cd /Users/sr320/Desktop/
/Users/sr320/Desktop
!/Users/sr320/Dropbox/Steven/ipig_r5/ipig /Users/sr320/Dropbox/Steven/ipig_r5/examples/PSM_example.mzid -c /Users/sr320/Dropbox/Steven/ipig_r5/ipig.conf
# /Volumes/web/oyster/bioinformatics/xml_files/interact-20120821_103B_251_QE_02.pep.mzid \
error: wrong number of parameters
!/Users/sr320/Dropbox/Steven/ipig_r5/ipig \
/Users/sr320/Dropbox/Steven/ipig_r5/examples/PSM_example.mzid \
error: can't find file (/Users/sr320/Desktop/ipig.conf)
!head -50 /Users/sr320/Desktop/Crassostrea_gigas.GCA_000297895.1.21.dat.dat
ID C12728 standard; DNA; HTG; 200 BP. XX AC supercontig:GCA_000297895.1:C12728:1:200:1 XX SV C12728.GCA_000297895.1 XX DT 29-NOV-2013 XX DE Crassostrea gigas supercontig C12728 GCA_000297895.1 full sequence 1..200 DE annotated by Ensembl Genomes XX KW . XX OS Crassostrea gigas (Crassostrea gigas) OC cellular organisms; Eukaryota; Opisthokonta; Metazoa; Eumetazoa; Bilateria; OC Protostomia; Lophotrochozoa; Mollusca; Bivalvia; Pteriomorphia; Ostreoida; OC Ostreoidea; Ostreidae; Crassostrea. XX CC This sequence displays annotation from Ensembl Genomes based on underlying CC annotation from GigaDB(http://dx.doi.org/10.5524/100030). See CC http://www.ensemblgenomes.org for more information. XX CC All feature locations are relative to the first (5') base of the sequence CC in this file. The sequence presented is always the forward strand of the CC assembly. Features that lie outside of the sequence contained in this file CC have clonal location coordinates in the format: <clone CC accession>.<version>:<start>..<end> XX CC The /gene indicates a unique id for a gene, /note="transcript_id=..." a CC unique id for a transcript, /protein_id a unique id for a peptide and CC note="exon_id=..." a unique id for an exon. These ids are maintained CC wherever possible between versions. XX FH Key Location/Qualifiers FT source 1..200 FT /organism="Crassostrea gigas" FT /db_xref="taxon:29159" FT misc_feature 1..200 FT /note="contig AFTI01025347.1 1..200(1)" XX SQ Sequence 200 BP; 39 A; 37 C; 28 G; 96 T; 0 other; TTTTTCTTAT TTTTATTTGT ACCAGTTAAT CCTGTGAGCC GCTTTTATGT CTCTTTCTGG 60 CCGTTTTTAT GTCTCTTTCT GTTGACTTTA TTATTCTCTC ATTTATGATT TAACATCTCA 120 TATGAATTAT TATGTGTATC TTGCATGGGA TATTTTGCCA CTTCGTGCCC ATAAAAATCA 180 ACACTTGTCT TTCGGTGTAT 200 // ID C12722 standard; DNA; HTG; 200 BP. XX AC supercontig:GCA_000297895.1:C12722:1:200:1 XX
need oyster data in this format
Example UCSC Genes:
#name chrom strand txStart txEnd cdsStart cdsEnd exonCount exonStarts exonEnds proteinID alignID
uc009vjk.2 chr1 + 322036 326938 324342 325605 3 322036,324287,324438, 322228,324345,326938, C9J4L2 uc009vjk.2
uc001aau.3 chr1 + 323891 328581 324342 325605 3 323891,324287,324438, 324060,324345,328581, C9J4L2 uc001aau.3
Example Ensemble Genes:
