Efficient and cost-effective batch analysis of multi-electrode array (MEA) data from human iPS cardiomyocytes using Intelligent Waveform Service (IWS)

Abstract

• Human induced pluripotent stem cell derived cardiomyocytes (hiPSC-CMs) with multi-electrode array (MEA) technology could be used to develop assays for predictive electrophysiological safety screening. • Large volumes of MEA data are generated and analysis using existing tools is time consuming. There is a need to improve timeliness and cost-effectiveness of data reporting. • Neural ID’s Intelligent Waveform Service (IWS) is propriety enterprise software that uses pattern-based learning of waveforms. • IWS was used to analyze MEA data generated from hiPSC-CMs treated with Terfenadine and results were compared to existing analysis tools. • We show that analysis and reporting times using IWS can be reduced by up to five times and employing pattern recognition technology will improve accuracy and facilitate greater use of MEAs in compound screening. Methods Results • The non-sedating anti-histamine Terfenadine was chosen to validate the IWS software. • Data was recorded from spontaneously beating hiPSCCMs (Cellular Dynamics International) using the MEA1060 system (Multi Channel Systems). Data was filtered (1Hz high pass, 3kHz low pass) and sampled at 10kHz. • After baseline recordings, Terfenadine was cumulatively added to the bath. The last minute of recording at baseline and each Terfenadine concentration was used for analysis. • IWS was used to analyze the following parameters: Field potential duration (FPD), total spike amplitude, beat rate and conduction time. • Data analysis is conducted on the server using templates which are batch processed for efficient resource utilization. • Gradient markers are defined to determine spike interval and context of targeted patterns. • Based on the marker locations, patterns are defined graphically (Fig. 2) to detect repolarization wave location and measure its peak value. • IWS creates an empirical data model and does not rely on a predetermined library of patterns, leading to higher recognition rates than industry standards and the ability to analyze a broader range of data. • By simply clicking and dragging, additional pattern examples can be added to the knowledge database (Fig. 3). • The same process is used to detect other types of patterns, such as spikes, with amplitude (maximum/minimum) measurements applied (Fig. 4). Intelligent Waveform Service (IWS) IWS is proprietary enterprise software (Fig. 1) that: • Leverages machine learning to provide waveform analytics of biosignals. • Automates and accelerates discovery & preclinical research, providing more complete results at a fraction of the time and cost. • Learns example patterns, then runs batch jobs against multiple file sets and data formats, making analytics shareable among researchers and groups. Figure 1 – IWS Architecture Figure 4 – Detecting Spike Patterns and Measuring Amplitude Figure 3 – Adding Pattern Examples to the Template Figure 2 – Pattern Creation and Metrology Set-Up