FunVIP 0.3.24.4__tar.gz → 0.3.24.6__tar.gz

{funvip-0.3.24.4 → funvip-0.3.24.6}/FunVIP.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.24.4
+Version: 0.3.24.6
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0

{funvip-0.3.24.4 → funvip-0.3.24.6}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: FunVIP
-Version: 0.3.24.4
+Version: 0.3.24.6
 Summary: Fungal Validation & Identification Pipeline
 Author-email: Changwan Seo <wan101010@snu.ac.kr>
 License: GPL-3.0

{funvip-0.3.24.4 → funvip-0.3.24.6}/funvip/main.py

@@ -34,6 +34,9 @@ def main():
     import logging
     import PyQt5
 
+    # To prevent pyqt error
+    os.environ["QT_QPA_PLATFORM"] = "offscreen"
+
     # To initialize logger to print ANSI color
     _ = subprocess.call("", shell=True)
 

{funvip-0.3.24.4 → funvip-0.3.24.6}/funvip/src/concatenate.py

@@ -148,33 +148,8 @@ def concatenate_df(V, path, opt):
             gene_list.append(gene)
 
             df = deepcopy(V.dict_gene_SR[gene].set_index(["qseqid", "sseqid"]))
-
-            """
-            df = deepcopy(
-                V.dict_gene_SR[gene]
-                .set_index(["qseqid", "sseqid"])
-                .drop(
-                    columns=[
-                        "pident",
-                        "length",
-                        "mismatch",
-                        "gaps",
-                        "qstart",
-                        "qend",
-                        "sstart",
-                        "send",
-                        "evalue",
-                        "bitscore",
-                        "subject_group",
-                    ]
-                )
-            )
-            """
             df_list.append(df)
 
-    print("line 175")
-    print(time_start - time())
-
     if len(df_list) <= 0:
         logging.warning(f"Stop concatenating because same or less than 0 gene exists")
         return V
@@ -214,24 +189,8 @@ def concatenate_df(V, path, opt):
             inplace=True,
         )
 
-        print("line 217")
-        print(time_start - time())
-
-        """
         # Column name managing on subject_group
-        def same_merge(x, list_col):
-            values = x[list_col].dropna()
-            if values.empty:
-                raise Exception
-            return values.iloc[0]
 
-        df_multigene_regression_ori[
-            "subject_group"
-        ] = df_multigene_regression_ori.apply(
-            lambda x: same_merge(x, [f"{gene}_subject_group" for gene in gene_list]),
-            axis=1,
-        )
-        """
         subject_group_cols = [f"{gene}_subject_group" for gene in gene_list]
         df_multigene_regression_ori["subject_group"] = (
             df_multigene_regression_ori[subject_group_cols].bfill(axis=1).iloc[:, 0]
@@ -240,13 +199,6 @@ def concatenate_df(V, path, opt):
         # For regression, leave anchor points with all genes existing
         df_multigene_regression = df_multigene_regression_ori
 
-        """
-        for gene in gene_list:
-            df_multigene_regression = df_multigene_regression[
-                df_multigene_regression[f"{gene}_bitscore"].notna()
-            ]
-            """
-
         mask = (
             df_multigene_regression_ori[[f"{gene}_bitscore" for gene in gene_list]]
             .notna()
@@ -255,9 +207,6 @@ def concatenate_df(V, path, opt):
 
         df_multigene_regression = df_multigene_regression_ori[mask]
 
-        print("line 243")
-        print(time_start - time())
-
         # Perform regression
         # Get regression line
         def distance_to_line(line, pts, l0=None, p0=None):
@@ -276,24 +225,13 @@ def concatenate_df(V, path, opt):
             D = (P - (P.dot.u) * u).length
             """
             # line origin other than (0,0,0,..)
+            # do not use line -= l0 because casting rule error might happen
             if l0 is not None:
-                line -= l0
+                line = line - l0
             # points origin other than (0,0,0,..)
+            # do not use pts -= l0 because casting rule error might happen
             if p0 is not None:
-                pts -= p0
-
-            """
-            # dot product
-            dp = np.dot(pts, line)
-            # dot product value divided by normalized vector of line
-            # np.linalg.norm(line) : size of the line vector
-            # pp should be orthographic projected length of the dot
-            pp = dp / np.linalg.norm(line)
-            # norm value of point
-            # length from p0 to point
-            pn = np.linalg.norm(pts, axis=1)
-            return np.sqrt(np.clip(pn**2 - pp**2, a_min=1e-10, a_max=None))
-            """
+                pts = pts - p0
 
             norm_line = np.linalg.norm(line)
             projected_lengths = np.dot(pts, line) / norm_line
@@ -329,32 +267,6 @@ def concatenate_df(V, path, opt):
                 K_optimized,
             )
 
