FunVIP 0.4.1__tar.gz → 0.5.1__tar.gz

funvip-0.5.1/FunVIP.egg-info/PKG-INFO

@@ -0,0 +1,159 @@
+Metadata-Version: 2.4
+Name: FunVIP
+Version: 0.5.1
+Summary: Fungal Validation & Identification Pipeline
+Author-email: Changwan Seo <wan101010@snu.ac.kr>
+License: GPL-3.0
+Project-URL: Homepage, https://github.com/Changwanseo/FunVIP
+Requires-Python: <3.13,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython==1.84
+Requires-Dist: ete3==3.1.3
+Requires-Dist: Cython
+Requires-Dist: dendropy
+Requires-Dist: GenMine<1.4.0,>=1.3.0
+Requires-Dist: lxml
+Requires-Dist: matplotlib
+Requires-Dist: numpy<2.0.0
+Requires-Dist: openpyxl==3.1.0
+Requires-Dist: pandas==2.2.2
+Requires-Dist: psutil
+Requires-Dist: pyyaml
+Requires-Dist: sip>=4.19.4
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: tabulate
+Requires-Dist: unidecode==1.2.0
+Requires-Dist: xlrd==2.0.1
+Requires-Dist: xlsxwriter
+Requires-Dist: xmltodict==0.12.0
+Requires-Dist: PyQt5>=5.15.0; sys_platform != "darwin"
+Dynamic: license-file
+
+
+# FunVIP [![DOI](https://zenodo.org/badge/588465720.svg)](https://zenodo.org/doi/10.5281/zenodo.10714946)
+
+
+FunVIP is now published please cite:
+#### Seo CW, Yoo S, Cho Y, Kim JS, Steinegger M, Lim YW. FunVIP: Fungal Validation and Identification Pipeline based on phylogenetic analysis. J. Microbiol. 2025;63(4):e2411017.
+<br><br/>
+
+
+
+
+### **Fun**gal **V**alidation & **I**dentification **P**ipeline
+#### An automatic tree-based sequence identification and validation pipeline for fungal (or maybe other) species
+
+
+
+- Automatic tree-based identification
+- Works with multiple genetic marker
+- Database sequence validation algorithm implemented
+
+![figure1 - ver17A](https://github.com/user-attachments/assets/22a50a62-14e8-41a7-87a0-8f5a1f9c3f62)
+
+Bug reports are always 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)
+* [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 or Mamba environment
+
+\* See [here](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)
+* [Mac - apple silicon](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Apple )
+* [Linux](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Linux)
+* [from source](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Installation)
+<br><br/>
+## Usage
+```FunVIP --db {Your database file} --query {Your query file} --email {Your email} --gene {Your genes} --preset {fast or accurate}```
+<br><br/>
+### Example
+```FunVIP --db Penicillium.xlsx --query Query.xlsx --email {Your email} --thread 8 --gene ITS BenA RPB2 CaM --preset fast```
+
+\* See documentation for detailed usage
+<br><br/>
+
+
+
+
+
+
+## How to make database?
+![figure1 - ver17B](https://github.com/user-attachments/assets/0043e6f6-7470-4c2b-bc96-b51f41c43ee4)
+
+
+
+
+[See example database here](https://github.com/Changwanseo/FunVIP/blob/main/funvip/test_dataset/penicillium/DB/DB_Penicillium.xlsx)
+
+
+<!--## 
+## What query formats can be used?
+#### Query formats can be either 
+fasta (```.fa```, ```.fna```, ```.fas```, ```.fasta```, ```.txt```) or
+tabular (```.xlsx```, ```.csv```,  ```.parquet```, ```.ftr```) form
+
+- fasta form : Do not use ambiguous accessions in your fasta name. For example, accessions "A1234" and "A123" can be confused in pipeline. Section and genus name of the sequences will be automatically assigned according to your database. So if you want to fix it, use tabular form
+- tabular form : your table should include ```ID```, and ```{gene names}``` (highly recommended for multigene analysis)-->
+
+<!--## Tips for method selection
+* SEARCH_METHOD : blast is faster for smaller dataset, while mmseqs are faster in huge dataset, but consumes a lot of memory
+* ALIGNMENT_METHOD : currently mafft is only available.
+* TRIMMING_METHOD : use trimal or gblocks, in your favor. gblocks usally cuts more, but can be differ by advanced option. Use none if you have enough time and resource for calculation
+* MODEL_METHOD : model method is currently not working good enough please wait
+* TREE_METHOD : fasttree is fastest, but least accurate (However, still a lot accurate than NJ tree). It is treated that iqtree is faster but slightly less accurate than raxml, but iqtree requires at least 1000 bootstrap. So in case of speed, raxml could be a little bit faster when low bootstrap selected-->
+
+## Results
+* ```Section Assignment.xlsx``` : Your clustering result is here. You can find which of your sequences are clustered to which section 
+* ```Identification_result.xlsx``` : Your final identification result. Shows how your sequences were assigned to species level through tree-based identification
+* ```report.xlsx``` : overall statistics about the tree. If your find taxon ends with numbers, these taxon are found to be paraphyletic, so should be checked
+* ```/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~~
+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)
+
+## License
+[GPL 3.0](https://github.com/Changwanseo/FunVIP/blob/main/LICENSE)
+
+
+<!--
+## Installation with conda (May not work with Linux or Mac)
+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
+-->
+<!--### GUI mode (\*Currently under development)
+1. Go to ~/FunID-dev
+2. ```streamlit run FunID_GUI.py```
+* GUI run is on experimental
+* If you want to edit GUI options, edit ```Option_manager.xlsx``` and variables in ```FunID_GUI.py```
+### Server mode (\* Currently under development)-->

