FunVIP 0.3.22.2__tar.gz → 0.3.23.1__tar.gz

{funvip-0.3.22.2 → funvip-0.3.23.1}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.22.2
+Version: 0.3.23.1
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -14,7 +14,7 @@ Requires-Dist: dendropy
 Requires-Dist: GenMine<1.2.0,>=1.1.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
-Requires-Dist: numpy
+Requires-Dist: numpy<2.0.0
 Requires-Dist: openpyxl==3.0.9
 Requires-Dist: pandas==1.4.2
 Requires-Dist: plotly==5.9.0

{funvip-0.3.22.2 → funvip-0.3.23.1}/FunVIP.egg-info/requires.txt

@@ -5,7 +5,7 @@ dendropy
 GenMine<1.2.0,>=1.1.0
 lxml
 matplotlib
-numpy
+numpy<2.0.0
 openpyxl==3.0.9
 pandas==1.4.2
 plotly==5.9.0

{funvip-0.3.22.2 → funvip-0.3.23.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.22.2
+Version: 0.3.23.1
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -14,7 +14,7 @@ Requires-Dist: dendropy
 Requires-Dist: GenMine<1.2.0,>=1.1.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
-Requires-Dist: numpy
+Requires-Dist: numpy<2.0.0
 Requires-Dist: openpyxl==3.0.9
 Requires-Dist: pandas==1.4.2
 Requires-Dist: plotly==5.9.0

{funvip-0.3.22.2 → funvip-0.3.23.1}/README.md

@@ -22,11 +22,12 @@ An automatic tree-based sequence identification and validation pipeline for fung
 - Data validation algorithm implemented
 
 
-# See [tutorial](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial.md) for detailed usage
+## See [tutorial](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial.md) for step by step tutorial
+## See [documentation](https://github.com/Changwanseo/FunVIP/blob/main/Documentation.md) for advanced usage
 
 
 ## Requirements
-- Conda environment (See [https://www.anaconda.com/products/individual](https://conda.io/projects/conda/en/latest/user-guide/install/index.html) to how to install conda environment)
+- 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)
 
 <!--
 ## Installation with conda (May not work with Linux or Mac)
@@ -37,7 +38,8 @@ An automatic tree-based sequence identification and validation pipeline for fung
 If this one fails, use next one
 -->
 
