diff --git a/.gitignore b/.gitignore index b72dc8c..3afcb4b 100644 --- a/.gitignore +++ b/.gitignore @@ -1,4 +1,5 @@ # ignore data folder +data/figures data/ecDNA_reconstruction/ data/ecDNA_mixtures/ data/simulation_benchmarking/ diff --git a/README.md b/README.md index 746a586..5a6a5bd 100644 --- a/README.md +++ b/README.md @@ -67,7 +67,7 @@ Additionally, the reconstruction and de-novo assembly for cell lines are compare # 5. Paper figures -Go to [figures](docs/figures.md) +Go to `../data/figures`. ## Citation diff --git a/docs/compare_shasta_decoil.md b/docs/compare_shasta_decoil.md index ac653f5..2249c07 100644 --- a/docs/compare_shasta_decoil.md +++ b/docs/compare_shasta_decoil.md @@ -1,4 +1,4 @@ -### 4.2.1 Perform de-novo assembly for cell lines using Shasta +### 4.3 Perform de-novo assembly for cell lines using Shasta ``` conda create env -f scripts/shasta/assembly.yaml @@ -10,8 +10,10 @@ sbatch shasta_v6.0.6.sh ../../../data/ecDNA_comparison/tr14/shasta_ sbatch shasta_v6.0.6.sh ../../../data/ecDNA_comparison/sta-nb-10dm/shasta_v6.0.6 ``` -### 4.2.1 Compare Decoil and Shasta outputs against the against published ecDNA structures +### 4.4 Compare Decoil and Shasta outputs against the against published ecDNA structures ``` bash run ../ecDNA_comparison/comparison_reconstruction_true.sh -``` \ No newline at end of file +``` + +Output is under `../data/ecDNA_comparison/`. \ No newline at end of file diff --git a/docs/figures.md b/docs/figures.md deleted file mode 100644 index e69de29..0000000 diff --git a/docs/properties.md b/docs/properties.md deleted file mode 100644 index e69de29..0000000 diff --git a/docs/reconstruction_celllines_patients.md b/docs/reconstruction_celllines_patients.md index 3739113..db0e9c9 100644 --- a/docs/reconstruction_celllines_patients.md +++ b/docs/reconstruction_celllines_patients.md @@ -60,12 +60,12 @@ This is available also as docker container [madagiurgiu25/decoil:1.1.2-slim](htt ### 4.2.2 Run reconstruction for cell lines ```bash -sbatch ../ecDNA_reconstruction/celllines/run_decoil_v112_07022024_slurmarray_celllines_hg19.sh -sbatch ../ecDNA_reconstruction/celllines/run_decoil_v112_07022024_slurmarray_celllines_hg38.sh +sbatch ../ecDNA_reconstruction/run_decoil_v112_07022024_slurmarray_celllines_hg19.sh +sbatch ../ecDNA_reconstruction/run_decoil_v112_07022024_slurmarray_celllines_hg38.sh ``` ### 4.2.3 Run reconstruction for patient samples ```bash -sbatch run_decoil_v112_07022024_slurmarray.sh +sbatch ../ecDNA_reconstruction/run_decoil_v112_07022024_slurmarray.sh ``` diff --git a/ecDNA_comparison/assemblyviz.R b/ecDNA_comparison/assemblyviz.R deleted file mode 100755 index 9818aa2..0000000 --- a/ecDNA_comparison/assemblyviz.R +++ /dev/null @@ -1,76 +0,0 @@ -## visualize assembly - -library(pafr) -library(ggplot2) -library(gridExtra) - -setwd("/Users/madag/Projects/PhD/github/decoil-paper/celllines/chp212") - -paffile1 <- "hg38_decoil.paf" -ali <- read_paf(paffile1) -p1 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="decoil") + theme_bw() - -paffile2 <- "hg38_shasta.paf" -ali <- read_paf(paffile2) -p2 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="shasta") + theme_bw() - -paffile3 <- "hg38_paper.paf" -ali <- read_paf(paffile3) -p3 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="helmsauer_etal_2020") + theme_bw() - - -grid.arrange(p1, p2, p3, nrow=1) - - -paffile <- system.file("extdata", "fungi.paf", package="pafr") -paffile <- "/Volumes/henssen_lab/work/evolution/assembly/K7-23273_initial_relapse.paf" - - paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/test/test.paf" - ali <- read_paf(paffile) - p1 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="test (AC)") + theme_bw() - - paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/A/test/test1.paf" - ali <- read_paf(paffile) - p2 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="AnC") + theme_bw() - - grid.arrange(p1, p2, nrow = 2) - -paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/AC/asm-to-ref.paf" -ali <- read_paf(paffile) -dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="circular reference") + theme_bw() - - -paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/A/ref-to-ref.paf" -ali <- read_paf(paffile) -p1 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="circular reference") + theme_bw() - -paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/A/asm-to-ref.paf" -ali <- read_paf(paffile) -p2 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="assembly") + theme_bw() - -paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/ACnDE/reads-to-ref.paf" -ali <- read_paf(paffile) -p3 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="cir reference ACnDE") + theme_bw() - -paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/ACnDE/asm-to-ref.paf" -ali <- read_paf(paffile) -p4 <- dotplot(ali, label_seqs=TRUE, alignment_colour="blue", ylab="hg38", xlab="assembly ACnDE") + theme_bw() - -grid.arrange(p1, p2, p3, p4, nrow = 2) - - - - -paffile <- "/home/mada/Projects/henssen_lab/Simulation/data/process/ACnDE/asm-to-ref.paf" -ali <- read_paf(paffile) -plot_synteny(ali, q_chrom="circle3", t_chrom="chr2:5000000-5130000", centre=TRUE) + - theme_bw() - -plot_synteny(long_ali, q_chrom="4", t_chrom="chr2:15000000-16800000", centre=TRUE) + - theme_bw() - -plot_synteny(long_ali, q_chrom="6", t_chrom="chr2:15000000-16800000", centre=TRUE) + - theme_bw() - -plot_synteny(long_ali, q_chrom="10", t_chrom="chr2:15000000-16800000", centre=TRUE) + - theme_bw()