{funvip-0.4.1 → funvip-0.5.1}/FunVIP.egg-info/requires.txt

@@ -2,7 +2,7 @@ biopython==1.84
 ete3==3.1.3
 Cython
 dendropy
-GenMine<1.2.0,>=1.1.0
+GenMine<1.4.0,>=1.3.0
 lxml
 matplotlib
 numpy<2.0.0

funvip-0.5.1/PKG-INFO

@@ -0,0 +1,159 @@
+Metadata-Version: 2.4
+Name: FunVIP
+Version: 0.5.1
+Summary: Fungal Validation & Identification Pipeline
+Author-email: Changwan Seo <wan101010@snu.ac.kr>
+License: GPL-3.0
+Project-URL: Homepage, https://github.com/Changwanseo/FunVIP
+Requires-Python: <3.13,>=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: biopython==1.84
+Requires-Dist: ete3==3.1.3
+Requires-Dist: Cython
+Requires-Dist: dendropy
+Requires-Dist: GenMine<1.4.0,>=1.3.0
+Requires-Dist: lxml
+Requires-Dist: matplotlib
+Requires-Dist: numpy<2.0.0
+Requires-Dist: openpyxl==3.1.0
+Requires-Dist: pandas==2.2.2
+Requires-Dist: psutil
+Requires-Dist: pyyaml
+Requires-Dist: sip>=4.19.4
+Requires-Dist: scikit-learn
+Requires-Dist: scipy
+Requires-Dist: tabulate
+Requires-Dist: unidecode==1.2.0
+Requires-Dist: xlrd==2.0.1
+Requires-Dist: xlsxwriter
+Requires-Dist: xmltodict==0.12.0
+Requires-Dist: PyQt5>=5.15.0; sys_platform != "darwin"
+Dynamic: license-file
+
+
+# FunVIP [![DOI](https://zenodo.org/badge/588465720.svg)](https://zenodo.org/doi/10.5281/zenodo.10714946)
+
+
+FunVIP is now published please cite:
+#### Seo CW, Yoo S, Cho Y, Kim JS, Steinegger M, Lim YW. FunVIP: Fungal Validation and Identification Pipeline based on phylogenetic analysis. J. Microbiol. 2025;63(4):e2411017.
+<br><br/>
+
+
+
+
+### **Fun**gal **V**alidation & **I**dentification **P**ipeline
+#### An automatic tree-based sequence identification and validation pipeline for fungal (or maybe other) species
+
+
+
+- Automatic tree-based identification
+- Works with multiple genetic marker
+- Database sequence validation algorithm implemented
+
+![figure1 - ver17A](https://github.com/user-attachments/assets/22a50a62-14e8-41a7-87a0-8f5a1f9c3f62)
+
+Bug reports are always 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)
+* [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 or Mamba environment
+
+\* See [here](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)
+* [Mac - apple silicon](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Apple )
+* [Linux](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Linux)
+* [from source](https://github.com/Changwanseo/FunVIP/blob/main/tutorial/installation.md##Installation)
+<br><br/>
+## Usage
+```FunVIP --db {Your database file} --query {Your query file} --email {Your email} --gene {Your genes} --preset {fast or accurate}```
+<br><br/>
+### Example
+```FunVIP --db Penicillium.xlsx --query Query.xlsx --email {Your email} --thread 8 --gene ITS BenA RPB2 CaM --preset fast```
+
+\* See documentation for detailed usage
+<br><br/>
+