-## Windows
+## Installation
+### Windows
 1. Install visual c++ [here](https://visualstudio.microsoft.com/visual-cpp-build-tools/)
 2. ```conda create -n FunVIP python>=3.8```
 3. ```conda activate FunVIP```
@@ -47,17 +49,18 @@ If this one fails, use next one
 * For upgrade use this command
 ``` pip install FunVIP --upgrade ```
 
-## Linux
+### Linux
 1. ```conda create -n FunVIP python>=3.8```
 2. ```conda activate FunVIP```
 3. ```pip install FunVIP```
-4. ```conda install -c bioconda raxml iqtree modeltest-ng mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
-5. run ```FunVIP --test Terrei --email [your email] ``` to check installation
+4. ```conda config --add channels conda-forge```
+5. ```conda install -c bioconda raxml iqtree "modeltest-ng>=0.1.7" mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
+6. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 
 
 * For intel mac system, this method probably work, but we couldn't test it because we don't have any intel mac device. We're looking for feedbacks in intel mac
 
-## Apple Silicon Mac
+### Apple Silicon Mac
 1. ```CONDA_SUBDIR=osx-64 conda create -n FunVIP python>=3.8```
 2. ```conda activate FunVIP```
 3. ```conda config --env --set subdir osx-64```
@@ -66,7 +69,7 @@ If this one fails, use next one
 6. ```conda install -c bioconda raxml iqtree mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
 7. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 
-## Installation from source (For developers and core users)
+### Installation from source (For developers and core users)
 * this is for developmental steps
 1. ```git clone https://github.com/Changwanseo/FunVIP.git```
 2. Move to ```~/FunVIP```

{funvip-0.3.22.2 → funvip-0.3.23.1}/funvip/src/cluster.py

@@ -484,7 +484,8 @@ def pipe_append_outgroup(V, path, opt):
         else:
             V.dict_dataset[group][gene].list_og_FI = outgroup
             # Add ambiguous group to FI
-            V.dict_dataset[group][gene].list_db_FI += ambiguous_group
+            if opt.ambiguous is True:
+                V.dict_dataset[group][gene].list_db_FI += ambiguous_group
             # Add outgroup and db in to dict_hash_FI
 
             # Should find out why this does not work at the end

{funvip-0.3.22.2 → funvip-0.3.23.1}/funvip/src/command.py

@@ -303,6 +303,11 @@ class CommandParser:
             help="outgroupoffset value. Highering this value may select more distant outgroup, default : 20",
             type=int,
         )
+        group_advanced.add_argument(
+            "--noambiguous",
+            action="store_true",
+            help="do not include ambiguous samples for sequence-set. Mostly for metabarcoding analysis",
+        )
 
         # Cache
         group_cache = self.parser.add_argument_group(

{funvip-0.3.22.2 → funvip-0.3.23.1}/funvip/src/tree_interpretation.py

@@ -672,15 +672,22 @@ class Tree_information:
                 elif children.support > self.opt.collapsebscutoff:
                     return False
             return True
+        # if taxon dict.keys() have 1 species: 1 kinds of species
         elif len(taxon_dict.keys()) == 1:
             # if taxon dict.keys() have only 1 species: group assigned
             for children in clade.children:
+                other_children = list(set(clade.children) - set([children]))[0]
+
                 # check query branch
                 if self.find_majortaxon(children, gene)[1].startswith("sp."):
                     if children.dist > self.opt.collapsedistcutoff:
                         return False
                     elif children.support > self.opt.collapsebscutoff:
                         return False
+                    elif other_children.dist > self.opt.collapsebscutoff:
+                        return False
+                    elif other_children.dist > self.opt.collapsedistcutoff:
+                        return False
             return True
         else:
             # more than 2 species : not monophyletic
@@ -720,8 +727,10 @@ class Tree_information:
                     return "db"
 
             # decides if the clade is monophyletic
+            # Warning there are other is_monophyletic function
             def is_monophyletic(self, clade, gene, taxon):
                 taxon_dict = self.taxon_count(clade, gene)
+                # print(taxon_dict)
                 # if taxon dict.keys() have 0 species: all query
                 # if any of the branch length was too long or bootstrap is to distinctive : False
                 if len(taxon_dict.keys()) == 0:
@@ -735,19 +744,26 @@ class Tree_information:
                 # if taxon dict.keys() have only 1 species: group assigned
                 elif len(taxon_dict.keys()) == 1:
                     for children in clade.children:
+                        other_children = list(set(clade.children) - set([children]))[0]
+
                         if self.find_majortaxon(children, gene)[1].startswith("sp."):
                             if children.dist > self.opt.collapsedistcutoff:
                                 return False
                             elif children.support > self.opt.collapsebscutoff:
                                 return False
+                            elif other_children.dist > self.opt.collapsebscutoff:
+                                return False
+                            elif other_children.dist > self.opt.collapsedistcutoff:
+                                return False
                     return True
                 else:  # more than 2 species : not monophyletic
                     return False
 
+            ## Start of local_check_monophyletic
             # if clade only has query species or not
             datatype = decide_clade(clade, gene)
 
-            # if only one clade, it is firmly monophyletic
+            # if only one clade, it is confirmly monophyletic
             if len(clade.children) == 1:
                 return datatype, True
 
@@ -759,6 +775,8 @@ class Tree_information:
             else:
                 return datatype, False
 
+            ## End of local_check_monophyletic
+
         def local_generate_collapse_information(self, clade, opt=None):
             collapse_info = Collapse_information()
             collapse_info.query_list = self.query_list

{funvip-0.3.22.2 → funvip-0.3.23.1}/funvip/src/validate_option.py

@@ -85,6 +85,7 @@ class Option:
         self.solveflat = True
         self.regex = None
         self.avx = True
+        self.ambiguous = True
         self.cachedb = True
         self.usecache = True
         self.tableformat = "csv"
@@ -165,6 +166,8 @@ class Option:
                 self.regex = parser_dict[key]
             elif key.lower() in ("avx"):
                 self.avx = parser_dict[key]
+            elif key.lower() in ("ambiguous"):
+                self.ambiguous = parser_dict[key]
             elif key.lower() in ("allow-innertrimming"):
                 self.allow_innertrimming = parser_dict[key]
             elif key.lower() in ("criterion"):
@@ -522,6 +525,12 @@ class Option:
         except:
             pass
 
+        try:
+            if parser.noambiguous is True:
+                self.ambiguous = False
+        except:
+            pass
+
         try:
             if not parser.criterion is None:
                 self.criterion = parser.criterion
@@ -1398,6 +1407,10 @@ class Option:
             list_warning.append(f"AVX is not available. Changing --noavx to True")
             self.avx = False
 
+        # noambiguous
+        # default : False
+        # if used, set True
+
         # criterion
         # default : BIC
         # Should be one of AIC, AICc, BIC

{funvip-0.3.22.2 → funvip-0.3.23.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "FunVIP"
-version = "0.3.22.2"
+version = "0.3.23.1"
 description = "Fungal Validation & Identification Pipeline"
 authors = [{name = "Changwan Seo", email = "wan101010@snu.ac.kr"}]
 urls = { "Homepage" = "https://github.com/Changwanseo/FunVIP" }
@@ -14,7 +14,7 @@ dependencies = [
     "GenMine>=1.1.0, <1.2.0",
     "lxml",
     "matplotlib",
-    "numpy",
+    "numpy<2.0.0",
     "openpyxl==3.0.9",
     "pandas==1.4.2",
     "plotly==5.9.0",