Merge pull request #26 from MPUSP/dev

feat: enable workflow to run with singularity

.snakemake-workflow-catalog.yml

@@ -2,5 +2,5 @@ usage:
   software-stack-deployment:
     conda: true
     singularity: false
-    singularity+conda: false
+    singularity+conda: true
   report: true

.test/config/config.yml

@@ -10,6 +10,7 @@ design_guides:
   target_type: ["target", "intergenic", "ntc"]
   tss_window: [-100, 400]
   tiling_window: 1000
+  tiling_min_dist: 0
   circular: False
   canonical: True
   strands: "both"

README.md

@@ -1,9 +1,11 @@
 # snakemake-crispr-guides
 
 ![Platform](https://img.shields.io/badge/platform-all-green)
-[![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-brightgreen.svg)](https://snakemake.github.io)
+[![Snakemake](https://img.shields.io/badge/snakemake-≥6.3.0-green.svg)](https://snakemake.github.io)
 [![GitHub actions status](https://github.com/MPUSP/snakemake-crispr-guides/workflows/Tests/badge.svg?branch=main)](https://github.com/MPUSP/snakemake-crispr-guides/actions?query=branch%3Amain+workflow%3ATests)
 [![run with conda](http://img.shields.io/badge/run%20with-conda-3EB049?labelColor=000000&logo=anaconda)](https://docs.conda.io/en/latest/)
+[![run with singularity](https://img.shields.io/badge/run%20with-singularity-1D355C.svg?labelColor=000000)](https://sylabs.io/docs/)
+[![workflow catalog](https://img.shields.io/badge/Snakemake%20workflow%20catalog-darkgreen)](https://snakemake.github.io/snakemake-workflow-catalog)
 
 ---
 
@@ -152,12 +154,18 @@ Before running the entire workflow, you can perform a dry run using:
 snakemake --dry-run
 ```
 
-To run the complete workflow with test files, execute the following command. The definition of the number of compute cores is mandatory.
+To run the complete workflow with test files using **`conda`**, execute the following command. The definition of the number of compute cores is mandatory.
 
 ```
 snakemake --cores 10 --use-conda
 ```
 
+To run the workflow with **`singularity`**, run:
+
+```
+snakemake --cores 10 --use-singularity --use-conda
+```
+
 To supply a custom config file and/or use options that override the defaults, run the workflow like this:
 
 ```
@@ -184,6 +192,7 @@ This table lists all parameters that can be used to run the workflow.
 | target_type            | string  | specify targets for guide design (see below)   | `["target", "intergenic", "ntc"]` |
 | tss_window             | numeric | upstream/downstream window around TSS          | `[0, 500]`                        |
 | tiling_window          | numeric | window size for intergenic regions             | `1000`                            |
+| tiling_min_dist        | numeric | min distance between TSS and intergenic region | `0`                               |
 | circular               | logical | is the genome circular?                        | `False`                           |
 | canonical              | logical | only canonical PAM sites are included          | `True`                            |
 | strands                | string  | target `coding`, `template` or `both`          | `both`                            |

config/README.md

@@ -30,12 +30,18 @@ Before running the entire workflow, you can perform a dry run using:
 snakemake --dry-run
 ```
 
-To run the complete workflow with test files, execute the following command. The definition of the number of compute cores is mandatory.
+To run the complete workflow with test files using **`conda`**, execute the following command. The definition of the number of compute cores is mandatory.
 
 ```
 snakemake --cores 10 --use-conda
 ```
 
+To run the workflow with **`singularity`**, run:
+
+```
+snakemake --cores 10 --use-singularity --use-conda
+```
+
 To supply a custom config file and/or use options that override the defaults, run the workflow like this:
 
 ```
@@ -62,6 +68,7 @@ This table lists all parameters that can be used to run the workflow.
 | target_type            | string  | specify targets for guide design (see below)   | `["target", "intergenic", "ntc"]` |
 | tss_window             | numeric | upstream/downstream window around TSS          | `[0, 500]`                        |
 | tiling_window          | numeric | window size for intergenic regions             | `1000`                            |
+| tiling_min_dist        | numeric | min distance between TSS and intergenic region | `0`                               |
 | circular               | logical | is the genome circular?                        | `False`                           |
 | canonical              | logical | only canonical PAM sites are included          | `True`                            |
 | strands                | string  | target `coding`, `template` or `both`          | `both`                            |

config/config.yml

@@ -10,6 +10,7 @@ design_guides:
   target_type: ["target", "intergenic", "ntc"]
   tss_window: [-100, 400]
   tiling_window: 1000
+  tiling_min_dist: 0
   circular: False
   canonical: True
   strands: "both"

workflow/Snakefile

@@ -14,11 +14,15 @@
 include: "rules/common.smk"
 
 
-# load and print configuration
+# load configuration
 # -----------------------------------------------------
 configfile: "config/config.yml"
 
 
+# container definition (optional)
+container: "oras://ghcr.io/MPUSP/snakemake-crispr-guides:1.1.0"
+
+
 # target rule
 # -----------------------------------------------------
 rule all:

workflow/scripts/design_guides.R

@@ -112,7 +112,12 @@ if ("target" %in% target_type) {
   genome(list_tx_window) <- "custom"
 
   # for intergenic regions: remove all guides that target within transcripts
-  index_intergenic <- findOverlaps(list_guides, list_tx_window, ignore.strand = TRUE)
+  list_total_window <- trim(resize(
+    list_tx_window,
+    width = width(list_tx_window) + (tiling_min_dist*2),
+    fix = "center"
+  ))
+  index_intergenic <- findOverlaps(list_guides, list_total_window, ignore.strand = TRUE)
   list_intergenic <- list_guides[-index_intergenic@from]
 
   # select only guides whose PAM overlaps with the TSS window