Oncodrive3D 1.0.7__tar.gz → 1.0.8__tar.gz

oncodrive3d-1.0.8/.github/workflows/release-publish.yml

@@ -0,0 +1,225 @@
+name: release-publish
+
+on:
+  release:
+    types:
+      - published
+
+permissions:
+  contents: read
+
+
+jobs:
+  validate-and-build:
+    name: Validate Version And Build Dist
+    runs-on: ubuntu-latest
+    outputs:
+      version: ${{ steps.version_check.outputs.version }}
+      tag_name: ${{ steps.version_check.outputs.tag_name }}
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+        with:
+          fetch-depth: 0
+
+      - name: Set Up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Set Up uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Validate Tag Version And Bump
+        id: version_check
+        env:
+          TAG_NAME: ${{ github.event.release.tag_name }}
+        run: |
+          set -euo pipefail
+
+          if [[ -z "${TAG_NAME}" ]]; then
+            echo "Could not determine release tag."
+            exit 1
+          fi
+
+          TAG_VERSION="${TAG_NAME#v}"
+          if [[ "${TAG_VERSION}" == "${TAG_NAME}" ]]; then
+            echo "Release tag must start with 'v' (for example: v1.0.9)."
+            exit 1
+          fi
+
+          CURRENT_VERSION=$(python - <<'PY'
+          import pathlib
+          import re
+
+          init_file = pathlib.Path('scripts/__init__.py').read_text(encoding='utf-8')
+          match = re.search(r'__version__\s*=\s*["\']([^"\']+)["\']', init_file)
+          if not match:
+              raise SystemExit('Could not find __version__ in scripts/__init__.py')
+          print(match.group(1))
+          PY
+          )
+
+          if [[ "${CURRENT_VERSION}" != "${TAG_VERSION}" ]]; then
+            echo "Version mismatch: scripts/__init__.py has ${CURRENT_VERSION}, tag is ${TAG_VERSION}."
+            exit 1
+          fi
+
+          PREVIOUS_TAG=$(git tag --sort=-v:refname | grep -E '^v[0-9]+' | grep -vx "${TAG_NAME}" | head -n 1 || true)
+          if [[ -n "${PREVIOUS_TAG}" ]]; then
+            PREVIOUS_FILE=$(git show "${PREVIOUS_TAG}:scripts/__init__.py" 2>/dev/null || true)
+            PREVIOUS_VERSION=$(printf '%s\n' "${PREVIOUS_FILE}" | sed -nE "s/^__version__[[:space:]]*=[[:space:]]*['\"]([^'\"]+)['\"].*/\1/p" | head -n 1)
+
+            if [[ -n "${PREVIOUS_VERSION}" ]]; then
+              python - "${PREVIOUS_VERSION}" "${CURRENT_VERSION}" <<'PY'
+              import re
+              import sys
+
+              previous = sys.argv[1]
+              current = sys.argv[2]
+
+              semver_pattern = re.compile(r'^\d+\.\d+\.\d+$')
+              if not semver_pattern.match(previous) or not semver_pattern.match(current):
+                  raise SystemExit(
+                      f'Both versions must use MAJOR.MINOR.PATCH numeric format for bump check. '
+                      f'Previous={previous}, Current={current}'
+                  )
+
+              p = tuple(int(x) for x in previous.split('.'))
+              c = tuple(int(x) for x in current.split('.'))
+
+              if c <= p:
+                  raise SystemExit(
+                      f'Version not bumped. Current release version {current} must be greater than previous release {previous}.'
+                  )
+
+              print(f'Version bump check passed: {previous} -> {current}')
+              PY
+            else
+              echo "Could not parse version from ${PREVIOUS_TAG}. Skipping bump comparison."
+            fi
+          else
