update workflows

.github/workflows/publish-pypi.yml

@@ -0,0 +1,52 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags: "*"
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    permissions:
+      id-token: write
+      repository-projects: write
+      contents: write
+      pages: write
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python 3.12
+        uses: actions/setup-python@v5
+        with:
+          python-version: 3.12
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox
+
+      - name: Test with tox
+        run: |
+          tox
+
+      - name: Build Project and Publish
+        run: |
+          python -m tox -e clean,build
+
+      # This uses the trusted publisher workflow so no token is required.
+      - name: Publish to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+
+      - name: Build docs
+        run: |
+          tox -e docs
+
+      - run: touch ./docs/_build/html/.nojekyll
+
+      - name: GH Pages Deployment
+        uses: JamesIves/github-pages-deploy-action@v4
+        with:
+          branch: gh-pages # The branch the action should deploy to.
+          folder: ./docs/_build/html
+          clean: true # Automatically remove deleted files from the deploy branch

.github/workflows/run-tests.yml

@@ -0,0 +1,73 @@
+name: Test the library
+
+on:
+  push:
+    branches:
+      - master # for legacy repos
+      - main
+  pull_request:
+    branches:
+      - master # for legacy repos
+      - main
+  workflow_dispatch: # Allow manually triggering the workflow
+  schedule:
+    # Run roughly every 15 days at 00:00 UTC
+    # (useful to check if updates on dependencies break the package)
+    - cron: "0 0 1,16 * *"
+
+permissions:
+  contents: read
+
+concurrency:
+  group: >-
+    ${{ github.workflow }}-${{ github.ref_type }}-
+    ${{ github.event.pull_request.number || github.sha }}
+  cancel-in-progress: true
+
+jobs:
+  test:
+    strategy:
+      matrix:
+        python: ["3.10", "3.11", "3.12", "3.13", "3.14"]
+        platform:
+          - ubuntu-latest
+          # - macos-latest
+          # - windows-latest
+    runs-on: ${{ matrix.platform }}
+    name: Python ${{ matrix.python }}, ${{ matrix.platform }}
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        id: setup-python
+        with:
+          python-version: ${{ matrix.python }}
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install tox coverage
+
+      - name: Run tests
+        run: >-
+          pipx run --python '${{ steps.setup-python.outputs.python-path }}'
+          tox
+          -- -rFEx --durations 10 --color yes --cov --cov-branch --cov-report=xml  # pytest args
+
+      - name: Check for codecov token availability
+        id: codecov-check
+        shell: bash
+        run: |
+          if [ ${{ secrets.CODECOV_TOKEN }} != '' ]; then
+            echo "codecov=true" >> $GITHUB_OUTPUT;
+          else
+            echo "codecov=false" >> $GITHUB_OUTPUT;
+          fi
+
+      - name: Upload coverage reports to Codecov with GitHub Action
+        uses: codecov/codecov-action@v5
+        if: ${{ steps.codecov-check.outputs.codecov == 'true' }}
+        env:
+          CODECOV_TOKEN: ${{ secrets.CODECOV_TOKEN }}
+          slug: ${{ github.repository }}
+          flags: ${{ matrix.platform }} - py${{ matrix.python }}

README.md

@@ -37,10 +37,18 @@ results = client.search_experiments(
     properties=["cancer", "breast"],
     species="homo sapiens"
 )
-print(results.head())
-#   Accession        Species                Type  ...
-# 0 E-MTAB-1624  homo sapiens  microarray data  ...
+print(results)
 ```
+    BiocFrame with 208 rows and 4 columns
+            Accession      Species                    Type                   Title
+                <list>       <list>                  <list>                  <list>
+    [0]  E-MTAB-8198 Homo sapiens Cell line - High-thr... Functional effect of...
+    [1]  E-MTAB-8532 Homo sapiens Human - One-color mi... DNA microarray studi...
+    [2] E-GEOD-43306 Homo sapiens   RNA-seq of coding RNA Translating transcri...
+                ...          ...                     ...                     ...
+    [205]   E-MTAB-779 Homo sapiens transcription profil... OncomiRs like let-7 ...
+    [206]  E-TABM-1118 Homo sapiens transcription profil... Transcrption profili...
+    [207]   E-TABM-601 Homo sapiens transcription profil... Transcription profil...
 
 ### Download RNA-seq Data
 
@@ -53,44 +61,35 @@ rnaseq = exp["rnaseq"]
 counts = rnaseq.assay("counts")  # numpy array: genes × samples
 
 print(f"Shape: {counts.shape[0]} genes × {counts.shape[1]} samples")
-# Shape: 58735 genes × 48 samples
+# Shape: 58735 genes × 24 samples
 
 # Sample metadata (BiocFrame)
 sample_info = rnaseq.get_column_data()
 print(sample_info.get_column_names())
+# ['cell line', 'compound', 'developmental stage', 'disease', 'dose', 'genotype', 'organism', 'organism part']
 
 # Gene annotations (BiocFrame)
 gene_info = rnaseq.get_row_data()
 print(gene_info.shape)
-```
-
-### Download Microarray Data
-
-```python
-exp = client.get_experiment("E-MTAB-1624")
-
-# Microarray data is keyed by array design
-array_design = "A-AFFY-126"
-eset = exp[array_design] # This is also a SummarizedExperiment now
+# (58735, 1)
 
-# Expression matrix (probes × samples)
-intensities = eset.assay("exprs")
-print(intensities.shape)
-# (54675, 96)
-
-# Sample metadata (BiocFrame)
-sample_annotations = eset.get_column_data()
-print(sample_annotations.shape)
-
-# Feature annotations (BiocFrame)
-probe_annotations = eset.get_row_data()
+print(rnaseq)
 ```
+    class: SummarizedExperiment
+    dimensions: (58735, 24)
+    assays(1): ['counts']
+    row_data columns(1): ['Gene Name']
+    row_names(58735): ['ENSG00000000003', 'ENSG00000000005', 'ENSG00000000419', ..., 'ENSG00000285992', 'ENSG00000285993', 'ENSG00000285994']
+    column_data columns(8): ['cell line', 'compound', 'developmental stage', 'disease', 'dose', 'genotype', 'organism', 'organism part']
+    column_names(24): ['ERR3456453', 'ERR3456442', 'ERR3456443', ..., 'ERR3456450', 'ERR3456459', 'ERR3456444']
+    metadata(2): accession source
+
 
