-
Notifications
You must be signed in to change notification settings - Fork 58
Open
Description
Hi,
Thank you for providing this wonderful tool. I'm processing DNase-seq data and I'm running into similar issues as reported in #153, #174, and #176.
When I try to train a bias model, I get this error:
Traceback (most recent call last):
File "/root/miniconda3/envs/chrombpnet/bin/chrombpnet", line 7, in <module>
sys.exit(main())
File "/root/miniconda3/envs/chrombpnet/lib/python3.10/site-packages/chrombpnet/CHROMBPNET.py", line 38, in main
pipelines.train_bias_pipeline(args)
File "/root/miniconda3/envs/chrombpnet/lib/python3.10/site-packages/chrombpnet/pipelines.py", line 278, in train_bias_pipeline
reads_to_bigwig.main(args)
File "/root/miniconda3/envs/chrombpnet/lib/python3.10/site-packages/chrombpnet/helpers/preprocessing/reads_to_bigwig.py", line 96, in main
plus_shift, minus_shift = auto_shift_detect.compute_shift(args.input_bam_file,
File "/root/miniconda3/envs/chrombpnet/lib/python3.10/site-packages/chrombpnet/helpers/preprocessing/auto_shift_detect.py", line 234, in compute_shift
plus_shift, minus_shift = compute_shift_DNASE(ref_plus_pwms, ref_minus_pwms, plus_pwm, minus_pwm)
File "/root/miniconda3/envs/chrombpnet/lib/python3.10/site-packages/chrombpnet/helpers/preprocessing/auto_shift_detect.py", line 211, in compute_shift_DNASE
raise ValueError("Input file shifts inconsistent. Please post an Issue")
ValueError: Input file shifts inconsistent. Please post an Issue
Following previous posts, I created a PWM for my file
The PWM seems similar to example DNase cleavage logos shown in previous posts. What’s surprising is that I have another sample from the same experiment, all processing steps identical, and for that one I’m able to train both the bias and chrombpnet models with good outputs. I have also confirmed that all reads are trimmed from the 3' end.
Any help would be appreciated, thank you!
Reactions are currently unavailable
Metadata
Metadata
Assignees
Labels
No labels