add preset genomes to config

alsmith151 · Jan 10, 2024 · 4a5a23f · 4a5a23f
1 parent b74cdbd
commit 4a5a23f
Show file tree

Hide file tree

Showing 6 changed files with 138 additions and 32 deletions.
diff --git a/seqnado/cli.py b/seqnado/cli.py
@@ -8,12 +8,15 @@
 
 @click.command(context_settings=dict(ignore_unknown_options=True))
 @click.argument("method", type=click.Choice(["atac", "chip", "rna", "snp"]))
-def cli_config(method, help=False):
+@click.option("-g", "--genome", default="other", help="Genome to use",
+              type=click.Choice(choices=['dm6', 'hg19', 'hg38', 'hg38_dm6', 'hg38_mm39', 'hg38_spikein', 'mm10', 'mm39', 'other']),)
+
+def cli_config(method, help=False, genome="other"):
     """
     Runs the config for the data processing pipeline.
     """
     import seqnado.config as config
-    config.create_config(method)
+    config.create_config(method, genome)
 
 
 

diff --git a/seqnado/config.py b/seqnado/config.py
@@ -1,6 +1,7 @@
 import os
 import datetime
 from jinja2 import Environment, FileSystemLoader
+import json
 
 # Helper Functions
 def get_user_input(prompt, default=None, is_boolean=False, choices=None):
@@ -13,11 +14,13 @@ def get_user_input(prompt, default=None, is_boolean=False, choices=None):
             continue
         return user_input
 
-def setup_configuration(assay, template_data):
+
+
+def setup_configuration(assay, genome, template_data):
     username = os.getenv('USER', 'unknown_user')
     today = datetime.datetime.now().strftime('%Y-%m-%d')
     project_name = get_user_input("What is your project name?", default=f"{username}_project")
-    genome = get_user_input("What is your genome name?", default="hg38", choices=['dm6', 'hg19', 'hg38', 'hg38_dm6', 'hg38_mm39', 'hg38_spikein', 'mm9', 'mm10', 'mm10_TetR_ChrX_and_Chr8', 'mm39', 'other'])
+
     common_config = {
         'username': username,
         'project_date': today,
@@ -26,14 +29,55 @@ def setup_configuration(assay, template_data):
     }
 
     template_data.update(common_config)
-
-    if assay in ["chip", "atac"]:
-        template_data['indicies'] = get_user_input("Path to Bowtie2 genome indices:", default=f"/ceph/project/milne_group/shared/seqnado_reference/{genome}/UCSC/bt2_index/{genome}") 
-    elif assay == "rna":
-        template_data['indicies'] = get_user_input("Path to STAR genome indices:", default=f"/ceph/project/milne_group/shared/seqnado_reference/{genome}/UCSC/STAR_2.7.10b")
 
-    template_data['chromosome_sizes'] = get_user_input("Path to chromosome sizes file:", default=f"/ceph/project/milne_group/shared/seqnado_reference/{genome}/UCSC/sequence/{genome}.chrom.sizes")
-    template_data['gtf'] = get_user_input("Path to GTF file:", default=f"/ceph/project/milne_group/shared/seqnado_reference/{genome}/UCSC/genes/{genome}.ncbiRefSeq.gtf")
+    with open('seqnado/workflow/config/preset_genomes.json', 'r') as file:
+        genome_values = json.load(file)
+
+    genome_dict = {}
+
+    if genome == "other":
+        if assay in ["chip", "atac"]:
+            genome_dict = {
+                "other": {
+                    "index": get_user_input("Path to Bowtie2 genome index:"),
+                    "chromosome_sizes": get_user_input("Path to chromosome sizes file:"),
+                    "gtf": get_user_input("Path to GTF file:"),
+                    "blacklist": get_user_input("Path to blacklist bed file:")
+                }
+            }
+        elif assay == "rna":
+            genome_dict = {
+                "other": {
+                    "index": get_user_input("Path to STAR v2.7.10b genome index:"),
+                    "chromosome_sizes": get_user_input("Path to chromosome sizes file:"),
+                    "gtf": get_user_input("Path to GTF file:"),
+                    "blacklist": get_user_input("Path to blacklist bed file:")
+                }
+            }
+
+    elif genome in genome_values:
+        if assay in ["chip", "atac"]:
+            genome_dict = {
+                genome: {
+                    "index": genome_values[genome]['bt2_index'],
+                    "chromosome_sizes": genome_values[genome]['chromosome_sizes'],
+                    "gtf": genome_values[genome]['gtf'],
+                    "blacklist": genome_values[genome]['blacklist']
+                }
+            }
+        elif assay == "rna":
+            genome_dict = {
+                genome: {
+                    "index": genome_values[genome]['star_index'],
+                    "chromosome_sizes": genome_values[genome]['chromosome_sizes'],
+                    "gtf": genome_values[genome]['gtf'],
+                    "blacklist": genome_values[genome]['blacklist']
+                }
+            }
+
+    template_data['indicies'] = genome_dict[genome]['index']
+    template_data['chromosome_sizes'] = genome_dict[genome]['chromosome_sizes']
+    template_data['gtf'] = genome_dict[genome]['gtf']
     template_data['read_type'] = get_user_input("What is your read type?", default="paired", choices=["paired", "single"])
 