+
+
+
+
+
+## How to make database?
+![figure1 - ver17B](https://github.com/user-attachments/assets/0043e6f6-7470-4c2b-bc96-b51f41c43ee4)
+
+
+
+
+[See example database here](https://github.com/Changwanseo/FunVIP/blob/main/funvip/test_dataset/penicillium/DB/DB_Penicillium.xlsx)
+
+
+<!--## 
+## What query formats can be used?
+#### Query formats can be either 
+fasta (```.fa```, ```.fna```, ```.fas```, ```.fasta```, ```.txt```) or
+tabular (```.xlsx```, ```.csv```,  ```.parquet```, ```.ftr```) form
+
+- fasta form : Do not use ambiguous accessions in your fasta name. For example, accessions "A1234" and "A123" can be confused in pipeline. Section and genus name of the sequences will be automatically assigned according to your database. So if you want to fix it, use tabular form
+- tabular form : your table should include ```ID```, and ```{gene names}``` (highly recommended for multigene analysis)-->
+
+<!--## Tips for method selection
+* SEARCH_METHOD : blast is faster for smaller dataset, while mmseqs are faster in huge dataset, but consumes a lot of memory
+* ALIGNMENT_METHOD : currently mafft is only available.
+* TRIMMING_METHOD : use trimal or gblocks, in your favor. gblocks usally cuts more, but can be differ by advanced option. Use none if you have enough time and resource for calculation
+* MODEL_METHOD : model method is currently not working good enough please wait
+* TREE_METHOD : fasttree is fastest, but least accurate (However, still a lot accurate than NJ tree). It is treated that iqtree is faster but slightly less accurate than raxml, but iqtree requires at least 1000 bootstrap. So in case of speed, raxml could be a little bit faster when low bootstrap selected-->
+
+## Results
+* ```Section Assignment.xlsx``` : Your clustering result is here. You can find which of your sequences are clustered to which section 
+* ```Identification_result.xlsx``` : Your final identification result. Shows how your sequences were assigned to species level through tree-based identification
+* ```report.xlsx``` : overall statistics about the tree. If your find taxon ends with numbers, these taxon are found to be paraphyletic, so should be checked
+* ```/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~~
+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)
+
+## License
+[GPL 3.0](https://github.com/Changwanseo/FunVIP/blob/main/LICENSE)
+
+
+<!--
+## Installation with conda (May not work with Linux or Mac)
+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
+-->
+<!--### GUI mode (\*Currently under development)
+1. Go to ~/FunID-dev
+2. ```streamlit run FunID_GUI.py```
+* GUI run is on experimental
+* If you want to edit GUI options, edit ```Option_manager.xlsx``` and variables in ```FunID_GUI.py```
+### Server mode (\* Currently under development)-->

