Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Splice types #215

Draft
wants to merge 8 commits into
base: dev
Choose a base branch
from
Draft

Splice types #215

Show file tree
Hide file tree
Changes from 7 commits
Commits
Show all changes
8 commits
Select commit Hold shift + click to select a range
5ced6c0
fds annotation code, blacklist files
lutzkaro Jun 24, 2021
35228e4
fds first annotation, UTR regions
lutzkaro Jun 25, 2021
ff37aa7
splice types, blacklist
lutzkaro Jun 29, 2021
3f0a51d
expression blacklist
lutzkaro Jul 2, 2021
372f41a
small changes
lutzkaro Jul 8, 2021
ef755a3
small changes
lutzkaro Jul 16, 2021
31ea16f
updated from dev
lutzkaro Jul 20, 2021
0906ad4
small changes and comments
lutzkaro Dec 17, 2021
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 15 additions & 1 deletion drop/modules/aberrant-expression-pipeline/OUTRIDER/results.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -44,15 +44,29 @@ res <- res[padjust <= snakemake@params$padjCutoff &
abs(zScore) > snakemake@params$zScoreCutoff]

gene_annot_dt <- fread(snakemake@input$gene_name_mapping)

print("IN OUTRIDER RESULTS: GENE NAME MAPPING DT")
print(gene_annot_dt)

print("RES BEFORE GENE NAME MAPPING")
print(res)

if(!is.null(gene_annot_dt$gene_name)){
if(grepl('ENSG00', res[1,geneID]) & grepl('ENSG00', gene_annot_dt[1,gene_id])){
res <- merge(res, gene_annot_dt[, .(gene_id, gene_name)],
res <- merge(res, gene_annot_dt[, .(gene_id, gene_name, blacklist)],
by.x = 'geneID', by.y = 'gene_id', sort = FALSE, all.x = TRUE)
setnames(res, 'gene_name', 'hgncSymbol')
res <- cbind(res[, .(hgncSymbol)], res[, - 'hgncSymbol'])
}
}


print("RES AFTER GENE NAME MAPPING")
print(res)




# Add HPO terms, requires online connection and for there to be annotated HPO terms
sa <- fread(snakemake@config$sampleAnnotation)
if(!is.null(sa$HPO_TERMS) & nrow(res) > 0){
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/00_define_datasets_from_anno.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "00_defineDataset.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - ids: '`sm lambda w: sa.getIDsByGroup(w.dataset, assay="RNA")`'
#' - fileMappingFile: '`sm cfg.getRoot() + "/file_mapping.csv"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Are we sure we want the config in requirements and not as params? There should be nothing in there that could change the outcome of the results.
This goes of course also for the other scripts.

#' - sampleAnnoFile: '`sm config["sampleAnnotation"]`'
#' output:
#' - colData: '`sm cfg.getProcessedDataDir() +
Expand All @@ -23,7 +23,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

#+ input
outFile <- snakemake@output$colData
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/01_0_countRNA_init.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "01_0_init.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - colData: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/annotations/{dataset}.tsv"`'
#' output:
Expand All @@ -19,7 +19,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
colDataFile <- snakemake@input$colData
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/01_1_countRNA_splitReads_samplewise.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "splitReads" / "{sample_id}.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - done_fds: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/cache/raw-{dataset}/fds.done"`'
#' output:
Expand All @@ -19,7 +19,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)
library(BSgenome)

