FunVIP 0.5.1__tar.gz → 0.5.3__tar.gz

{funvip-0.5.1 → funvip-0.5.3}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: FunVIP
-Version: 0.5.1
+Version: 0.5.3
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -11,8 +11,9 @@ License-File: LICENSE
 Requires-Dist: biopython==1.84
 Requires-Dist: ete3==3.1.3
 Requires-Dist: Cython
+Requires-Dist: contourpy<1.3
 Requires-Dist: dendropy
-Requires-Dist: GenMine<1.4.0,>=1.3.0
+Requires-Dist: GenMine<1.5.0,>=1.3.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
 Requires-Dist: numpy<2.0.0

{funvip-0.5.1 → funvip-0.5.3}/FunVIP.egg-info/requires.txt

@@ -1,8 +1,9 @@
 biopython==1.84
 ete3==3.1.3
 Cython
+contourpy<1.3
 dendropy
-GenMine<1.4.0,>=1.3.0
+GenMine<1.5.0,>=1.3.0
 lxml
 matplotlib
 numpy<2.0.0

{funvip-0.5.1 → funvip-0.5.3}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: FunVIP
-Version: 0.5.1
+Version: 0.5.3
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -11,8 +11,9 @@ License-File: LICENSE
 Requires-Dist: biopython==1.84
 Requires-Dist: ete3==3.1.3
 Requires-Dist: Cython
+Requires-Dist: contourpy<1.3
 Requires-Dist: dendropy
-Requires-Dist: GenMine<1.4.0,>=1.3.0
+Requires-Dist: GenMine<1.5.0,>=1.3.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
 Requires-Dist: numpy<2.0.0

{funvip-0.5.1 → funvip-0.5.3}/funvip/src/dataset.py

@@ -554,30 +554,41 @@ class FunVIP_var:
                             critical_flag = 1
 
                             # Report one non_overlapping pair
+                            # generate list of sequence pair for easy break
+                            list_candidates = []
                             for i in range(len(seq_list) - 1):
-                                seq1 = seq_list[i]
-                                seq1_hash = seq1.id
-                                seq1_str = str(seq.seq)
-
                                 for j in range(i + 1, len(seq_list)):
-                                    seq2 = seq_list[j]
-                                    seq2_hash = seq2.id
-                                    seq2_str = str(seq.seq)
+                                    list_candidates.append((i, j))
 
-                                    has_overlap = False
+                            for seq_pair in list_candidates:
+                                has_overlap = False
 
-                                    for k in range(len(seq1_str)):
-                                        if seq1_str[k] != "-" and seq2_str[k] != "-":
-                                            has_overlap = True
-                                            break
+                                i = seq_pair[0]
+                                j = seq_pair[1]
 
-                            seq1_id = self.dict_hash_FI[seq1_hash]
-                            seq2_id = self.dict_hash_FI[seq2_hash]
-
-                            logging.critical(
-                                f"At least one pair of sequence does not overlap, such as {seq1_id} and {seq2_id}"
-                            )
-                            critical_flag = 1
+                                seq1 = seq_list[i]
+                                seq1_hash = seq1.id
+                                seq1_str = str(seq1.seq)
+
+                                seq2 = seq_list[j]
+                                seq2_hash = seq2.id
+                                seq2_str = str(seq2.seq)
+
+                                for k in range(len(seq1_str)):
+                                    if seq1_str[k] != "-" and seq2_str[k] != "-":
+                                        has_overlap = True
+                                        break
+
+                                # If no overlap, report
+                                if has_overlap is False:
+                                    seq1_id = self.dict_hash_FI[seq1_hash]
+                                    seq2_id = self.dict_hash_FI[seq2_hash]
+
+                                    logging.critical(
+                                        f"At least one pair of sequence does not overlap, such as {seq1_id} and {seq2_id}"
+                                    )
+                                    critical_flag = 1
+                                    break
 
                             fail_list.append((group, gene))
                             # for tree, use hash dict with genus and species information

{funvip-0.5.1 → funvip-0.5.3}/funvip/src/search.py

@@ -237,6 +237,7 @@ def search(query_fasta, db_fasta, path, opt) -> pd.DataFrame():
         f"{path.tmp}/{opt.runname}.m8",
         sep="\t",
         header=None,
+        quoting=1,
         names=[
             "qseqid",
             "sseqid",

{funvip-0.5.1 → funvip-0.5.3}/funvip/src/validate_input.py

@@ -111,8 +111,13 @@ class Funinfo:
 
         # Genus with space causes error while mafft
         # Genus with slash causes error while tree construction
-        genus = genus.strip().replace(" ", "_").replace("/", "_")
-        genus = manage_unicode(genus, column="Genus")
+        # 0.5.3 update : manage_unicode should run first to manage terminal spaces
+        genus = (
+            manage_unicode(genus, column="Genus")
+            .strip()
+            .replace(" ", "_")
+            .replace("/", "_")
+        )
 
         # Check ambiguity
         if self.genus != "" and self.genus != genus:
@@ -137,8 +142,8 @@ class Funinfo:
         # Genus with slash causes error while tree construction
 
         # species = species.strip().replace(" ", "_").replace("/", "_")
-        species = species.strip().replace("/", "_")
-        species = manage_unicode(species, column="Species")
+        # 0.5.3 update : manage_unicode should run first to manage terminal spaces
+        species = manage_unicode(species, column="Species").strip().replace("/", "_")
 