{funvip-0.4.1 → funvip-0.5.1}/README.md

@@ -1,18 +1,31 @@
 
 # FunVIP [![DOI](https://zenodo.org/badge/588465720.svg)](https://zenodo.org/doi/10.5281/zenodo.10714946)
+
+
+FunVIP is now published please cite:
+#### Seo CW, Yoo S, Cho Y, Kim JS, Steinegger M, Lim YW. FunVIP: Fungal Validation and Identification Pipeline based on phylogenetic analysis. J. Microbiol. 2025;63(4):e2411017.
+<br><br/>
+
+
+
+
 ### **Fun**gal **V**alidation & **I**dentification **P**ipeline
 #### An automatic tree-based sequence identification and validation pipeline for fungal (or maybe other) species
 
+
+
 - Automatic tree-based identification
 - 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
+Bug reports are always 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
+
+
+#### 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)
@@ -88,7 +101,7 @@ tabular (```.xlsx```, ```.csv```,  ```.parquet```, ```.ftr```) form
 
 ## 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~~ FunVIP article is currently accepted. Will be published soon.
+Will be tested by our lab memebers to fix bugs and advance features~~
 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-0.4.1 → funvip-0.5.1}/funvip/main.py

@@ -410,3 +410,24 @@ def main():
             logging.info(f"Time report generation: {round(time_end-time_visualize,3)}s")
         except:
             logging.warning(f"Failed logging reoprt generation time")
+
+        # At the end of the run, print critical messages once again to be noticed
+        with open(path.criticallog, "r") as frclog:
+            critical_log_lines = frclog.readlines()
+
+            critical_logs = []
+            flag_critical = 0
+            for line in critical_log_lines:
+                if "[CRITICAL]" in line:
+                    flag_critical = 1
+                elif "[WARNING]" in line or "[ERROR]" in line:
+                    flag_critical = 0
+
+                if flag_critical == 1:
+                    critical_logs.append(line)
+
+            if len(critical_logs) > 0:
+                print("\n!!!<<<IMPORTANT NOTICE FROM FUNVIP RUN>>>!!!")
+
+            for line in critical_logs:
+                print(line)

{funvip-0.4.1 → funvip-0.5.1}/funvip/src/cluster.py

@@ -114,6 +114,7 @@ def assign_gene(result_dict, V, cutoff=0.99):
     return V
 
 
+# This function assigns group to each FI
 def cluster(FI, V_list_group, V_cSR, path, opt):
     # Reduce memory by focusing on relevant rows
     df_search = V_cSR[V_cSR["qseqid"] == FI.hash]
@@ -222,23 +223,23 @@ def append_outgroup(V_list_FI, df_search, gene, group, path, opt):
     # split that same group to include all to alignment, and leave other groups for outgroup selection
     cutoff_df = cutoff_df[cutoff_df["subject_group"] != group]
 
-    ## For ambiugous database, mostly because of contaminated database
+    ## Add suspicious database, mostly because of contaminated database
+    # Use term "ambiguous" instead of "suspicious" because of previous compatibility
     # For each of the input, should use different cutoff
     ambiguous_db = set()
-    for qseqid, _df in cutoff_set_df.groupby(["qseqid"]):
-        # Select dataframe corresponding to current qseqid
-        df_qseqid = df_search[df_search["qseqid"] == qseqid]
-        """
-        print(
-            f"Ambiguous ingroup cutoff selected for query {qseqid} group {group} gene {gene} cutoff {min(list(_df['bitscore']))}"
-        )
-        """
-        # Get the list of subjects, which is closer than furtest ingroup
-        ambiguous_df = df_qseqid[df_qseqid["bitscore"] >= min(list(_df["bitscore"]))]
-        # Within the furthest match, get possible ingroups with ambiguous group
-        ambiguous_df = ambiguous_df[ambiguous_df["subject_group"] != group]
-        # Add inner ambiugities to ambiguous db
-        ambiguous_db.update([FI_dict[i] for i in list(ambiguous_df["sseqid"])])
+    if opt.suspicious is True:
+        for qseqid, _df in cutoff_set_df.groupby(["qseqid"]):
+            # Select dataframe corresponding to current qseqid
+            df_qseqid = df_search[df_search["qseqid"] == qseqid[0]]
+
+            # Get the list of subjects, which is closer than furtest ingroup
+            ambiguous_df = df_qseqid[
+                df_qseqid["bitscore"] >= min(list(_df["bitscore"]))
+            ]
+            # Within the furthest match, get possible ingroups with ambiguous group
+            ambiguous_df = ambiguous_df[ambiguous_df["subject_group"] != group]
+            # Add inner ambiugities to ambiguous db
+            ambiguous_db.update([FI_dict[i] for i in list(ambiguous_df["sseqid"])])
 
