Merge pull request #145 from baigal628/master

Release of v1.5.1

DESCRIPTION

@@ -1,7 +1,7 @@
 Package: MAESTRO
 Type: Package
 Title: Model-based Analyses of Single-cell Transcriptome and Regulome
-Version: 1.5.0
+Version: 1.5.1
 Date: 2021-03-05
 Author: Chenfei Wang, Dongqing Sun, Tao Liu, Changxin Wan, Ming (Tommy) Tang, Gali Bai
 Maintainer: Dongqing Sun<dongqingsun96@gmail.com>, Gali Bai<gali.bai@hotmail.com>

MAESTRO/MAESTRO

@@ -5,7 +5,7 @@
 # @Last Modified by:   Gali Bai, Dongqing Sun
 # @Last Modified time: 2021-06-07 11:11:58
 
-version = "1.5.0"
+version = "1.5.1"
 
 import logging
 import sys, os
@@ -59,7 +59,7 @@ def main():
         exit(0)
     elif args.subcommand == "samples-init":
         sample_json(args)
-  
+
     elif args.subcommand == "scatac-init":
         scatac_validator(args)
         scatac_config(args)

MAESTRO/MAESTRO_PipeInit.py

@@ -3,8 +3,7 @@
 # @E-mail: Dongqingsun96@gmail.com
 # @Date:   2020-02-23 19:40:27
 # @Last Modified by: Gali Bai
-# @Last Modified time: 2021-06-14 17:34:46
-
+# @Last Modified time: 2021-07-12 17:34:46
 
 import os
 import shutil
@@ -199,6 +198,17 @@ def scrna_parser(subparsers):
         choices = ["GRCh38", "GRCm38"], type = str,
         help = "Specify the genome assembly (GRCh38 for human and GRCm38 for mouse). DEFAULT: GRCh38.")
 
+    #STARsolo arguments
+    group_star = workflow.add_argument_group("STARsolo parameters arguments")
+    group_star.add_argument("--STARsolo_Features", dest= "STARsolo_Features", default = "Gene", type = str,
+        choices = ["Gene", "GeneFull", "Gene GeneFull", "SJ", "Velocyto"],
+        help = "Parameters passed to STARsolo --soloFeatures."
+        "specify --soloFeatures Gene for single-cell data."
+        "specify --soloFeatures GeneFull for single-nuclei data"
+        "specify --soloFeatures Gene GeneFull for getting both counts in exons level and exon + intron level (velocity)")
+    group_star.add_argument("--STARsolo_threads", dest = "STARsolo_threads", default = 12, type = int,
+        help = "Threads for running STARsolo. DEFAULT: 12.")
+
     # Output arguments
     group_output = workflow.add_argument_group("Running and output arguments")
     group_output.add_argument("--cores", dest = "cores", default = 10,
@@ -423,6 +433,8 @@ def scrna_config(args):
             sample_file = args.sample_file,
             species = args.species,
             platform = args.platform,
+            STARsolo_Features = args.STARsolo_Features,
+            STARsolo_threads = args.STARsolo_threads,
             mergedname = args.mergedname,
             outprefix = args.outprefix,
             rseqc = args.rseqc,

MAESTRO/Snakemake/scRNA/config_template.yaml

@@ -7,7 +7,7 @@ SAMPLES_JSON: {{ sample_file }}
 STARsolo_threads: 12
 
 # can specify "--soloFeatures FullGene" for single nuclei data
-STARsolo_custom: '--soloFeatures Gene'
+STARsolo_Features: {{STARsolo_Features}}
 
