FunVIP 0.3.24.7__tar.gz → 0.4.0__tar.gz

{funvip-0.3.24.7 → funvip-0.4.0}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: FunVIP
-Version: 0.3.24.7
+Version: 0.4.0
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -17,7 +17,6 @@ Requires-Dist: matplotlib
 Requires-Dist: numpy<2.0.0
 Requires-Dist: openpyxl==3.1.0
 Requires-Dist: pandas==2.2.2
-Requires-Dist: plotly==5.9.0
 Requires-Dist: psutil
 Requires-Dist: pyyaml
 Requires-Dist: sip>=4.19.4

{funvip-0.3.24.7 → funvip-0.4.0}/FunVIP.egg-info/requires.txt

@@ -8,7 +8,6 @@ matplotlib
 numpy<2.0.0
 openpyxl==3.1.0
 pandas==2.2.2
-plotly==5.9.0
 psutil
 pyyaml
 sip>=4.19.4

{funvip-0.3.24.7 → funvip-0.4.0}/PKG-INFO

@@ -1,6 +1,6 @@
-Metadata-Version: 2.1
+Metadata-Version: 2.2
 Name: FunVIP
-Version: 0.3.24.7
+Version: 0.4.0
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0
@@ -17,7 +17,6 @@ Requires-Dist: matplotlib
 Requires-Dist: numpy<2.0.0
 Requires-Dist: openpyxl==3.1.0
 Requires-Dist: pandas==2.2.2
-Requires-Dist: plotly==5.9.0
 Requires-Dist: psutil
 Requires-Dist: pyyaml
 Requires-Dist: sip>=4.19.4

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/main.py

@@ -223,6 +223,7 @@ def main():
         logging.info("TRIMMING")
         V, path, opt = trim.pipe_trimming(V, path, opt)
         # Alignment validations - whether some of the sequences does not have overlapping regions
+        # Calculate TCS score if speicified by option
         V.validate_alignments(path=path, opt=opt)
         R.update_report(
             V=V,

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/preset/accurate.yaml

@@ -1,8 +1,7 @@
 MODE: identification
 CONTINUE: false
 QUERYONLY: true
-CONFIDENT: false
-CONCATENATE: true
+CONFIDENT: fale
 MAXOUTGROUP: 3
 SEARCH: blast
 ALIGNMENT: mafft
@@ -26,5 +25,4 @@ MAFFT-ep: 0.1
 AVX: true
 CACHEDB: true
 USECACHE: true
-FULLGENUS: true
 

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/preset/fast.yaml

@@ -22,4 +22,3 @@ MAFFT-ep: 0.1
 AVX: true
 CACHEDB: true
 USECACHE: true
-FULLGENUS: true

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/cluster.py

@@ -245,14 +245,14 @@ def append_outgroup(V_list_FI, df_search, gene, group, path, opt):
     # If no or fewer than designated number of outgroup matches to condition, use flexible criteria
     if cutoff_df.groupby(["subject_group"]).count().empty:
         logging.warning(
-            f"Not enough outgroup sequences matched for group {group} | gene {gene}. There might be outlier sequence that does not matches to group. Trying flexible cutoff"
+            f"Not enough outgroup sequences matched for {opt.level} {group} | gene {gene}. There might be outlier sequence that does not matches to group. Trying flexible cutoff"
         )
         cutoff_df = df_search[df_search["bitscore"] > 0]
         cutoff_df = cutoff_df[cutoff_df["subject_group"] != group]
 
     elif cutoff_df.groupby(["subject_group"]).count()["sseqid"].max() < opt.maxoutgroup:
         logging.warning(
-            f"Not enough outgroup sequences matched for group {group} | gene {gene}. There might be outlier sequence that does not matches to group. Trying flexible cutoff"
+            f"Not enough outgroup sequences matched for {opt.level} {group} | gene {gene}. There might be outlier sequence that does not matches to group. Trying flexible cutoff"
         )
         cutoff_df = df_search[df_search["bitscore"] > 0]
         cutoff_df = cutoff_df[cutoff_df["subject_group"] != group]
@@ -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-0.3.24.7 → funvip-0.4.0}/funvip/src/command.py

