A new version of ResearchHub is available.Try it now
Healthy Research Rewards
ResearchHub is incentivizing healthy research behavior. At this time, first authors of open access papers are eligible for rewards. Visit the publications tab to view your eligible publications.
Got it
JC
Juan Caicedo
Author with expertise in Advanced Techniques in Bioimage Analysis and Microscopy
Achievements
Cited Author
Open Access Advocate
Key Stats
Upvotes received:
0
Publications:
10
(70% Open Access)
Cited by:
954
h-index:
12
/
i10-index:
12
Reputation
Biology
< 1%
Chemistry
< 1%
Economics
< 1%
Show more
How is this calculated?
Publications
5

Learning representations for image-based profiling of perturbations

Nikita Moshkov et al.Aug 15, 2022
Abstract Measuring the phenotypic effect of treatments on cells through imaging assays is an efficient and powerful way of studying cell biology, and requires computational methods for transforming images into quantitative data that highlight phenotypic outcomes. Here, we present an optimized strategy for learning representations of treatment effects from high-throughput imaging data, which follows a causal framework for interpreting results and guiding performance improvements. We use weakly supervised learning (WSL) for modeling associations between images and treatments, and show that it encodes both confounding factors and phenotypic features in the learned representation. To facilitate their separation, we constructed a large training dataset with Cell Painting images from five different studies to maximize experimental diversity, following insights from our causal analysis. Training a WSL model with this dataset successfully improves downstream performance, and produces a reusable convolutional network for image-based profiling, which we call Cell Painting CNN-1 . We conducted a comprehensive evaluation of our strategy on three publicly available Cell Painting datasets, discovering that representations obtained by the Cell Painting CNN-1 can improve performance in downstream analysis for biological matching up to 30% with respect to classical features, while also being more computationally efficient.
1

Cell Painting predicts impact of lung cancer variants

Juan Caicedo et al.Nov 20, 2021
Abstract Most variants in most genes across most organisms have an unknown impact on the function of the corresponding gene. This gap in knowledge is especially acute in cancer, where clinical sequencing of tumors now routinely reveals patient-specific variants whose functional impact on the corresponding gene is unknown, impeding clinical utility. Transcriptional profiling was able to systematically distinguish these variants of unknown significance (VUS) as impactful vs. neutral in an approach called expression-based variant-impact phenotyping (eVIP). We profiled a set of lung adenocarcinoma-associated somatic variants using Cell Painting, a morphological profiling assay that captures features of cells based on microscopy using six stains of cell and organelle components. Using deep-learning-extracted features from each cell’s image, we found that cell morphological profiling (cmVIP) can predict variants’ functional impact and, particularly at the single-cell level, reveals biological insights into variants which can be explored in our public online portal. Given its low cost, convenient implementation, and single-cell resolution, cmVIP profiling therefore seems promising as an avenue for using non-gene-specific assays to systematically assess the impact of variants, including disease-associated alleles, on gene function.
1
Citation3
0
Save