according to the experimental protocols entered by the operator into the control software. The application further includes industrial


cell culture incubators, plate and tip feeders, pipetting stations, labellers, barcode scanners, plate sealers, fluorescence readers and spectrophotometers. AGAMEDE is equipped with an automated confocal microscope HCA with four fluorescence channels. For the biotechnology community, this instrument is the equivalent of the Hubble telescope brought into the microcosm. Instead of astronomical objects, it photographs and analyses millions of cells and tissue structures with similar quality and efficiency. The device is complemented by an acoustic dispenser that releases quantities of liquid in the nanolitre range (millionths of a millilitre). Rapid dispensing of such small volumes of solution reduces research costs and increases throughput. It allows experiments to be conducted using a collection of over 115,000 chemical compounds available. Roman Janik, coordinator of solutions for


the life science industry in Poland, commented: “We all worked under time pressure to develop a solution that would relieve the lab technicians as quickly as possible. We were able to deliver a weekly throughput of 100,000 samples, which is scalable.” Tomasz Scholz, robotics engineer at Mitsubishi Electric, added: “The AGAMEDE project is an interdisciplinary project that combines the worlds of robotics, computer science, industrial design, mathematics, biology and chemistry. The solutions we used in it are innovative and unique.”


Mitsubishi Electric gb3a.mitsubishielectric.com


MARCH 2022 DESIGN SOLUTIONS 45


Page 1  |  Page 2  |  Page 3  |  Page 4  |  Page 5  |  Page 6  |  Page 7  |  Page 8  |  Page 9  |  Page 10  |  Page 11  |  Page 12  |  Page 13  |  Page 14  |  Page 15  |  Page 16  |  Page 17  |  Page 18  |  Page 19  |  Page 20  |  Page 21  |  Page 22  |  Page 23  |  Page 24  |  Page 25  |  Page 26  |  Page 27  |  Page 28  |  Page 29  |  Page 30  |  Page 31  |  Page 32  |  Page 33  |  Page 34  |  Page 35  |  Page 36  |  Page 37  |  Page 38  |  Page 39  |  Page 40  |  Page 41  |  Page 42  |  Page 43  |  Page 44  |  Page 45  |  Page 46  |  Page 47  |  Page 48  |  Page 49  |  Page 50  |  Page 51  |  Page 52  |  Page 53  |  Page 54  |  Page 55  |  Page 56  |  Page 57  |  Page 58