awesome-awesomeness/html/cytodata.html

<h1 id="awesome-cytodata-awesome">Awesome Cytodata <a
href="https://awesome.re"><img src="https://awesome.re/badge.svg"
alt="Awesome" /></a></h1>
<blockquote>
<p>A curated list of awesome cytodata resources.</p>
</blockquote>
<figure>
<img src="cytodata-logo.png" alt="cytodata logo" />
<figcaption aria-hidden="true">cytodata logo</figcaption>
</figure>
<p><a href="https://cytodata.org/">Cytodata</a> refers to a community of
researchers and resources involved in the <strong>image-based
profiling</strong> of <strong>biological phenotypes</strong>. These
<strong>biological phenotypes</strong> are typically induced by genetic
or chemical perturbations and often represent disease states.
<strong>Image-based profiling</strong> is used to inspect these
phenotypes to uncover biological insight including discovering the
impact of genetic alterations and determining the mechanism of action of
compounds.</p>
<p>This page represents a curated list of software, datasets, landmark
publications, and image-based profiling methods. Our goal is to provide
researchers, both new and established, a place to discover and document
awesome Cytodata resources.</p>
<h2 id="contents">Contents</h2>
<ul>
<li><a href="#datasets">Datasets</a>
<ul>
<li><a href="#raw-images">Raw Images</a></li>
<li><a href="#chemical-perturbations">Chemical Perturbations</a></li>
<li><a href="#genetic-perturbations">Genetic Perturbations</a></li>
</ul></li>
<li><a href="#software">Software</a></li>
<li><a href="#publications">Publications</a>
<ul>
<li><a href="#reviews">Reviews</a></li>
<li><a href="#applications">Applications</a></li>
<li><a href="#methods">Methods</a></li>
</ul></li>
</ul>
<h2 id="datasets">Datasets</h2>
<p>Annotated datasets, including <strong>raw images</strong> and
<strong>processed profiles</strong>, for image-based profiling of
chemical and genetic perturbations.</p>
<h3 id="raw-images">Raw Images</h3>
<ul>
<li><a href="https://broad.io/CellPaintingGallery">The Cell Painting
Gallery</a> - The Cell Painting Gallery is a collection of image
datasets created using the Cell Painting assay (or similar); it is
maintained by the Carpenter–Singh lab at the Broad Institute.</li>
<li><a href="https://data.broadinstitute.org/bbbc/">Broad Bioimage
Benchmark Collection</a> - The Broad Bioimage Benchmark Collection
(BBBC) is a collection of freely downloadable microscopy image sets. In
addition to the images themselves, each set includes a description of
the biological application and some type of “ground truth” (expected
results).</li>
<li><a href="https://idr.openmicroscopy.org/">Image Data Resource</a> -
Public repository of image datasets from published scientific
studies.</li>
<li><a href="https://www.rxrx.ai/rxrx1">RxRx1</a> - RxRx1 is a set of
125,514 high-resolution 512x512 6-channel fluorescence microscopy images
of human cells under 1,108 genetic perturbations in 51 experimental
batches across four cell types. The images were produced by Recursion
Pharmaceuticals in their labs in Salt Lake City, Utah. Researchers will
use this dataset for studying and benchmarking methods for dealing with
biological batch effects, as well as areas in machine learning such as
domain adaptation, transfer learning, and k-shot learning.</li>
<li><a href="https://www.rxrx.ai/rxrx19">RxRx19</a> - RxRx19 is the
first morphological dataset that demonstrates the rescue of
morphological effects of COVID-19.</li>
<li><a
href="https://www.proteinatlas.org/humanproteome/subcellular">Human
Protein Atlas</a> - Among other assays, the HPA performed confocal
imaging of displaying the location of more than 2/3 of human proteins in
cell lines. <a
href="https://github.com/CellProfiling/HPA-competition#script-to-download-hpav18">Raw
images</a> or <a
href="https://www.proteinatlas.org/about/download">infered protein
subcellular locations</a> can be downloaded.</li>
</ul>
<h3 id="chemical-perturbations">Chemical Perturbations</h3>
<ul>
<li><a href="https://doi.org/10.1371/journal.pone.0080999">Gustafsdottir