+            echo "No previous v* tag found. Skipping bump comparison."
+          fi
+
+          echo "version=${CURRENT_VERSION}" >> "${GITHUB_OUTPUT}"
+          echo "tag_name=${TAG_NAME}" >> "${GITHUB_OUTPUT}"
+
+      - name: Build Distribution Packages
+        run: |
+          uv build
+
+      - name: Upload Distribution Artifacts
+        uses: actions/upload-artifact@v4
+        with:
+          name: python-dist
+          path: dist/*
+          if-no-files-found: error
+
+  publish-testpypi:
+    name: Publish To TestPyPI
+    runs-on: ubuntu-latest
+    needs: validate-and-build
+    steps:
+      - name: Download Distribution Artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: python-dist
+          path: dist
+
+      - name: Publish To TestPyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          repository-url: https://test.pypi.org/legacy/
+          user: __token__
+          password: ${{ secrets.TEST_PYPI_API_TOKEN }}
+          packages-dir: dist
+          skip-existing: true
+
+  smoke-test-testpypi:
+    name: Install And Smoke Test From TestPyPI
+    runs-on: ubuntu-latest
+    needs:
+      - validate-and-build
+      - publish-testpypi
+    steps:
+      - name: Set Up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.10'
+
+      - name: Set Up uv
+        uses: astral-sh/setup-uv@v5
+
+      - name: Install Package From TestPyPI And Run Smoke Test
+        env:
+          VERSION: ${{ needs.validate-and-build.outputs.version }}
+        run: |
+          set -euo pipefail
+
+          uv venv .venv --python 3.10
+
+          for attempt in 1 2 3 4 5 6; do
+            if uv pip install --python .venv/bin/python --index-url https://test.pypi.org/simple/ --extra-index-url https://pypi.org/simple "oncodrive3d==${VERSION}"; then
+              break
+            fi
+
+            if [[ "${attempt}" == "6" ]]; then
+              echo "Failed to install oncodrive3d==${VERSION} from TestPyPI after retries."
+              exit 1
+            fi
+
+            echo "Package not available yet on TestPyPI (attempt ${attempt}/6). Retrying in 30s..."
+            sleep 30
+          done
+
+          .venv/bin/oncodrive3d --help >/dev/null
+
+  publish-pypi:
+    name: Publish To PyPI
+    runs-on: ubuntu-latest
+    needs:
+      - validate-and-build
+      - smoke-test-testpypi
+    steps:
+      - name: Download Distribution Artifacts
+        uses: actions/download-artifact@v4
+        with:
+          name: python-dist
+          path: dist
+
+      - name: Publish To PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          user: __token__
+          password: ${{ secrets.PYPI_API_TOKEN }}
+          packages-dir: dist
+          skip-existing: true
+
+  publish-docker:
+    name: Build And Push Docker Image
+    runs-on: ubuntu-latest
+    needs:
+      - validate-and-build
+      - publish-pypi
+    steps:
+      - name: Checkout
+        uses: actions/checkout@v4
+
+      - name: Set Up Docker Buildx
+        uses: docker/setup-buildx-action@v3
+
+      - name: Log In To Docker Hub
+        uses: docker/login-action@v3
+        with:
+          registry: docker.io
+          username: ${{ secrets.DOCKERHUB_USERNAME }}
+          password: ${{ secrets.DOCKERHUB_TOKEN }}
+
+      - name: Build And Push Docker Image
+        uses: docker/build-push-action@v6
+        with:
+          context: .
+          file: ./Dockerfile
+          push: true
+          tags: docker.io/bbglab/oncodrive3d:${{ needs.validate-and-build.outputs.version }}

