Merge pull request #1 from COMBINE-lab/dev

Dev

.github/workflows/release-please.yml

@@ -0,0 +1,38 @@
+on:
+  push:
+    branches:
+      - main 
+
+name: release-please
+
+jobs:
+  release-please:
+    if: github.repository_owner == 'COMBINE-lab'
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v2
+
+      - uses: GoogleCloudPlatform/release-please-action@v3
+        id: release_main
+        with:
+          release-type: rust
+          package-name: roers
+          bump-minor-pre-major: true
+          path: .
+
+      - name: Install stable toolchain
+        uses: actions-rs/toolchain@v1
+        if: ${{ steps.release_main.outputs.release_created }}
+        with:
+          toolchain: stable
+          override: true
+
+      - uses: Swatinem/[email protected]
+        if: ${{ steps.release_main.outputs.release_created }}
+
+      - name: Publish roers
+        if: ${{ steps.release_main.outputs.release_created }}
+        uses: actions-rs/cargo@v1
+        with:
+          command: publish
+          args: --token ${{ secrets.CRATES_IO_TOKEN }}

Cargo.toml

@@ -2,6 +2,31 @@
 name = "roers"
 version = "0.1.0"
 edition = "2021"
+authors = [
+  "Dongze He <[email protected]>",
+  "Rob Patro <[email protected]>",
+]
+description = "A tool to prepare augmented annotations for single-cell RNA-seq analysis."
+license-file = "LICENSE"
+readme = "README.md"
+repository = "https://github.com/COMBINE-lab/roers"
+homepage = "https://github.com/COMBINE-lab/roers"
+include = [
+  "/src/lib/lib.rs",
+  "/src/main.rs",
+  "/Cargo.toml",
+  "/Cargo.lock",
+  "/README.md",
+  "/LICENSE",
+]
+keywords = [
+  "genomics",
+  "GTF-GFF",
+  "splici",
+  "scRNA-seq",
+  "augmented-reference",
+]
+categories = ["science", "data-structures"]
 
 # See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
 [[bin]]
@@ -15,11 +40,11 @@ path = "src/lib/lib.rs"
 [dependencies]
 anyhow = "1.0.71"
 clap = { version = "4.3.3", features = ["derive", "wrap_help","cargo"] }
-grangers = { git = "https://github.com/COMBINE-lab/grangers.git", branch="dev" }
+grangers = { git = "https://github.com/COMBINE-lab/grangers.git", branch="dev", version = "0.1.4" }
 polars = { version = "0.30", features = ["lazy","dataframe_arithmetic","sort_multiple", "checked_arithmetic","rows","dtype-struct", "dtype-categorical", "list_eval","concat_str", "strings"]}
 peak_alloc = "0.2.0"
 tracing = "0.1.37"
 tracing-subscriber = { version = "0.3.17", features = ["env-filter"] }
 noodles = { version = "0.41.0", features = ["fasta"] }
-serde = {version = "1.0.163", features = ["derive"]}
+serde = {version = "1.0.164", features = ["derive"]}
 serde_json = "1.0.96"

README.md

@@ -1 +1,3 @@
-# roers
+# roers
+
+A rust library for preparing expanded transcriptome references for quantification with [`alevin-fry`](https://alevin-fry.readthedocs.io/en/latest/).

src/lib/lib.rs

@@ -1,10 +1,10 @@
 use anyhow::Context;
 use clap::builder::{PossibleValuesParser, TypedValueParser};
-use grangers::grangers::{options, Grangers};
+use grangers::{options, Grangers};
 use polars::lazy::dsl::concat_str;
 use polars::prelude::*;
-use serde_json::json;
 use serde::Serialize;
+use serde_json::json;
 use std::collections::HashSet;
 use std::ops::Add;
 use std::path::PathBuf;
@@ -337,7 +337,7 @@ pub fn make_ref(aug_ref_opts: AugRefOpts) -> anyhow::Result<()> {
                     info!("Processing {} intronic records", intron_gr.df().height(),);
 
                     // no_flanking_merge decides when the order of merge and extend
-                    // if no_flanking_merge is true, we merge first, then extend 
+                    // if no_flanking_merge is true, we merge first, then extend
                     if no_flanking_merge {
                         // Then, we merge the overlapping introns
                         intron_gr = intron_gr.merge(
@@ -349,12 +349,8 @@ pub fn make_ref(aug_ref_opts: AugRefOpts) -> anyhow::Result<()> {
                     }
 
                     // add flanking end to both side of each intron
-                    intron_gr.extend(
-                        flank_length,
-                        &options::ExtendOption::Both,
-                        false,
-                    )?;
-
+                    intron_gr.extend(flank_length, &options::ExtendOption::Both, false)?;
+
                     // if no_flanking_merge is false, we merge after extend
                     if !no_flanking_merge {
                         // Then, we merge the overlapping introns
@@ -471,7 +467,7 @@ pub fn make_ref(aug_ref_opts: AugRefOpts) -> anyhow::Result<()> {
                     // we get the range (transcript body) of each transcript
                     let mut tx_gr = exon_gr.transcripts(None, true)?;
 
-                    // Then we append a -T to mark the sequence as transcript body 
+                    // Then we append a -T to mark the sequence as transcript body
                     tx_gr.df = tx_gr
                         .df
                         .lazy()
@@ -566,15 +562,11 @@ pub fn make_ref(aug_ref_opts: AugRefOpts) -> anyhow::Result<()> {
             "gene_id" => &names,
         )?;
 
-        if aug_type.is_some() {                    
+        if aug_type.is_some() {
             // if we are here, we need to add a column for splice_status cuz it is an augmented reference
-            extra_t2g.with_column(Series::new(
-                "splice_status",
-                vec!["S"; extra_t2g.height()],
-            ))?;
-
+            extra_t2g.with_column(Series::new("splice_status", vec!["S"; extra_t2g.height()]))?;
         }
-        
+
         t2g_map.extend(&extra_t2g)?;
 
         // extend gene_id_to_name for the custom spliced targets
@@ -619,14 +611,11 @@ pub fn make_ref(aug_ref_opts: AugRefOpts) -> anyhow::Result<()> {
             "gene_id" => &names,
         )?;
 
-        if aug_type.is_some() {                    
+        if aug_type.is_some() {
             // if we are here, we need to add a column for splice_status cuz it is an augmented reference
-            extra_t2g.with_column(Series::new(
-                "splice_status",
-                vec!["U"; extra_t2g.height()],
-            ))?;
+            extra_t2g.with_column(Series::new("splice_status", vec!["U"; extra_t2g.height()]))?;
         }
-        
+
         t2g_map.extend(&extra_t2g)?;
 
         // extend gene_id_to_name for the custom spliced targets