library(rtracklayer) g <- readGFF("https://raw.githubusercontent.com/vsbuffalo/bds-files/master/chapter-09-working-with-range-data/mm_GRCm38.75_protein_coding_genes.gtf") head(g) #> seqid source type start end score strand phase #> 1 1 protein_coding gene 3205901 3671498 NA - NA #...
args=parser.parse_args()defget_id(id_list,id_from,trans_to):withopen(args.gtf,'r')asgff:result=[]hash_dict=dict()forlineingff:line1=line.strip().split('\t',8)try:Name=line1[8]except:continuetry:from_type=eval(Name.split(id_from)[1].split(';')[0])#hash methods, it need ...
tblastn -query proteins.fa -db target_genome.fa -num_threads 16 -outfmt 6 > prots_vs_genome.tab Run blast2gff.py on the output file. This will reformat the tabular blast hits into gff3 alignment style. Simple filtering options can be applied with-e-sand-F. If the queries were from ...