NVIDIA-Genomics-Research / AtacWorks

Deep learning based processing of Atac-seq data
https://clara-parabricks.github.io/AtacWorks/
Other
127 stars 23 forks source link

error message needing help #244

Open elffairy90 opened 3 years ago

elffairy90 commented 3 years ago

Hi,

Could I run my code like this? Do you see any problems? I mean for the weights_path, could it be my own big.wig of a clean sample? But, when I ran this, i ran into this following problem. I'm new to dry lab, I would really appreciate your help! Thank you!

atacworks denoise \ --noisybw /data/jwang/files_atacworks/test/control_R1.mLb.clN.bigWig \ --genome /data/jwang/AtacWorks/data/reference/mm10.auto.sizes \ --weights_path /data/jwang/files_atacworks/training/atacworks/control_R1.mLb.clN.bigWig \ --out_home "./" \ --exp_name "atacworks_denoise" \ --distributed \ --num_workers 0

INFO:2021-07-18 10:57:51,501:AtacWorks-intervals] Generating intervals tiling across all chromosomes in sizes file: /data/jwang/AtacWorks/data/reference/mm10.auto.sizes INFO:2021-07-18 10:57:51,598:AtacWorks-intervals] Done! Traceback (most recent call last): File "/usr/local/share/virtualenvs/env37/bin/atacworks", line 8, in sys.exit(main()) File "/usr/local/share/virtualenvs/env37/lib/python3.7/site-packages/scripts/main.py", line 487, in main extension=".bw") File "/usr/local/share/virtualenvs/env37/lib/python3.7/site-packages/atacworks/dl4atac/utils.py", line 235, in gather_files_from_cmdline assert path.endswith(extension) AssertionError

avantikalal commented 2 years ago

HI @elffairy90. --weights_path should be not a bigwig file but the path to a trained AtacWorks model. You can either train a model yourself using clean and noisy bigwig files (see tutorial 1) or else download one of our trained models. We recommend training a model if you have data available.