et al. 2013</a> - Cell painting profiles from 1,600 bioactive compounds
in U2OS cells (Access from public S3 bucket:
<code>s3://cytodata/datasets/Bioactives-BBBC022-Gustafsdottir/profiles/Bioactives-BBBC022-Gustafsdottir/</code>).</li>
<li><a href="https://doi.org/10.1073/pnas.1410933111">Wawer et
al. 2014</a> - Cell painting profiles from 31,770 compounds in U2OS
cells (<a
href="http://www.broadinstitute.org/mlpcn/data/Broad.PNAS2014.ProfilingData.zip">Click
to download</a>).</li>
<li><a href="https://doi.org/10.1093/gigascience/giw014">Bray et
al. 2017</a> - Cell painting profiles from 30,616 compounds in U2OS
cells (Center Driven Research Project <em>CDRP</em>) (<a
href="https://doi.org/10.5524/100351">Download from GigaDB</a> | Access
from public S3 bucket:
<code>s3://cytodata/datasets/CDRPBIO-BBBC036-Bray/profiles_cp/CDRPBIO-BBBC036-Bray/</code>).</li>
<li><a href="https://doi.org/10.1038/s41592-022-01667-0">Haghighi et
al. 2021</a> - Cell painting matched to L1000 profiles in 4 experiments,
including compound and genetic screens (<a
href="https://github.com/carpenterlab/2021_Haghighi_submitted">Details
on GitHub</a>).</li>
</ul>
<h3 id="genetic-perturbations">Genetic Perturbations</h3>
<ul>
<li><a href="https://doi.org/10.1371/journal.pone.0131370">Singh et
al. 2015</a> - 3,072 cell painting profiles from 41 genes knocked down
with RNA interference (RNAi) in U2OS cells (<a
href="https://github.com/carpenterlab/2016_bray_natprot/blob/6dcdcf72cd90bb2dbf238b3ecf94691246d8f104/supplementary_files/profiles.csv.zip">Access
from GitHub</a>).</li>
<li><a href="https://doi.org/10.7554/eLife.24060.001">Rohban et
al. 2017</a> - Cell painting data from 220 overexpressed genes in U2OS
cells (Access from public S3 bucket:
<code>s3://cytodata/datasets/TA-ORF-BBBC037-Rohban/profiles_cp/TA-ORF-BBBC037-Rohban/</code>).</li>
<li>Unpublished - Cell painting profiles of 596 overexpressed alleles
from 53 genes in A549 cells (Access from public S3 bucket:
<code>s3://cytodata/datasets/LUAD-BBBC043-Caicedo/profiles_cp/LUAD-BBBC043-Caicedo/</code>)</li>
<li>Unpublished - 3,456 cell painting profiles from CRISPR experiments
knocking down 59 genes in A549, ES2, and HCC44 cells (<a
href="https://github.com/broadinstitute/cell-health/tree/master/0.generate-profiles/data/profiles">Access
from GitHub</a>).</li>
</ul>
<h2 id="software">Software</h2>
<p>Open source software packages for image-based profiling of biological
phenotypes.</p>
<ul>
<li><a href="https://www.cellclassifier.org/">Advanced Cell
Classifier</a> - A software package for exploration, annotation and
classification of cells within large datasets using machine
learning.</li>
<li><a href="http://cellprofiler.org/">CellProfiler</a> - CellProfiler
is a free open-source software for measuring and analyzing cell
images.</li>
<li><a href="http://cellprofiler.org/cp-analyst/">CellProfiler
Analyst</a> - Interactive data exploration, analysis, and classification
of large biological image sets.</li>
<li><a href="https://github.com/cytomining/cytominer">Cytominer</a> -
Methods for image-based cell profiling in R.</li>
<li><a href="https://github.com/aoles/EBImage">EBImage</a> - Image
processing toolbox for R.</li>
<li><a href="http://htsvis.dkfz.de/HTSvis/">HTSvis</a> - A web app for
exploratory data analysis and visualization of arrayed high-throughput
screens.</li>
<li><a
href="https://github.com/menchelab/BioProfiling.jl">BioProfiling.jl</a>
- Toolkit for filtering and curation of morphological profiles in
Julia.</li>
<li><a href="https://github.com/cytomining/pycytominer">PyCytominer</a>
- Methods for image-based cell profiling in Python.</li>
<li><a href="https://imjoy.io">ImJoy</a> - A platform compiling tool for
deep-learning based image analyses with a GUI.</li>
<li><a href="https://github.com/BodenmillerGroup/histoCAT">histoCAT</a>
- Toolbox to extract quantitative phenotypic descriptors and contextual
information for histology and multiplex imaging.</li>
</ul>
<h2 id="publications">Publications</h2>