{oncodrive3d-1.0.7 → oncodrive3d-1.0.8}/Dockerfile

@@ -1,4 +1,5 @@
-FROM ghcr.io/astral-sh/uv:0.5-python3.10-bookworm AS build-stage
+# syntax=docker/dockerfile:1.7
+FROM ghcr.io/astral-sh/uv:0.9-python3.10-bookworm AS build-stage
 
 # Set environment variables
 ENV UV_COMPILE_BYTECODE=1 \
@@ -14,8 +15,8 @@ COPY scripts scripts
 COPY README.md README.md
 
 # Install dependencies and build the project
-RUN mkdir -p /root/.cache/uv \
-    && uv sync --frozen --no-dev \
+RUN --mount=type=cache,target=/root/.cache/uv \
+    uv sync --frozen --no-dev \
     && uv build
 
 # Second stage: Runtime image
@@ -25,13 +26,8 @@ FROM python:3.10.18-bookworm AS runtime-stage
 ENV BGDATA_LOCAL="/bgdatacache" \
     BBGLAB_HOME="/home/user/.config/bbglab/"
 
-# Copy oncodrive3d from the build stage
-COPY --from=build-stage /oncodrive3d/dist /oncodrive3d/dist
 WORKDIR /oncodrive3d
 
-# Install oncodrive3d
-RUN pip install dist/*.tar.gz
-
 # Create required directories
 RUN install -d -m 0755 "$BGDATA_LOCAL" "$BBGLAB_HOME"
 
@@ -52,16 +48,26 @@ remote_repository = \"https://bbglab.irbbarcelona.org/bgdata\"\n\
 [cache_repositories]" > "$BBGLAB_HOME/bgdatav2.conf"
 
 # Pre-fetch and prepare genome data
-RUN apt-get update && apt-get install -y curl \
-    && pip install bgdata bgreference \
-    && bgdata get datasets/genomereference/hg38 \
-    && bgdata get datasets/genomereference/mm39 \
-    && python3 -c "from bgreference import hg38; hg38(1, 1300000, 3000)" \
-    && python3 -c "from bgreference import mm39; mm39(1, 1300000, 3000)" \
+RUN apt-get update && apt-get install -y --no-install-recommends curl \
     && rm -rf /var/lib/apt/lists/*
 
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install bgdata bgreference
+
+RUN bgdata get datasets/genomereference/hg38
+RUN bgdata get datasets/genomereference/mm39
+
+RUN python3 -c "from bgreference import hg38; hg38(1, 1300000, 3000)"
+RUN python3 -c "from bgreference import mm39; mm39(1, 1300000, 3000)"
+
 # Set permissions for cache directory
 RUN chmod -R 0755 "$BGDATA_LOCAL"
 
+# Copy and install oncodrive3d after data prefetch so package updates do not
+# invalidate the expensive genome-data cache layers.
+COPY --from=build-stage /oncodrive3d/dist /oncodrive3d/dist
+RUN --mount=type=cache,target=/root/.cache/pip \
+    pip install dist/*.tar.gz
+
 # Set entrypoint (optional)
 CMD ["python3"]

{oncodrive3d-1.0.7 → oncodrive3d-1.0.8}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: Oncodrive3D
-Version: 1.0.7
+Version: 1.0.8
 Summary: Oncodrive3D is a method designed to analyse patterns of somatic mutations across tumors to identify three-dimensional (3D) clusters of missense mutations and detect genes that are under positive selection.
 Project-URL: Homepage, https://github.com/bbglab/clustering_3d
 Project-URL: Repository, https://github.com/bbglab/clustering_3d
@@ -45,8 +45,6 @@ The method leverages **AlphaFold 2-predicted protein structures** and Predicted
 
 ![Graphical abstract of Oncodrive3D](docs/images/graphical_abstract.png "Oncodrive3D")
 
----
-
 ## Requirements
 
 Before you begin, ensure **Python 3.10 or later** is installed on your system.  
@@ -55,7 +53,7 @@ Additionally, you may need to install additional development tools. Depending on
 - If you have sudo privileges:
 
    ```bash
-   sudo apt install built-essential
+   sudo apt install build-essential
    ```
 
 - For HPC cluster environment, it is recommended to use [Conda](https://docs.conda.io/projects/conda/en/latest/user-guide/install/index.html) (or [Mamba](https://mamba.readthedocs.io/en/latest/)):
@@ -94,13 +92,22 @@ Additionally, you may need to install additional development tools. Depending on
 
 ## Building Datasets
 
-This step build the datasets necessary for Oncodrive3D to run the 3D clustering analysis. It is required once after installation or whenever you need to generate datasets for a different organism or apply a specific threshold to define amino acid contacts.
+This step builds the datasets necessary for Oncodrive3D to run the 3D clustering analysis. It is required once after installation or whenever you need to generate datasets for a different organism or apply a specific threshold to define amino acid contacts.
 
 > [!WARNING]
 > This step is highly time- and resource-intensive, requiring a significant amount of free disk space and computational power. It will download and process a large amount of data. Ensure sufficient resources are available before proceeding, as insufficient capacity may result in extended runtimes or processing failures.
+>
+> Reliable internet access is required because AlphaFold structures, Ensembl annotations, Pfam files, and other resources are downloaded on demand during the build.
+
+> [!WARNING]
+> Human datasets built with the default settings pull canonical transcript metadata from the January 2024 Ensembl archive (release 111 / GENCODE v45). For maximum compatibility, annotate your input variants with the same Ensembl/Gencode release or supply the unfiltered VEP output together with `--o3d_transcripts --use_input_symbols`.
+
+> [!NOTE]
+> Predicted Aligned Error (PAE) files for older AlphaFold DB versions (e.g., v4) are no longer hosted after 2025. If you need PAE for an older AF version, download and supply them locally via `--custom_pae_dir`.  
+> MANE structures are available only in AlphaFold DB v4, while non-MANE builds default to v6. Since MANE mode forces v4 structures, you should also supply the corresponding PAE files through `--custom_pae_dir`.
 