@@ -91,7 +91,7 @@ class CommandParser:
             "--continue",
             dest="continue_from_previous",
             action="store_true",
-            help="Continue from previous run",
+            help="Continue from previous run, default: False",
         )
         group_run.add_argument(
             "--step",
@@ -106,7 +106,7 @@ class CommandParser:
         group_run.add_argument(
             "--all",
             action="store_true",
-            help="Run FunVIP for all database sequences, regardless of corrresponding sequences exists in query, default : False",
+            help="Run FunVIP for all database sequences, regardless of corresponding sequences exists in query, default : False",
         )
         group_run.add_argument(
             "--confident",
@@ -127,6 +127,11 @@ class CommandParser:
             help="Multiple sequence alignment methods, [mafft], default : mafft",
             type=str,
         )
+        group_method.add_argument(
+            "--notcs",
+            action="store_true",
+            help="Skip T-COFFEE TCS(Transitive Consistency Score) for alignment validation. default: False",
+        )
         group_method.add_argument(
             "--trim",
             help="Trimming methods, [trimal, gblocks, none], default : trimal",
@@ -227,9 +232,9 @@ class CommandParser:
             type=int,
         )
         group_advanced.add_argument(
-            "--solveflat",
+            "--nosolveflat",
             action="store_true",
-            help="Whether to automatically detect 0 length branch and automatically solve them, default : True",
+            help="Do not detect 0 length branch and automatically solve them, default : False",
         )
         group_advanced.add_argument(
             "--regex",
@@ -284,7 +289,7 @@ class CommandParser:
         group_advanced.add_argument(
             "--allow-innertrimming",
             dest="allow_innertrimming",
-            help="Turn off FunVIP adjustment to not to trim inner alignment columns",
+            help="Turn off FunVIP adjustment to not to trim inner alignment columns, default: False",
             action="store_true",
         )
         group_advanced.add_argument(
@@ -296,7 +301,7 @@ class CommandParser:
         group_advanced.add_argument(
             "--noavx",
             action="store_true",
-            help="do not use AVX for RAxML, default: False",
+            help="Do not use AVX for RAxML, default: False",
         )
         group_advanced.add_argument(
             "--outgroupoffset",
@@ -306,7 +311,7 @@ class CommandParser:
         group_advanced.add_argument(
             "--noambiguous",
             action="store_true",
-            help="do not include ambiguous samples for sequence-set. Mostly for metabarcoding analysis",
+            help="Do not include ambiguous samples for sequence-set. Mostly for metabarcoding analysis. It may result wrong result with problematic database.",
         )
 
         # Cache
@@ -315,9 +320,9 @@ class CommandParser:
             description="Save search database for faster run in next time",
         )
         group_cache.add_argument(
-            "--cachedb",
+            "--nocachedb",
             action="store_true",
-            help="Cache current search database, turn off if your database is too big for system directory, default : True",
+            help="Disable caching current search database. Use it if your database is too big for system directory, default : True",
         )
         group_cache.add_argument(
             "--usecache",
@@ -344,7 +349,7 @@ class CommandParser:
         group_save.add_argument(
             "--nosearchresult",
             action="store_true",
-            help="Do not save blast/mmseqs search matrix, use when dataset gets too big and generates IO bottleneck",
+            help="Do not save blast/mmseqs search matrix, use when dataset gets too big and generates IO bottleneck, default: False",
         )
 
         # Preset

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/concatenate.py

@@ -57,10 +57,10 @@ def combine_alignment(V, opt, path):
 
