Protocols

Protocol

Cell Engineering

This protocol describes the conditions to introduce an endogenous GFP-3XHA tag into specific organellar protein markers of interest.

Link

Protocol

Microscopy Imaging

Protocol for sample preparation and microscopy imaging.

Link

Protocol

Image Processing

Microscopy image processing pipeline.

Link

DynaCLR

We have developed self-supervised deep learning method to analyze the cell and organelle dynamics in response to perturbations, DynaCLR (Dynamic cell state analysis using Contrastive Learning of Representations).

Demos

The DynaCLR demos with setup and running instructions can be found here

Paper

DynaCLR Preprint

A self-supervised method for embedding cell and organelle Dynamics via Contrastive Learning of Representations of time-lapse images. DynaCLR integrates single-cell tracking and time-aware contrastive sampling to learn robust, temporally regularized representations of cell dynamics.

arXiv

Dataset

DynaCLR Embeddings Visualization Demo

DynaCLR vs ImageNet cell images and PHATE embeddings.

Online demo (40MB)

Code

VisCy

VisCy (blend of vision and cyto) is a deep learning pipeline for training and deploying computer vision models for image-based phenotyping at single-cell resolution.

GitHub