<p>Publications related to image-based profiling.</p>
<h3 id="reviews">Reviews</h3>
<ul>
<li><a
href="https://www.nature.com/articles/s41573-020-00117-w">Image-based
profiling for drug discovery: due for a machine-learning upgrade?</a> -
2020 review of applications in image-based profiling from a Carpenter
lab/pharma perspective.</li>
<li><a href="https://doi.org/10.1038/nmeth.4397">Data-analysis
strategies for image-based cell profiling</a> - Introduce the steps
required to create high-quality image-based (i.e., morphological)
profiles from a collection of microscopy images.</li>
<li><a href="https://doi.org/10.1016/j.tcb.2016.03.008">High-content
screening for quantitative cell biology</a> - Describe some recent
applications of HCS, ranging from the identification of genes required
for specific biological processes to the characterization of genetic
interactions.</li>
<li><a
href="https://doi.org/10.1016/j.cell.2015.11.007">Microscopy-based
high-content screening</a> - Describe the state of the art for
image-based screening experiments and delineate experimental approaches
and image-analysis approaches as well as discussing challenges and
future directions, including leveraging CRISPR/Cas9-mediated genome
engineering.</li>
<li><a href="https://doi.org/10.1016/j.copbio.2016.04.003">Applications
in image-based profiling of perturbations</a> - Describe applications of
image-based profiling including target and MOA identification, lead
hopping, library enrichment, gene annotation and identification of
disease-specific phenotypes</li>
<li><a href="https://doi.org/10.1002/cyto.a.22909">Large-scale
image-based screening and profiling of cellular phenotypes</a> -
Overview of image-based profiling, including its applications and
challenges.</li>
<li><a href="https://dx.doi.org/10.1002%2Fbies.201400011">How cells
explore shape space: A quantitative statistical perspective of cellular
morphogenesis</a> - Discussion on the biology of cell shape changes
based on quantitative descriptors.</li>
<li><a href="https://doi.org/10.1016/J.COISB.2018.05.004">Machine
learning and image-based profiling in drug discovery</a> - Introduction
to morphological profiling and discussion on what machine learning has
to offer.</li>
<li><a href="https://doi.org/10.15252/msb.202110768">Pooled genetic
screens with image-based profiling</a> - Review of the different
modalities available for genetic screens and which ones are suitable for
morphological profiling.</li>
</ul>
<h3 id="collections">Collections</h3>
<ul>
<li><a href="https://www.nature.com/collections/cfcdjceech">Deep
learning in microscopy</a> - A collection of review and research
articles published in Nature Methods related to multiple use cases of
deep learning, including noise reduction, segmentation, tracking and
representation learning.</li>
<li><a href="https://journals.sagepub.com/toc/jbxb/25/7">High-Content
Imaging and Informatics</a> - A collection of high-content imaging
method and application articles published in SLAS Discovery.</li>
</ul>
<h3 id="applications">Applications</h3>
<ul>
<li><a href="https://rdcu.be/ccBFH">Expanding the antibacterial
selectivity of polyether ionophore antibiotics through diversity-focused
semisynthesis</a> - Poulsen lab paper from 2020 where antibiotics are
tested for their ability to leave mammalian cells as intact as possible,
per the Cell Painting assay.</li>
<li><a href="https://doi.org/10.1038/nmeth1032">Image-based multivariate
profiling of drug responses from single cells</a> - A multivariate
method for classifying untreated and treated human cancer cells based on
∼300 single-cell phenotypic measurements.</li>
<li><a href="https://doi.org/10.1016/j.molmet.2019.03.001">Discovering
metabolic disease gene interactions by correlated effects on cellular
morphology</a> - Profiling disease-gene interaction during adipocyte
differentiation.</li>
<li><a href="https://doi.org/10.1038/nature08869">Phenotypic profiling
of the human genome by time-lapse microscopy reveals cell division
