Merge pull request #49 from sanjaynagi/diffexp-nb-gene-id-by-position…

…-22-08-23

README.md

@@ -30,6 +30,9 @@ Documentation: https://sanjaynagi.github.io/AnoExpress/
 
 <br></br>
 
+[![Custom badge](https://img.shields.io/endpoint?color=white&logo=Google%20Colab&url=https%3A%2F%2Fraw.githubusercontent.com%2Fsanjaynagi%2FAnoExpress%2Fmain%2Fgraphics%2Fbadge-diffexp.json)](https://colab.research.google.com/github/sanjaynagi/AnoExpress/blob/main/workflow/notebooks/differential-expression-meta-analysis.ipynb)  
+
+
 #### Contributing datasets
 
 If you would like to contribute a dataset from a major malaria vector, please raise an [issue](https://github.com/sanjaynagi/AnoExpress/issues) or [email me!](mailto:[email protected]?subject=AnoExpress-datasets) The project has been working from the stage of raw read counts.

anoexpress/anoexpress.py

@@ -92,7 +92,7 @@ def data(data_type, analysis, microarray=False, gene_id=None, sort_by=None, anno
     microarray: bool, optional
       whether to include the IR-Tex microarray data in the requested data. Default is False.
     gene_id: str or list, optional
-      A string (AGAP/AFUN identifier), or list of strings, or path to a file containing a list of gene ids in the first column. 
+      A string (AGAP/AFUN identifier or genomic span in the format 2L:500-10000), or list of strings, or path to a file containing a list of gene ids in the first column. 
       Input file can be .tsv, .txt, or .csv, or .xlsx.
     sort_by: {"median", "mean", "agap", "position", None}, optional
       sort by median/mean of fold changes (descending), or by AGAP, or by position in the genome, or dont sort input gene ids.
@@ -130,7 +130,15 @@ def data(data_type, analysis, microarray=False, gene_id=None, sort_by=None, anno
     # subset to the gene ids of interest including reading file 
     if gene_id is not None:
       if isinstance(gene_id, str):
-        if gene_id.endswith(('.tsv', '.txt')):
+        if gene_id.startswith(('2L', '2R', '3L', '3R', 'X', '2RL', '3RL')):
+          import malariagen_data
+          if analysis == 'fun':
+            assert "Unfortunately the genome feature file in malariagen_data does not contain AFUN identifiers, so we cannot subset by genomic span for An. funestus."
+          else:
+            ag3 = malariagen_data.Ag3()
+          gff = ag3.genome_features(region=gene_id).query("type == 'gene'")
+          gene_id = gff.ID.to_list()
+        elif gene_id.endswith(('.tsv', '.txt')):
             gene_id = pd.read_csv(gene_id, sep="\t", header=None).iloc[:, 0].to_list()
         elif gene_id.endswith('.csv'):
             gene_id = pd.read_csv(gene_id, header=None).iloc[:, 0].to_list()

graphics/badge-diffexp.json

@@ -0,0 +1,6 @@
+{
+  "schemaVersion": 1,
+  "label": "AnoExpress",
+  "message": "Reproduce differential expression meta-analysis in Colab",
+  "logoSvg": "https://upload.wikimedia.org/wikipedia/commons/d/d0/Google_Colaboratory_SVG_Logo.svg"
+}

pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "anoexpress"
-version = "0.1.8"
+version = "0.2.0"
 description = "A package to access insecticide resistance gene expression meta analyse in Anopheles mosquitoes"
 authors = [
     "Sanjay Nagi <[email protected]>",

tests/test_anoexpress.py

@@ -131,7 +131,20 @@ def test_plot_gene_expression_type(plot_type):
         microarray=False, 
         plot_type=plot_type,
         )
-
+
+
+@pytest.mark.parametrize(
+    "gene_id", 
+    ['2L:28,500,500-28,520,000', 'X:8,500,500-8,530,000']
+)
+def test_plot_gene_expression_spans(gene_id):
+
+    xpress.plot_gene_expression(
+        gene_id=gene_id, 
+        analysis="gamb_colu", 
+        microarray=False, 
+        plot_type='strip',
+        )
 
 def test_contig_expression():