FunVIP 0.3.21__tar.gz → 0.3.22.1__tar.gz

{funvip-0.3.21 → funvip-0.3.22.1}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.21
+Version: 0.3.22.1
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -11,7 +11,7 @@ Requires-Dist: biopython==1.78
 Requires-Dist: ete3==3.1.3
 Requires-Dist: Cython
 Requires-Dist: dendropy
-Requires-Dist: GenMine>=1.0.13
+Requires-Dist: GenMine<1.2.0,>=1.1.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
 Requires-Dist: numpy

{funvip-0.3.21 → funvip-0.3.22.1}/FunVIP.egg-info/SOURCES.txt

@@ -1,4 +1,5 @@
 LICENSE
+MANIFEST.in
 README.md
 pyproject.toml
 FunVIP.egg-info/PKG-INFO
@@ -151,8 +152,10 @@ funvip/external/trimal.v1.4/trimAl/source/utils.cpp
 funvip/external/trimal.v1.4/trimAl/source/utils.h
 funvip/external/trimal.v1.4/trimAl/source/utils.o
 funvip/external/trimal.v1.4/trimAl/source/values.h
+funvip/preset/.gitignore
 funvip/preset/accurate.yaml
 funvip/preset/fast.yaml
+funvip/src/.gitignore
 funvip/src/__init__.py
 funvip/src/align.py
 funvip/src/cluster.py
@@ -167,7 +170,6 @@ funvip/src/logics.py
 funvip/src/modeltest.py
 funvip/src/ncbi.py
 funvip/src/opt_generator.py
-funvip/src/patch.py
 funvip/src/reporter.py
 funvip/src/save.py
 funvip/src/search.py
@@ -180,6 +182,32 @@ funvip/src/validate_input.py
 funvip/src/validate_option.py
 funvip/src/validation.py
 funvip/src/version.py
+funvip/src/__pycache__/CATV_pipe.cpython-310.pyc
+funvip/src/__pycache__/CAT_V.cpython-310.pyc
+funvip/src/__pycache__/CAT_V.cpython-39.pyc
+funvip/src/__pycache__/CAT_V_pipe.cpython-39.pyc
+funvip/src/__pycache__/__init__.cpython-310.pyc
+funvip/src/__pycache__/__init__.cpython-39.pyc
+funvip/src/__pycache__/align.cpython-310.pyc
+funvip/src/__pycache__/cluster.cpython-39.pyc
+funvip/src/__pycache__/dataset.cpython-39.pyc
+funvip/src/__pycache__/ext.cpython-310.pyc
+funvip/src/__pycache__/ext.cpython-39.pyc
+funvip/src/__pycache__/hasher.cpython-39.pyc
+funvip/src/__pycache__/initialize.cpython-39.pyc
+funvip/src/__pycache__/io.cpython-310.pyc
+funvip/src/__pycache__/io.cpython-39.pyc
+funvip/src/__pycache__/logger.cpython-39.pyc
+funvip/src/__pycache__/modeltest.cpython-39.pyc
+funvip/src/__pycache__/multigene.cpython-39.pyc
+funvip/src/__pycache__/ncbi.cpython-39.pyc
+funvip/src/__pycache__/opt_generator.cpython-39.pyc
+funvip/src/__pycache__/reporter.cpython-39.pyc
+funvip/src/__pycache__/search.cpython-39.pyc
+funvip/src/__pycache__/tool.cpython-39.pyc
+funvip/src/__pycache__/validation.cpython-39.pyc
+funvip/src/__pycache__/visualize.cpython-39.pyc
+funvip/src/templates/template.html
 funvip/test_dataset/penicillium/Options.config
 funvip/test_dataset/penicillium/preset.yaml
 funvip/test_dataset/penicillium/DB/DB_Penicillium.xlsx

{funvip-0.3.21 → funvip-0.3.22.1}/FunVIP.egg-info/requires.txt

@@ -2,7 +2,7 @@ biopython==1.78
 ete3==3.1.3
 Cython
 dendropy
-GenMine>=1.0.13
+GenMine<1.2.0,>=1.1.0
 lxml
 matplotlib
 numpy

funvip-0.3.22.1/MANIFEST.in

@@ -0,0 +1,5 @@
+recursive-include funvip/data *
+recursive-include funvip/external *
+recursive-include funvip/preset *
+recursive-include funvip/src *
+recursive-include funvip/test_dataset *

{funvip-0.3.21 → funvip-0.3.22.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.21
+Version: 0.3.22.1
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -11,7 +11,7 @@ Requires-Dist: biopython==1.78
 Requires-Dist: ete3==3.1.3
 Requires-Dist: Cython
 Requires-Dist: dendropy
-Requires-Dist: GenMine>=1.0.13
+Requires-Dist: GenMine<1.2.0,>=1.1.0
 Requires-Dist: lxml
 Requires-Dist: matplotlib
 Requires-Dist: numpy