     template_data['split_fastq'] = get_user_input("Do you want to split FASTQ files? (yes/no)", default="no", is_boolean=True)
@@ -53,7 +97,7 @@ def setup_configuration(assay, template_data):
 
     template_data['remove_blacklist'] = get_user_input("Do you want to remove blacklist regions? (yes/no)", default="yes", is_boolean=True)
     if template_data['remove_blacklist']:
-        template_data['blacklist'] = get_user_input("Path to blacklist file:", default=f"/ceph/project/milne_group/shared/seqnado_reference/{genome}/UCSC/blacklist/{genome}.blacklist.bed")
+        template_data['blacklist'] = genome_dict[genome]['blacklist']
 
     if assay == "atac":
         template_data['shift_atac_reads'] = get_user_input("Shift ATAC-seq reads? (yes/no)", default="yes", is_boolean=True)
@@ -181,18 +225,22 @@ def setup_configuration(assay, template_data):
     # These need to be replaced
     # e.g. --extendReads -bs 1 --normalizeUsing RPKM
     bamcoverage: -bs 1 --normalizeUsing CPM
+
+heatmap:
+    options:
+    colormap: RdYlBu_r
 """
 
-def create_config(assay):
+def create_config(assay, genome):
     env = Environment(loader=FileSystemLoader('.'))
     template = env.get_template("seqnado/workflow/config/config.yaml.jinja")
     template_deseq2 = env.get_template("seqnado/workflow/config/deseq2.qmd.jinja")
 
     # Initialize template data
-    template_data = {'assay': assay}
+    template_data = {'assay': assay, 'genome': genome}
 
     # Setup configuration
-    setup_configuration(assay, template_data)
+    setup_configuration(assay, genome, template_data)
 
     # Create directory and render template
     dir_name = f"{template_data['project_date']}_{template_data['assay']}_{template_data['project_name']}"

diff --git a/seqnado/utils.py b/seqnado/utils.py
@@ -294,6 +294,14 @@ def define_output_files(
     ]
     assay_output = []
 
+    if make_heatmaps:
+            assay_output.extend(
+                [
+                    "seqnado_output/heatmap/heatmap.pdf",
+                    "seqnado_output/heatmap/metaplot.pdf",
+                ]
+            )
+
     if make_ucsc_hub:
         hub_dir = kwargs["ucsc_hub_details"].get("directory")
         hub_name = kwargs["ucsc_hub_details"].get("name")
@@ -337,14 +345,6 @@ def define_output_files(
                     )
                 )
 
-        if make_heatmaps:
-            assay_output.extend(
-                [
-                    "seqnado_output/heatmap/heatmap.pdf",
-                    "seqnado_output/heatmap/metaplot.pdf",
-                ]
-            )
-
     elif assay == "RNA":
         if make_bigwigs and pileup_method:
             assay_output.extend(
@@ -355,7 +355,7 @@ def define_output_files(
                     strand=["plus", "minus"],
                 )
             )
-
+            
         if run_deseq2:
             project_id = kwargs["deseq2"].get("project_id")
             assay_output.append(f"DESeq2_{project_id}.html")

