Merge pull request #34 from tmaklin/dev

First public release

.github/workflows/build_and_test.yml

@@ -25,7 +25,7 @@ jobs:
       run: rustup update ${{ matrix.toolchain }} && rustup default ${{ matrix.toolchain }}
 
     - name: Build binary
-      run: cargo build --features cli --verbose
+      run: cargo build --all-features --verbose
 
     - name: Run unit and integration tests
-      run: cargo test --no-fail-fast --verbose
+      run: cargo test --all-features --no-fail-fast --verbose

.github/workflows/make_release.yml

@@ -12,35 +12,9 @@ jobs:
   create-release:
     name: Create and publish release
     runs-on: ubuntu-latest
-    environment: Make sablast release
+    environment: Make kbo release
 
     steps:
-      - name: Download artifacts
-        uses: dawidd6/action-download-artifact@v6
-        with:
-          workflow: build_artifacts.yml
-          workflow_conclusion: success
-
-      - name: Organise files
-        shell: bash
-        run: |
-          mv sablast-candidate-x86_64-unknown-linux-musl/sablast-candidate-x86_64-unknown-linux-musl.tar.gz ./
-          mv sablast-candidate-x86_64-apple-darwin/sablast-candidate-x86_64-apple-darwin.tar.gz ./
-          mv sablast-candidate-aarch64-apple-darwin/sablast-candidate-aarch64-apple-darwin.tar.gz ./
-
-      - name: Rename mac artifacts
-        shell: bash
-        run: |
-          tar -zxvf sablast-candidate-x86_64-apple-darwin.tar.gz && mv sablast-candidate-x86_64-apple-darwin sablast-${{ github.ref_name }}-x86_64-apple-darwin && tar -zcvf sablast-candidate-x86_64-apple-darwin.tar.gz sablast-${{ github.ref_name }}-x86_64-apple-darwin
-          tar -zxvf sablast-candidate-aarch64-apple-darwin.tar.gz && mv sablast-candidate-aarch64-apple-darwin sablast-${{ github.ref_name }}-aarch64-apple-darwin && tar -zcvf sablast-candidate-aarch64-apple-darwin.tar.gz sablast-${{ github.ref_name }}-aarch64-apple-darwin
-
-      - name: Designate version
-        shell: bash
-        run: |
-          mv sablast-candidate-x86_64-unknown-linux-musl.tar.gz sablast-${{ github.ref_name }}-x86_64-linux-musl.tar.gz
-          mv sablast-candidate-x86_64-apple-darwin.tar.gz sablast-${{ github.ref_name }}-x86_64-apple-darwin.tar.gz
-          mv sablast-candidate-aarch64-apple-darwin.tar.gz sablast-${{ github.ref_name }}-aarch64-apple-darwin.tar.gz
-
       - name: Get current date
         id: date
         run: echo "::set-output name=date::$(date +'%d %B %Y')"
@@ -49,12 +23,8 @@ jobs:
         uses: softprops/action-gh-release@v2
         with:
           token: ${{ secrets.MAKE_RELEASE_TOKEN }}
-          name: sablast-${{ github.ref_name }} (${{ steps.date.outputs.date }})
+          name: kbo-${{ github.ref_name }} (${{ steps.date.outputs.date }})
           draft: false
           prerelease: false
           fail_on_unmatched_files: true
           generate_release_notes: true
-          files: |
-            sablast-${{ github.ref_name }}-x86_64-linux-musl.tar.gz
-            sablast-${{ github.ref_name }}-x86_64-apple-darwin.tar.gz
-            sablast-${{ github.ref_name }}-aarch64-apple-darwin.tar.gz

Cargo.toml

@@ -1,43 +1,18 @@
 [package]
-name = "sablast"
-version = "0.3.0"
+name = "kbo"
+version = "0.4.0"
 edition = "2021"
 rust-version = "1.77.0"
 authors = ["Tommi Mäklin <[email protected]>"]
 description = "Spectral Burrows-Wheeler transform accelerated local alignment search"
 readme = "README.md"
-homepage = "https://github.com/tmaklin/sablast"
-repository = "https://github.com/tmaklin/sablast"
+homepage = "https://github.com/tmaklin/kbo"
+repository = "https://github.com/tmaklin/kbo"
 license = "MIT OR Apache-2.0"
 
-# See more keys and their definitions at https://doc.rust-lang.org/cargo/reference/manifest.html
-
-[features]
-cli = ["dep:needletail", "dep:clap", "dep:rayon", "dep:log", "dep:stderrlog"]
-
-[[bin]]
-name = "sablast"
-path = "src/cli/main.rs"
-required-features = ["cli"]
-
 [dependencies]
 ## core
-sbwt = "0.3.1"
-
-## cli
-clap = { version = "4", features = ["derive"], optional = true}
-
-### io
-#### TODO Re-enable reading compressed sequences in needletail
-##### This requires resolving the libllzma linker issue in build_artifacts.yml
-needletail = { version = "0.5.1", default-features = false, optional = true }
-
-### logging
-log = { version = "0.4.20", optional = true }
-stderrlog = { version = "0.6.0", optional = true }
-
-### threading
-rayon = { version = "1", optional = true }
+sbwt = { version = "0.3.4", features = ["bpks-mem"] }
 
 ## docs
 embed-doc-image="0.1.4"

README.md

@@ -1,5 +1,35 @@
-# sablast
+# kbo
 Spectral Burrows-Wheeler transform accelerated local alignment search.
 
+kbo is an approximate local aligner based on converting [_k_-bounded matching
+statistics](https://www.biorxiv.org/content/10.1101/2024.02.19.580943v1)
+into a character representation of the underlying alignment sequence.
+
+Documentation is available at [https://docs.rs/kbo](https://docs.rs/kbo).
+
+## Installation
+kbo is distributed as three separate Rust packages:
+- [kbo](https://github.com/tmaklin/kbo) contains a Rust library implementing the core algorithm (this repository).
+- [kbo-cli](https://github.com/tmaklin/kbo-cli) provides a command-line interface for `kbo find` and `kbo map`.
+- [kbo-gui](https://github.com/tmaklin/kbo-cli) provides a WebAssembly graphical user interface for running kbo in the browser.
+
+## About
+kbo supports two main operations:
+
+- `kbo find` matches the _k_-mers in a query sequence with the
+  reference and reports the local alignment segments found within the
+  reference. Find is useful for problems that can be solved with
+  [blast](https://blast.ncbi.nlm.nih.gov/Blast.cgi).
+- `kbo map` maps the query sequence against a reference
+  sequence, and reports the nucleotide sequence of the alignment relative to
+  the reference. Map solves the same problem as
+  [snippy](https://github.com/tseemann/snippy) and [ska
+  map](https://docs.rs/ska/latest/ska/#ska-map).
+
+kbo uses the [Spectral Burrows-Wheeler
+Transform](https://docs.rs/sbwt/latest/sbwt/) data structure that allows
+efficient _k_-mer matching between a target and a query sequence and
+fast retrieval of the _k_-bounded matching statistic for each _k_-mer match.
+
 ## License
-sablast is dual-licensed under the [MIT](LICENSE-MIT) and [Apache 2.0](LICENSE-APACHE) licenses.
+kbo is dual-licensed under the [MIT](LICENSE-MIT) and [Apache 2.0](LICENSE-APACHE) licenses.