Metadata-guided Consistency Learning for High Content Images
Preprint
Abstract
High content imaging assays can capture rich phenotypic response data for large sets of compound treatments, aiding in the characterization and discovery of novel drugs. However, extracting representative features from high content images that can capture subtle nuances in phenotypes remains challenging. The lack of high-quality labels makes it difficult to achieve satisfactory results with supervised deep learning. Self-Supervised learning methods have shown great success on natural images, and offer an attractive alternative also to microscopy images. However, we find that self-supervised learning techniques underperform on high content imaging assays. One challenge is the undesirable domain shifts present in the data known as batch effects, which are caused by biological noise or uncontrolled experimental conditions. To this end, we introduce Cross-Domain Consistency Learning (CDCL), a self-supervised approach that is able to learn in the presence of batch effects. CDCL enforces the learning of biological similarities while disregarding undesirable batch-specific signals, leading to more useful and versatile representations. These features are organised according to their morphological changes and are more useful for downstream tasks -- such as distinguishing treatments and mechanism of action.Keywords
All Related Versions
This publication has 11 references indexed in Scilit:
- Learning representations for image-based profiling of perturbationsNature Communications, 2024
- Morphology and gene expression profiling provide complementary information for mapping cell stateCell Systems, 2022
- Cell Morphological Profiling Enables High-Throughput Screening for PROteolysis TArgeting Chimera (PROTAC) Phenotypic SignatureACS Chemical Biology, 2022
- Emerging Properties in Self-Supervised Vision Transformers2021
- Fully unsupervised deep mode of action learning for phenotyping high-content cellular imagesBioinformatics, 2021
- Accurate Prediction of Biological Assays with High-Throughput Microscopy Images and Convolutional NetworksJournal of Chemical Information and Modeling, 2019
- A test metric for assessing single-cell RNA-seq batch correctionNature Methods, 2018
- Repurposing High-Throughput Image Assays Enables Biological Activity Prediction for Drug DiscoveryCell Chemical Biology, 2018
- Cell Painting, a high-content image-based assay for morphological profiling using multiplexed fluorescent dyesNature Protocols, 2016
- Adjusting batch effects in microarray expression data using empirical Bayes methodsBiostatistics, 2006