 ### Batch Downloads
 
 ```python
 # Download multiple experiments
-accessions = results["Accession"].head(10).tolist()
+accessions = results.get_column("Accession")[:10]
 experiments = client.get_experiments(accessions)
 
 # Access individual experiments

setup.cfg

@@ -50,7 +50,6 @@ python_requires = >=3.9
 install_requires =
     importlib-metadata; python_version<"3.8"
     requests
-    pandas
     numpy
     biocframe
     summarizedexperiment

src/expressionatlas/__init__.py

@@ -26,7 +26,6 @@
 finally:
     del version, PackageNotFoundError
 
-
 from expressionatlas.client import ExpressionAtlasClient
 from expressionatlas.download import (
     get_atlas_data,
@@ -41,5 +40,3 @@
     InvalidAccessionError,
 )
 from expressionatlas.models import SearchResult
-from summarizedexperiment import SummarizedExperiment
-from biocutils import NamedList

src/expressionatlas/client.py

@@ -5,12 +5,12 @@
 import logging
 from collections.abc import Sequence
 
-import pandas as pd
+from biocframe import BiocFrame
+from biocutils import NamedList
 
 from expressionatlas.api import BioStudiesAPI
 from expressionatlas.download import get_atlas_data, get_atlas_experiment
-from expressionatlas.models import search_results_to_dataframe
-from biocutils import NamedList
+from expressionatlas.models import search_results_to_biocframe
 from expressionatlas.validation import validate_accession
 
 logger = logging.getLogger(__name__)
@@ -74,7 +74,7 @@ def search_experiments(
         self,
         properties: str | Sequence[str],
         species: str | None = None,
-    ) -> pd.DataFrame:
+    ) -> BiocFrame:
         """
         Search for Expression Atlas experiments matching given criteria.
 
@@ -90,8 +90,8 @@ def search_experiments(
 
         Returns
         -------
-        pandas.DataFrame
-            DataFrame with columns: Accession, Species, Type, Title.
+        BiocFrame
+            BiocFrame with columns: Accession, Species, Type, Title.
             Sorted by Species, Type, then Accession.
 
         Raises
@@ -130,8 +130,8 @@ def search_experiments(
 
         results = self.api.search(properties=list(properties), species=species)
 
-        # Filter out connection errors and convert to DataFrame
-        df = search_results_to_dataframe(results)
+        # Filter out connection errors and convert to BiocFrame
+        df = search_results_to_biocframe(results)
 
         # Log warning if any connection errors occurred
         error_count = sum(1 for r in results if r.connection_error)
@@ -232,16 +232,24 @@ def get_experiments(
         ...     species="homo sapiens",
         ... )
         >>> # Download all RNA-seq experiments from search results
-        >>> rnaseq_accessions = results[
-        ...     results[
-        ...         "Type"
-        ...     ].str.contains(
-        ...         "RNA-seq",
-        ...         na=False,
+        >>> types = results.get_column(
+        ...     "Type"
+        ... )
+        >>> accessions = results.get_column(
+        ...     "Accession"
+        ... )
+        >>> rnaseq_accessions = [
+        ...     acc
+        ...     for acc, typ in zip(
+        ...         accessions,
+        ...         types,
         ...     )
-        ... ]["Accession"]
+        ...     if typ
+        ...     and "RNA-seq"
+        ...     in typ
+        ... ]
         >>> experiments = client.get_experiments(
-        ...     rnaseq_accessions.tolist()
+        ...     rnaseq_accessions
         ... )
         >>> # Access: experiments["E-MTAB-XXXX"]["rnaseq"].assays["counts"]
         """