                 # Generate partition file
                 with open(
-                    f"{path.out_alignment}/{opt.runname}_{group}.partition", "w"
+                    f"{path.out_alignment}/partition/{opt.runname}_{group}.partition",
+                    "w",
                 ) as fw:
                     tot_len = 0
-                    print(gene_list)
                     for gene in gene_list:
                         # gene_list.append(gene)
                         fw.write(f"DNA, {gene}= {tot_len+1}-{tot_len+len_dict[gene]}\n")
@@ -109,7 +109,8 @@ def combine_alignment(V, opt, path):
                     )
                 )
                 with open(
-                    f"{path.out_alignment}/{opt.runname}_{group}.partition", "w"
+                    f"{path.out_alignment}/partition/{opt.runname}_{group}.partition",
+                    "w",
                 ) as fw:
                     fw.write(f"DNA, {singlegene}= 1-{gene_length}\n")
 
@@ -273,9 +274,15 @@ def concatenate_df(V, path, opt):
                 mean_linear_constant = linear_constant.mean()
 
                 # Fill missing bitscores
+                """
                 df[f"{gene}_bitscore"].fillna(
                     coeff[k] - mean_linear_constant * grad[k], inplace=True
                 )
+                """
+                df.fillna(
+                    {f"{gene}_bitscore": coeff[k] - mean_linear_constant * grad[k]},
+                    inplace=True,
+                )
             return df
 
         # Change to numpy for faster cazlculation

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/dataset.py

@@ -1,10 +1,13 @@
 from funvip.src import save
 from funvip.src import hasher
+from funvip.src import ext
+from funvip.src.opt_generator import opt_generator
 from Bio import SeqIO
 import os
 import sys
 import shutil
 import numpy as np
+import multiprocessing as mp
 import logging
 import re
 import json
@@ -207,7 +210,7 @@ class FunVIP_var:
         for group in self.list_group:
             logging.info(f"Generating dataset for {group}")
 
-            print(f"opt.queryonly: {opt.queryonly}")
+            # print(f"opt.queryonly: {opt.queryonly}")
 
             dict_funinfo[group] = {}
 
@@ -455,6 +458,7 @@ class FunVIP_var:
 
     # Validate if any multiple sequence alignment has no overlapping region
     def validate_alignments(self, path, opt):
+        # 1. Manual validation for illegal alignments
         fail_list = []
         remove_dict = {}
         tree_hash_dict = hasher.encode(self.list_FI, newick=True)
@@ -510,16 +514,6 @@ class FunVIP_var:
 
                         remove_dict[group][gene] = remove_hash
 
-                        """
-                        for _hash in remove_hash:
-                            if _hash in self.dict_dataset[group][gene].list_db_FI:
-                                self.dict_dataset[group][gene].list_db_FI.pop(_hash)
-                            if _hash in self.dict_dataset[group][gene].list_query_FI:
-                                self.dict_dataset[group][gene].list_query_FI.pop(_hash)
-                            if _hash in self.dict_dataset[group][gene].list_og_FI:
-                                self.dict_dataset[group][gene].list_og_FI.pop(_hash)
-                        """
-
                         # Remove unusable sequence and re-read it
                         ## db_list, query_list, outgroup_list might has to be changed
                         seq_list = [
@@ -591,12 +585,12 @@ class FunVIP_var:
         # Add issue
         for fail in fail_list:
             for FI in self.list_FI:
-                if FI.adjusted_group == fail[0]:
-                    if fail[1] in FI.seq:
-                        if FI.seq[fail[1]] != "":
-                            FI.issues.add(f"alignfail:{fail[1]}")
-
-        # print(fail_list)
+                if (
+                    FI.adjusted_group == fail[0]
+                    and fail[1] in FI.seq
+                    and FI.seq[fail[1]] != ""
+                ):
+                    FI.issues.add(f"alignfail:{fail[1]}")
 
         logging.debug("Remove dict")
         logging.debug(remove_dict)
@@ -701,7 +695,55 @@ class FunVIP_var:
                     if FI.seq[fail[1]] != "":
                         FI.issues.add(f"lackseq")
 