 # Species to use [GRCh38, GRCm38] (GRCh38 for human and GRCm38 for mouse)
 species: {{ species }}

MAESTRO/Snakemake/scRNA/rules/sc_rna_map.smk

@@ -16,11 +16,11 @@ if config["platform"] == "10x-genomics":
         output:
             bam = "Result/STAR/{sample}/{sample}Aligned.sortedByCoord.out.bam",
             bai = "Result/STAR/{sample}/{sample}Aligned.sortedByCoord.out.bam.bai",
-            rawmtx = "Result/STAR/{sample}/{sample}Solo.out/Gene/raw/matrix.mtx",
-            feature = "Result/STAR/{sample}/{sample}Solo.out/Gene/raw/features.tsv",
-            barcode = "Result/STAR/{sample}/{sample}Solo.out/Gene/raw/barcodes.tsv"
+            rawmtx = "Result/STAR/{sample}/{sample}Solo.out/%s/raw/matrix.mtx" %(config["STARsolo_Features"].split(" ")[0]),
+            feature = "Result/STAR/{sample}/{sample}Solo.out/%s/raw/features.tsv" %(config["STARsolo_Features"].split(" ")[0]),
+            barcode = "Result/STAR/{sample}/{sample}Solo.out/%s/raw/barcodes.tsv" %(config["STARsolo_Features"].split(" ")[0])
         params:
-            star_custom = config.get("STARsolo_custom", ""),
+            star_custom = config["STARsolo_Features"],
             outprefix = "Result/STAR/{sample}/{sample}",
             transcript = lambda wildcards: ','.join(FILES[wildcards.sample]["R2"]),
             barcode = lambda wildcards: ','.join(FILES[wildcards.sample]["R1"]),
@@ -47,7 +47,7 @@ if config["platform"] == "10x-genomics":
                 --outSAMtype BAM SortedByCoordinate \
                 --outSAMattributes NH HI nM AS CR UR CB UB GX GN sS sQ sM \
                 --soloType CB_UMI_Simple \
-                {params.star_custom} \
+                --soloFeatures {params.star_custom} \
                 --soloCBwhitelist {input.whitelist} \
                 --soloCBstart {params.barcodestart} \
                 --soloCBlen {params.barcodelength} \
@@ -62,6 +62,7 @@ if config["platform"] == "10x-genomics":
 
             samtools index -b -@ {threads} {output.bam} >> {log} 2>&1
             """
+
 elif config["platform"] == "Dropseq":
     rule scrna_map:
         input:
@@ -111,6 +112,7 @@ elif config["platform"] == "Dropseq":
 
             samtools index -b -@ {threads} {output.bam}
             """
+
 elif config["platform"] == "Smartseq2":
     rule scrna_map:
         input:

MAESTRO/Snakemake/scRNA/rules/sc_rna_merge.smk

@@ -1,8 +1,8 @@
 rule scrna_merge:
     input:
-        rawmtx = expand("Result/STAR/{sample}/{sample}Solo.out/Gene/raw/matrix.mtx", sample=ALL_SAMPLES),
-        features = expand("Result/STAR/{sample}/{sample}Solo.out/Gene/raw/features.tsv", sample=ALL_SAMPLES)[1],
-        barcodes = expand("Result/STAR/{sample}/{sample}Solo.out/Gene/raw/barcodes.tsv", sample=ALL_SAMPLES)
+        rawmtx = expand("Result/STAR/{sample}/{sample}Solo.out/%s/raw/matrix.mtx" %(config["STARsolo_Features"].split(" ")[0]), sample=ALL_SAMPLES),
+        features = expand("Result/STAR/{sample}/{sample}Solo.out/%s/raw/features.tsv" %(config["STARsolo_Features"].split(" ")[0]), sample=ALL_SAMPLES)[1],
+        barcodes = expand("Result/STAR/{sample}/{sample}Solo.out/%s/raw/barcodes.tsv" %(config["STARsolo_Features"].split(" ")[0]), sample=ALL_SAMPLES)
     output:
         mergedmtx = "Result/STAR/%s/rawmatrix/matrix.mtx" % config["mergedname"],
         mergedfeatures = "Result/STAR/%s/rawmatrix/features.tsv" % config["mergedname"],

MAESTRO/Snakemake/scRNA/rules/sc_rna_qc.smk

@@ -1,9 +1,9 @@
 if config["platform"] == "10x-genomics" or config["platform"] == "Dropseq":
     rule scrna_qc:
         input:
-            rawmtx = "Result/STAR/{sample}/{sample}Solo.out/Gene/raw/matrix.mtx",
-            feature = "Result/STAR/{sample}/{sample}Solo.out/Gene/raw/features.tsv",
-            barcode = "Result/STAR/{sample}/{sample}Solo.out/Gene/raw/barcodes.tsv"
+            rawmtx = "Result/STAR/{sample}/{sample}Solo.out/%s/raw/matrix.mtx" %(config["STARsolo_Features"].split(" ")[0]),
+            feature = "Result/STAR/{sample}/{sample}Solo.out/%s/raw/features.tsv" %(config["STARsolo_Features"].split(" ")[0]),
+            barcode = "Result/STAR/{sample}/{sample}Solo.out/%s/raw/barcodes.tsv" %(config["STARsolo_Features"].split(" ")[0])
         output:
             countgene = "Result/QC/{sample}/{sample}_count_gene_stat.txt",
             filtermatrix = "Result/QC/{sample}/{sample}_filtered_gene_count.h5",

