Warning message - unsure if process is running or not?

[benjytan88]

I am running pyScenic using a Singularity container (v 0.12.1) on my dataset of 90k cells and 38k genes. The process has been running for ~15 hours now and I couldn't see any output files, not even intermediate files. I'm not sure if the process is running or not as the error message is not really helpful. I've seen several similar problems (#482, #559) but no definite solution yet. The error message is as below:

2025-08-15 23:38:46,923 - pyscenic.cli.pyscenic - INFO - Loading expression matrix.
2025-08-15 23:49:29,922 - pyscenic.cli.pyscenic - INFO - Inferring regulatory networks.
2025-08-15 23:49:32,830 - distributed.diskutils - INFO - Found stale lock file and directory '/tmp/dask-worker-space/worker-d11wfcny', purging
2025-08-15 23:49:32,831 - distributed.diskutils - INFO - Found stale lock file and directory '/tmp/dask-worker-space/worker-x_b1nsov', purging
2025-08-15 23:51:11,895 - distributed.worker - WARNING - Could not find data: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:45117', 'tcp://127.0.0.1:39271', 'tcp://127.0.0.1:45549']} on workers: [] (who_has: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:45117', 'tcp://127.0.0.1:39271', 'tcp://127.0.0.1:45549']})
2025-08-15 23:51:11,895 - distributed.worker - WARNING - Could not find data: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:45117', 'tcp://127.0.0.1:39271', 'tcp://127.0.0.1:45549']} on workers: [] (who_has: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:45117', 'tcp://127.0.0.1:39271', 'tcp://127.0.0.1:45549']})
2025-08-15 23:51:12,442 - distributed.scheduler - WARNING - Worker tcp://127.0.0.1:40685 failed to acquire keys: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ('tcp://127.0.0.1:45117', 'tcp://127.0.0.1:39271', 'tcp://127.0.0.1:45549')}
2025-08-15 23:51:12,442 - distributed.scheduler - WARNING - Worker tcp://127.0.0.1:41113 failed to acquire keys: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ('tcp://127.0.0.1:45117', 'tcp://127.0.0.1:39271', 'tcp://127.0.0.1:45549')}
2025-08-15 23:51:18,149 - distributed.worker - WARNING - Could not find data: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:37527']} on workers: [] (who_has: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:37527']})
2025-08-15 23:51:18,694 - distributed.scheduler - WARNING - Worker tcp://127.0.0.1:42825 failed to acquire keys: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ('tcp://127.0.0.1:37527',)}
2025-08-15 23:51:30,560 - distributed.worker - WARNING - Could not find data: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:40685']} on workers: [] (who_has: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ['tcp://127.0.0.1:40685']})
2025-08-15 23:51:31,417 - distributed.scheduler - WARNING - Worker tcp://127.0.0.1:32861 failed to acquire keys: {'ndarray-93797bde12500efd0a5f0ff429118ad7': ('tcp://127.0.0.1:40685',)}

I needed to run SCENIC analysis for my data, but I have been stuck on making it work for the past 2 weeks. Would appreciate if anyone could offer a solution.

[ghuls]

Try to run with less threads or make sure you have enough memory.