From f021a52fa2d2da1551bf315612ad6681b9813cca Mon Sep 17 00:00:00 2001
From: Dainius Kirsnauskas <kirsnauskas@gmail.com>
Date: Wed, 1 May 2024 16:19:57 +0300
Subject: [PATCH] splice_ai

---
 README.md                       | 18 ++++++++++++++-
 install_spliceai.sh             |  8 +++++++
 requirements.txt                |  4 +++-
 tests/tools/spliceai/input.vcf  | 38 +++++++++++++++++++++++++++++++
 tests/tools/spliceai/output.vcf | 40 +++++++++++++++++++++++++++++++++
 tools/__init__.py               |  0
 6 files changed, 106 insertions(+), 2 deletions(-)
 create mode 100755 install_spliceai.sh
 create mode 100644 tests/tools/spliceai/input.vcf
 create mode 100644 tests/tools/spliceai/output.vcf
 create mode 100644 tools/__init__.py

diff --git a/README.md b/README.md
index 86378ba..5a9e4b0 100644
--- a/README.md
+++ b/README.md
@@ -1 +1,17 @@
-# kath
\ No newline at end of file
+# kath
+
+VERY NICE TOOL DESCRIPTION
+
+## Install
+1. Install Python and its dependencies
+```
+sudo apt update
+sudo apt install python3 python3-dev python3-pip
+python install -r requirements.txt
+```
+
+2. Download files required for spliceAI and test tool, output should be the same as output.vcf in tests/tools/spliceai/output.vcf
+```
+./install_spliceai.sh
+spliceai -I ./tests/tools/spliceai/input.vcf -O ./tests/tools/spliceai/actual_output.vcf -R ./tools/spliceai/hg19.fa -A grch37
+```
\ No newline at end of file
diff --git a/install_spliceai.sh b/install_spliceai.sh
new file mode 100755
index 0000000..ac25879
--- /dev/null
+++ b/install_spliceai.sh
@@ -0,0 +1,8 @@
+#!/bin/bash
+mkdir ./tools/spliceai
+
+wget http://hgdownload.cse.ucsc.edu/goldenPath/hg19/bigZips/hg19.fa.gz -O ./tools/spliceai/hg19.fa.gz
+gzip -d ./tools/spliceai/hg19.fa.gz -c ./tools/spliceai/hg19.fa
+
+wget http://hgdownload.cse.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz -O ./tools/spliceai/hg38.fa.gz
+gzip -d ./tools/spliceai/hg38.fa.gz -c ./tools/spliceai/hg38.fa
diff --git a/requirements.txt b/requirements.txt
index 337dcd2..658f13b 100644
--- a/requirements.txt
+++ b/requirements.txt
@@ -1,3 +1,5 @@
 requests
 pandas
-selenium
\ No newline at end of file
+selenium
+spliceai
+tensorflow
\ No newline at end of file
diff --git a/tests/tools/spliceai/input.vcf b/tests/tools/spliceai/input.vcf
new file mode 100644
index 0000000..8d049d2
--- /dev/null
+++ b/tests/tools/spliceai/input.vcf
@@ -0,0 +1,38 @@
+##fileformat=VCFv4.2
+##fileDate=20191004
+##reference=GRCh37/hg19
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO
+1	25000	.	A	C,G,T	.	.	.
+2	152389953	.	T	A,C,G	.	.	.
+2	179415988	.	C	CA	.	.	.
+2	179446218	.	ATACT	A	.	.	.
+2	179446218	.	ATACT	AT,ATA	.	.	.
+2	179642185	.	G	A	.	.	.
+19	38958362	.	C	T	.	.	.
+21	47406854	.	CCA	C	.	.	.
+21	47406856	.	A	AT	.	.	.
+X	129274636	.	A	C,G,T	.	.	.
diff --git a/tests/tools/spliceai/output.vcf b/tests/tools/spliceai/output.vcf
new file mode 100644
index 0000000..bd27d40
--- /dev/null
+++ b/tests/tools/spliceai/output.vcf
@@ -0,0 +1,40 @@
+##fileformat=VCFv4.2
+##FILTER=<ID=PASS,Description="All filters passed">
+##fileDate=20191004
+##reference=GRCh37/hg19
+##contig=<ID=1,length=249250621>
+##contig=<ID=2,length=243199373>
+##contig=<ID=3,length=198022430>
+##contig=<ID=4,length=191154276>
+##contig=<ID=5,length=180915260>
+##contig=<ID=6,length=171115067>
+##contig=<ID=7,length=159138663>
+##contig=<ID=8,length=146364022>
+##contig=<ID=9,length=141213431>
+##contig=<ID=10,length=135534747>
+##contig=<ID=11,length=135006516>
+##contig=<ID=12,length=133851895>
+##contig=<ID=13,length=115169878>
+##contig=<ID=14,length=107349540>
+##contig=<ID=15,length=102531392>
+##contig=<ID=16,length=90354753>
+##contig=<ID=17,length=81195210>
+##contig=<ID=18,length=78077248>
+##contig=<ID=19,length=59128983>
+##contig=<ID=20,length=63025520>
+##contig=<ID=21,length=48129895>
+##contig=<ID=22,length=51304566>
+##contig=<ID=X,length=155270560>
+##contig=<ID=Y,length=59373566>
+##INFO=<ID=SpliceAI,Number=.,Type=String,Description="SpliceAIv1.3.1 variant annotation. These include delta scores (DS) and delta positions (DP) for acceptor gain (AG), acceptor loss (AL), donor gain (DG), and donor loss (DL). Format: ALLELE|SYMBOL|DS_AG|DS_AL|DS_DG|DS_DL|DP_AG|DP_AL|DP_DG|DP_DL">
+#CHROM	POS	ID	REF	ALT	QUAL	FILTER	INFO
+1	25000	.	A	C,G,T	.	.	.
+2	152389953	.	T	A,C,G	.	.	.
+2	179415988	.	C	CA	.	.	.
+2	179446218	.	ATACT	A	.	.	.
+2	179446218	.	ATACT	AT,ATA	.	.	.
+2	179642185	.	G	A	.	.	.
+19	38958362	.	C	T	.	.	.
+21	47406854	.	CCA	C	.	.	.
+21	47406856	.	A	AT	.	.	.
+X	129274636	.	A	C,G,T	.	.	.
diff --git a/tools/__init__.py b/tools/__init__.py
new file mode 100644
index 0000000..e69de29