     ambiguous_db = list(ambiguous_db)
 
@@ -308,12 +309,20 @@ def append_outgroup(V_list_FI, df_search, gene, group, path, opt):
                     f"Outgroup [{subject_group}] selected to [{group}]\n {text_outgroup_list}"
                 )
 
+                # Move outgroup within ambiguous db to outgroup
+                for FI in ambiguous_db:
+                    if FI.group == subject_group:
+                        ambiguous_db.remove(FI)
+                        outgroup_dict[subject_group].append(FI)
+
                 return (
                     group,
                     gene,
                     outgroup_dict[subject_group],
                     ambiguous_db,
                 )
+
+            # If not use the outgroup sequences with the maximum number
             else:
                 if len(outgroup_dict[subject_group]) > max_cnt:
                     max_cnt = len(outgroup_dict[subject_group])
@@ -330,6 +339,12 @@ def append_outgroup(V_list_FI, df_search, gene, group, path, opt):
             f"Final outgroup selection for group {group} : {outgroup_dict[max_group]}"
         )
 
+        # Move outgroup within ambiguous db to outgroup
+        for FI in ambiguous_db:
+            if FI.group == max_group:
+                ambiguous_db.remove(FI)
+                outgroup_dict[max_group].append(FI)
+
         return (group, gene, outgroup_dict[max_group], ambiguous_db)
 
     # If outgroup cannot be selected
@@ -507,6 +522,7 @@ def pipe_append_outgroup(V, path, opt):
 
     # append outgroup by running result
     # (group, gene, outgroup, ambiguous_group)
+    critical_flag = 0
     for result in result_append_outgroup:
         # Parsing result
         group = result[0]
@@ -524,9 +540,10 @@ def pipe_append_outgroup(V, path, opt):
         print(f"query: {len(V.dict_dataset[group][gene].list_qr_FI)}")
 
         if len(outgroup) == 0 and len(ambiguous_group) == 0:
-            logging.warning(
+            logging.critical(
                 f"Removing {group} {gene} from analysis because outgroup cannot be selected"
             )
+            critical_flag = 1
             V.dict_dataset[group].pop(gene, None)
         elif (
             len(outgroup)
@@ -535,15 +552,17 @@ def pipe_append_outgroup(V, path, opt):
             + len(V.dict_dataset[group][gene].list_qr_FI)
             < 4
         ):
-            logging.warning(
+            logging.critical(
                 f"Removing {group} {gene} from analysis because not enough sequences are provided to infer phylogenetic tree"
             )
+            critical_flag = 1
             V.dict_dataset[group].pop(gene, None)
 
         else:
             V.dict_dataset[group][gene].list_og_FI = outgroup
+
             # Add ambiguous group to FI
-            if opt.ambiguous is True:
+            if opt.suspicious is True:
                 V.dict_dataset[group][gene].list_db_FI += ambiguous_group
             # Add outgroup and db in to dict_hash_FI
 
@@ -552,11 +571,16 @@ def pipe_append_outgroup(V, path, opt):
     for group in groups:
         try:
             if len(V.dict_dataset[group]) == 0:
-                logging.warning(
+                logging.critical(
                     f"Removing {group} from analysis because outgroup cannot be selected to all genes"
                 )
+                critical_flag = 1
                 V.dict_dataset.pop(group, None)
         except:
             pass
 
+    # Terminate if terminate option is given, and critical error occurs
+    if critical_flag == 1 and opt.terminate is True:
+        raise Exception
+
     return V, path, opt