-        # return V
+        # Validate multiple sequence alignment with TCS score from T-COFFEE
+        # As T-COFFEE build is only available in Mac and Linux, should check if it is available
+        if opt.method.tcs is True:
+            bad_cnt = 0
+
+            if opt.verbose < 3:
+                tcs_opt = opt_generator(
+                    V=self, opt=opt, path=path, step="tcs", thread=1
+                )
+                p = mp.Pool(opt.thread)
+                p.starmap(ext.TCS, tcs_opt)
+                p.close()
+                p.join()
+
+            else:
+                tcs_opt = opt_generator(V=self, opt=opt, path=path, step="tcs")
+                for option in tcs_opt:
+                    ext.TCS(*option)
+
+                # non-multithreading mode for debugging
+                for group in self.dict_dataset:
+                    for gene in self.dict_dataset[group]:
+                        # Running TCS for concatenated alignment is duplicate
+                        if gene != "concatenated":
+                            tcs_out = f"{path.out_alignment}/alignment/{opt.runname}_{group}_{gene}.tcs"
+                            # Parse tcs result
+                            with open(tcs_out, "r") as f_tcs:
+                                tcs_result_raw = f_tcs.read()
+                                tcs_result = tcs_result_raw.split("*")[2].split("cons")[
+                                    0
+                                ]
+                                for line in tcs_result.split("\n")[1:-1]:
+                                    _hash = line.split(":")[0].strip()
+                                    tcs_score = int(line.split(":")[1].strip())
+                                    if (
+                                        tcs_score < 50
+                                    ):  # cutoff 50 comes from TCS documentation
+                                        FI_id = self.dict_hash_FI[_hash].id
+                                        logging.warning(
+                                            f"{FI_id} has poor alignment score in {group} {gene}"
+                                        )
+                                        bad_cnt += 1
+
+            if bad_cnt == 0:
+                logging.info(f"All sequences in alignment passed TCS validation")
+            else:
+                logging.warning(
+                    f"{bad_cnt} sequences in alignment failed TCS validation. Please check sequneces"
+                )
 
     # check inconsistency exists along identification result of each genes
     def check_inconsistent(self):

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/ext.py

@@ -80,7 +80,8 @@ def makeblastdb(fasta, db, path):
         # run make blast db
         CMD = f"{path_makeblastdb} -in {fasta_tmp} -blastdb_version 4 -title {db_tmp} -dbtype nucl"
         logging.info(CMD)
-        Run = subprocess.call(CMD, shell=True)
+        # I cannot find any "quiet" options for makeblastdb
+        Run = subprocess.call(CMD, stdout=open(os.devnull, "wb"), shell=True)
         # Change db names
         shutil.move(fasta_tmp + ".nsq", db + ".nsq")
         shutil.move(fasta_tmp + ".nin", db + ".nin")
@@ -93,7 +94,8 @@ def makeblastdb(fasta, db, path):
     else:
         CMD = f"makeblastdb -in '{fasta}' -blastdb_version 4 -title '{db}' -dbtype nucl"
         logging.info(CMD)
-        return_code = subprocess.call(CMD, shell=True)
+        # I cannot find any "quiet" options for makeblastdb
+        return_code = subprocess.call(CMD, stdout=open(os.devnull, "wb"), shell=True)
 
         if return_code != 0:
             logging.error(f"Make blast_db failed!!")
@@ -325,14 +327,14 @@ def RAxML(
         if " " in out:
             out = f'"{out}"'
 