genes</a> - This study provides an in-depth analysis of cell division
phenotypes and makes the entire high-content data set available as a
resource to the community.</li>
<li><a href="https://doi.org/10.1016/j.taap.2019.114876">Bioactivity
screening of environmental chemicals using imaging-based high-throughput
phenotypic profiling</a> - Use of image-based profiling to screen the
bioactivity of environmental chemicals</li>
<li><a href="https://doi.org/10.1016/j.chembiol.2018.01.015">Repurposing
High-Throughput Image Assays Enables Biological Activity Prediction for
Drug Discovery</a> - Using image-based profiles to predict the
bioactivity of small molecules in other unrelated assays.</li>
<li><a href="https://doi.org/10.1038/s41598-020-69354-8">Tales of 1,008
Small Molecules: Phenomic Profiling through Live-cell Imaging in a Panel
of Reporter Cell Lines</a> - Demonstrating the effects of
polypharmacology in MOA prediction while offering solutions for
overcoming it in future image-based profiling studies.</li>
<li><a href="https://doi.org/10.1038/s41467-019-13058-9">Mapping the
perturbome network of cellular perturbations</a> - Image-based profiling
and network analysis of drug combinations.</li>
<li><a href="https://doi.org/10.1016/j.celrep.2021.109318">Morphological
profiling of human T and NK lymphocytes by high-content cell imaging</a>
- Image-based profiling of actin organization at the immunological
synapse.</li>
<li><a href="https://doi.org/10.1126/science.aal3321">A subcellular map
of the human proteome</a> - Classification of protein subcellular
location from confocal microscopy images of the Human Protein
Atlas.</li>
<li><a href="https://doi.org/10.1038/s41586-021-04115-9">A multi-scale
map of cell structure fusing protein images and interactions</a> -
Combining confocal imaging and mass spectrometry representations of
proteins to predict physical proximity and characterize cellular
organization.</li>
<li><a href="https://doi.org/10.1091/mbc.E20-12-0784">Predicting cell
health phenotypes using image-based morphology profiling</a> -
Image-based profiles as predictors of apoptosis, proliferation and other
cell health descriptors.</li>
<li><a href="https://doi.org/10.15252/msb.20199243">Systematic genetics
and single‐cell imaging reveal widespread morphological pleiotropy and
cell‐to‐cell variability</a> - Analysis of single-cell profiles to
characterize variability, pleiotropy and incomplete penetrance.</li>
<li><a href="https://doi.org/10.15252/msb.20178064">Large‐scale
image‐based profiling of single‐cell phenotypes in arrayed CRISPR‐Cas9
gene perturbation screens</a> - Demonstrates feasibility of imaging
arrayed CRISPR screens and offers a way to characterize transfection
efficacy in individual cells.</li>
<li><a href="https://doi.org/10.1038/s41467-022-30722-9">Multiparametric
phenotyping of compound effects on patient derived organoids</a> -
Profiling chemical effects on patient-derived organoids.</li>
<li><a href="https://doi.org/10.15252/MSB.20156400">A chemical-genetic
interaction map of small molecules using high-throughput imaging in
cancer cells</a> - Profiling the morphological changes induced in 1280
compounds in 12 knockout cell lines.</li>
<li><a href="https://doi.org/10.7554/eLife.40174">Time-resolved mapping
of genetic interactions to model rewiring of signaling pathways</a> -
Changes in genetic interactions across time based on multiple
morphological descriptors.</li>
<li><a href="https://doi.org/10.1016/j.cels.2019.09.002">High-Content
Imaging of Unbiased Chemical Perturbations Reveals that the Phenotypic
Plasticity of the Actin Cytoskeleton Is Constrained</a> - Defining
morphological clusters in a large compound screen.</li>
<li><a href="https://doi.org/10.7554/eLife.05464">A map of directional
genetic interactions in a metazoan cell</a> - Characterizing genetic
interactions by integrating 21 phenotypic descriptors.</li>
<li><a href="https://doi.org/10.1016/j.cell.2022.10.017">The phenotypic
landscape of essential human genes</a> - Comparing morphological