 > [!NOTE]
-> The first time that you run Oncodrive3D building dataset step with a given reference genome, it will download it from our servers. By default the downloaded datasets go to`~/.bgdata`. If you want to move these datasets to another folder you have to define the system environment variable `BGDATA_LOCAL` with an export command.
+> The first time that you run Oncodrive3D building dataset step with a given reference genome, it will download it from our servers. By default the downloaded datasets go to `~/.bgdata`. If you want to move these datasets to another folder you have to define the system environment variable `BGDATA_LOCAL` with an export command.
 
 ```
 Usage: oncodrive3d build-datasets [OPTIONS]
@@ -115,13 +122,16 @@ Examples:
 Options:
   -o, --output_dir PATH           Path to the directory where the output files will be saved. 
                                   Default: ./datasets/
-  -s, --organism PATH             Specifies the organism (`human` or `mouse`). 
-                                  Default: human
+  -s, --organism TEXT             Specifies the organism (`human` or `mouse`; also accepts `Homo sapiens` / `Mus musculus`). 
+                                  Default: Homo sapiens
   -m, --mane                      Use structures predicted from MANE Select transcripts 
                                   (applicable to Homo sapiens only).
   -M, --mane_only                 Use only structures predicted from MANE Select transcripts
                                   (applicable to Homo sapiens only).
-  -C, --custom_mane_pdb_dir       Path to directory containing custom MANE PDB structures.
+  -C, --custom_mane_pdb_dir PATH  Path to directory containing custom MANE PDB structures (requires --mane_only).
+                                  Default: None
+      --custom_pae_dir PATH       Path to directory containing pre-downloaded PAE JSON files.
+                                  The directory will be copied into the build as `pae/`.
                                   Default: None
   -f, --custom_mane_metadata_path Path to a dataframe (typically a samplesheet.csv) including 
                                   Ensembl IDs and sequences of the custom pdbs.
@@ -130,6 +140,9 @@ Options:
                                   Default: 10
   -c, --cores INT                 Number of CPU cores for computation. 
                                   Default: All available CPU cores
+  --af_version INT                AlphaFold DB version for non-MANE builds (MANE uses v4).
+                                  Default: 6
+  -y, --yes                       Run without interactive prompts.
   -v, --verbose                   Enables verbose output.
   -h, --help                      Show this message and exit.  
 ```
@@ -138,27 +151,31 @@ For more information on the output of this step, please refer to the [Building D
 
 > [!TIP]
 > ### Increasing MANE Structural Coverage
-> To maximize structural coverage of **MANE Select transcripts**, you can predict missing structures locally and integrate them into Oncodrive3D using:
+> To maximize structural coverage of **MANE Select transcripts**, you can [predict missing structures locally and integrate them into Oncodrive3D](tools/preprocessing/README.md) using:
 >
 > - `tools/preprocessing/prepare_samplesheet.py`: a standalone utility that:
->   - Retrieve the full MANE entries from NCBI.
+>   - Retrieves the full MANE entries from NCBI.
 >   - Identifies proteins missing from the AlphaFold MANE dataset.
 >   - Generates:
 >     - A `samplesheet.csv` with Ensembl protein IDs, FASTA paths, and optional sequences.
 >     - Individual FASTA files for each missing protein.
 >
-> - `--custom_mane_pdb_dir`: use this to provide your own predicted PDB structures (e.g., from [nf-core/proteinfold](https://nf-co.re/proteinfold/1.1.1/)).
+> - `tools/preprocessing/update_samplesheet_and_structures.py`: takes the samplesheet folder produced above and:
+>   - Reuses canonical AlphaFold structures when possible to shrink the nf-core input.
+>   - Ingests nf-core/proteinfold predictions and keeps the `missing/` set up to date.
+>   - Generates a `final_bundle/samplesheet.csv` plus `final_bundle/pdbs/`, ready to be passed to `oncodrive3d build-datasets --mane_only` via `--custom_mane_metadata_path` and `--custom_mane_pdb_dir`.
 >
-> - `--custom_mane_metadata_path`: path to the corresponding `samplesheet.csv`, which must include:
->   - `sequence`: Ensembl protein ID (required)
->   - `refseq`: amino acid sequence (used to inject sequence into PDB if missing)
+> - When invoking `oncodrive3d build-datasets`, supply:
+>   - `--custom_mane_pdb_dir`: use this to provide your own predicted PDB structures (e.g., from [nf-core/proteinfold](https://nf-co.re/proteinfold/1.1.1/) or `final_bundle/pdbs/` produced by `update_samplesheet_and_structures.py`).
+>   - `--custom_mane_metadata_path`: path to the corresponding `samplesheet.csv` (e.g., `final_bundle/samplesheet.csv`).
 >
+> See the documentation of [MANE Preprocessing Toolkit](tools/preprocessing/README.md) for the full workflow to expand coverage of the MANE associated structures.
 
