Merge pull request #40 from Changwanseo/development

0.3.23.5 pull
Changwanseo · Jul 25, 2024 · f905b43 · f905b43
2 parents 227af86 + bc5252f
commit f905b43
Show file tree

Hide file tree

Showing 3 changed files with 44 additions and 1 deletion.
diff --git a/funvip/src/concatenate.py b/funvip/src/concatenate.py
@@ -155,7 +155,30 @@ def concatenate_df(V, path, opt):
         # Leave non-empty dataframes
         if isinstance(V.dict_gene_SR[gene], pd.DataFrame):
             gene_list.append(gene)
+
             df = deepcopy(V.dict_gene_SR[gene].set_index(["qseqid", "sseqid"]))
+
+            """
+            df = deepcopy(
+                V.dict_gene_SR[gene]
+                .set_index(["qseqid", "sseqid"])
+                .drop(
+                    columns=[
+                        "pident",
+                        "length",
+                        "mismatch",
+                        "gaps",
+                        "qstart",
+                        "qend",
+                        "sstart",
+                        "send",
+                        "evalue",
+                        "bitscore",
+                        "subject_group",
+                    ]
+                )
+            )
+            """
             df_list.append(df)
 
     if len(df_list) <= 0:
@@ -179,6 +202,7 @@ def concatenate_df(V, path, opt):
         df_multigene_regression_ori = pd.concat(df_list, axis=1)
 
         # Drop unnecessary columns for processing
+
         df_multigene_regression_ori.drop(
             columns=[
                 "pident",

diff --git a/funvip/src/search.py b/funvip/src/search.py
@@ -88,6 +88,7 @@ def calculate_pident(df):
     # mismatch, gaps, and bitscore were calculated as sum of fragments
     # evalues were calculated by multiplying them, because they are probability
 
+    """
     df = df.groupby(["qseqid", "sseqid"], dropna=True, as_index=False).aggregate(
         {
             "qseqid": lambda x: set(x),
@@ -104,6 +105,24 @@ def calculate_pident(df):
             "bitscore": np.sum,
         }
     )
+    """
+    # This part should be tested, especially in previous versions
+    df = df.groupby(["qseqid", "sseqid"], dropna=True, as_index=False).aggregate(
+        {
+            "qseqid": lambda x: set(x),
+            "sseqid": lambda x: set(x),
+            "pident": lambda x: tuple(x),
+            "length": lambda x: tuple(x),
+            "mismatch": "sum",
+            "gaps": "sum",
+            "qstart": lambda x: tuple(x),
+            "qend": lambda x: tuple(x),
+            "sstart": lambda x: tuple(x),
+            "send": lambda x: tuple(x),
+            "evalue": "prod",
+            "bitscore": "sum",
+        }
+    )
 
     # Calculate pident
     df["pident"] = df.apply(calculate_pident, axis=1)

diff --git a/pyproject.toml b/pyproject.toml
@@ -1,6 +1,6 @@
 [project]
 name = "FunVIP"
-version = "0.3.23.4"
+version = "0.3.23.5"
 description = "Fungal Validation & Identification Pipeline"
 authors = [{name = "Changwan Seo", email = "[email protected]"}]
 urls = { "Homepage" = "https://github.com/Changwanseo/FunVIP" }