descriptors in a pooled CRISPR screen with in-situ sequencing</li>
<li><a href="https://doi.org/10.1101/580654">Evaluation of Gene
Expression and Phenotypic Profiling Data as Quantitative Descriptors for
Predicting Drug Targets and Mechanisms of Action</a> - Benchmarking
profiling modalities, including image-based profiles, for mechanism of
action prediction.</li>
<li><a href="https://doi.org/10.15252/msb.202211087">The molecular
architecture of cell cycle arrest</a> - Comparing cellular features
across stages of the cell cycle.</li>
<li><a href="https://doi.org/10.1038/s41586-022-05563-7">Integrated
intracellular organization and its variations in human iPS cells</a> -
Decomposing cellular and nuclear shapes in 3D in multiple iPSC and
studying association between cellular structures.</li>
<li><a href="https://doi.org/10.1038/s41587-020-0651-8">Single-cell
metabolic profiling of human cytotoxic T cells</a> - Combining metabolic
profiling and spatial information to define immune subsets in tumor
microenvironments.</li>
<li><a href="https://doi.org/10.1038/s41586-019-1876-x">The single-cell
pathology landscape of breast cancer</a> - Defining cell populations and
their interactions in breast cancer based on shape, intensity and
contextual information from multiplexed imaging.</li>
<li><a href="https://doi.org/10.1101%2Fgr.276059.121">Identification of
phenotype-specific networks from paired gene expression–cell shape
imaging data</a> - Looking for gene networks underlying cellular
morphology by matching expression and imaging data.</li>
<li><a href="https://doi.org/10.1371/journal.pcbi.1009888">Predicting
drug polypharmacology from cell morphology readouts using variational
autoencoder latent space arithmetic</a> - Model cell morphology with
autoencoders to estimate effects of drug combinations.</li>
<li><a href="https://doi.org/10.1158/2643-3230.BCD-21-0219">Deep
Morphology Learning Enhances Ex Vivo Drug Profiling-Based Precision
Medicine</a> - Concrete description of how morphological information can
be extracted from patient material and guide treatment.</li>
</ul>
<h3 id="methods">Methods</h3>
<ul>
<li><a href="https://doi.org/10.1038/nprot.2016.105">Cell Painting, a
high-content image-based assay for morphological profiling using
multiplexed fluorescent dyes</a> - Protocol describing the design and
execution of experiments using Cell Painting.</li>
<li><a href="https://doi.org/10.1371/journal.pone.0080999">Multiplex
Cytological Profiling Assay to Measure Diverse Cellular States</a> -
Cell Painting assay.</li>
<li><a href="https://doi.org/10.1038/nmeth.3323">CIDRE: an
illumination-correction method for optical microscopy</a> -
Retrospective method for illumination-correction based on energy
minimization.</li>
<li><a
href="https://doi.org/10.1046/j.1365-2818.2000.00669.x">Retrospective
shading correction based entropy minimization</a> - Method for
retrospective shading correction based on entropy minimization.</li>
<li><a href="https://doi.org/10.1038/s41467-019-10154-8">Capturing
single-cell heterogeneity via data fusion improves image-based
profiling</a> - Adds dispersion and covariances to population averages
to capture single-cell heterogeneity.</li>
<li><a href="https://doi.org/10.1142/S0219720005001004">Minimum
redundancy feature selection from microarray gene expression data</a> -
Minimum redundancy - maximum relevance feature selection framework.</li>
<li><a href="https://doi.org/10.1371/journal.pcbi.1007348">Learning
unsupervised feature representations for single cell microscopy images
with paired cell inpainting</a> - Selfsupervised method to learn feature
representations of single cells in microscopy images without labelled
training data.</li>
<li><a href="https://doi.org/10.1109/CVPR.2018.00970">Weakly supervised
learning of single-cell feature embeddings</a> - Training CNNs using a
weakly supervised approach for feature learning.</li>
<li><a href="https://doi.org/10.1021/acs.jcim.8b00670">Accurate