 
 
 ## Running 3D clustering Analysis
 
-For in depth information on how to obtain the required input data and for comprehensive information about the output, please refer to the [Input and Output Documentation](https://github.com/bbglab/oncodrive3d/tree/master/docs/run_input_output.md) of the 3D clustering analysis.  
+For in-depth information on how to obtain the required input data and for comprehensive information about the output, please refer to the [Input and Output Documentation](https://github.com/bbglab/oncodrive3d/tree/master/docs/run_input_output.md) of the 3D clustering analysis.  
 
 ### Input
 
@@ -168,21 +185,13 @@ For in depth information on how to obtain the required input data and for compre
 
 - **<mut_profile>** (`optional`): Dictionary including the normalized frequencies of mutations (*values*) in every possible trinucleotide context (*keys*), such as 'ACA>A', 'ACC>A', and so on.
 
----
-
 > [!NOTE] 
 > Examples of the input files are available in the [Test Input Folder](https://github.com/bbglab/oncodrive3d/tree/master/test/input).  
 Please refer to these examples to understand the expected format and structure of the input files.
 
----
-
----
-
 > [!NOTE]
 > Oncodrive3D uses the mutational profile of the cohort to build an accurate background model. However, it’s not strictly required. If the mutational profile is not provided, the tool will use a simple uniform distribution as the background model for simulating mutations and scoring potential 3D clusters.
 
