FunVIP 0.3.25__tar.gz → 0.4.1__tar.gz

{funvip-0.3.25 → funvip-0.4.1}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: FunVIP
-Version: 0.3.25
+Version: 0.4.1
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0

{funvip-0.3.25 → funvip-0.4.1}/FunVIP.egg-info/SOURCES.txt

@@ -100,6 +100,10 @@ funvip/external/mmseqs_Windows/matrices/blosum90.out
 funvip/external/mmseqs_Windows/matrices/blosum95.out
 funvip/external/mmseqs_Windows/matrices/nucleotide.out
 funvip/external/mmseqs_Windows/util/bash-completion.sh
+funvip/external/modeltest-ng_Windows/cyggcc_s-seh-1.dll
+funvip/external/modeltest-ng_Windows/cygstdc++-6.dll
+funvip/external/modeltest-ng_Windows/cygwin1.dll
+funvip/external/modeltest-ng_Windows/modeltest-ng.exe
 funvip/external/trimal.v1.4/trimAl/AUTHORS
 funvip/external/trimal.v1.4/trimAl/CHANGELOG
 funvip/external/trimal.v1.4/trimAl/LICENSE

{funvip-0.3.25 → funvip-0.4.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: FunVIP
-Version: 0.3.25
+Version: 0.4.1
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0

{funvip-0.3.25 → funvip-0.4.1}/README.md

@@ -4,26 +4,30 @@
 #### An automatic tree-based sequence identification and validation pipeline for fungal (or maybe other) species
 
 - Automatic tree-based identification
-- Works with multigene
-- Data validation algorithm implemented
+- Works with multiple genetic marker
+- Database sequence validation algorithm implemented
 
 ![figure1 - ver17A](https://github.com/user-attachments/assets/22a50a62-14e8-41a7-87a0-8f5a1f9c3f62)
 
 This is Beta release. Bug reports are welcomed
 <br><br/>
 
+### IMPORTANT NOTICE: The python dependency for Linux platform has changed from 3.12 to 3.11 for TCS inclusion. Please remake conda environment for FunVIP 0.3.25 update
+
 ## Tutorial
 * [Part 1 - Getting started!](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial.md)
 * [Part 2 - Preparing database and query](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial2.md)
-* [Advacned tips](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/advanced.md)
+* [Advanced tips](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/advanced.md)
 <br><br/>
 ## Documentation
 * See [Documentation](https://github.com/Changwanseo/FunVIP/blob/main/Documentation.md) for advanced usage !
 <br><br/>
 ## Requirements
-- Conda environment
+- Conda or Mamba environment
+
+\* See [here](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) for how to install conda environment
 
-\* See [https://www.anaconda.com/products/individual](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) for how to install conda environment
+\* Recently, Mamba is a lot faster than conda. See [here](https://github.com/conda-forge/miniforge?tab=readme-ov-file) to how to install mamba environment
 <br><br/>
 ## Installation
 * [Windows](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Windows)
@@ -77,9 +81,14 @@ tabular (```.xlsx```, ```.csv```,  ```.parquet```, ```.ftr```) form
 * ```/Tree/{section}_{gene}.svg``` : Final collapsed tree in svg format. Can be edited in vector graphics programs, or in powerpoint (by ungroup)
 * ```/Tree/{section}_{gene}_original.svg ``` : Uncollapsed tree for inspection
 
+* Example output tree of FunVIP
+![image](https://github.com/user-attachments/assets/7291c990-62d0-4579-8ae7-adc5d39a7fed)
+
+
+
 ## Scheduling
-1. Beta release part 1 (2023 Feburary ~ As paper published, ver 0.3)
-Will be tested by our lab memebers to fix bugs and advance features
+1. ~~Beta release part 1 (2023 Feburary ~ As paper published, ver 0.3)
+Will be tested by our lab memebers to fix bugs and advance features~~ FunVIP article is currently accepted. Will be published soon.
 2. Beta release part 2 (As paper published ~ When pipeline gets stabled, ver 0.4)
 Will be tested by peer taxonomists
 3. Stable release (ver 1.0)

{funvip-0.3.25 → funvip-0.4.1}/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-0.4.1}/funvip/src/ext.py

@@ -266,10 +266,15 @@ def Trimal(fasta, out, path, algorithm="gt", threshold=0.2):
 
 
 # Modeltest
-def Modeltest_ng(fasta, out, models, thread):
+def Modeltest_ng(fasta, out, path, models, thread):
+    path_modeltestng = f"{path.sys_path}/external/modeltest-ng_Windows/modeltest-ng.exe"
     if platform == "win32":
+        CMD = f"{path_modeltestng} -i '{fasta}' -o '{out}' -t ml -p {thread} --disable-checkpoint {models}"
+        """
         logging.error("Modeltest-NG is not available in windows. Try IQTREE modeltest")
         raise Exception
+        """
+
     else:
         CMD = f"modeltest-ng -i '{fasta}' -o '{out}' -t ml -p {thread} --disable-checkpoint {models}"
 
@@ -367,8 +372,10 @@ def FastTree(fasta, out, hash_dict, path, model=""):
     if model == "skip":
         model = ""
     if platform == "win32":
+        """
         if " " in model:
-            model = f'"{model}"'
+            model = f"{model}"
+        """
         if " " in fasta:
             fasta = f'"{fasta}"'
         if " " in path.tmp:

{funvip-0.3.25 → funvip-0.4.1}/funvip/src/modeltest.py

@@ -379,6 +379,7 @@ def modeltest(V, path, opt) -> dict:
                 ext.Modeltest_ng(
                     fasta=f"{path.out_alignment}/{opt.runname}_trimmed_{group}_{gene}.fasta",
                     models=models,
+                    path=path,
                     out=f"{path.out_modeltest}/{opt.runname}_{group}_{gene}",
                     thread=opt.thread,
                 )
@@ -455,7 +456,9 @@ def modeltest(V, path, opt) -> dict:
             logging.info(
                 "IQTREE will perform ModelFinder internally in tree construction step, skipping in modeltest step"
             )
-            model_dict[group][gene] = "skip"
+            for group in group_dict:
+                for gene in group_dict[group]:
+                    model_dict[group][gene] = "skip"
 
     else:  # including opt.model_method.lower() == "none":
         for group in group_dict:

{funvip-0.3.25 → funvip-0.4.1}/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-0.4.1}/funvip/src/validate_option.py

@@ -859,6 +859,7 @@ class Option:
             "series",
             "subsection",
             "section",
+            "subgenus",
             "genus",
             "subtribe",
             "tribe",
@@ -1041,10 +1042,13 @@ class Option:
             self.method.modeltest = modeltest_adjust[self.method.modeltest.lower()]
             if not (self.method.modeltest in modeltest):
                 list_error.append(f"modeltest method should be one of {str(modeltest)}")
+
+            """
             if self.method.modeltest == "modeltest-ng" and sys.platform == "win32":
                 list_error.append(
                     f"Modeltest-ng is currently not available in windows platform. Please select other modeltest methods or use linux platform"
                 )
+            """
 
         # tree
         # Check if search method is one of default, fasttree, raxml, iqtree

{funvip-0.3.25 → funvip-0.4.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "FunVIP"
-version = "0.3.25"
+version = "0.4.1"
 description = "Fungal Validation & Identification Pipeline"
 authors = [{name = "Changwan Seo", email = "wan101010@snu.ac.kr"}]
 urls = { "Homepage" = "https://github.com/Changwanseo/FunVIP" }