Soorya19Pradeep

Cellular infection phenotyping using annotated viral sensor data & label-free images

4

The goal of the analysis is to identify infected and uninfected cells in a FOV using either viral sensor fluorescence or label-free images with nuclear instance segmentation label to output...

Improving the visualization of predictions logged on Tensorboard by setting appropriate intensity scale. Currently the intensity scaling of the predicted images shows artifacts from other structures of cells not involved...

Three channel output using covnext model

9

I want to train the covnext model for the infection classifier problem. The model will use two or more input channels (phase + HSP90 channels + infection score channels, etc.)...

The following error message is seen when I try to convert Micromanager data `/hpc/instruments/cm.dragonfly/Dashboard_aim2/2024_08_14_ZIKV_pal17_48h/2024_08_14_ZIKV_pal17_48h_1/` using iohub convert function: > WARNING:tifffile.tifffile: invalid value offset 0 > WARNING:tifffile.tifffile: failed to read display...

Computed features vs PC with new AnnData format

2

The code is modified to read from the zarrs with the new anndata format. @srivarra, can you let me know if there is a better way to do this? @edyoshikun...

Following issues were observed with the PC viewer: - [ ] plotly caches some information in the web browser. Clearing cache from the browser and rerunning code helps here: SP...

Prediction on multiple dataset

1

@edyoshikun , @ziw-liu, I need to run inference on multiple datasets for the organelle box project. The main bottleneck is computing PHATE on these datasets together. Currently, the PHATE is...