{funvip-0.3.21 → funvip-0.3.22.1}/README.md

@@ -1,10 +1,9 @@
 [![DOI](https://zenodo.org/badge/588465720.svg)](https://zenodo.org/doi/10.5281/zenodo.10714946)
 
-#### This is Beta release. Unstable. We're eagaring bug reports
+#### This is Beta release. Bug reports are welcomed
 
 ## Scheduling
 ### Beta release part 1 (2023 Feburary ~ As paper published, ver 0.3)
-- ~~Will operate normally most of the case~~ We tried our best, but it's still very buggy. Please report bugs for us
 - Will be tested by our lab memebers to fix bugs and advance features
 
 ### Beta release part 2 (As paper published ~ When pipeline gets stabled, ver 0.4)
@@ -13,77 +12,75 @@
 ### Stable release (ver 1.0)
 
 
-
-
 # FunVIP
 "Fun"gal "V"alidation & "I"dentification "P"ipeline
 
-A automatic tree-based sequence identification pipeline for fungal species
+An automatic tree-based sequence identification and validation pipeline for fungal species
 
 - Automatic tree-based identification
 - Works with multigene
 - Data validation algorithm implemented
 
 
-# See [tutorial](https://github.com/Changwanseo/FunID/blob/main/tutorial/tutorial.md) for detailed usage
+# See [tutorial](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/tutorial.md) for detailed usage
 
 
 ## Requirements
-- Conda environment (See https://www.anaconda.com/products/individual to install)
+- 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)
 
 <!--
 ## Installation with conda (May not work with Linux or Mac)
-1. ```conda create -n FunID python=3.10```
-2. ```conda activate FunID```
-3. ```conda install -c cwseo FunID```
-4. run ```FunID --test Penicillium ``` to check installation
+1. ```conda create -n FunVO{ python=3.10```
+2. ```conda activate FunVIP```
+3. ```conda install -c cwseo FunVIP```
+4. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 If this one fails, use next one
 -->
 
 ## Windows
-1. Install visual c++ [here](https://visualstudio.microsoft.com/ko/visual-cpp-build-tools/)
-2. ```conda create -n FunID python=3.9```
-3. ```conda activate FunID```
-4. ```pip install FunID```
-5. run ```FunID --test Penicillium ``` to check installation
+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```
+4. ```pip install FunVIP```
+5. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 
 * For upgrade use this command
-``` pip install FunID --upgrade ```
+``` pip install FunVIP --upgrade ```
 
 ## Linux
-1. ```conda create -n FunID python=3.9```
-2. ```conda activate FunID```
-3. ```pip install FunID```
+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 ```FunID --test Penicillium ``` to check installation
+5. 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
-1. ```CONDA_SUBDIR=osx-64 conda create -n FunID python=3.10```
-2. ```conda activate FunID```
+1. ```CONDA_SUBDIR=osx-64 conda create -n FunVIP python>=3.8```
+2. ```conda activate FunVIP```
 3. ```conda config --env --set subdir osx-64```
 4. ```conda install pyqt```
-5. ```pip install FunID```
+5. ```pip install FunVIP```
 6. ```conda install -c bioconda raxml iqtree mmseqs2 "blast>=2.12" mafft trimal gblocks fasttree```
-7. run ```FunID --test Penicillium ``` to check installation
+7. run ```FunVIP --test Terrei --email [your email] ``` to check installation
 
-## Installation from source (For developers)
+## Installation from source (For developers and core users)
 * this is for developmental steps
-1. ```git clone https://github.com/Changwanseo/FunID.git```
-2. Move to ```~/FunID```
-3. ```conda create -n FunID python=3.10```
-4. ```conda activate FunID```
+1. ```git clone https://github.com/Changwanseo/FunVIP.git```
+2. Move to ```~/FunVIP```
+3. ```conda create -n FunVIP python=3.10```
+4. ```conda activate FunVIP```
 5. ```pip install ./```
-6. run ```FunID --test Penicillium ``` to check installation
+6. run ```FunVIP --test Terrei --email [your email]``` to check installation
 
 
 ## Usage
-```FunID --db {Your database file} --query {Your query file} --email {Your email} --gene {Your genes} --preset {fast or accurate}```
+```FunVIP --db {Your database file} --query {Your query file} --email {Your email} --gene {Your genes} --preset {fast or accurate}```
 
 ### Example
-```FunID --db Penicillium.xlsx --query Query.xlsx --email {Your email} --gene ITS BenA RPB2 CaM --preset fast```
+```FunVIP --db Penicillium.xlsx --query Query.xlsx --email {Your email} --gene ITS BenA RPB2 CaM --preset fast```
 
 
 \* See documentation for detailed usage
@@ -101,12 +98,12 @@ If this one fails, use next one
 
 
 ## How to make database?
-  ![Fig 2 FunID interface, usage, and input example](https://github.com/Changwanseo/FunID/assets/64393882/78e5dd58-a656-4395-bda9-0ee671411e2c)
+![Fig 2 Database and command configuration of FunID (ver2) ](https://github.com/Changwanseo/FunVIP/assets/64393882/9ba71eb9-91e9-4c0b-ac60-b9b7be993694)
 