MAESTRO/sample2json.py

@@ -58,14 +58,14 @@ def sample_json(args):
                     full_path = join(root, file)
                     if args.assay_type == "scrna":
                         #R1 will be sample barcode, R2 will be reverse reads, I1 will be the index
-                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]_(L[0-9]{3})_([IR][12])_[0-9]+.fastq.gz", file)
+                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]+_(L[0-9]{3})_([IR][12])_[0-9]+.fastq.gz", file)
                         if m:
                             sample = m.group(1)
                             lane = m.group(2)
                             reads = m.group(3)
                             FILES[sample][reads].append(full_path)
                     elif args.assay_type == "scatac" and args.platform == "10x-genomics":
-                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]_(L[0-9]{3})_([IR][123])_[0-9]+.fastq.gz", file)
+                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]+_(L[0-9]{3})_([IR][123])_[0-9]+.fastq.gz", file)
                         if m:
                             sample = m.group(1)
                             lane = m.group(2)
@@ -94,14 +94,14 @@ def sample_json(args):
                     full_path = join(root, file)
                     if args.assay_type == "scrna":
                         #R1 will be sample barcode, R2 will be reverse reads, I1 will be the index
-                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]_(L[0-9]{3})_([IR][12])_[0-9]+.fastq", file)
+                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]+_(L[0-9]{3})_([IR][12])_[0-9]+.fastq", file)
                         if m:
                             sample = m.group(1)
                             lane = m.group(2)
                             reads = m.group(3)
                             FILES[sample][reads].append(full_path)
                     elif args.assay_type == "scatac" and args.platform == "10x-genomics":
-                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]_(L[0-9]{3})_([IR][123])_[0-9]+.fastq", file)
+                        m = re.search(r"([A-Z0-9a-z_]+)_S[0-9]+_(L[0-9]{3})_([IR][123])_[0-9]+.fastq", file)
                         if m:
                             sample = m.group(1)
                             lane = m.group(2)

README.md

@@ -77,7 +77,11 @@ We are hosting MAESTRO documentation, instruction and tutorials at [MAESTRO Webs
 * Support multi-sample scATAC-seq when starting from bam file with CB tag or 10X like fragment file.
 * Fix the ratio of genes mapped to mitochondrial to percentage.
 * Move MAESTRO documentation to [workfowr](https://github.com/jdblischak/workflowr).
-
+### v1.5.1
+* Expand STARsolo --soloFeatures and --runThreadN as MAESTRO subcommands.
+* Support single-nuclei RNA-seq pipeline.
+* Fix bug in sample initiation subcommand to read fastq with sample id greater than 9.
+* Update MAESTRO documentation to v1.5.1. Add snRNA-seq tutorials. Expand scRNA-seq tutorial with lisa2 TF prediction custom analysis. Add multi-scATAC-seq genome track plot for pseudobulk peaks. Explain multi-samples peak calling parameters.
 
 ## System requirements
 * Linux/Unix
@@ -107,7 +111,7 @@ $ conda config --add channels bioconda
 $ conda config --add channels conda-forge
 # To make the installation faster, we recommend using mamba
 $ conda install mamba -c conda-forge
-$ mamba create -n MAESTRO maestro=1.5.0 -c liulab-dfci
+$ mamba create -n MAESTRO maestro=1.5.1 -c liulab-dfci
 # Activate the environment
 $ conda activate MAESTRO
 ```

conda/MAESTRO/meta.yaml

@@ -1,6 +1,6 @@
 package:
   name: maestro
-  version: "1.5.0"
+  version: "1.5.1"
 source:
   path: ../../
 # build:

setup.py

@@ -18,7 +18,7 @@
 def main():
     setup(
         name = "MAESTRO",
-        version = "1.5.0",
+        version = "1.5.1",
         package_dir = {'MAESTRO':'MAESTRO'},
         packages = ['MAESTRO'],
         package_data={'MAESTRO':['Snakemake/scRNA/*', 'Snakemake/integrate/*', 'Snakemake/scATAC/*', 'Snakemake/scATAC/rules/*', 'Snakemake/scRNA/rules/*', 'R/*', 'utils/*','annotations/*', 'html/*', '']},