         # Check ambiguity
         if self.ori_species != "" and self.ori_species != species:
@@ -160,8 +165,8 @@ class Funinfo:
             group = ""
 
         # Group with space causes error while mafft
-        group = group.strip().replace(" ", "_")
-        group = manage_unicode(group, column="Group")
+        # 0.5.3 update : manage_unicode should run first to manage terminal spaces
+        group = manage_unicode(group, column="Group").strip().replace(" ", "_")
 
         # Check ambiguity
         if self.group != "" and self.group != group:
@@ -456,15 +461,35 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
             if table.endswith(extension):
                 try:
                     if dict_extension[extension] == "csv":
-                        df = pd.read_csv(
-                            table, sep=",", encoding="UTF-8", keep_default_na=False
-                        )
-                        flag_read_table = 1
+                        encodings = ["UTF-8", "latin-1", "cp1252"]
+                        for enc in encodings:
+                            try:
+                                df = pd.read_csv(
+                                    table,
+                                    sep=",",
+                                    encoding=enc,
+                                    keep_default_na=False,
+                                    quoting=1,
+                                )
+                                flag_read_table = 1
+                                break
+                            except UnicodeDecodeError:
+                                continue
                     elif dict_extension[extension] == "tsv":
-                        df = pd.read_csv(
-                            table, sep="\t", encoding="UTF-8", keep_default_na=False
-                        )
-                        flag_read_table = 1
+                        encodings = ["UTF-8", "latin-1", "cp1252"]
+                        for enc in encodings:
+                            try:
+                                df = pd.read_csv(
+                                    table,
+                                    sep="\t",
+                                    encoding=enc,
+                                    keep_default_na=False,
+                                    quoting=1,
+                                )
+                                flag_read_table = 1
+                                break
+                            except UnicodeDecodeError:
+                                continue
                     elif dict_extension[extension] == "excel":
                         df = pd.read_excel(table)
                         flag_read_table = 1
@@ -544,7 +569,9 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
         )
 
         # Sequence column operations, download sequences with GenMine
-        if 1:  # If download on/off option added, change this part
+        if (
+            1
+        ):  # If download on/off option added, change this part: for future server side implementation
             download_dict = {}  # for downloaded sequences
             download_set = set()
             # 1 letter + 5 digit regex should be last, because they overlap with 2 letter + 6 digit ids / shotgun
@@ -587,7 +614,7 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
                 # Write GenMine input file
                 with open(f"{path.GenMine}/Accessions.txt", "w") as fg:
                     for acc in download_list:
-                        fg.write(f"{acc.strip()}\n")
+                        fg.write(f"{manage_unicode(acc).strip()}\n")
 
                 # Run GenMine
                 accession_path = f"{path.GenMine}/Accessions.txt"
@@ -741,12 +768,14 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
                 seq_error = 0
                 if gene in df.columns:
                     if not (pd.isna(df[gene][n])):
+                        # To prevent somewhat unicode error
+                        seq_to_operate = manage_unicode(df[gene][n]).strip()
                         # skip blank sequences
-                        if df[gene][n].startswith(">"):
+                        if seq_to_operate.startswith(">"):
                             # remove fasta header
-                            seq_string = "".join(df[gene][n].split("\n")[1:])
+                            seq_string = "".join(seq_to_operate.split("\n")[1:])
                         else:
-                            seq_string = df[gene][n]
+                            seq_string = seq_to_operate
 
                         # adjust seq_string
                         seq_string = seq_string.replace("\n", "").replace(" ", "")
@@ -755,7 +784,7 @@ def input_table(funinfo_dict, path, opt, table_list, datatype):
                         seq_error_cnt = 0
                         seq_error_list = []
 
-                        seq_string = manage_unicode(seq_string)
+                        # seq_string = manage_unicode(seq_string)
                         for x in seq_string:  # x is every character of sequence
                             if not x.lower() in "acgtryswkmbdhvn-.":
                                 seq_error_cnt += 1

{funvip-0.5.1 → funvip-0.5.3}/funvip/src/visualize.py

@@ -104,7 +104,13 @@ def visualize(
 
     ## Read result
     if FunVIP_result.endswith(".csv"):
-        df = pd.read_csv(FunVIP_result)
+        encodings = ["UTF-8", "latin-1", "cp1252"]
+        for enc in encodings:
+            try:
+                df = pd.read_csv(FunVIP_result, encoding=enc, quoting=1)
+                break
+            except UnicodeDecodeError:
+                continue
     elif FunVIP_result.endswith(".xlsx"):
         df = pd.read_excel(FunVIP_result)
     else:

{funvip-0.5.1 → funvip-0.5.3}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "FunVIP"
-version = "0.5.1"
+version = "0.5.3"
 description = "Fungal Validation & Identification Pipeline"
 authors = [{name = "Changwan Seo", email = "wan101010@snu.ac.kr"}]
 urls = { "Homepage" = "https://github.com/Changwanseo/FunVIP" }
@@ -10,8 +10,9 @@ dependencies = [
     "biopython==1.84",
     "ete3==3.1.3",
     "Cython",
+    "contourpy<1.3",
     "dendropy",
-    "GenMine>=1.3.0, <1.4.0",
+    "GenMine>=1.3.0, <1.5.0",
     "lxml",
     "matplotlib",
     "numpy<2.0.0",