diff options
-rw-r--r-- | bh20sequploader/bh20seq-schema.yml | 22 | ||||
-rw-r--r-- | bh20sequploader/supporting_webuploader.yml | 28 | ||||
-rw-r--r-- | scripts/from_genbank_to_fasta_and_yaml.py | 12 | ||||
-rw-r--r-- | scripts/sequences.acc | 396 |
4 files changed, 282 insertions, 176 deletions
diff --git a/bh20sequploader/bh20seq-schema.yml b/bh20sequploader/bh20seq-schema.yml index 0520e36..4cd0865 100644 --- a/bh20sequploader/bh20seq-schema.yml +++ b/bh20sequploader/bh20seq-schema.yml @@ -84,6 +84,11 @@ $graph: type: string? jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0001479 + specimen_source2: + doc: A specimen that derives from an anatomical part or substance arising from an organism, e.g. tissue, organ + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/OBI_0001479 collection_date: doc: Date when the sample was taken type: string? @@ -139,6 +144,11 @@ $graph: type: string jsonldPredicate: _id: http://purl.obolibrary.org/obo/OBI_0600047 + sample_sequencing_technology2: + doc: Technology that was used to sequence this sample (e.g Sanger, Nanopor MiniION) + type: string? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/OBI_0600047 sequence_assembly_method: doc: Protocol which provides instructions on the alignment of sequencing reads to reference genome type: string? @@ -146,9 +156,19 @@ $graph: _id: http://www.ebi.ac.uk/efo/EFO_0002699 sequencing_coverage: doc: Sequence coverage defined as the average number of reads representing a given nucleotide (e.g. 100x) - type: int? + type: float? + jsonldPredicate: + _id: http://purl.obolibrary.org/obo/FLU_0000848 + sequencing_coverage2: + doc: If a second sequence technology was use you can submit its coverage here + type: float? jsonldPredicate: _id: http://purl.obolibrary.org/obo/FLU_0000848 + additional_technology_information: + doc: Field for additional technology information + type: string? + jsonldPredicate: + _id: http://semanticscience.org/resource/SIO_001167 - name: submitterSchema type: record diff --git a/bh20sequploader/supporting_webuploader.yml b/bh20sequploader/supporting_webuploader.yml index 6b8946f..3650526 100644 --- a/bh20sequploader/supporting_webuploader.yml +++ b/bh20sequploader/supporting_webuploader.yml @@ -10,6 +10,34 @@ host_sex: Female: http://purl.obolibrary.org/obo/NCIT_C27993 unknown: http://purl.obolibrary.org/obo/NCIT_C17998 +sample_sequencing_technology: + Illumina NextSeq 500: http://www.ebi.ac.uk/efo/EFO_0009173 + Oxford Nanopore MinION: http://www.ebi.ac.uk/efo/EFO_0008632 + Illumina MiSeq: http://www.ebi.ac.uk/efo/EFO_0004205 + IonTorrent: http://purl.obolibrary.org/obo/NCIT_C125894 + Oxford Nanopore Sequencing: http://purl.obolibrary.org/obo/NCIT_C146818 + Sanger dideoxy sequencing: http://purl.obolibrary.org/obo/NCIT_C19641 + +sample_sequencing_technology2: + Illumina NextSeq 500: http://www.ebi.ac.uk/efo/EFO_0009173 + Oxford Nanopore MinION: http://www.ebi.ac.uk/efo/EFO_0008632 + Illumina MiSeq: http://www.ebi.ac.uk/efo/EFO_0004205 + IonTorrent: http://purl.obolibrary.org/obo/NCIT_C125894 + Oxford Nanopore Sequencing: http://purl.obolibrary.org/obo/NCIT_C146818 + Sanger dideoxy sequencing: http://purl.obolibrary.org/obo/NCIT_C19641 + +specimen_source: + nasopharyngeal swab: http://purl.obolibrary.org/obo/NCIT_C155831 + oropharyngeal swab: http://purl.obolibrary.org/obo/NCIT_C155835 + sputum: http://purl.obolibrary.org/obo/NCIT_C13278 + bronchoalveolar lavage fluid: http://purl.obolibrary.org/obo/NCIT_C13195 + +specimen_source2: + nasopharyngeal swab: