-
Notifications
You must be signed in to change notification settings - Fork 0
Commit
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Continued work to complete the combined processed/pa-ncRNA gtf and co…
…unts matrix, among other things
- Loading branch information
Kris Alavattam
committed
May 24, 2023
1 parent
570fd3d
commit 9f5f8d8
Showing
7 changed files
with
3,751 additions
and
48 deletions.
There are no files selected for viewing
3,179 changes: 3,179 additions & 0 deletions
3,179
results/2023-0215/work_assess-process_R64-1-1_gff3_part-1.5.nb.html
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
13 changes: 10 additions & 3 deletions
13
results/2023-0215/work_assess-process_R64-1-1_gff3_part-1.nb.html
Large diffs are not rendered by default.
Oops, something went wrong.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
185 changes: 185 additions & 0 deletions
185
results/2023-0215/work_combine-gtfs_processed-pa-ncRNA_part-0.Rmd
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| Original file line number | Diff line number | Diff line change |
|---|---|---|
| @@ -0,0 +1,185 @@ | ||
| --- | ||
| title: "work_combine-gtfs_processed-pa-ncRNA_part-0.Rmd" | ||
| author: "KA" | ||
| email: "[email protected]" | ||
| output: | ||
| html_notebook: | ||
| toc: yes | ||
| toc_float: true | ||
| --- | ||
|
|
||
| ## Get situated | ||
| ### Code | ||
| <details> | ||
| <summary><i>Code: Get situated</i></summary> | ||
|
|
||
| ```{r Get situated, results='hide', message=FALSE, warning=FALSE} | ||
| #!/usr/bin/env Rscript | ||
| library(GenomicRanges) | ||
| library(IRanges) | ||
| library(plyr) | ||
| library(readxl) | ||
| library(rtracklayer) | ||
| library(tidyverse) | ||
| options(scipen = 999) | ||
| options(ggrepel.max.overlaps = Inf) | ||
| if(base::isTRUE(stringr::str_detect(getwd(), "kalavattam"))) { | ||
| p_local <- "/Users/kalavattam/Dropbox/FHCC" | ||
| } else { | ||
| p_local <- "/Users/kalavatt/projects-etc" | ||
| } | ||
| p_wd <- "2022_transcriptome-construction/results/2023-0215" | ||
| setwd(paste(p_local, p_wd, sep = "/")) | ||
| getwd() | ||
| rm(p_local, p_wd) | ||
| ``` | ||
| </details> | ||
| <br /> | ||
| <br /> | ||
|
|
||
| ## Load and combine `gtf`s | ||
| ### Load `gtf` files [derived/"processed" from R64-1-1](./work_assess-process_R64-1-1_gff3_part-1.Rmd) | ||
| #### Code | ||
| <details> | ||
| <summary><i>Code: Load `gtf` files derived/"processed" from R64-1-1</i></summary> | ||
|
|
||
| ```{r Load gtf files derived/processed from R64-1-1, results='hide', message=FALSE, warning=FALSE} | ||
| #!/usr/bin/env Rscript | ||
| read_processed_gtf <- function(file) { | ||
| tbl <- file %>% | ||
| rtracklayer::import() %>% | ||
| tibble::as_tibble() %>% | ||
| dplyr::select(-c(width, score, phase)) %>% | ||
| dplyr::rename(feature = type.1) %>% | ||
| dplyr::arrange(seqnames, start) | ||
| tbl[tbl == "NA"] <- NA_character_ | ||
| return(tbl) | ||
| } | ||
| p_processed <- "./outfiles_gtf-gff3/comprehensive/S288C_reference_genome_R64-1-1_20110203" | ||
| f_gene <- "processed_gene_sense.gtf" | ||
| f_PG <- "processed_PG_sense.gtf" | ||
| f_snRNA <- "processed_snRNA_sense.gtf" | ||
| f_snoRNA <- "processed_snoRNA_sense.gtf" | ||
| f_TE <- "processed_TE_sense.gtf" | ||
| t_gene <- paste(p_processed, f_gene, sep = "/") %>% read_processed_gtf() | ||
| t_PG <- paste(p_processed, f_PG, sep = "/") %>% read_processed_gtf() | ||
