Jump to content


Boston, MA, and Virtual Conference
February 5–9, 2022

Join Genedata experts at the SLAS2022 conference at booth #1227.

Don't miss the opportunity to see how Genedata Screener analyzes, visualizes, and manages screening data from in-vitro screening assay technologies across the enterprise, including very complex as well as ultra-high throughput experiments. You also have the chance to find out more about Genedata Imagence, a high content screening (HCS) image analysis software based on deep learning. To get more information about our software or to arrange a meeting, please contact  screener(at)genedata.com or imagence(at)genedata.com, respectively.

Recommended Oral Presentations

High throughput covalent fragment screening with MALDI mass spectrometry
Don D. Nguyen, PhD, High Throughput MS Scientist, Merck, Hessen, German

Advances in Bioanalytics and Biomarkers
Monday, February 7 | 10:30 – 11:00  am EST

Fragment based drug discovery is one of the tools in the toolbox of drug discovery approaches.  Amongst them, covalent fragment screening can lead to viable chemical starting points with high potency and selectivity, prolonged duration of action with good pharmacokinetic profiles, and can even be applied to targets deemed less druggable.  Covalent fragment screening is traditionally performed by crystallographic-, nuclear magnetic resonance- (NMR), and mass spectrometry- (MS) based methods.  Crystallographic methods provide a chemical and structural basis of target-compound interaction allowing for further rational design and growth of the fragment starting point.  NMR-based methods offer binding site elucidation, potential determination of binding modes, as well as being able to establish structure activity relationships.  Liquid chromatography mass spectrometry (LC-MS) offers direct and unbiased measurement of target-compound interactions and can even specify compound binding down to a specific amino acid.  While each of these methods have separate strengths, all three methods suffer from relatively low throughput, making it difficult to screen large fragment libraries.  Matrix assisted laser desorption ionization (MALDI)-MS maintains the benefits unbiased analyses of LC-MS, albeit with a small penalty of more complex sample preparation.  However, the speed benefits granted by MALDI—both in data acquisition as well as the coupling possibilities to high throughput automation systems—far outweigh any negatives, while also offering less complex data and low sample amount requirements.  Here we present a MALDI-based workflow taking advantage of high throughput screening (HTS) automation equipment in combination with a high throughput focused MALDI and Genedata Screener software designed for large scale MS data analysis. Together, the workflow leads to increased throughput and automated analysis of covalent fragment screens.

Automated Image Analysis with Deep Learning to drive Cardiac Safety Profiling
Jeroen Overman, PhD, Senior Scientist Mechanistic Biology & Profiling, AstraZeneca, England, United Kingdom

Data Science and AI
Tuesday, February 8 | 11:00 – 11:30  am EST

Cardiotoxicity is a crucial consideration during early stages of drug development to de-risk new therapies and maximise patient safety. Current in vitro models are restrictive as they are either highly target-centric (e.g. hERG) or have limited translatability for structural cardiotoxicity due to simplified cell systems or analysis methods. In answer to this, a deep learning based image analysis approach (Genedata Imagence) was deployed on a 3D cardiac microtissue (CMT) high content imaging assay, with the aim of deriving increased mechanistic insight and increased sensitivity.

One of the main challenges here was to maintain tissue-level phenotypic information while achieving a high enough object count for robust classification at scale. A solution was found in analysing 50-100 tissue subregions from widefield or 2D projections of the CMT images. This enabled phenotypic classification on a tissue level while maintaining high enough throughput for production-level profiling. Applying this approach, a neural network was trained using a collection of known cardiotoxins in live CMTs to annotate phenotypes that represent a potential cardiac safety risk. Around a dozen distinct phenotypes were identified and trained to a high degree of confidence, based on a triple stain for mitochondria, ER and nuclei. To guide in the phenotype interpretation for a range of end-users, the most similar phenotypes were grouped to fall into 6 categories, but drill-down options were kept available for detailed analysis. In addition, the neural network was also able to identify and flag a broad spectrum of interference, including (cellular) debris and fluorescence artefacts.

From a test set of roughly 80 in-house compounds, phenotypic classification achieved excellent correlation with the legacy segmentation-based analysis approach. In addition, we observe several benefits of the deep learning approach: 1) Direct correlation of test compounds to known cardiotoxins that were used to train the network enables increased mechanistic insight; 2) Identification of novel phenotypes even while the assay is in production, allows for the continuous improvement of the neural network and phenotypic clustering of test compounds; 3) Increased assay robustness; 4) Time-savings through automated analysis of production-level screens and easy of development/transfer. Finally, early data suggests we observe higher assay sensitivity, which could enable detection of cardiotoxins that were previously missed.