diff --git a/seqnado/workflow/config/preset_genomes.json b/seqnado/workflow/config/preset_genomes.json
@@ -0,0 +1,58 @@
+{
+    "dm6": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/dm6/UCSC/bt2_index/dm6",
+        "star_index": "/ceph/project/milne_group/shared/seqnado_reference/dm6/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/dm6/UCSC/sequence/dm6.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/dm6/UCSC/genes/dm6.ncbiRefSeq.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/dm6/dm6-blacklist.v2.bed.gz"
+    },
+    "hg19": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/hg19/UCSC/bt2_index/hg19",
+        "star_index": "/ceph/project/milne_group/shared/seqnado_reference/hg19/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/hg19/UCSC/sequence/hg19.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/hg19/UCSC/genes/hg19.ncbiRefSeq.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/hg19/hg19-blacklist.v2.bed.gz "
+    },
+    "hg38": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/bt2_index/hg38",
+        "star_index": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/sequence/hg38.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/hg38/UCSC/genes/hg38.ncbiRefSeq.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/hg38/hg38-blacklist.v2.bed.gz"
+    },
+    "hg38_dm6": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/hg38_dm6/UCSC/bt2_index/hg38_dm6",
+        "star_index": "NA",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/hg38_dm6/UCSC/sequence/hg38_dm6.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/hg38_dm6/UCSC/genes/hg38_dm6.ncbiRefSeq.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/hg38_dm6/hg38_dm6-blacklist.v2.bed.gz"
+    },
+    "hg38_mm39": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/hg38_mm39/bt2_index/hg38_mm39",
+        "star_index": "NA",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/hg38_mm39/sequence/hg38_mm39.fa.fai",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/hg38_mm39/genes/hg38_mm39.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/hg38_mm39/hg38_mm39-blacklist.bed.gz"
+    },
+    "hg38_spikein": {
+        "bt2_index": "NA",
+        "star_index": "/ceph/project/milne_group/shared/seqnado_reference/hg38_spikein/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/hg38_spikein/hg38_spikein.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/hg38_spikein/UCSC/genes/hg38_spikein_transcripts.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/hg38/hg38-blacklist.v2.bed.gz"
+    },
+    "mm10": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/mm10/UCSC/bt2_index/mm10",
+        "star_index": "/ceph/project/milne_group/shared/seqnado_reference/mm10/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/mm10/UCSC/sequence/mm10.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/mm10/UCSC/genes/mm10.ncbiRefSeq.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/mm10/mm10-blacklist.v2.bed.gz"
+    },
+    "mm39": {
+        "bt2_index": "/ceph/project/milne_group/shared/seqnado_reference/mm39/UCSC/bt2_index/mm39",
+        "star_index": "/ceph/project/milne_group/shared/seqnado_reference/mm39/UCSC/STAR_2.7.10b",
+        "chromosome_sizes": "/ceph/project/milne_group/shared/seqnado_reference/mm39/UCSC/sequence/mm39.chrom.sizes",
+        "gtf": "/ceph/project/milne_group/shared/seqnado_reference/mm39/UCSC/genes/mm39.ncbiRefSeq.gtf",
+        "blacklist": "/ceph/project/milne_group/shared/seqnado_reference/mm39/mm10-blacklist.v2.Liftover.mm39.bed.gz"
+    }
+}
diff --git a/seqnado/workflow/rules/heatmap.smk b/seqnado/workflow/rules/heatmap.smk
@@ -2,6 +2,8 @@ import seqnado.utils
 
 if ASSAY == "ChIP":
     prefix = SAMPLE_NAMES_IP 
+elif ASSAY == "RNA":
+    prefix = [x + y for x in SAMPLE_NAMES for y in ["_plus", "_minus"]]
 else:
     prefix = SAMPLE_NAMES
 
@@ -34,10 +36,7 @@ rule heatmap_plot:
         mem_mb=lambda wildcards, attempt: 2000 * 2**attempt,
     log: 
         "seqnado_output/logs/heatmap/heatmap.log",
-    shell: """plotHeatmap -m {input.matrix} \
-        -out {output.heatmap} \
-        --colorMap {params.colormap} \
-        --boxAroundHeatmaps no"""
+    shell: """plotHeatmap -m {input.matrix} -out {output.heatmap} --colorMap {params.colormap} --boxAroundHeatmaps no"""
 
 
 rule heatmap_metaplot:
@@ -51,7 +50,4 @@ rule heatmap_metaplot:
         mem_mb=lambda wildcards, attempt: 2000 * 2**attempt,
     log: 
         "seqnado_output/logs/heatmap/metaplot.log",
-    shell: """plotProfile -m {input.matrix} \
-        -out {output.metaplot} \
-        --colorMap {params.colormap} \
-        --perGroup"""
+    shell: """plotProfile -m {input.matrix} -out {output.metaplot} --perGroup"""
diff --git a/seqnado/workflow/snakefile_rna b/seqnado/workflow/snakefile_rna
@@ -48,6 +48,7 @@ include: "rules/alignment_counts.smk"
 include: "rules/pileup.smk"
 include: "rules/deseq2_rna.smk"
 include: "rules/hub.smk"
+include: "rules/heatmap.smk"
 
 
 # Define output files