dataset <- snakemake@wildcards$dataset
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/01_2_countRNA_splitReads_merge.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "01_2_splitReadsMerge.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets"`'
#' threads: 20
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - sample_counts: '`sm lambda w: cfg.AS.getSplitCountFiles(w.dataset)`'
#' output:
#' - countsJ: '`sm cfg.getProcessedDataDir() +
Expand All @@ -23,7 +23,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
workingDir <- snakemake@params$workingDir
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/01_3_countRNA_nonSplitReads_samplewise.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "nonsplitReads" / "{sample_id}.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - spliceSites: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/cache/raw-{dataset}/spliceSites_splitCounts.rds"`'
#' output:
Expand All @@ -18,7 +18,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
colDataFile <- snakemake@input$colData
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/01_4_countRNA_nonSplitReads_merge.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "01_4_nonSplitReadsMerge.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets"`'
#' threads: 20
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - sample_counts: '`sm lambda w: cfg.AS.getNonSplitCountFiles(w.dataset)`'
#' - gRangesNonSplitCounts: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/cache/raw-{dataset}/gRanges_NonSplitCounts.rds"`'
Expand All @@ -19,7 +19,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
workingDir <- snakemake@params$workingDir
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/01_5_countRNA_collect.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "01_5_collect.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - countsJ: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/raw-{dataset}/rawCountsJ.h5"`'
#' - countsSS: '`sm cfg.getProcessedDataDir() +
Expand All @@ -23,7 +23,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
workingDir <- snakemake@params$workingDir
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/02_psi_value_calculation_FraseR.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "02_PSIcalc.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets/"`'
#' threads: 30
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - counting_done: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/raw-{dataset}/counting.done" `'
#' output:
Expand All @@ -18,7 +18,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
workingDir <- snakemake@params$workingDir
Expand Down
15 changes: 13 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/03_filter_expression_FraseR.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "03_filter.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets/"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - theta: '`sm cfg.getProcessedDataDir()+
#' "/aberrant_splicing/datasets/savedObjects/raw-{dataset}/theta.h5"`'
#' output:
Expand All @@ -20,7 +20,9 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)
#source(snakemake@input$spliceTypeSetup, echo=FALSE)
#source(snakemake@input$addAnnotation)

opts_chunk$set(fig.width=12, fig.height=8)

Expand Down Expand Up @@ -53,5 +55,14 @@ if (params$filter == TRUE) {
message(paste("filtered to", nrow(fds), "junctions"))
}

fds <- saveFraserDataSet(fds)

# Add the junction annotations to the fds
#message("03: load db for annotation")
#txdb <- loadDb(snakemake@input$txdb)
Copy link
Contributor

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Please clean up if you do not need the lines.

#seqlevelsStyle(txdb) <- seqlevelsStyle(fds)
#fds <- createFDSAnnotations(fds, txdb)
#message("03: save object after annotation")

fds <- saveFraserDataSet(fds)
file.create(snakemake@output$done)
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/Counting/Summary.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,9 +5,9 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "CountSummary.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets/"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - filter: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/{dataset}/filter.done" `'
#' output:
Expand All @@ -17,7 +17,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

suppressPackageStartupMessages({
library(cowplot)
Expand Down
5 changes: 2 additions & 3 deletions drop/modules/aberrant-splicing-pipeline/Counting/exportCounts.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,9 +4,8 @@
#' wb:
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "{genomeAssembly}--{annotation}_export.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - annotation: '`sm cfg.getProcessedDataDir() + "/preprocess/{annotation}/txdb.db"`'
#' - fds_theta: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/raw-{dataset}/theta.h5"`'
Expand All @@ -17,7 +16,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)
library(AnnotationDbi)

#
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/FRASER/04_fit_hyperparameters_FraseR.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "04_hyper.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets/"`'
#' threads: 12
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - filter: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/{dataset}/filter.done" `'
#' output:
Expand All @@ -18,7 +18,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

if ("random_seed" %in% names(snakemake@config)){
rseed <- snakemake@config$random_seed
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/FRASER/05_fit_autoencoder_FraseR.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "05_fit.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets/"`'
#' threads: 20
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - hyper: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/{dataset}/hyper.done" `'
#' output:
Expand All @@ -18,7 +18,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
workingDir <- snakemake@params$workingDir
Expand Down
4 changes: 2 additions & 2 deletions drop/modules/aberrant-splicing-pipeline/FRASER/06_calculation_stats_AE_FraseR.R
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,10 +5,10 @@
#' log:
#' - snakemake: '`sm str(tmp_dir / "AS" / "{dataset}" / "06_stats.Rds")`'
#' params:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - workingDir: '`sm cfg.getProcessedDataDir() + "/aberrant_splicing/datasets/"`'
#' threads: 20
#' input:
#' - setup: '`sm cfg.AS.getWorkdir() + "/config.R"`'
#' - fdsin: '`sm cfg.getProcessedDataDir() +
#' "/aberrant_splicing/datasets/savedObjects/{dataset}/" +
#' "predictedMeans_theta.h5"`'
Expand All @@ -20,7 +20,7 @@
#'---

saveRDS(snakemake, snakemake@log$snakemake)
source(snakemake@params$setup, echo=FALSE)
source(snakemake@input$setup, echo=FALSE)

dataset <- snakemake@wildcards$dataset
fdsFile <- snakemake@input$fdsin
Expand Down
Loading