----
-
 ### Main Output
 
 - **Gene-level output**: CSV file (`\<cohort>.3d_clustering_genes.csv`) containing the results of the analysis at the gene level. Each row represents a gene, sorted from the most significant to the least significant based on the 3D clustering analysis. The table also includes genes that were not analyzed, with the reason for exclusion provided in the `status` column.
@@ -208,17 +217,31 @@ Options:
                                    annotated mutations for the cohort. [required]
   -p, --mut_profile_path PATH      Path to the JSON file specifying the cohort's mutational 
                                    profile (192 key-value pairs).
+  -m, --mutability_config_path PATH
+                                   Path to the JSON file with information on mutability, used when
+                                   mutation calls originate from cohorts with highly heterogeneous
+                                   sequencing depth across sites.
   -o, --output_dir PATH            Path to the output directory for results. 
                                    Default: ./output/
   -d, --data_dir PATH              Path to the directory containing the datasets built in the 
                                    building datasets step. 
                                    Default: ./datasets/
+  -n, --n_iterations INT           Number of densities to be simulated.
+                                   Default: 10000
+  -a, --alpha FLOAT                Significance threshold for residue and gene p-values.
+                                   Default: 0.01
   -c, --cores INT                  Number of CPU cores to use. 
                                    Default: All available CPU cores
   -s, --seed INT                   Random seed for reproducibility.
   -v, --verbose                    Enables verbose output.
   -t, --cancer_type STR            Cancer type to include as metadata in the output file.
   -C, --cohort STR                 Cohort name for metadata and output file naming. 
+  --no_fragments                   Disable processing of fragmented (AF-F) proteins.
+  --only_processed                 Include only processed genes in the output.
+  --thr_mapping_issue FLOAT        Threshold for the ratio of mutations with mapping issues 
+                                   (out of structure, WT mismatch, zero mutability). A value 
+                                   of 1 disables filtering mismatching mutations.
+                                   Default: 0.1
   -P, --cmap_prob_thr FLOAT        Threshold for defining residues contacts based on distance 
                                    on predicted structure and predicted aligned error (PAE). 
                                    Default: 0.5
@@ -231,13 +254,14 @@ Options:
   -h, --help                       Show this message and exit.  
 ```
 
+> [!TIP]
+> To maximize the number of matching transcripts between the input mutations and the AlphaFold predicted structures used by Oncodrive3D, it is recommended to use the unfiltered output of VEP (including all possible transcripts) as input, along with the flags `--o3d_transcripts` `--use_input_symbols` in the `oncodrive3d run` command.
 
----
+### Handling Heterogeneous Sequencing Depth
 
-> [!NOTE]
-> To maximize the number of matching transcripts between the input mutations and the AlphaFold predicted structures used by Oncodrive3D, it is recommended to use the unfiltered output of VEP (including all possible transcripts) as input, along with the flags `--o3d_transcripts` `--use_input_symbols` in the `oncodrive3d run` command.
+Oncodrive3D can ingest **site-specific mutability tables** when a single mutational profile is not representative of the cohort (e.g., mutation calling performed on highly heterogeneous-depth datasets such as ultra depth **Duplex sequencing** panels commonly used in normal tissue analysis). Provide an indexed TSV describing per-site mutability together with a JSON config via `--mutability_config_path`. The run automatically switches from trinucleotide rates to per-position probabilities and tracks additional diagnostics (`Mut_zero_mut_prob`, `Pos_zero_mut_prob`, status `Mut_with_zero_prob/No_mutability`).  
 
----
+Please see the [Mutability-aware runs guide](docs/mutability.md) for the expected file formats, config schema, and troubleshooting tips.
 
 ### Running With Singularity
 
@@ -247,7 +271,6 @@ singularity exec oncodrive3d.sif oncodrive3d run -i <input_maf> -p <mut_profile>
                                                  -d <build_folder> -C <cohort_name>
 ```
 
-
 ### Testing
 
 To verify that Oncodrive3D is installed and configured correctly, you can perform a test run using the provided test input files: 
@@ -261,6 +284,11 @@ oncodrive3d run -d <build_folder> \
 
 Check the output in the `test/output/` directory to ensure the analysis completes successfully.
 
+## Building Annotations & Plotting
+
+Oncodrive3D ships with an optional plotting pipeline: run `oncodrive3d build-annotations` once to cache structural/functional tracks, then use `oncodrive3d plot` and/or `chimerax-plot` to generate plots and tables that help interpret the clustering signal and distinguish real biology from artifacts.  
+
+Please refer to [Annotation & plotting workflow](docs/annotations_plotting.md) for prerequisites, command examples, and output descriptions.
 
 ## Parallel Processing on Multiple Cohorts
 
@@ -270,9 +298,7 @@ For more information, refer to the [Oncodrive3D Pipeline](https://github.com/bbg
 
 ### Usage
 
----
-
-> [!WARNING]
+> [!NOTE]
 > When using the Nextflow script, ensure that your input files are organized in the following directory structure (you only need either the `maf/` or `vep/` directory):
 > 
 > ```plaintext
@@ -289,8 +315,6 @@ For more information, refer to the [Oncodrive3D Pipeline](https://github.com/bbg
 > - `vep/`: Contains VEP annotation files with the `.vep.tsv.gz` extension, which include annotated mutations with all possible transcripts.
 > - `mut_profile/`: Contains mutational profile files with the `.sig.json` extension.
 
----
-
 ```
 Usage: nextflow run main.nf [OPTIONS]
 
@@ -318,10 +342,10 @@ Options:
   --vep_input BOOL                Use `vep/` subdir as input and select transcripts matching 
                                   the Ensembl transcript IDs in Oncodrive3D built datasets. 
                                   Default: false
-  --mane BOOL                     Prioritize structures corresponding to MANE transcrips if 
+  --mane BOOL                     Prioritize structures corresponding to MANE transcripts if 
                                   multiple structures are associated to the same gene.
                                   Default: false
-  --seed INT:                     Seed value for reproducibility.
+  --seed INT                      Seed value for reproducibility.
                                   Default: 128
 ```