Is rnamotif mandatory? how do i complement it to the software? #13
Comments
|
fixed calling the rnamotif through export rnamotif directory, but the same prolem still persists: [06:04:37] INFO Beginning search for viroid-like RNAs using 30 threads... INFO Searching for circular sequences in k_15_final_contigs.fa. Not compiled with -d:danger. This will likely cause severe slowdowns. KeyError: ('CPEB3_ribozyme',) |
here's a consistent output of a run:
[10:05:23] INFO Beginning search for viroid-like RNAs using 10 threads... easy_search.py:108 INFO Searching for circular sequences in k_15_final_contigs.fa. find_circs.py:61Not compiled with -d:danger. This will likely cause severe slowdowns.
[10:05:24] DONE 1,904 circRNAs found from 46,303 sequences (11 Mbp/sec). rich_wrapper.py:115 INFO Removing duplicate sequences... dedup.py:25 DONE 0 duplicate sequences removed. rich_wrapper.py:115 INFO Searching k_15_final_contigs_vdsearch/deduped_circs.fasta using cmsearch infernal.py:99[10:05:54] DONE Done searching for ribozymes using cmsearch. rich_wrapper.py:115 ERROR Unable to find rnamotif executable. utils.py:17 WARNING Could not run RNAmotif. Skipping. easy_search.py:178 INFO Analyzing 155 ribozymes in 118 sequences to find viroid-like sequences... ribozyme_filter.py:95╭─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/bin/vdsearch:33 in │
│ │
│ 30 │
│ 31 if name == 'main': │
│ 32 │ sys.argv[0] = re.sub(r'(-script.pyw?|.exe)?$', '', sys.argv[0]) │
│ ❱ 33 │ sys.exit(load_entry_point('vdsearch', 'console_scripts', 'vdsearch')()) │
│ 34 │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ distribution = <function distribution at 0x7fdfe38e6040> │ │
│ │ importlib_load_entry_point = <function importlib_load_entry_point at 0x7fdfe4a89160> │ │
│ │ load_entry_point = <function importlib_load_entry_point at 0x7fdfe4a89160> │ │
│ │ re = <module 're' from │ │
│ │ '/home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/re.p… │ │
│ │ sys = <module 'sys' (built-in)> │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/typer/main.py:289 in │
│ call │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/typer/main.py:280 in │
│ call │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/click/core.py:1157 in │
│ call │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/rich_click/rich_command.p │
│ y:126 in main │
│ │
│ 123 │ │ try: │
│ 124 │ │ │ try: │
│ 125 │ │ │ │ with self.make_context(prog_name, args, **extra) as ctx: │
│ ❱ 126 │ │ │ │ │ rv = self.invoke(ctx) │
│ 127 │ │ │ │ │ if not standalone_mode: │
│ 128 │ │ │ │ │ │ return rv │
│ 129 │ │ │ │ │ # it's not safe to
ctx.exit(rv)here! ││ │
│ ╭─────────────────────────────────────── locals ────────────────────────────────────────╮ │
│ │ _detect_program_name = <function _detect_program_name at 0x7fdfe2bc3670> │ │
│ │ args = [ │ │
│ │ │ 'easy-search', │ │
│ │ │ 'k_15_final_contigs.fa', │ │
│ │ │ '--outdir', │ │
│ │ │ 'k_15_final_contigs_vdsearch', │ │
│ │ │ '--threads', │ │
│ │ │ '10' │ │
│ │ ] │ │
│ │ complete_var = None │ │
│ │ ctx = <rich_click.rich_context.RichContext object at 0x7fdf24ed2eb0> │ │
