Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels

Cross-Zamirski, Jan Oscar; Williams, Guy B.; Mouchet, Elizabeth; Schönlieb, Carola‐Bibiane; Turkki, Riku; Wang, Yinhai

doi:10.48550/arxiv.2209.07819

Cited by 8 publications

(12 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, these methods require segmentation to locate single cells. Other approaches extract representations from whole images using supervised learning 29,30 , transfer learning 31 or a combination of self-and weakly-supervised learning 32 . These approaches are limited by the availability of training labels or the dependence on pretrained weights (e.g.…”

Section: Introductionmentioning

confidence: 99%

Self-supervision advances morphological profiling by unlocking powerful image representations

Kim

Adaloglou

Osterland

et al. 2023

Preprint

View full text Add to dashboard Cite

Morphological profiling is a powerful technology that enables unbiased characterization of cellular states through image-based screening. Inspired by recent progress in self-supervised learning (SSL), we sought to explore the potential benefits of using SSL in this domain and conducted a comprehensive benchmark study of recent SSL methods for learning representations from Cell Painting images without segmentation. We trained DINO, MAE, and SimCLR on subsets of the JUMP-CP consortium data, one of the largest publicly available Cell Painting image sets, and observed improved model performance with larger and more heterogeneous training sets. Our best model (DINO) surpassed the widely used profiling tool CellProfiler by 29% in mean average precision (mAP) on classifying chemical perturbations and significantly accelerated feature extraction by 50x, at a lower cost. Moreover, DINO outperformed CellProfiler in clustering gene families on an independent gene overexpression dataset. Our findings indicate that SSL methods can improve the efficiency and performance of morphological profiling, offering the potential to expedite drug discovery and reduce compute costs.

show abstract

Section: Introductionmentioning

confidence: 99%

Self-supervision advances morphological profiling by unlocking powerful image representations

Kim

Adaloglou

Osterland

et al. 2023

Preprint

View full text Add to dashboard Cite

show abstract

“…A more recent alternative deep learning framework that has been successful at learning HCS phenotypes is self-supervised learning 22,23 . These models work by learning to relate cropped and augmented regions from the same input image, thereby learning the patterns that are inherent in the dataset.…”

Section: Machine Learning Use Casesmentioning

confidence: 99%

“…RxRx3 can easily be used for training weakly-supervised models since the treatment column in the metadata has a unique string for each of the 102,705 perturbations in the dataset. Additionally, RxRx3 can be used for training SSL models by leveraging the raw images directly and potentially using relevant metadata 23–25 .…”

Section: Machine Learning Use Casesmentioning

confidence: 99%

RxRx3: Phenomics Map of Biology

Fay¹,

Kraus²,

Victors³

et al. 2023

Preprint

View full text Add to dashboard Cite

The combination of modern genetic perturbation techniques with high content screening has enabled genome-scale cell microscopy experiments that can be leveraged to construct maps of biology. These are built by processing microscopy images to produce readouts in unified and relatable representation space to capture known biological relationships and discover new ones. To further enable the scientific community to develop methods and insights from map-scale data, here we release RxRx3, the first ever public high-content screening dataset combining genome-scale CRISPR knockouts with multiple-concentration screening of small molecules (a set of FDA approved and commercially available bioactive compounds). The dataset contains 6-channel fluorescent microscopy images and associated deep learning embeddings from over 2.2 million wells that span 17,063 CRISPR knockouts and 1,674 compounds at 8 doses each. RxRx3 is one of the largest collections of cellular screening data, and as far as we know, the largest generated consistently via a common experimental protocol within a single laboratory. Our goal in releasing RxRx3 is to demonstrate the benefits of generating consistent data, enable the development of the machine learning methods on this scale of data and to foster research, methods development, and collaboration.

show abstract

“…Recently, self-supervised methods have been shown to match the performance of supervised models on natural image computer vision tasks [49,50,51]. Applying such training techniques for microscopy screening data [52,53] represents a potentially fruitful direction for this work.…”

Section: Future Directionsmentioning

confidence: 99%

RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods

Sypetkowski¹,

Rezanejad²,

Saberian³

et al. 2023

Preprint

View full text Add to dashboard Cite

High-throughput screening techniques are commonly used to obtain large quantities of data in many fields of biology. It is well known that artifacts arising from variability in the technical execution of different experimental batches within such screens confound these observations and can lead to invalid biological conclusions. It is therefore necessary to account for these batch effects when analyzing outcomes. In this paper we describe RxRx1, a biological dataset designed specifically for the systematic study of batch effect correction methods. The dataset consists of 125,510 high-resolution fluorescence microscopy images of human cells under 1,138 genetic perturbations in 51 experimental batches across 4 cell types. Visual inspection of the images alone clearly demonstrates significant batch effects. We propose a classification task designed to evaluate the effectiveness of experimental batch correction methods on these images and examine the performance of a number of correction methods on this task. Our goal in releasing RxRx1 is to encourage the development of effective experimental batch correction methods that generalize well to unseen experimental batches. The dataset can be downloaded at https://rxrx.ai.

show abstract

Self-Supervised Learning of Phenotypic Representations from Cell Images with Weak Labels

Cited by 8 publications

References 24 publications

Self-supervision advances morphological profiling by unlocking powerful image representations

Self-supervision advances morphological profiling by unlocking powerful image representations

RxRx3: Phenomics Map of Biology

RxRx1: A Dataset for Evaluating Experimental Batch Correction Methods

Contact Info

Product

Resources

About