bed file is not formed in the output directory.

[arthasking123]

Hi, I runned all the script in the README.md using the GLORI data, and failed to get the bed file in the output directory at last.

Here is the log:

Running RODAN basecaller 500 reads processed 1000 reads processed 1500 reads processed 2000 reads processed 2500 reads processed 3000 reads processed 3500 reads processed 4000 reads processed 4500 reads processed 5000 reads processed 5500 reads processed 6000 reads processed 6500 reads processed 7000 reads processed 7500 reads processed 8000 reads processed 8500 reads processed 9000 reads processed 9500 reads processed 10000 reads processed 10500 reads processed 11000 reads processed 11500 reads processed 12000 reads processed 12500 reads processed 13000 reads processed 13500 reads processed 14000 reads processed 14500 reads processed 15000 reads processed 15500 reads processed 16000 reads processed 16500 reads processed 17000 reads processed 17500 reads processed 18000 reads processed 18500 reads processed 19000 reads processed 19500 reads processed 20000 reads processed 20500 reads processed 21000 reads processed 21500 reads processed 22000 reads processed 22500 reads processed 23000 reads processed 23500 reads processed 24000 reads processed 24500 reads processed 25000 reads processed 25500 reads processed 26000 reads processed 26500 reads processed 27000 reads processed 27500 reads processed 28000 reads processed 28500 reads processed 29000 reads processed 29500 reads processed 30000 reads processed 30500 reads processed 31000 reads processed 31500 reads processed 32000 reads processed 32500 reads processed 33000 reads processed 33500 reads processed 34000 reads processed 34500 reads processed 35000 reads processed 35500 reads processed 36000 reads processed 36500 reads processed 37000 reads processed 37500 reads processed 38000 reads processed 38500 reads processed 39000 reads processed 39500 reads processed 40000 reads processed 40500 reads processed Total 40578 reads Finished in 1469.0 mins [samfaipath] build FASTA index... [M::mm_idx_gen::5.0210.81] collected minimizers [M::mm_idx_gen::5.8921.42] sorted minimizers [M::main::5.8921.42] loaded/built the index for 1 target sequence(s) [M::mm_mapopt_update::6.1501.40] mid_occ = 422 [M::mm_idx_stat] kmer size: 14; skip: 5; is_hpc: 0; #seq: 1 [M::mm_idx_stat::6.3491.39] distinct minimizers: 20203919 (56.71% are singletons); average occurrences: 2.607; average spacing: 2.962 [M::worker_pipeline::20.1816.33] mapped 40578 sequences [M::main] Version: 2.17-r941 [M::main] CMD: minimap2 --secondary=no -ax splice -uf -k14 -t 36 --cs /home/huajin/mafia/mAFiA/data/GRCh38_96.X.fa /home/huajin/mafia/mAFiA/output/rodan.fasta [M::main] Real time: 20.215 sec; CPU: 127.844 sec; Peak RSS: 7.359 GB

========================================================= ref_file : /home/huajin/mafia/mAFiA/data/GRCh38_96.X.fa max_num_reads : 1000 min_coverage : 50 enforce_ref_5mer : False backbone_model_path : /home/huajin/mafia/mAFiA/models/RODAN_HEK293_IVT.torch extraction_layer : convlayers.conv21 feature_width : 0 classifier_type : logistic_regression classifier_model_dir : /home/huajin/mafia/mAFiA/models/classifiers bam_file : /home/huajin/mafia/mAFiA/output/minimap.q50.bam fast5_dir : /home/huajin/mafia/mAFiA/data/fast5_chrX out_dir : /home/huajin/mafia/mAFiA/output batchsize : 2048 features_file : None mod_file : /home/huajin/mafia/mAFiA/data/GLORI_chrX.bed mod_prob_thresh : 0.5

Starting with fast5 Loading data test Indexing fast5 files from /home/huajin/mafia/mAFiA/data/fast5_chrX 100%|██████████| 11/11 [00:12<00:00, 1.14s/it] 40578 reads indexed Building dictionary of reads to mapped references Finding my backbone... Using device cpu, model RODAN_HEK293_IVT.torch at extraction layer convlayers.conv21 Parsing genome reference GRCh38_96.X.fa... Loading motif classifiers... Target motifs:
100%|██████████| 7004/7004 [00:00<00:00, 44903.09it/s] Total 0 mod. sites written to /home/huajin/mafia/mAFiA/output/mAFiA.sites.bed Total 40630 mod. reads written to /home/huajin/mafia/mAFiA/output/mAFiA.reads.bam Finished in 0.3 mins

here is the file list of the output directory:

[arthasking123]

@ADHDrian

[ADHDrian]

Hi @arthasking123 , could you please check if your /home/huajin/mafia/mAFiA/models/classifiers contains the 5mer models?