│ │ extra = {} │ │
│ │ prog_name = 'vdsearch' │ │
│ │ self = │ │
│ │ standalone_mode = True │ │
│ │ windows_expand_args = True │ │
│ ╰───────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/click/core.py:1688 in │
│ invoke │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/click/core.py:1434 in │
│ invoke │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/click/core.py:783 in │
│ invoke │
│ │
│ /home/Public/Anaconda3/ENTER/envs/vdsearch/lib/python3.9/site-packages/typer/main.py:607 in │
│ wrapper │
│ │
│ /home/Public/software/vdsearch/vdsearch/commands/easy_search.py:187 in easy_search │
│ │
│ 184 │ rz_seqs = outdir / "seqs_with_rzs.fasta" │
│ 185 │ viroidlike_rzs = outdir / "seqs_with_rzs.tsv" │
│ 186 │ if not rz_seqs.exists() or not viroidlike_rzs.exists(): │
│ ❱ 187 │ │ ribozymes = ribozyme_filter( │
│ 188 │ │ │ cmsearch_tblout, │
│ 189 │ │ │ output_tsv=viroidlike_rzs, │
│ 190 │ │ │ cm_file=reference_cms, │
│ │
│ ╭─────────────────────────────────────── locals ────────────────────────────────────────╮ │
│ │ canonicalize = True │ │
│ │ circs = PosixPath('k_15_final_contigs_vdsearch/circs.fasta') │ │
│ │ circular = False │ │
│ │ cmsearch_output = PosixPath('k_15_final_contigs_vdsearch/infernal.out') │ │
│ │ cmsearch_tblout = PosixPath('k_15_final_contigs_vdsearch/infernal.tblout') │ │
│ │ deduped_circs = PosixPath('k_15_final_contigs_vdsearch/deduped_circs.fasta') │ │
│ │ fasta = PosixPath('k_15_final_contigs.fa') │ │
│ │ force = False │ │
│ │ lockfile = PosixPath('k_15_final_contigs_vdsearch/.vdsearch.lock') │ │
│ │ outdir = PosixPath('k_15_final_contigs_vdsearch') │ │
│ │ reference_cms = PosixPath('/home/ZL_DSL_Meta/.config/vdsearch/data/cms/merged') │ │
│ │ reference_db = PosixPath('/home/ZL_DSL_Meta/.config/vdsearch/data/viroiddb.fasta') │ │
│ │ rnamotif_output = PosixPath('k_15_final_contigs_vdsearch/rnamotif.tsv') │ │
│ │ rz_seqs = PosixPath('k_15_final_contigs_vdsearch/seqs_with_rzs.fasta') │ │
│ │ threads = 10 │ │
│ │ tmpdir = PosixPath('.') │ │
│ │ viroidlike_rzs = PosixPath('k_15_final_contigs_vdsearch/seqs_with_rzs.tsv') │ │
│ ╰───────────────────────────────────────────────────────────────────────────────────────╯ │
│ │
│ /home/Public/software/vdsearch/vdsearch/commands/ribozyme_filter.py:122 in ribozyme_filter │
│ │
│ 119 │ │ if use_cm_cutoff and cutoffs: │
│ 120 │ │ │ rz_plus.update( │
│ 121 │ │ │ │ rz_df.query( │
│ ❱ 122 │ │ │ │ │ f"strand == '+' & score > {cutoffs[rz_name][cm_cutoff_type]}" │
│ 123 │ │ │ │ ).seq_id │
│ 124 │ │ │ ) │
│ 125 │ │ │ rz_minus.update( │
│ │
│ ╭─────────────────────────────────────────── locals ───────────────────────────────────────────╮ │
│ │ cm_cutoff_type = 'GA' │ │
│ │ cm_file = PosixPath('/home/ZL_DSL_Meta/.config/vdsearch/data/cms/merged') │ │
│ │ cutoffs = { │ │
│ │ │ 'twister-P1': {'GA': 67.2, 'TC': 67.2, 'NC': 67.1}, │ │
│ │ │ 'Twister-P5': {'GA': 37.6, 'TC': 37.6, 'NC': 37.5}, │ │
│ │ │ 'Hatchet': {'GA': 51.0, 'TC': 54.5, 'NC': 39.6}, │ │
│ │ │ 'Twister-sister': {'GA': 37.8, 'TC': 37.8, 'NC': 36.0}, │ │
│ │ │ 'Hammerhead_3': {'GA': 41.8, 'TC': 41.8, 'NC': 41.7}, │ │