-        CMD = f"{path.sys_path}/external/RAxML_Windows/raxmlHPC-PTHREADS-AVX2.exe -s {fasta} -n {out} -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model}"
+        CMD = f"{path.sys_path}/external/RAxML_Windows/raxmlHPC-PTHREADS-AVX2.exe -s {fasta} -n {out} -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model} --silent"
     elif platform == "darwin":
         CMD = f"raxmlHPC-PTHREADS -s '{fasta}' -n '{out}' -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model}"
     else:
         if version == "old":
-            CMD = f"raxmlHPC-PTHREADS-AVX -s '{fasta}' -n '{out}' -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model}"
+            CMD = f"raxmlHPC-PTHREADS-AVX -s '{fasta}' -n '{out}' -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model} --silent"
         elif version == "new":
-            CMD = f"raxmlHPC-PTHREADS-AVX2 -s '{fasta}' -n '{out}' -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model}"
+            CMD = f"raxmlHPC-PTHREADS-AVX2 -s '{fasta}' -n '{out}' -p 1 -T {thread} -f a -# {bootstrap} -x 1 {model} --silent"
         else:
             logging.error(
                 f"DEVELOPMENTAL ERROR - unexpected RAxML version, {version} in ext.py"
@@ -455,3 +457,26 @@ def IQTREE(
         hash_file_path=f"{path.out_tree}/hash_{file}",
         decoded_file_path=f"{path.out_tree}/{file}",
     )
+
+
+# TCS calculation from T-COFFEE
+def TCS(fasta, thread, out):
+    if platform == "win32":
+        logging.error("TCS(From T-COFFEE) is only available in Linux")
+        raise Exception
+    else:
+        # T_COFFEE env variable MAX_N_PID_4_TCOFFEE should be changed for 64bit machine
+        # should be already done in installation check process
+        # subprocess.call("export MAX_N_PID_4_TCOFFEE=4194304", shell=True)
+        CMD = f"t_coffee -infile {fasta} -cpu {thread} -method fast_pair -type DNA -evaluate -output score_ascii -outfile {out} -quiet"
+
+    logging.info(CMD)
+    # Even though "quiet" option exists, TCS show some blank lines
+    # Run = subprocess.call(CMD, stdout=open(os.devnull, "wb"), shell=True)
+    Run = subprocess.run(
+        CMD, stdout=open(os.devnull, "wb"), stderr=subprocess.STDOUT, shell=True
+    ).returncode
+
+    if Run != 0:
+        logging.error(f"TCS Failed!")
+        raise Exception

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/initialize.py

@@ -31,10 +31,10 @@ def check(
     obj,
     type_,
     criterion,
-    value=np.NaN,
-    min_=np.NaN,
-    max_=np.NaN,
-    default=np.NaN,
+    value=np.nan,
+    min_=np.nan,
+    max_=np.nan,
+    default=np.nan,
     solve=False,
 ):
     # obj : option things that should be checked
@@ -187,9 +187,17 @@ class Path:
             for program in check_commands:
                 cmd = check_commands[program]
                 # Quietly call each programs
+                """
                 return_code = subprocess.call(
                     cmd, shell=True, stdout=open(os.devnull, "wb")
                 )
+                """
+                return_code = subprocess.run(
+                    cmd,
+                    shell=True,
+                    stdout=open(os.devnull, "wb"),
+                    stderr=subprocess.STDOUT,
+                ).returncode
                 if return_code != 0:
                     print(f"[ERROR] {program} not installed!")
                     install_flag = 1
@@ -198,12 +206,18 @@ class Path:
             # I don't know why, but apt install RAxML can use raxmlHPC-PTHREADS-AVX,
             # while conda install RAxML can use raxmlHPC -PTHREADS-AVX / raxmlHPC-PTHREADS-AVX2 (blank between raxmlHPC and -PTHREADS-AVX)
             # However, if using 'raxmlHPC -PTHREADS-AVX', the computer cannot utilize full threads
-            return_code_1 = subprocess.call(
-                "raxmlHPC-PTHREADS-AVX -h", shell=True, stdout=open(os.devnull, "wb")
-            )
-            return_code_2 = subprocess.call(
-                "raxmlHPC-PTHREADS-AVX2 -h", shell=True, stdout=open(os.devnull, "wb")
-            )
+            return_code_1 = subprocess.run(
+                "raxmlHPC-PTHREADS-AVX -h",
+                shell=True,
+                stdout=open(os.devnull, "wb"),
+                stderr=subprocess.STDOUT,
+            ).returncode
+            return_code_2 = subprocess.run(
+                "raxmlHPC-PTHREADS-AVX2 -h",
+                shell=True,
+                stdout=open(os.devnull, "wb"),
+                stderr=subprocess.STDOUT,
+            ).returncode
 
             if return_code_1 != 0 and return_code_2 != 0:
                 print(f"[ERROR] RAxML not installed!")
@@ -224,6 +238,9 @@ class Path:
                     )
                 raise Exception
 