#bin name chrom strand txStart txEnd cdsStart cdsEnd exonCount exonStarts exonEnds score name2 cdsStartStat cdsEndStat exonFrames
9 ENST00000472741 chr1 - 1026425 1051467 1051467 1051467 3 1026425,1027370,1051439, 1026945,1027483,1051467, 0 ENSG00000131591 none none -1,-1,-1,
34 ENST00000478275 chr1 - 212859759 212872097 212872097 212872097 2 212859759,212870302, 212860321,212872097, 0 ENSG00000123685 none none -1,-1,
!tail /Volumes/web/cnidarian/ets_v9_f.gff
scaffold22 GLEAN exon 1863760 1864161 . + 0 ID=CGI_10028938; scaffold22 GLEAN CDS 1869336 1885890 0.999933 - . Parent=CGI_10028939; scaffold22 GLEAN exon 1885752 1885890 . - 0 ID=CGI_10028939; scaffold22 GLEAN exon 1884184 1884318 . - 2 ID=CGI_10028939; scaffold22 GLEAN exon 1882962 1883093 . - 2 ID=CGI_10028939; scaffold22 GLEAN exon 1881349 1881486 . - 2 ID=CGI_10028939; scaffold22 GLEAN exon 1879212 1879349 . - 2 ID=CGI_10028939; scaffold22 GLEAN exon 1870764 1870843 . - 2 ID=CGI_10028939; scaffold22 GLEAN exon 1870289 1870360 . - 0 ID=CGI_10028939; scaffold22 GLEAN exon 1869336 1869428 . - 0 ID=CGI_10028939;
!head -20 /Volumes/web/cnidarian/Crassostrea_gigas.GCA_000297895.1.21.gff3
##gff-version 3 scaffold1611 protein_coding gene 1263 9963 . - . ID=CGI_10014322;Name=CGI_10014322 scaffold1611 protein_coding mRNA 1263 9963 . - . ID=EKC25967;Parent=CGI_10014322 scaffold1611 protein_coding start_codon 9961 9963 . - 0 ID=start_codon:EKC25967:1;Parent=EKC25967 scaffold1611 protein_coding exon 9922 9963 . - . ID=exon:EKC25967:1;Parent=EKC25967 scaffold1611 protein_coding exon 8502 8667 . - . ID=exon:EKC25967:2;Parent=EKC25967 scaffold1611 protein_coding exon 7374 7534 . - . ID=exon:EKC25967:3;Parent=EKC25967 scaffold1611 protein_coding exon 3861 4046 . - . ID=exon:EKC25967:4;Parent=EKC25967 scaffold1611 protein_coding exon 1635 1742 . - . ID=exon:EKC25967:5;Parent=EKC25967 scaffold1611 protein_coding exon 1263 1268 . - . ID=exon:EKC25967:6;Parent=EKC25967 scaffold1611 protein_coding CDS 9922 9963 . - 0 ID=CDS:EKC25967:1;Parent=EKC25967 scaffold1611 protein_coding CDS 8502 8667 . - 0 ID=CDS:EKC25967:2;Parent=EKC25967 scaffold1611 protein_coding CDS 7374 7534 . - 2 ID=CDS:EKC25967:3;Parent=EKC25967 scaffold1611 protein_coding CDS 3861 4046 . - 0 ID=CDS:EKC25967:4;Parent=EKC25967 scaffold1611 protein_coding CDS 1635 1742 . - 0 ID=CDS:EKC25967:5;Parent=EKC25967 scaffold1611 protein_coding CDS 1263 1268 . - 0 ID=CDS:EKC25967:6;Parent=EKC25967 scaffold1611 protein_coding stop_codon 1263 1265 . - 0 ID=stop_codon:EKC25967:1;Parent=EKC25967 scaffold1611 protein_coding gene 61530 69027 . - . ID=CGI_10014325;Name=CGI_10014325 scaffold1611 protein_coding mRNA 61530 69027 . - . ID=EKC25970;Parent=CGI_10014325 scaffold1611 protein_coding start_codon 69025 69027 . - 0 ID=start_codon:EKC25970:1;Parent=EKC25970