-        # Reset df before filling it
-        """
-        def calculate_prediction(row, gene_list, coeff, grad):
-            # Calculate linear_constant of the strain
-            linear_constant = []
-            for k, gene in enumerate(gene_list):
-                if not np.isnan(row[f"{gene}_bitscore"]):
-                    #  (coeff - value) / gradient = linear constant
-                    linear_constant.append(
-                        (coeff[k] - row[f"{gene}_bitscore"]) / grad[k]
-                    )
-
-            # Predict unknown BLAST value
-            for k, gene in enumerate(gene_list):
-                if np.isnan(row[f"{gene}_bitscore"]):
-                    #  prediction value  = coeff - linear constant * gradient
-                    prediction = coeff[k] - np.mean(linear_constant) * grad[k]
-                    row[f"{gene}_bitscore"] = prediction
-            return row
-
-        
-        def apply_prediction(row, gene_list, coeff, grad):
-            row = calculate_prediction(row, gene_list, coeff, grad)
-            return row
-        """
-
         def vectorized_prediction(df, gene_list, coeff, grad):
             for k, gene in enumerate(gene_list):
                 linear_constant = (coeff[k] - df[f"{gene}_bitscore"]) / grad[k]
@@ -366,23 +278,14 @@ def concatenate_df(V, path, opt):
                 )
             return df
 
-        print("line 344")
-        print(time_start - time())
-
         # Change to numpy for faster cazlculation
         np_bitscore = df_multigene_regression[
             [f"{gene}_bitscore" for gene in gene_list]
         ].to_numpy()
 
-        print("line 353")
-        print(time_start - time())
-
         # get coefficient and gradient with regression
         coeff, grad = optimize_regression_line(np_bitscore)
 
-        print("optimize regression line")
-        print(time_start - time())
-
         # Inform users about linear regression result
         # (C0 - X0) / K0 = (C1 -X1) / X1 = (C2 - X2) / X2 = K
         trend_line_string = ""
@@ -403,15 +306,6 @@ def concatenate_df(V, path, opt):
             df_multigene_regression, gene_list, coeff, grad
         )
 
-        print("vectorized regression line")
-        print(time_start - time())
-
-        """
-        df_multigene_regression = df_multigene_regression.apply(
-            apply_prediction, args=(gene_list, coeff, grad), axis=1
-        )
-        """
-
         # Also update each gene bitscore matrix
         # This part is needed, for multigene analysis, for example ITS, CaM and RPB2
         # If query only exists for ITS and CaM, no blast result for RPB2 were generated
@@ -423,9 +317,6 @@ def concatenate_df(V, path, opt):
         ].mean(axis=1)
         V.cSR = df_multigene_regression.reset_index()
 
-        print("mean and reset index line")
-        print(time_start - time())
-
     # Save it
     # decode df is not working well here
     if opt.nosearchresult is False:
@@ -435,7 +326,4 @@ def concatenate_df(V, path, opt):
             fmt=opt.tableformat,
         )
 
-    print("save table")
-    print(time_start - time())
-
     return V

{funvip-0.3.24.4 → funvip-0.3.24.6}/funvip/src/ext.py

@@ -292,10 +292,10 @@ def ModelFinder(fasta, opt, path, thread):
     if platform == "win32":
         if " " in fasta:
             fasta = f'"{fasta}"'
-        CMD = f"{path.sys_path}/external/iqtree/bin/iqtree2.exe --seqtype DNA -s {fasta} {model_term} -merit {opt.criterion} -T {thread} -mem {opt.memory}"
+        CMD = f"{path.sys_path}/external/iqtree/bin/iqtree2.exe --seqtype DNA -s {fasta} {model_term} -merit {opt.criterion} -nt AUTO -ntmax {thread} -mem {opt.memory} --quiet"
     else:
         # not final
-        CMD = f"iqtree --seqtype DNA -s '{fasta}' {model_term} -merit {opt.criterion} -T {thread} -mem {opt.memory}"
+        CMD = f"iqtree --seqtype DNA -s '{fasta}' {model_term} -merit {opt.criterion} -nt AUTO -ntmax {thread} -mem {opt.memory} --quiet"
     logging.info(CMD)
     Run = subprocess.call(CMD, shell=True)
 
@@ -418,9 +418,9 @@ def IQTREE(
         else:
             tmp_fasta = fasta
 
-        CMD = f"{path.sys_path}/external/iqtree/bin/iqtree2.exe -s {tmp_fasta} -B {bootstrap} -T {thread} {model}"
+        CMD = f"{path.sys_path}/external/iqtree/bin/iqtree2.exe -s {tmp_fasta} -B {bootstrap} -nt AUTO -ntmax {thread} {model}"
     else:
-        CMD = f"iqtree -s {fasta} -B {bootstrap} -T {thread} {model}"
+        CMD = f"iqtree -s {fasta} -B {bootstrap} -nt AUTO -ntmax {thread} {model}"
 
     logging.info(f"partition: {partition}")
     # Partitioned analysis cannot be used with memory option