│ │ │ 'Hairpin-meta1': {'GA': 40.0, 'TC': 40.9, 'NC': 38.5}, │ │
│ │ │ 'Hovlinc': {'GA': 42.3, 'TC': 42.3, 'NC': 36.2}, │ │
│ │ │ 'Hairpin-meta2': {'GA': 210.0, 'TC': 212.6, 'NC': 35.7}, │ │
│ │ │ 'HDV-F-prausnitzii': {'GA': 44.0, 'TC': 44.1, 'NC': 43.8}, │ │
│ │ │ 'Pistol': {'GA': 34.0, 'TC': 34.0, 'NC': 33.8}, │ │
│ │ │ ... +12 │ │
│ │ } │ │
│ │ infernal_tblout = PosixPath('k_15_final_contigs_vdsearch/infernal.tblout') │ │
│ │ max_evalue = 0.01 │ │
│ │ output_tsv = PosixPath('k_15_final_contigs_vdsearch/seqs_with_rzs.tsv') │ │
│ │ ribozymes = │ │ seq_id accession ribozyme from to strand score │ │
│ │ evalue inc │ │
│ │ 0 k141_27579 - twister-P1 260 363 + 12.1 │ │
│ │ 6.600 ? │ │
│ │ 1 k141_42017 - Twister-sister 88 10 - 19.5 │ │
│ │ 0.062 ? │ │
│ │ 2 k141_25190 - Twister-sister 217 147 - 19.1 │ │
│ │ 0.081 ? │ │
│ │ 3 k141_41430 - Twister-sister 12 82 + 18.4 │ │
│ │ 0.120 ? │ │
│ │ 4 k141_20387 - Twister-sister 76 18 - 16.9 │ │
│ │ 0.310 ? │ │
│ │ .. ... ... ... ... ... ... ... │ │
│ │ ... .. │ │
│ │ 150 k141_47732 - Pospi_RY 214 255 + 12.8 │ │
│ │ 8.100 ? │ │
│ │ 151 k141_6600 - Pospi_RY 189 230 + 12.8 │ │
│ │ 8.100 ? │ │
│ │ 152 k141_38451 - Pospi_RY 184 225 + 12.8 │ │
│ │ 8.100 ? │ │
│ │ 153 k141_34836 - Pospi_RY 152 75 - 12.5 │ │
│ │ 9.700 ? │ │
│ │ 154 k141_64733 - Pospi_RY 152 75 - 12.5 │ │
│ │ 9.700 ? │ │
│ │ │ │
│ │ [155 rows x 9 columns] │ │
│ │ rnamotif_name = 'Hammerhead_3' │ │
│ │ rnamotif_txt = PosixPath('k_15_final_contigs_vdsearch/rnamotif.tsv') │ │
│ │ rz_df = │ │ seq_id accession ribozyme from to strand score │ │
│ │ evalue inc │ │
│ │ 102 k141_36226 - CPEB3_ribozyme 153 100 - 13.0 │ │
│ │ 0.47 ? │ │
│ │ 103 k141_50486 - CPEB3_ribozyme 189 125 - 11.4 │ │
│ │ 1.50 ? │ │
│ │ 104 k141_46816 - CPEB3_ribozyme 141 226 + 10.8 │ │
│ │ 2.40 ? │ │
│ │ 105 k141_20248 - CPEB3_ribozyme 212 148 - 10.7 │ │
│ │ 2.70 ? │ │
│ │ 106 k141_19770 - CPEB3_ribozyme 155 229 + 10.4 │ │
│ │ 3.40 ? │ │
│ │ 107 k141_21114 - CPEB3_ribozyme 101 149 + 10.0 │ │
│ │ 4.70 ? │ │
│ │ 108 k141_19420 - CPEB3_ribozyme 37 9 - 9.8 │ │
│ │ 5.30 ? │ │
│ │ 109 k141_13469 - CPEB3_ribozyme 58 1 - 9.6 │ │
│ │ 6.20 ? │ │
│ │ 110 k141_46874 - CPEB3_ribozyme 224 169 - 9.6 │ │
│ │ 6.40 ? │ │
│ │ 111 k141_34158 - CPEB3_ribozyme 58 9 - 9.4 │ │
│ │ 7.20 ? │ │
│ │ 112 k141_18044 - CPEB3_ribozyme 90 24 - 9.3 │ │
│ │ 8.10 ? │ │
│ │ 113 k141_22929 - CPEB3_ribozyme 253 284 + 9.2 │ │
│ │ 8.30 ? │ │
│ │ 114 k141_9993 - CPEB3_ribozyme 61 10 - 9.1 │ │
│ │ 9.30 ? │ │
│ │ rz_minus = set() │ │
│ │ rz_name = ('CPEB3_ribozyme',) │ │
│ │ rz_plus = set() │ │
│ │ rz_significant = set() │ │
│ │ use_cm_cutoff = True │ │
│ │ use_evalue_cutoff = True │ │
│ ╰──────────────────────────────────────────────────────────────────────────────────────────────╯ │
╰──────────────────────────────────────────────────────────────────────────────────────────────────╯
KeyError: ('CPEB3_ribozyme',)
How do i resolve this? how do i add the rnamotif into the pipeline? how to complete the run since it's clearly not finished?
The text was updated successfully, but these errors were encountered: