-
Notifications
You must be signed in to change notification settings - Fork 34
Open
Description
I've tried to run this twice now, it's a very large dataset the Xenium Output is like 95GB and the transcrip.csv is like 7 GB. I'm not sure if the large file size has something to do with this? I am also running this on a linux cloud workstation, perhaps that is the issue?
(runa_20250711) user@w-matthewevrardctr-mcdccdxm:~$ baysor run transcripts.csv cell_segmentation_mask.tif --prior-segmentation-confidence=0.7 -x x_location -y y_location -z z_location -g feature_name -m 30 -s 5 --polygon-format='GeometryCollectionLegacy' -o segmentation_results.csv
--plot
[21:58:58] Info: Run R37315fd90
[21:58:58] Info: (2025-07-11) Run Baysor v0.7.1
[21:58:58] Info: Loading data...
[22:04:58] Info: Loaded 69592945 transcripts, 10009 genes.
[22:06:36] Info: Loading segmentation mask...
[22:13:39] Warning: Maximum transcript coordinates are (22360, 11485), which is much smaller than the prior image size: (105309, 54075). May be result of an error.
└ Baysor.DataLoading /home/viktor_petukhov/.julia/dev/Baysor/src/data_loading/prior_segmentation.jl:34
[22:13:59] Info: Done
[22:13:59] Info: Estimating prior segmentation polygons...
[22:14:18] Info: Done
[22:14:26] Info: Estimating noise level
[23:49:18] Info: Done
[00:40:13] Info: Clustering molecules...
Progress: 100%|██████████████████████████████████████████| Time: 10:15:48
Iteration: 1719
Max. difference: 0.00635
Fraction of probs changed: 0.0303
[12:22:01] Info: Algorithm stopped after 1719 iterations. Max. probability difference: 0.00635. Converged: true.
[12:22:03] Info: Done
[12:24:34] Info: Initializing algorithm. Scale: 5.0, scale std: 1.25, initial #components: 4639528, #molecules: 69592945.
Killed
Metadata
Metadata
Assignees
Labels
No labels