--- title: "14.1-joining-annotations" output: html_document --- --- title: "14-joining-annotations" output: html_document --- ```{r} library(tidyverse) ``` ```{bash} pwd ``` Bringing in the list of 46753 CDS IDs ```{r} cdslist <- read.csv("../analyses/GCF_000297895_cdslist.tab", header = FALSE) ``` UNIPROT (but need to redo!!! - end premature) ```{r} suniprot <- read.csv("../analyses/Cg-uniprot_blastx_02.tab", header = FALSE, sep="\t") %>% distinct(V1, .keep_all = TRUE) ``` SPUR Protein hits ```{r} spur <- read.csv("../analyses/Cg-ProteinsSpur5.0_blastx.tab", header = FALSE, sep="\t") %>% distinct(V1, .keep_all = TRUE) ``` SPUR nucleotide ```{r} spurn <- read.csv("../analyses/Cg-SpurCDS_blastn.tab", header = FALSE, sep="\t") %>% distinct(V1, .keep_all = TRUE) ``` Drosophila ``` !{bldir}blastn \ -task blastn \ -query ../data/GCF_000297895.1_oyster_v9_cds_from_genomic.fna \ -db ../blastdb/dmel-all-gene-r6.37 \ -out ../analyses/Cg-dmel-gene_blastn_02.tab \ -evalue 1E-05 \ -num_threads 1 \ -max_target_seqs 1 \ -max_hsps 1 \ -outfmt "6 qaccver saccver evalue" ``` ```{r} dmel <- read.csv("../analyses/Cg-dmel-gene_blastn_02.tab", header = FALSE, sep="\t") %>% distinct(V1, .keep_all = TRUE) ``` Celg Gene symbols ```{r} celsym <- read.csv("../analyses/Cg_Ce-genesym.tab", header = FALSE, sep="\t") ``` JOIN ```{r} comb <- left_join(cdslist, uniprot, by = "V1") %>% left_join(spur, by = "V1") %>% left_join(spurn, by = "V1") %>% left_join(dmel, by = "V1") %>% left_join(celsym, by = c("V1" = "V2")) %>% select(V1, V2.x, V11.x, V2.y, V11.y, V2.x.x, V3.x.x, V2.y.y, V3.y.y, V1.y, V3, V4) %>% rename(cdsID = V1, uniprot = V2.x, u_ev = V11.x, spur = V2.y, s_ev = V11.y, spurN = V2.x.x, spurN_ev = V3.x.x, dmel = V2.y.y, dmel_ev = V3.y.y, cel_ID = V1.y, cel_ev = V3, cel_sym = V4) ``` # GOing back to Giles Blast ../data/bestblast_/bestblast.tab ```{r} giles <- read.csv("../data/bestblast_/bestblast.tab", header = TRUE, sep = "\t") %>% select(ID, HitAcc, HitDesc, E.Value) ``` ```{r} comb_g <- left_join(comb, giles, by = c("cdsID" = "ID")) ``` ```{r} loc <- read.csv("../data/bestblast_/LOC_seqID_key.tab", header = FALSE, sep = "\t") ``` ```{r} loc_dt <- left_join(loc, comb_g, by = c("V1" = "cdsID")) ``` ```{r} write_tsv( loc_dt, "../analyses/Cg-annot-join-V1.1.tab" ) ``` JOining Marker file ```{r} top <- read.csv("../data/topmarker_bla_mitov7_top10perCluster.txt", header = TRUE, sep = "\t") ``` ```{r} annot <- read.csv("../analyses/Cg-annot-join-V1.1.tab", header = TRUE, sep = "\t") ``` ```{r} library(tidyverse) ``` ```{r} top.annotv1.1 <- left_join(top, annot, by = c("gene_id" = "V2")) ``` ```{r} write_tsv( top.annotv1.1, "../analyses/top.annotv1.1.tab" ) ```