http://purl.obolibrary.org/obo/NCIT_C155831 + oropharyngeal swab: http://purl.obolibrary.org/obo/NCIT_C155835 + sputum: http://purl.obolibrary.org/obo/NCIT_C13278 + bronchoalveolar lavage fluid: http://purl.obolibrary.org/obo/NCIT_C13195 + host_species: OLS-ontology: ncbitaxon diff --git a/scripts/from_genbank_to_fasta_and_yaml.py b/scripts/from_genbank_to_fasta_and_yaml.py index 0cc1a57..6a55b5e 100644 --- a/scripts/from_genbank_to_fasta_and_yaml.py +++ b/scripts/from_genbank_to_fasta_and_yaml.py @@ -7,7 +7,7 @@ import os path_ncbi_virus_accession = 'sequences.acc' -date = '20200414' +date = '20200415' path_seq_fasta = 'seq_from_nuccore.{}.fasta'.format(date) path_metadata_xml = 'metadata_from_nuccore.{}.xml'.format(date) @@ -19,9 +19,15 @@ for term in term_list: tmp_list = Entrez.read( Entrez.esearch(db='nuccore', term=term, idtype='acc', retmax='10000') )['IdList'] - print(term, len(tmp_list)) - + + # Remove mRNAs, ncRNAs, Proteins, and predicted models (more information here: https://en.wikipedia.org/wiki/RefSeq) + tmp_list = [x for x in tmp_list if x[:2] not in ['NM', 'NR', 'NP', 'XM', 'XR', 'XP', 'WP']] + # Remove the version in the id + tmp_list = [x.split('.')[0] for x in tmp_list] + + print(term, len(tmp_list)) + id_set.update([x.split('.')[0] for x in tmp_list]) print(term_list, len(id_set)) diff --git a/scripts/sequences.acc b/scripts/sequences.acc index 62bde2c..a420fb4 100644 --- a/scripts/sequences.acc +++ b/scripts/sequences.acc @@ -1,25 +1,159 @@ -MT325599 -MT325601 -MT325602 -MT325607 -MT325608 -MT325609 -MT325610 -MT325612 -MT325616 -MT325617 -MT325618 -MT325622 -MT325623 -MT325600 -MT325606 -MT325611 -MT325613 -MT325615 -MT325619 -MT325620 -MT325624 -MT325625 +NC_045512 +MT334522 +MT334523 +MT334524 +MT334525 +MT334526 +MT334527 +MT334528 +MT334529 +MT334530 +MT334531 +MT334532 +MT334533 +MT334534 +MT334535 +MT334536 +MT334537 +MT334538 +MT334539 +MT334540 +MT334541 +MT334542 +MT334543 +MT334544 +MT334545 +MT334546 +MT334555 +MT334547 +MT334548 +MT334549 +MT334550 +MT334551 +MT334552 +MT334553 +MT334554 +MT334556 +MT334557 +MT334558 +MT334559 +MT334560 +MT334561 +MT334562 +MT334563 +MT334564 +MT334565 +MT334566 +MT334567 +MT334568 +MT334569 +MT334570 +MT334571 +MT334572 +MT334573 +MT324062 +MT324680 +MT324684 +MT325573 +MT325574 +MT325576 +MT325577 +MT325578 +MT325580 +MT325591 +MT325592 +MT325593 +MT325595 +MT325605 +MT325627 +MT326028 +MT326029 +MT326031 +MT326048 +MT326093 +MT326092 +MT326091 +MT326090 +MT326085 +MT326084 +MT326083 +MT326082 +MT326081 +MT326080 +MT326077 +MT326067 +MT326057 +MT326024 +MT326025 +MT326032 +MT326033 +MT326035 +MT326036 +MT326037 +MT326040 +MT326041 +MT326043 +MT326044 +MT326046 +MT326049 +MT326050 +MT326052 +MT326053 +MT326055 +MT326056 +MT326059 +MT326062 +MT326063 +MT326066 +MT326069 +MT326070 +MT326071 +MT326073 +MT326074 +MT326075 +MT326088 +MT326089 +MT327745 +MT325568 +MT325572 +MT325575 +MT325583 +MT325584 +MT325604 +MT325631 +MT325632 +MT325635 +MT325636 +MT325637 +MT326095 +MT326096 +MT326103 +MT326112 +MT326113 +MT326114 +MT326115 +MT326122 +MT326131 +MT326132 +MT326133 +MT325563 +MT326164 +MT326166 +MT326167 +MT325570 +MT325579 +MT325581 +MT325582 +MT325586 +MT325594 +MT325598 +MT325626 +MT325628 +MT325633 +MT325634 +MT326030 +MT326038 +MT326058 MT325565 MT325566 MT326147 @@ -56,7 +190,6 @@ MT326121 MT326119 MT326109 MT326100 -MT325568 MT324679 MT325561 MT325571 @@ -95,31 +228,11 @@ MT326177 MT326184 MT326185 MT326187 -MT325572 -MT325575 -MT325583 -MT325584 -MT325604 -MT325631 -MT325632 -MT325635 -MT325636 -MT325637 -MT326095 -MT326096 -MT326103 -MT326112 -MT326113 -MT326114 -MT326115 -MT326122 -MT326131 -MT326132 -MT326133 -MT325563 -MT326164 -MT326166 -MT326167 +MT324681 +MT324682 +MT324683 +MT328032 +MT328035 MT325569 MT326097 MT326106 @@ -177,146 +290,83 @@ MT326101 MT326099 MT326098 MT326094 -MT326093 -MT326092 -MT326091 -MT326090 -MT326085 -MT326084 -MT326083 -MT326082 -MT326081 -MT326080 -MT326077 -MT326067 -MT326057 -MT326024 -MT326025 -MT326032 -MT326033 -MT326035 -MT326036 -MT326037 -MT326040 -MT326041 -MT326043 -MT326044 -MT326046 -MT326049 -MT326050 -MT326052 -MT326053 -MT326055 -MT326056 -MT326059 -MT326062 -MT326063 -MT326066 -MT326069 -MT326070 -MT326071 -MT326073 -MT326074 -MT326075 -MT326088 -MT326089 -MT327745 -MT324062 -MT324680 -MT324684 -MT325573 -MT325574 -MT325576 -MT325577 -MT325578 -MT325580 -MT325591 -MT325592 -MT325593 -MT325595 -MT325605 -MT325627 -MT326028 -MT326029 -MT326031 -MT326048 -MT325570 -MT325579 -MT325581 -MT325582 -MT325586 -MT325594 -MT325598 -MT325626 -MT325628 -MT325633 -MT325634 -MT326030 -MT326038 -MT326058 -MT324681 -MT324682 -MT324683 -MT328032 -MT328035 +MT325599 +MT325601 +MT325602 +MT325607 +MT325608 +MT325609 +MT325610 +MT325612 +MT325616 +MT325617 +MT325618 +MT325622 +MT325623 +MT325600 +MT325606 +MT325611 +MT325613 +MT325615 +MT325619 +MT325620 +MT325624 +MT325625 +MT322394 +MT322395 +MT322420 +MT322424 MT039874 MT077125 -MT322394 +MT322396 MT322397 -MT322398 MT322399 +MT322403 +MT322406 +MT322407 +MT322412 +MT322413 +MT322414 +MT322416 +MT322398 MT322400 MT322401 -MT322403 +MT322402 MT322404 MT322405 -MT322406 MT322408 MT322409 MT322410 MT322411 -MT322412 -MT322413 -MT322414 MT322415 -MT322416 MT322417 MT322418 MT322419 -MT322420 MT322421 MT322422 MT322423 -MT322424 -MT322396 -MT322402 -MT322395 -MT322407 -MT320538 MT320891 +MT320538 MT308692 MT308693 +MT308695 +MT308696 MT308698 MT308699 +MT308701 MT308703 MT308704 MT308694 -MT308695 -MT308696 MT308697 MT308700 -MT308701 MT308702 MT304476 MT304474 MT304475 MT293547 MT304477 -MT304483 -MT300186 MT304478 MT304479 -MT304480 MT304481 MT304482 MT304484 @@ -324,9 +374,12 @@ MT304485 MT304486 MT304487 MT304488 +MT304491 +MT304480 +MT304483 MT304489 MT304490 -MT304491 +MT300186 MT291831 MT291836 MT291834 @@ -366,7 +419,6 @@ MT293168 MT293175 MT293190 MT293191 -MT273658 MT293159 MT292582 MT293162 @@ -376,7 +428,6 @@ MT293165 MT293156 MT293157 MT293158 -MT281577 MT293171 MT293174 MT293176 @@ -426,6 +477,8 @@ MT293223 MT291826 MT291832 MT291833 +MT273658 +MT281577 MT281530 MT276331 MT276325 @@ -645,8 +698,6 @@ MT253700 MT253705 MT253709 MT253708 -MT233526 -MT246667 MT246451 MT246453 MT246454 @@ -689,6 +740,8 @@ MT246472 MT246473 MT246483 MT246484 +MT233526 +MT246667 MT240479 MT232869 MT232870 @@ -774,8 +827,8 @@ MT127113 MT127114 MT127115 MT126808 -LC528233 LC528232 +LC528233 MT123290 MT123291 MT123292 @@ -807,8 +860,8 @@ MT066159 MT066175 MT066176 LC523807 -LC523808 LC523809 +LC523808 MT044258 MT044257 MT042777 @@ -830,7 +883,6 @@ LC522350 MT027062 MT027063 MT027064 -MT020781 MT019530 MT019531 MT020881 @@ -838,13 +890,14 @@ MT019533 MT019529 MT019532 MT020880 +MT020781 LR757995 LR757996 LR757997 LR757998 MT007544 -MT008023 MT008022 +MT008023 MN996530 MN996531 MN996527 @@ -856,22 +909,21 @@ MN988668 MN988669 MN994467 MN988713 -MN938387 -MN938389 -MN975263 -MN975268 +MN938384 +MN975262 +MN985325 +MN975264 +MN975266 MN975267 +MN975268 MN938388 +MN938389 MN938390 -MN975264 -MN975265 -MN975266 -MN938386 +MN975263 MN938385 -MN938384 -MN975262 -MN985325 +MN938386 +MN938387 +MN975265 MN970003 MN970004 -NC_045512 MN908947 |