+            # For t-coffee, check it and just turn off it tcs is not installed
+            # it should be done in validation_option.py so moved
+
         # Location for list of genus file
         self.genusdb = f"{self.sys_path}/data/genus_line.txt"
 
@@ -247,7 +264,8 @@ class Path:
         self.root = os.path.abspath(self.root)
 
         # Logging directory
-        self.log = f"{self.root}/log.txt"
+        self.log = f"{self.root}/log.txt"  # for overall logging
+        self.criticallog = f"{self.root}/log_critical.txt"  # for warnings and errors
         self.extlog = f"{self.root}/log"  # for saving external program logs
         mkdir(self.extlog)
 
@@ -288,6 +306,10 @@ class Path:
         mkdir(f"{self.out_alignment}/hash")
         # For failed alignments
         mkdir(f"{self.out_alignment}/failed")
+        # For partition file
+        mkdir(f"{self.out_alignment}/partition")
+        # For tcs results
+        mkdir(f"{self.out_alignment}/tcs")
 
         # modeltest result directory
         self.out_modeltest = f"{self.root}/06_Modeltest"
@@ -311,7 +333,7 @@ def initialize(path_run, parser):
 
     # Move option loading as independent class or function
     # Generate path class
-    print(f"Output location: {path_run}")
+    print(f"[INFO] Output location: {path_run}")
     path = Path(path_run)
 
     # Parsing options

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/logger.py

@@ -54,6 +54,12 @@ def setup_logging(list_info, list_warning, list_error, path, opt, tool):
     for handler in logging.root.handlers:
         handler.setFormatter(formatter)
 
+    # Add a new FileHandler for warnings, errors, and critical messages
+    warning_error_critical_handler = logging.FileHandler(path.criticallog)
+    warning_error_critical_handler.setLevel(logging.WARNING)
+    warning_error_critical_handler.setFormatter(formatter)
+    logging.getLogger().addHandler(warning_error_critical_handler)
+
     # Delayed logging for option parsing
 
     # I don't know why, but in some environment, ANSI color works only after first subprocess.call was done

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/opt_generator.py

@@ -65,6 +65,22 @@ def opt_generator(V, opt, path, step, thread=None):
                             )
                         )
 
+    # For tcs alignment validation
+    elif step == "tcs":
+        for group in V.dict_dataset:
+            for gene in V.dict_dataset[group]:
+                if gene != "concatenated":
+                    tcs_out = (
+                        f"{path.out_alignment}/tcs/{opt.runname}_{group}_{gene}.tcs"
+                    )
+                    list_opt.append(
+                        (
+                            f"{path.out_alignment}/{opt.runname}_trimmed_{group}_{gene}.fasta",
+                            thread,
+                            tcs_out,
+                        )
+                    )
+
     else:
         logging.error(f"[Error] Unexpected step {step} given for opt_generator")
         raise Exception

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/reporter.py

@@ -3,7 +3,8 @@ import pandas as pd
 import matplotlib.pyplot as plt
 import io
 import logging
-import plotly.express as px
+
+# import plotly.express as px
 import sys
 from tabulate import tabulate
 from funvip.src.tool import index_step
@@ -298,7 +299,7 @@ class Report:
 
         # Count groups
         for group in sorted(list(set(self.query_result["GROUP_ASSIGNED"]))):
-            df_group = df_result_group.get_group(group)
+            df_group = df_result_group.get_group((group,))
 
