search

comprna / CHEUI

Concurrent identification of m6A and m5C modifications in individual molecules from nanopore sequencing
Other
30 stars 2 forks source link

multi-threading in running model 1 #21

Open rezarahman12 opened 1 year ago

rezarahman12 commented 1 year ago

Hi CHEUI team,

I'm running the below cheui script for almost 24 hours with 28 CPU in HPC, however, it seems slow. Is there any way to specify CPU core as we can do in CHEUI preprocessing steps?

python /scratch/qbi/uqmrah19/CHEUI/scripts/CHEUI_predict_model1.py \ -i /scratch/qbi/uqmrah19/CHEUI/cheui/ONT_Reza/cheui_analysis/ctrl1/out_A_signals+IDs.p/eventalign_signals+IDS.p \ -m /scratch/qbi/uqmrah19/CHEUI/CHEUI_trained_models/CHEUI_m6A_model1.h5 \ -o ./read_level_m6A_predictions_WT_rep1.txt \ -l WT_rep1

I appreciate your time.

Best regards Reza

vetmohit89 commented 5 days ago

Hello, I'm experiencing similar issues. The CHEUI_predict_model1.py script runs painfully slow, possibly due to loading and predicting on every single signal. Is there a way to speed up this process?