Scheduler fails Unable to find Assembly Contigs

[mbthornton-lbl]

root@scheduler-fc8fcc767-z86pz:/conf# INFO:root:Initializing Scheduler
WARNING:root:Didn't find a parent for nmdc:wfmgan-11-6x59p192.1
WARNING:root:Didn't find a parent for nmdc:wfmag-11-nvfqkd03.1
WARNING:root:Didn't find a parent for nmdc:wfmag-11-3nm9fq82.1
INFO:root:JOB RECORD: nmdc:192a1266-a79c-11ef-abb9-8e4702faa80f
ERROR:root:Unable to find Assembly Contigs in {'Annotation Amino Acid FASTA': DataObject(id='nmdc:dobj-11-80wdmm94', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_proteins.faa', description='FASTA Amino Acid File for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Annotation Amino Acid FASTA', description='FASTA amino acid file for annotated proteins'), file_size_bytes=1568923013, insdc_experiment_identifiers=[], md5_checksum='a86132980f260a7f10cc6a6ca0200da7', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_proteins.faa', was_generated_by=None), 'Functional Annotation GFF': DataObject(id='nmdc:dobj-11-0q655h25', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_functional_annotation.gff', description='Functional Annotation for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Functional Annotation GFF', description='GFF3 format file with functional annotations'), file_size_bytes=1746294812, insdc_experiment_identifiers=[], md5_checksum='0f8e90c3a8b13a8e369f5a2762e0d74d', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_functional_annotation.gff', was_generated_by=None), 'Annotation KEGG Orthology': DataObject(id='nmdc:dobj-11-j63y7w76', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_ko.tsv', description='KEGG Orthology for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Annotation KEGG Orthology', description='Tab delimited file for KO annotation'), file_size_bytes=217090712, insdc_experiment_identifiers=[], md5_checksum='09e81f0dc07ca591106812751674139c', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_ko.tsv', was_generated_by=None), 'Annotation Enzyme Commission': DataObject(id='nmdc:dobj-11-9k2tj186', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_ec.tsv', description='EC Annotations for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Annotation Enzyme Commission', description='Tab delimited file for EC annotation'), file_size_bytes=145259101, insdc_experiment_identifiers=[], md5_checksum='ce9c9cf852f51c1ca64f3caecbad1a95', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_ec.tsv', was_generated_by=None), 'Scaffold Lineage tsv': DataObject(id='nmdc:dobj-11-12c5en51', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_scaffold_lineage.tsv', description='Scaffold Lineage tsv for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Scaffold Lineage tsv', description='phylogeny at the scaffold level'), file_size_bytes=554693882, insdc_experiment_identifiers=[], md5_checksum='f2ef2add9be4c317155f270566e5a7cc', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_scaffold_lineage.tsv', was_generated_by=None), 'Clusters of Orthologous Groups (COG) Annotation GFF': DataObject(id='nmdc:dobj-11-j7tbme68', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_cog.gff', description='COGs for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Clusters of Orthologous Groups (COG) Annotation GFF', description='GFF3 format file with COGs'), file_size_bytes=902621715, insdc_experiment_identifiers=[], md5_checksum='e00b5e9dc77643bb151a1fea422463fc', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_cog.gff', was_generated_by=None), 'Pfam Annotation GFF': DataObject(id='nmdc:dobj-11-zsykqk88', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_pfam.gff', description='Pfam Annotation for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Pfam Annotation GFF', description='GFF3 format file with Pfam'), file_size_bytes=852026969, insdc_experiment_identifiers=[], md5_checksum='366244e495fd7287cbc40ca2289622c3', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_pfam.gff', was_generated_by=None), 'TIGRFam Annotation GFF': DataObject(id='nmdc:dobj-11-4zj3g939', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_tigrfam.gff', description='TIGRFam for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='TIGRFam Annotation GFF', description='GFF3 format file with TIGRfam'), file_size_bytes=104667821, insdc_experiment_identifiers=[], md5_checksum='d51a0a28872db5de8ae938087dd5a5ce', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_tigrfam.gff', was_generated_by=None), 'Product Names': DataObject(id='nmdc:dobj-11-4prrz075', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_product_names.tsv', description='Product names for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Product Names', description='Product names file'), file_size_bytes=538047136, insdc_experiment_identifiers=[], md5_checksum='f96bb33f707d1853868c232c0f68ddfa', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_product_names.tsv', was_generated_by=None), 'Gene Phylogeny tsv': DataObject(id='nmdc:dobj-11-th8bzt06', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_gene_phylogeny.tsv', description='Gene Phylogeny for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Gene Phylogeny tsv', description='Gene Phylogeny tsv'), file_size_bytes=968555416, insdc_experiment_identifiers=[], md5_checksum='367e5c6b49164afef3009432c4c11653', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_gene_phylogeny.tsv', was_generated_by=None), 'Crispr Terms': DataObject(id='nmdc:dobj-11-gc193s54', type='nmdc:DataObject', name='nmdc_wfmgan-11-6x59p192.1_crt.crisprs', description='Crispr Terms for nmdc:wfmgan-11-6x59p192.1', alternative_identifiers=[], compression_type=None, data_category=None, data_object_type=FileTypeEnum(text='Crispr Terms', description='Crispr Terms'), file_size_bytes=464124, insdc_experiment_identifiers=[], md5_checksum='9b0344d27ffcba7db05d31f4ff589cc3', url='https://data.microbiomedata.org/data/nmdc:omprc-11-cegmwy02/nmdc:wfmgan-11-6x59p192.1/nmdc_wfmgan-11-6x59p192.1_crt.crisprs', was_generated_by=None)}
Traceback (most recent call last):
  File "/usr/local/lib/python3.9/runpy.py", line 197, in _run_module_as_main
    return _run_code(code, main_globals, None,
  File "/usr/local/lib/python3.9/runpy.py", line 87, in _run_code
    exec(code, run_globals)
  File "/src/nmdc_automation/workflow_automation/sched.py", line 350, in <module>
    main()
  File "/src/nmdc_automation/workflow_automation/sched.py", line 342, in main
    sched.cycle(dryrun=dryrun, skiplist=skiplist, allowlist=allowlist)
  File "/src/nmdc_automation/workflow_automation/sched.py", line 317, in cycle
    raise ex
  File "/src/nmdc_automation/workflow_automation/sched.py", line 311, in cycle
    jr = self.create_job_rec(job)
  File "/src/nmdc_automation/workflow_automation/sched.py", line 138, in create_job_rec
    raise ValueError(f"Unable to find {do_type} in {do_by_type}")