 
 
 
-[See example database here](https://github.com/Changwanseo/FunID/blob/main/funid/test_dataset/penicillium/DB/DB_Penicillium.xlsx)
+[See example database here](https://github.com/Changwanseo/FunVIP/blob/main/funvip/test_dataset/penicillium/DB/DB_Penicillium.xlsx)
 
 
 <!--## 
@@ -132,7 +129,7 @@ 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
 
-## How does FunID work?
+## How does FunVIP work?
 ![figure1 - ver4](https://github.com/Changwanseo/FunID/assets/64393882/6a366d32-6aaf-4d0c-8102-8c7dd5fda4c2)
 
 

{funvip-0.3.21 → funvip-0.3.22.1}/funvip/main.py

@@ -10,7 +10,6 @@ def main():
     from funvip.src import validate_input
     from funvip.src import modeltest
     from funvip.src import concatenate
-    from funvip.src import patch
     from funvip.src import reporter
     from funvip.src import tool
     from funvip.src import save
@@ -84,6 +83,8 @@ def main():
             path = var["path"]
         if "model_dict" in var:
             model_dict = var["model_dict"]
+        if "GenMine_flag" in var:
+            GenMine_flag = var["GenMine_flag"]
 
     # To deal with location changes when rerun
     path_root = f"{os.getcwd()}/{opt.runname}"

{funvip-0.3.21 → funvip-0.3.22.1}/funvip/src/dataset.py

@@ -434,7 +434,6 @@ class FunVIP_var:
     # Validate if any multiple sequence alignment has no overlapping region
     def validate_alignments(self, path, opt):
         fail_list = []
-
         remove_dict = {}
         tree_hash_dict = hasher.encode(self.list_FI, newick=True)
         for group in self.dict_dataset:
@@ -571,10 +570,11 @@ class FunVIP_var:
         for fail in fail_list:
             for FI in self.list_FI:
                 if FI.adjusted_group == fail[0]:
-                    if FI.seq[fail[1]] != "":
-                        FI.issues.add(f"alignfail:{fail[1]}")
+                    if fail[1] in FI.seq:
+                        if FI.seq[fail[1]] != "":
+                            FI.issues.add(f"alignfail:{fail[1]}")
 
-        print(fail_list)
+        # print(fail_list)
 
         logging.debug("Remove dict")
         logging.debug(remove_dict)

{funvip-0.3.21 → funvip-0.3.22.1}/funvip/src/reporter.py

@@ -258,6 +258,7 @@ class Report:
             # For unused FI
             else:
                 self.result["DATATYPE"].append("unused")
+                self.result["GROUP_ASSIGNED"].append("-")
 
                 for gene in set_gene:
                     # Check if data analysis had performed for specific FI, group, gene combination
@@ -272,6 +273,17 @@ class Report:
                 self.result["STATUS"].append("unused")
 
         ## update query only result on report.txt
+
+        logging.debug(f"ID: {len(self.result['ID'])}")
+        logging.debug(f"HASH: {len(self.result['HASH'])}")
+        logging.debug(f"DATATYPE: {len(self.result['DATATYPE'])}")
+        logging.debug(f"ISSUES: {len(self.result['ISSUES'])}")
+        logging.debug(f"GROUP_ORIGINAL: {len(self.result['GROUP_ORIGINAL'])}")
+        logging.debug(f"GROUP_ASSIGNED: {len(self.result['GROUP_ASSIGNED'])}")
+        logging.debug(f"SPECIES_ORIGINAL: {len(self.result['SPECIES_ORIGINAL'])}")
+        logging.debug(f"SPECIES_ASSIGNED: {len(self.result['SPECIES_ASSIGNED'])}")
+        logging.debug(f"STATUS: {len(self.result['STATUS'])}")
+
         self.query_result = pd.DataFrame(self.result)
         # Filter if queryonly is True
         if opt.queryonly is True:

{funvip-0.3.21 → funvip-0.3.22.1}/funvip/src/save.py

@@ -26,7 +26,7 @@ import shelve
 # In future, try selectively save to reduce datasize
 # Session saving function
 def save_session(opt, path, global_var: dict, var: dict) -> None:
-    managed_keys = ("V", "R", "opt", "path", "model_dict")
+    managed_keys = ("V", "R", "opt", "path", "model_dict", "GenMine_flag")
 
     # if opt.save_run is True:
     save = shelve.open(path.save, "n")

funvip-0.3.22.1/funvip/src/templates/template.html

@@ -0,0 +1,17 @@
+<!DOCTYPE html>
+<html lang="en">
+<head>
+    <title>Identification Report</title>
+</head>
+<body>
+    <ul id="navigation">
+    {% for item in navigation %}
+        <li><a href= "{{ item.href }}" > {{ item.caption }} </a></li>
+    {% endfor %}
+    </ul>
+
+    <h1>Identification Result</h1>
+    {{ table | safe }}
+    {# a comment #}
+</body>
+</html>