| t_snRNA <- paste(p_processed, f_snRNA, sep = "/") %>% read_processed_gtf() | ||
| t_snoRNA <- paste(p_processed, f_snoRNA, sep = "/") %>% read_processed_gtf() | ||
| t_TE <- paste(p_processed, f_TE, sep = "/") %>% read_processed_gtf() | ||
| t_processed <- dplyr::bind_rows(t_gene, t_PG, t_snRNA, t_snoRNA, t_TE) %>% | ||
| dplyr::arrange(seqnames, start) | ||
| rm(p_processed, f_gene, f_PG, f_snRNA, f_snoRNA, f_TE) | ||
| rm(t_gene, t_PG, t_snRNA, t_snoRNA, t_TE) | ||
| ``` | ||
| </details> | ||
| <br /> | ||
|
|
||
| ### Load [pa-ncRNA `gtf` file](./work_representative-non-coding-transcriptome_part-4.Rmd) | ||
| #### Code | ||
| <details> | ||
| <summary><i>Code: Load pa-ncRNA `gtf` file</i></summary> | ||
|
|
||
| ```{r} | ||
| #!/usr/bin/env Rscript | ||
| read_pa_ncRNA_gtf <- function(file) { | ||
| tbl <- file %>% | ||
| rtracklayer::import() %>% | ||
| tibble::as_tibble() %>% | ||
| dplyr::select(-c( | ||
| width, score, phase, details_type_alpha, details_type, details_id, | ||
| details_all, n_types, n_features, n_types_features, length | ||
| )) %>% | ||
| dplyr::mutate( | ||
| feature = "pancRNA", | ||
| orf_classification = NA_character_, | ||
| source_id = NA_character_ | ||
| ) %>% | ||
| dplyr::arrange(seqnames, start) | ||
| return(tbl) | ||
| } | ||
| p_pa_ncRNA <- "./outfiles_gtf-gff3/representation" | ||
| f_pa_ncRNA <- "Greenlaw-et-al_representative-non-coding-transcriptome.gtf" | ||
| t_pa_ncRNA <- paste(p_pa_ncRNA, f_pa_ncRNA, sep = "/") %>% read_pa_ncRNA_gtf() | ||
| rm(p_pa_ncRNA, f_pa_ncRNA) | ||
| ``` | ||
| </details> | ||
| <br /> | ||
|
|
||
| ### Row-bind the "processed" and pa-ncRNA `gtf`s | ||
| <details> | ||
| <summary><i>Code: Row-bind the "processed" and pa-ncRNA `gtf`s</i></summary> | ||
|
|
||
| ```{r} | ||
| #!/usr/bin/env Rscript | ||
| t_bound <- dplyr::bind_rows(t_processed, t_pa_ncRNA) %>% | ||
| dplyr::arrange(seqnames, start) | ||
| ``` | ||
| </details> | ||
| <br /> | ||
| <br /> | ||
|
|
||
| ## Write out combined "processed" and pa-ncRNA `gtf` | ||
| ### Code | ||
| <details> | ||
| <summary><i>Code: Row-bind the "processed" and pa-ncRNA `gtf`s</i></summary> | ||
|
|
||
| ```{r} | ||
| #!/usr/bin/env Rscript | ||
| write_gtf <- function(x, y) { | ||
| # ... | ||
| # :param x: tibble | ||
| # :param y: outfile | ||
| # :return: NA | ||
| readr::write_tsv( | ||
| x, | ||
| y, | ||
| col_names = FALSE, | ||
| quote = "none", | ||
| escape = "none" | ||
| ) | ||
| } | ||
| p_gtf <- "./outfiles_gtf-gff3/representation" | ||
| f_gtf <- "Greenlaw-et-al_representative-coding-non-coding-etc-transcriptome.gtf" | ||
| t_gtf <- t_bound %>% | ||
| dplyr::mutate(score = ".", frame = ".") %>% | ||
| dplyr::relocate(c("seqnames", "source", "type"), .before = "start") %>% | ||
| dplyr::relocate(c("score", "strand", "frame"), .after = "end") %>% | ||
| dplyr::mutate( | ||
| attribute = paste( | ||
| paste0("gene_id \"", gene_id, "\""), | ||
| paste0("transcript_id \"", transcript_id, "\""), | ||
| paste0("type \"", feature, "\""), | ||
| paste0("orf_classification \"", orf_classification, "\""), | ||
| paste0("source_id \"", source_id, "\""), | ||
| sep = "; " | ||
| ) | ||
| ) %>% | ||
| dplyr::select( | ||
| -c(gene_id, transcript_id, feature, orf_classification, source_id) | ||
| ) | ||
| write_gtf(t_gtf, paste(p_gtf, f_gtf, sep = "/")) | ||
| ``` | ||
| </details> | ||
| <br /> |
Oops, something went wrong.