{funvip-0.4.1 → funvip-0.5.1}/funvip/src/command.py

@@ -309,9 +309,14 @@ class CommandParser:
             type=int,
         )
         group_advanced.add_argument(
-            "--noambiguous",
+            "--nosuspicious",
             action="store_true",
-            help="Do not include ambiguous samples for sequence-set. Mostly for metabarcoding analysis. It may result wrong result with problematic database.",
+            help="Do not include suspicious samples for sequence-set. Mostly for metabarcoding analysis. May deduce inaccurate result with problematic database.",
+        )
+        group_advanced.add_argument(
+            "--terminate",
+            action="store_true",
+            help="Terminate FunVIP run when critical error detected",
         )
 
         # Cache

{funvip-0.4.1 → funvip-0.5.1}/funvip/src/dataset.py

@@ -462,6 +462,8 @@ class FunVIP_var:
         fail_list = []
         remove_dict = {}
         tree_hash_dict = hasher.encode(self.list_FI, newick=True)
+
+        critical_flag = 0
         for group in self.dict_dataset:
             remove_dict[group] = {}
             for gene in self.dict_dataset[group]:
@@ -545,9 +547,38 @@ class FunVIP_var:
                         ## If all value of vectors are zero, it means that all regions have at least one gap
                         ## Raise warning for this
                         if np.all((vector_products == 0)):
-                            logging.warning(
+                            logging.critical(
                                 f"Alignment for {group} {gene} does not have any overlapping regions! Removing from analysis"
                             )
+
+                            critical_flag = 1
+
+                            # Report one non_overlapping pair
+                            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)
+
+                                    has_overlap = False
+
+                                    for k in range(len(seq1_str)):
+                                        if seq1_str[k] != "-" and seq2_str[k] != "-":
+                                            has_overlap = True
+                                            break
+
+                            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
+
                             fail_list.append((group, gene))
                             # for tree, use hash dict with genus and species information
                             # Decoding process in done in tree building processes, so these alignments cannot be decoded. So decode them here
@@ -575,6 +606,10 @@ class FunVIP_var:
                     # If alignment corresponding to dataset does not exists, raise warning or error
                     pass
 
+        # Terminate if terminate option is given, and critical error occurs
+        if critical_flag == 1 and opt.terminate is True:
+            raise Exception
+
         # Remove bad datasets
         for fail in fail_list:
             group = fail[0]

{funvip-0.4.1 → funvip-0.5.1}/funvip/src/hasher.py

@@ -18,6 +18,11 @@ def newick_legal(string: str) -> str:
     return str(string)
 
 
+# Fix "&" sign appropriate for svg
+def svg_legal(string: str) -> str:
+    return string.replace("&", "&")
+
+
 # Encode funinfo_list and return hash dict
 def encode(funinfo_list: list, newick: bool = False) -> dict:
     hash_dict = {}
@@ -53,13 +58,28 @@ def encode(funinfo_list: list, newick: bool = False) -> dict:
 # Decode given file with given hash_dict
 
 
-def decode(hash_dict: dict, file: str, out: str, newick: bool = True) -> None:
+def decode(
+    hash_dict: dict, file: str, out: str, newick: bool = True, svg: bool = False
+) -> None:
     with open(file, "rt") as fp:
         content = fp.read()
 
+    if newick and svg:
+        hash_dict = {
+            re.escape(k): svg_legal(newick_legal(v)) for k, v in hash_dict.items()
+        }
+    elif newick:
+        hash_dict = {re.escape(k): newick_legal(v) for k, v in hash_dict.items()}
+    elif svg:
+        hash_dict = {re.escape(k): svg_legal(v) for k, v in hash_dict.items()}
+    else:
+        hash_dict = {re.escape(k): v for k, v in hash_dict.items()}
+
+    """
     hash_dict = {
         re.escape(k): (newick_legal(v) if newick else v) for k, v in hash_dict.items()
     }
+    """
     pattern = re.compile("|".join(hash_dict.keys()))
 
     # Perform the substitution