Biology subjects

Turkki, R.

Publications and source records attributed to Turkki, R..

3 recordsLinked to original sources

bioRxiv2023

Cell Painting-based bioactivity prediction boosts high-throughput screening hit-rates and compound diversity

Efficiently identifying bioactive compounds towards a target of interest remains a time- and resource-intensive task in early drug discovery. The ability to accurately predict bioactivity using morphological profiles has the potential to rationalize the process, enabling smaller screens of focused compound sets. Towards this goal, we explored the application of deep learning with Cell Painting, a high-content image-based assay, for compound bioactivity prediction in early drug screening. Combining Cell Painting data and unrefined single-concentration activity readouts from high-throughput screening (HTS) assays, we investigated to what degree morphological profiles could predict compound activity across a set of 140 unique assays. We evaluated the performance of our models across different target classes, assay technologies, and disease areas. The predictive performance of the models was high, with a tendency for better predictions on cell-based assays and kinase targets. The average ROC-AUC was 0.744 with 62% of assays reaching [≥]0.7, 30% reaching [≥]0.8 and 7% reaching [≥]0.9 average ROC-AUC, outperforming commonly used structure-based predictions in terms of predictive performance and compound structure diversity. In many cases, bioactivity prediction from Cell Painting data could be matched using brightfield images rather than multichannel fluorescence images. Experimental validation of our predictions in follow-up assays confirmed enrichment of active compounds. Our results suggest that models trained on Cell Painting data can predict compound activity in a range of high-throughput screening assays robustly, even with relatively noisy HTS assay data. With our approach, enriched screening sets with higher hit rates and higher hit diversity can be selected, which could reduce the size of HTS campaigns and enable primary screening with more complex assays.

bioinformatics↗

bioRxiv2022

Cell morphological profiling enables high-throughput screening for PROteolysis TArgeting Chimera (PROTAC) phenotypic signature

PROTACs (PROteolysis TArgeting Chimeras) use the ubiquitin-proteasome system to degrade a protein of interest for therapeutic benefit. Advances in targeted protein degradation technology have been remarkable with several molecules moving into clinical studies. However, robust routes to assess and better understand the safety risks of PROTACs need to be identified, which is an essential step towards delivering efficacious and safe compounds to patients. In this work, we used Cell Painting, an unbiased high content imaging method, to identify phenotypic signatures of PROTACs. Chemical clustering and model prediction allowed the identification of a mitotoxicity signature that could not be expected by screening the individual PROTAC components. The data highlighted the benefit of unbiased phenotypic methods for identifying toxic signatures and the potential to impact drug design. HighlightsO_LIMorphological profiling detects various PROTACs phenotypic signatures C_LIO_LIPhenotypic signatures can be attributed to diverse biological responses C_LIO_LIChemical clustering from phenotypic signatures separates on drug selection C_LIO_LITrained in-silico machine learning models to predict PROTACs mitochondrial toxicity C_LI

pharmacology and toxicology↗

bioRxiv2021

Label-free prediction of Cell Painting from brightfield images

Cell Painting is a high-content image-based assay which can reveal rich cellular morphology and is applied in drug discovery to predict bioactivity, assess toxicity and understand diverse mechanisms of action of chemical and genetic perturbations. In this study, we investigate label-free Cell Painting by predicting the five fluorescent Cell Painting channels from paired brightfield z-stacks using deep learning models. We train and validate the models with a dataset representing 1000s of pan-assay interference compounds sampled from 17 unique batches. The model predictions are evaluated using a test set from two additional batches, treated with compounds comprised from a publicly available phenotypic set. In addition to pixel-level evaluation, we process the label-free Cell Painting images with a segmentation-based feature-extraction pipeline to understand whether the generated images are useful in downstream analysis. The mean Pearson correlation coefficient (PCC) of the images across all five channels is 0.84. Without actually incorporating these features into the model training we achieved a mean correlation of 0.45 from the features extracted from the images. Additionally we identified 30 features which correlated greater than 0.8 to the ground truth. Toxicity analysis on the label-free Cell Painting resulted a sensitivity of 62.5% and specificity of 99.3% on images from unseen batches. Additionally, we provide a breakdown of the feature profiles by channel and feature type to understand the potential and limitation of the approach in morphological profiling. Our findings demonstrate that label-free Cell Painting has potential above the improved visualization of cellular components, and it can be used for downstream analysis. The findings also suggest that label-free Cell Painting could allow for repurposing the imaging channels for other non-generic fluorescent stains of more targeted biological interest, thus increasing the information content of the assay.

bioinformatics↗