Merge pull request #2 from clara-parabricks-workflows/add_codonfm

Add codonfm

Author: gburnett-nvidia

.gitignore

@@ -0,0 +1,3 @@
+myenv
+data
+parabricks_sample*

.gitmodules

@@ -0,0 +1,3 @@
+[submodule "CodonFM"]
+	path = CodonFM
+	url = git@github.com:gburnett-nvidia/CodonFM.git

CodonFM

@@ -29,15 +29,20 @@ Users may have to wait 5-10 minutes for the instance to start depending on cloud
 
 # Notebooks
 
-### **germline_wes**
+### **germline_wes.ipynb**
 
 - This example uses the Parabricks 4.4.0 release.
 - This example uses whole exome (WES) data from sample NA12878. 
 - In the first step, we will map the sequence reads to the reference genome. The input FASTQ files are aligned using the Burrows-Wheeler Aligner (BWA) through the Parabricks fq2bam tool. 
 - Lastly, we will run DeepVariant, a deep learning based variant caller on the aligned reads. - It uses a convolutional neural network to find single nucleotide variants (SNVs) and insertions/deletions (InDels).
 
+### **pangenome.ipynb**
+
 After a user is able to run this flow, they can try running this on their own data as well as explore cloud examples available at the end of the notebook.
 
+- This example uses the Parabricks 4.6.0 release 
+- It runs through 
+
 # Deployment 
 
 There are two ways to deploy this launchable depending on what level of customization is desired. 

README.md

@@ -0,0 +1,12 @@
+#!/bin/bash 
+
+# Install bcftools 
+wget https://github.com/samtools/bcftools/releases/download/1.23/bcftools-1.23.tar.bz2
+tar xjf bcftools-1.23.tar.bz2
+cd bcftools-1.23 && \
+    ./configure && \
+    make && \
+    make install
+
+# Install CodonFM Python requirements
+pip install -r CodonFM/requirements.txt