Prediction of Biological Assays with High-Throughput Microscopy Images
and Convolutional Networks</a> - End-to-end learning with CNNs to
predict bioactivity of small molecules in unrelated assays using
image-based profiles.</li>
<li><a href="https://doi.org/10.1002/cyto.a.23863">Evaluation of Deep
Learning Strategies for Nucleus Segmentation in Fluorescence Images</a>
- Comparing several deep learning methods for nuclear segmentation.</li>
<li><a href="https://doi.org/10.1101/085118">Automating Morphological
Profiling with Generic Deep Convolutional Networks</a> - Transfer of
activation features of generic CNNs to extract features for image-based
profiling.</li>
<li><a href="https://doi.org/10.1038/ncomms14836">A BaSiC tool for
background and shading correction of optical microscopy images</a> -
Illumination-correction method accounting for space- and time-dependent
biases.</li>
<li><a href="https://doi.org/10.1038/s41592-020-01018-x">Cellpose: a
generalist algorithm for cellular segmentation</a> - Generalist deep
learning model for cell and nucleus segmentation with pre-trained
weights.</li>
<li><a href="https://doi.org/10.1371/journal.pcbi.1005177">Deep Learning
Automates the Quantitative Analysis of Individual Cells in Live-Cell
Imaging Experiments</a> - DeepCell: collection of deep learning
segmentation models.</li>
<li><a href="https://doi.org/10.1101/161422">Improving Phenotypic
Measurements in High-Content Imaging Screens</a> - Embedding single-cell
and compound profiles using transfer learning, examplified on mechanism
of action prediction.</li>
<li><a href="https://doi.org/10.1177/1087057112469257">The
Multidimensional Perturbation Value</a> - Proposing a score to define
significant activity in screens.</li>
<li><a href="https://doi.org/10.1038/s41598-022-12914-x">Label-Free
Prediction of Cell Painting from Brightfield Images</a> - Reconstructing
images for Cell Painting dyes and ensuring corresponding morphological
measurements are preserved.</li>
<li><a href="https://doi.org/10.3389/fbinf.2022.788607">ShapoGraphy: A
User-Friendly Web Application for Creating Bespoke and Intuitive
Visualisation of Biomedical Data</a> - Method to visualize morphological
profiles.</li>
<li><a href="https://doi.org/10.1101/227645">CytoGAN: Generative
Modeling of Cell Images</a> - Generative network displaying potential
for learning latent representation of biological conditions from cell
images.</li>
<li><a
href="https://doi.org/https://doi.org/10.1093/bioinformatics/btaa905">Self-supervised
feature extraction from image time series in plant phenotyping using
triplet networks</a> - Direct extraction of phenotypic features from
plant images.</li>
<li><a href="https://doi.org/10.1016/j.cels.2022.10.001">Morphology and
gene expression profiling provide complementary information for mapping
cell state</a> - Comparison of the information contained in Cell
Painting and L1000 assays for the same perturbations.</li>
<li><a href="https://doi.org/10.1093/bioinformatics/btab497">Fully
unsupervised deep mode of action learning for phenotyping high-content
cellular images</a> - Unsupervised approach to represent cellular
morphology with clusters corresponding to meaningful relations such as
mechanism of action. With an overview of deep learning methods for
morphological profiling and classification.</li>
<li><a href="https://doi.org/10.1038/s41592-022-01508-0">Automated
high-speed 3D imaging of organoid cultures with multi-scale phenotypic
quantification</a> - Experimental and computational workflow to extract
3D morphological descriptors of organoids using light-sheet
microscopy.</li>
</ul>
<h2 id="contribute">Contribute</h2>
<p>Contributions welcome! Read the <a
href="contributing.md">contribution guidelines</a> first.</p>
<h2 id="license">License</h2>
<p><a href="http://creativecommons.org/publicdomain/zero/1.0"><img
src="http://mirrors.creativecommons.org/presskit/buttons/88x31/svg/cc-zero.svg"
alt="CC0" /></a></p>
<p><a href="https://github.com/cytodata/awesome-cytodata">cytodata.md
Github</a></p>