             # Collect statistics
             """
@@ -828,7 +829,7 @@ class Report:
             dict_citation = {
                 "FunVIP": "https://github.com/Changwanseo/FunVIP",
                 "GenMine": "Seo, C. W., Kim, S. H., Lim, Y. W., & Park, M. S. (2022). Re-identification on Korean Penicillium sequences in GenBank collected by software GenMine. Mycobiology, 50(4), 231-237.",
-                "BLASTn": "Altschul, S. F., Gish, W., Miller, W., Myers, E. W., & Lipman, D. J. (1990). Basic local alignment search tool. Journal of molecular biology, 215(3), 403-410.",
+                "BLASTn": "Camacho, C., Coulouris, G., Avagyan, V., Ma, N., Papadopoulos, J., Bealer, K., & Madden, T. L. (2009). BLAST+: architecture and applications. BMC bioinformatics, 10, 1-9.",
                 "MMseqs2": "Steinegger, M., & Söding, J. (2017). MMseqs2 enables sensitive protein sequence searching for the analysis of massive data sets. Nature biotechnology, 35(11), 1026-1028.",
                 "MAFFT": "Katoh, K., & Standley, D. M. (2013). MAFFT multiple sequence alignment software version 7: improvements in performance and usability. Molecular biology and evolution, 30(4), 772-780.",
                 "Gblocks": "Talavera, G., & Castresana, J. (2007). Improvement of phylogenies after removing divergent and ambiguously aligned blocks from protein sequence alignments. Systematic biology, 56(4), 564-577.",

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/search.py

@@ -1,6 +1,7 @@
 from funvip.src import cluster, tool, hasher, validate_input, save
 from funvip.src.ext import blast, makeblastdb, mmseqs, makemmseqsdb
 from funvip.src.save import save_df
+from funvip.src.tool import mkdir
 import copy
 import pandas as pd
 import numpy as np
@@ -156,7 +157,7 @@ def search(query_fasta, db_fasta, path, opt) -> pd.DataFrame():
                 os.path.isdir(f"{path.in_db}/{opt.method.search.lower()}/{_hash}")
                 is True
             ):
-                logging.info("[INFO] Found existing database! Skipping database build")
+                logging.info("Found existing database! Skipping database build")
                 db = f"{path.in_db}/{opt.method.search.lower()}/{_hash}/{_hash}"
 
             # When parsing existing DB failed
@@ -170,7 +171,7 @@ def search(query_fasta, db_fasta, path, opt) -> pd.DataFrame():
                     )
 
                     # Create DB saving directory
-                    os.mkdir(f"{path.in_db}/{opt.method.search.lower()}/{_hash}")
+                    mkdir(f"{path.in_db}/{opt.method.search.lower()}/{_hash}")
                     db = f"{path.in_db}/{opt.method.search.lower()}/{_hash}/{_hash}"
 
                     # DB saving starts
@@ -184,14 +185,14 @@ def search(query_fasta, db_fasta, path, opt) -> pd.DataFrame():
                     logging.info(
                         "--cachedb not selected, saving database will be passed"
                     )
-                    os.mkdir(f"{path.tmp}/{opt.runname}/{_hash}")
+                    mkdir(f"{path.tmp}/{opt.runname}/{_hash}")
                     db = f"{path.tmp}/{opt.runname}/{_hash}/{_hash}"
 
                     # Create search database
                     create_search_db(opt, db_fasta, db, path)
 
     else:
-        os.mkdir(f"{path.tmp}/{opt.runname}/{_hash}")
+        mkdir(f"{path.tmp}/{opt.runname}/{_hash}")
         db = f"{path.tmp}/{opt.runname}/{_hash}/{_hash}"
         # Create search database
         create_search_db(opt, db_fasta, db, path)

{funvip-0.3.24.7 → funvip-0.4.0}/funvip/src/tool.py

@@ -26,9 +26,14 @@ def initialize_path(path):
     genus_file = path.genusdb
 
 
+# Check if directory exists and make if not
+# If intermediate directory does not exists, also do it
 def mkdir(path):
+    os.makedirs(path, exist_ok=True)
+    """
     if os.path.exists(path) == False:
         os.makedirs(path)
+    """
 
 
 def union_funinfo_list(funinfo_list1, funinfo_list2):