{funvip-0.3.24.4 → funvip-0.3.24.6}/funvip/src/modeltest.py

@@ -1,6 +1,9 @@
 from funvip.src import ext
-import os, shutil, copy
+import os
+import shutil
+import copy
 import logging
+import multiprocessing as mp
 
 cmd_translator_modeltestng_fasttree = {
     "JC": "",
@@ -362,9 +365,9 @@ def modeltest(V, path, opt) -> dict:
     model_dict = copy.deepcopy(group_dict)
 
     # By group and by gene
-    for group in group_dict:
-        for gene in group_dict[group]:
-            if opt.method.modeltest.lower() == "modeltest-ng":
+    if opt.method.modeltest.lower() == "modeltest-ng":
+        for group in group_dict:
+            for gene in group_dict[group]:
                 # As modeltest-ng shows only top 10 results,
                 # we should reduce number of models to prevent none of the model fits
                 if opt.method.tree == "fasttree":
@@ -397,17 +400,41 @@ def modeltest(V, path, opt) -> dict:
                     path=path,
                     opt=opt,
                 )
-            elif opt.method.modeltest.lower() == "iqtree":
-                if not (opt.method.tree == "iqtree"):
-                    # Run IQTREE ModelFinder
-                    ext.ModelFinder(
-                        fasta=f"{path.out_alignment}/{opt.runname}_trimmed_{group}_{gene}.fasta",
-                        opt=opt,
-                        path=path,
-                        thread=opt.thread,
-                    )
+    # In case of IQTREE ModelFinder, for optimization, run it with multithreaded
+    elif opt.method.modeltest.lower() == "iqtree":
+        if not (opt.method.tree == "iqtree"):
+            if opt.verbose < 3:
+                modelfinder_opt = []
+                for group in group_dict:
+                    for gene in group_dict[group]:
+                        modelfinder_opt.append(
+                            (
+                                f"{path.out_alignment}/{opt.runname}_trimmed_{group}_{gene}.fasta",
+                                opt,
+                                path,
+                                1,
+                            )
+                        )
+
+                p = mp.Pool(opt.thread)
+                _ = p.starmap(ext.ModelFinder, modelfinder_opt)
+                p.close()
+                p.join()
+
+            else:  # non-multithreading mode for debugging
+                for group in group_dict:
+                    for gene in group_dict[group]:
+                        # Run IQTREE ModelFinder
+                        ext.ModelFinder(
+                            fasta=f"{path.out_alignment}/{opt.runname}_trimmed_{group}_{gene}.fasta",
+                            opt=opt,
+                            path=path,
+                            thread=opt.thread,
+                        )
 
-                    # Move modeltest result to appropriate location
+            # Move modeltest result to appropriate location
+            for group in group_dict:
+                for gene in group_dict[group]:
                     try:
                         shutil.move(
                             f"{path.out_alignment}/{opt.runname}_trimmed_{group}_{gene}.fasta.iqtree",
@@ -424,13 +451,15 @@ def modeltest(V, path, opt) -> dict:
                         path=path,
                         opt=opt,
                     )
-                else:
-                    logging.info(
-                        "IQTREE will perform ModelFinder internally in tree construction step, skipping in modeltest step"
-                    )
-                    model_dict[group][gene] = "skip"
+        else:
+            logging.info(
+                "IQTREE will perform ModelFinder internally in tree construction step, skipping in modeltest step"
+            )
+            model_dict[group][gene] = "skip"
 
-            else:  # including opt.model_method.lower() == "none":
+    else:  # including opt.model_method.lower() == "none":
+        for group in group_dict:
+            for gene in group_dict[group]:
                 if opt.method.tree == "raxml":
                     logging.info("Skipping modeltest. Using GTRGAMMA as default")
                     model_dict[group][gene] = "-m GTRGAMMA"

{funvip-0.3.24.4 → funvip-0.3.24.6}/funvip/src/search.py

@@ -359,8 +359,8 @@ def search_df(V, path, opt):
                 )
 
                 # Cutoff by outgroupcutoff
-                print(vars(opt))
-                print(opt.cluster.outgroupoffset)
+                # print(vars(opt))
+                # print(opt.cluster.outgroupoffset)
                 df_search = df_search[
                     df_search["bitscore"] > opt.cluster.outgroupoffset
                 ]

{funvip-0.3.24.4 → funvip-0.3.24.6}/funvip/src/tree.py

@@ -172,8 +172,7 @@ def pipe_tree(V, path, opt, model_dict):
             p.close()
             p.join()
 
-        else:
-            # non-multithreading mode for debugging
+        else:  # non-multithreading mode for debugging
             fasttree_result = []
             for option in fasttree_opt:
                 fasttree_result.append(ext.FastTree(*option))

{funvip-0.3.24.4 → funvip-0.3.24.6}/pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "FunVIP"
-version = "0.3.24.4"
+version = "0.3.24.6"
 description = "Fungal Validation & Identification Pipeline"
 authors = [{name = "Changwan Seo", email = "wan101010@snu.ac.kr"}]
 urls = { "Homepage" = "https://github.com/Changwanseo/FunVIP" }