FunVIP 0.3.25__tar.gz → 0.4.0__tar.gz

{funvip-0.3.25 → funvip-0.4.0}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: FunVIP
-Version: 0.3.25
+Version: 0.4.0
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0

{funvip-0.3.25 → funvip-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: FunVIP
-Version: 0.3.25
+Version: 0.4.0
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0

{funvip-0.3.25 → funvip-0.4.0}/funvip/src/cluster.py

@@ -516,11 +516,29 @@ def pipe_append_outgroup(V, path, opt):
 
         # Add outgroup and ambiguous groups to dataset
         # Ambiguous groups are strains locating between outgroup and ingroups, so cannot be decided
+
+        print(f"{group} {gene}")
+        print(f"outgroup {len(outgroup)}")
+        print(f"ambiguous_group {len(ambiguous_group)}")
+        print(f"db: {len(V.dict_dataset[group][gene].list_db_FI)}")
+        print(f"query: {len(V.dict_dataset[group][gene].list_qr_FI)}")
+
         if len(outgroup) == 0 and len(ambiguous_group) == 0:
             logging.warning(
                 f"Removing {group} {gene} from analysis because outgroup cannot be selected"
             )
             V.dict_dataset[group].pop(gene, None)
+        elif (
+            len(outgroup)
+            + len(ambiguous_group)
+            + len(V.dict_dataset[group][gene].list_db_FI)
+            + len(V.dict_dataset[group][gene].list_qr_FI)
+            < 4
+        ):
+            logging.warning(
+                f"Removing {group} {gene} from analysis because not enough sequences are provided to infer phylogenetic tree"
+            )
+            V.dict_dataset[group].pop(gene, None)
 
         else:
             V.dict_dataset[group][gene].list_og_FI = outgroup

{funvip-0.3.25 → funvip-0.4.0}/funvip/src/validate_input.py

@@ -7,6 +7,7 @@ import json
 import pandas as pd
 import numpy as np
 import logging
+import random
 
 from copy import deepcopy
 
@@ -26,6 +27,8 @@ from funvip.src import save
 from funvip.src.logics import isnewicklegal, isuniquecolumn, isvalidcolor
 from funvip.src.hasher import decode, newick_legal, hash_funinfo_list
 
+# funinfo_dict: {"ID" : FI}
+
 
 ## newick illegal characters
 # fmt: off
@@ -577,9 +580,13 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
                     f"Running GenMine to download {len(download_set)} sequences from GenBank"
                 )
 
+                # Shuffle accession to download to prevent bans
+                download_list = list(download_set)
+                random.shuffle(download_list)
+
                 # Write GenMine input file
                 with open(f"{path.GenMine}/Accessions.txt", "w") as fg:
-                    for acc in download_set:
+                    for acc in download_list:
                         fg.write(f"{acc.strip()}\n")
 
                 # Run GenMine
@@ -733,7 +740,7 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
             for gene in opt.gene:
                 seq_error = 0
                 if gene in df.columns:
-                    if not (pd.isna(df[gene][n])) or str(df[gene][n]).strip() == "":
+                    if not (pd.isna(df[gene][n])):
                         # skip blank sequences
                         if df[gene][n].startswith(">"):
                             # remove fasta header
@@ -763,12 +770,22 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
                                 f"In table {table}, Sequence {df['id'][n]} {seq_string} detected as nan, removing it"
                             )
                         elif seq_error_cnt == 0:
-                            # remove gaps for preventing BLAST error
-                            errors.append(
-                                newinfo.update_seq(
-                                    gene, seq_string.replace("-", "").replace(".", "")
+                            # Decide rather to update or not here
+                            if (
+                                len(
+                                    seq_string.replace("-", "").replace(".", "").strip()
+                                )
+                                > 0
+                            ):
+                                # remove gaps for preventing BLAST error
+                                errors.append(
+                                    newinfo.update_seq(
+                                        gene,
+                                        seq_string.replace("-", "")
+                                        .replace(".", "")
+                                        .strip(),
+                                    )
                                 )
-                            )
 
         # After successfully parsed this table, save it
         save.save_df(

{funvip-0.3.25 → funvip-0.4.0}/funvip/src/validate_option.py

@@ -859,6 +859,7 @@ class Option:
             "series",
             "subsection",
             "section",
+            "subgenus",
             "genus",
             "subtribe",
             "tribe",

{funvip-0.3.25 → funvip-0.4.0}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "FunVIP"
-version = "0.3.25"
+version = "0.4.0"
 description = "Fungal Validation & Identification Pipeline"
 authors = [{name = "Changwan Seo", email = "wan101010@snu.ac.kr"}]
 urls = { "Homepage" = "https://github.com/Changwanseo/FunVIP" }