diff --git a/intro-rna-seq/Intro_to_RNA-seq_data_analysis.zip b/intro-rna-seq/Intro_to_RNA-seq_data_analysis.zip index 02dc6cd..54c8c8a 100644 Binary files a/intro-rna-seq/Intro_to_RNA-seq_data_analysis.zip and b/intro-rna-seq/Intro_to_RNA-seq_data_analysis.zip differ diff --git a/intro-rna-seq/README.md b/intro-rna-seq/README.md index ca76e48..68f3695 100644 --- a/intro-rna-seq/README.md +++ b/intro-rna-seq/README.md @@ -10,4 +10,5 @@ 6. all_steps_wynton.sh (shell script for running all the analysis steps on UCSF Wynton command-line interface using the practice data provided) 7. steps_on_wynton_part1.txt (text file with steps used on wynton to setup the folders, upload the data and create a singularity container) 8. steps_on_wynton_part2.txt (text file with steps used on wynton to run the bulk RNA-seq analysis using the demo files) -9. all_steps_docker_desktop.sh (shell script with commands for running all the analysis steps using Docker Desktop and the demo files) +9. all_steps_docker_desktop_mac.sh (commands for running all the analysis steps using Docker Desktop and the demo files on MacOS) +10. all_steps_docker_desktop_windows.sh (commands for running all the analysis steps using Docker Desktop and the demo files on Windows) diff --git a/intro-rna-seq/Workshop_May2023_Intro_to_RNA-seq_analysis-Michela_and_Ayushi.pptx b/intro-rna-seq/Workshop_May2023_Intro_to_RNA-seq_analysis-Michela_and_Ayushi.pptx index 689b784..274166b 100644 Binary files a/intro-rna-seq/Workshop_May2023_Intro_to_RNA-seq_analysis-Michela_and_Ayushi.pptx and b/intro-rna-seq/Workshop_May2023_Intro_to_RNA-seq_analysis-Michela_and_Ayushi.pptx differ diff --git a/intro-rna-seq/all_steps_docker_desktop_mac.sh b/intro-rna-seq/all_steps_docker_desktop_mac.sh new file mode 100644 index 0000000..6dc1b72 --- /dev/null +++ b/intro-rna-seq/all_steps_docker_desktop_mac.sh @@ -0,0 +1,56 @@ +#!/bin/bash + +# This script should be run on your local laptop or computer +# Please make sure you have installed Docker Desktop using the instructions at: https://www.docker.com/products/docker-desktop/ +# Before running this script, do the following +## 1. open the Docker Dekstop and make sure it is running +## 2. Download the workshop materials at https://github.com/gladstone-institutes/Bioinformatics-Workshops/raw/master/intro-rna-seq/Intro_to_RNA-seq_data_analysis.zip?raw=true. +## 3. Unzip the workshop materials in the Downloads folder +## 4. Open a new terminal window + +#check if docker is running +#the below command will print out the docker version if docker is running +docker --version + +#get the docker image from https://hub.docker.com/r/nfcore/rnaseq/ +#we will be using this image for all the analyses +docker pull nfcore/rnaseq + +#check if the docker image was downloaded successfully +docker images + +#spin up a docker container +#change the path below to the path on your computer where the downloaded materials are unzipped +##for M1 chip mac, use the below command +docker run --platform linux/amd64 --name rna_bash --rm -it -v ~/Downloads/Intro_to_RNA-seq_data_analysis:/home nfcore/rnaseq bash +##for all other computers, use the below command +docker run --name rna_bash --rm -it -v ~/Downloads/Intro_to_RNA-seq_data_analysis:/home nfcore/rnaseq bash + +#a new prompt will apear and the conatiner is now active +#the home directory should have all the contents of the downloaded materials folder +#go to the home directory in the docker container +cd home + +#run fastqc +fastqc Bacteria_GATTACA_L001_R1_001.fastq + +#trim the reads using cutadapt +cutadapt -a file:Adapter_Sequence.fasta -o trimmed.fastq Bacteria_GATTACA_L001_R1_001.fastq + +#run fastqc on the trimmed reads +fastqc trimmed.fastq + +#create a new folder +mkdir star_index + +#create the STAR index +STAR --runMode genomeGenerate --genomeDir ./star_index --genomeFastaFiles rDNA_sequence.fasta --genomeSAindexNbases 3 + +#run STAR for the trimmed reads +STAR --genomeDir ./star_index --readFilesIn ./trimmed.fastq + +#generate the read count matrix using featureCounts +featureCounts -a rDNA.gtf -t CDS -o counts.txt Aligned.out.sam + + +# END # \ No newline at end of file diff --git a/intro-rna-seq/all_steps_docker_desktop_windows.sh b/intro-rna-seq/all_steps_docker_desktop_windows.sh new file mode 100644 index 0000000..9d36403 --- /dev/null +++ b/intro-rna-seq/all_steps_docker_desktop_windows.sh @@ -0,0 +1,60 @@ +#!/bin/bash + +# This script should be run on your local laptop or computer +# Please make sure you have installed Docker Desktop using the instructions at: https://www.docker.com/products/docker-desktop/ +# Before running this script, do the following +## 1. open the Docker Dekstop and make sure it is running +## If Docker Desktop gives a pop-up that it requires a newer WSL kernel version, open a new command prompt window and run the below command: +## $ wsl --update +## Restart Docker Desktop +## 2. Download the workshop materials at https://github.com/gladstone-institutes/Bioinformatics-Workshops/raw/master/intro-rna-seq/Intro_to_RNA-seq_data_analysis.zip?raw=true. +## 3. Unzip the workshop materials in the Downloads folder +## 4. Open a new command prompt window + +##run the below commands in the command prompt window +#check if docker is running +#the below command will print out the docker version if docker is running +docker --version + +#get the docker image from https://hub.docker.com/r/nfcore/rnaseq/ +#we will be using this image for all the analyses +docker pull nfcore/rnaseq + +#check if the docker image was downloaded successfully +docker images + +#spin up a docker container +#change the path below to the path on your computer where the downloaded materials are unzipped +docker run --name rna_bash --rm -it -v C:\Users\ayushi.agrawal\Downloads\Intro_to_RNA-seq_data_analysis\Intro_to_RNA-seq_data_analysis:/home nfcore/rnaseq bash + +#a new prompt will apear and the conatiner is now active +#the home directory should have all the contents of the downloaded materials folder +#go to the home directory in the docker container +cd home + +#run fastqc +fastqc Bacteria_GATTACA_L001_R1_001.fastq + +#trim the reads using cutadapt +cutadapt -a file:Adapter_Sequence.fasta -o trimmed.fastq Bacteria_GATTACA_L001_R1_001.fastq + +#run fastqc on the trimmed reads +fastqc trimmed.fastq + + +#STAR does not work on windows so, we will be using another aligner "HISAT2" for the demo +#create a new folder +mkdir hisat2_index + +#create the hisat2 index +hisat2-build -p 7 rDNA_sequence.fasta hisat2_index/rDNA_ + +#run hisat2 for the trimmed reads +#HISAT2 and STAR are different aligners with different defaults, scoring algorithms, etc. This might result in different outputs from the two aligners. +hisat2 -p 7 -x hisat2_index/rDNA_ -U ./trimmed.fastq -S hisat2_aligned_out.sam + +#generate the read count matrix using featureCounts +featureCounts -a rDNA.gtf -t CDS -o counts.txt hisat2_aligned_out.sam + + +# END # \ No newline at end of file