tfclass-predict 1.1.2__tar.gz → 1.1.4__tar.gz

{tfclass_predict-1.1.2/src/tfclass_predict.egg-info → tfclass_predict-1.1.4}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tfclass_predict
-Version: 1.1.2
+Version: 1.1.4
 Summary: tfclass_predict allows to estimate transcription factor bindingsites in the TFClass hierarchy.
 Author-email: Christian Ickes <christian.ickes@med.uni-goettingen.de>, Hazal Timucin <hazal.timucin@med.uni-goettingen.de>
 Project-URL: Homepage, https://gitlab.gwdg.de/hti/tfclass_dnabert
@@ -23,6 +23,7 @@ Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: pyBigWig
 Requires-Dist: tf-keras
+Requires-Dist: tqdm
 Dynamic: license-file
 
 # TFClassPredict
@@ -53,7 +54,7 @@ Alternatively, the human genome (v38) and the TFClassPredict (TFCP) model can be
 
 [HG38](http://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz) from UCSC
 
-[TFCP_model](https://owncloud.gwdg.de/index.php/s/kUqk2XXaC8bh8HM)
+[TFCP_model](https://owncloud.gwdg.de/index.php/s/QqfAJqcRYbnA5VZ)
 
 All downloads need to be **unzipped** so that the path to `TFCP_precompiled` directory or the path to the `hg38.fa` file and directory `TFCP_model` can be passed to the command-line tool or `PredictionManager`.
 

{tfclass_predict-1.1.2 → tfclass_predict-1.1.4}/README.md

@@ -26,7 +26,7 @@ Alternatively, the human genome (v38) and the TFClassPredict (TFCP) model can be
 
 [HG38](http://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz) from UCSC
 
-[TFCP_model](https://owncloud.gwdg.de/index.php/s/kUqk2XXaC8bh8HM)
+[TFCP_model](https://owncloud.gwdg.de/index.php/s/QqfAJqcRYbnA5VZ)
 
 All downloads need to be **unzipped** so that the path to `TFCP_precompiled` directory or the path to the `hg38.fa` file and directory `TFCP_model` can be passed to the command-line tool or `PredictionManager`.
 

{tfclass_predict-1.1.2 → tfclass_predict-1.1.4}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "tfclass_predict"
-version = "1.1.2"
+version = "1.1.4"
 authors = [
     { name="Christian Ickes", email="christian.ickes@med.uni-goettingen.de" },
     { name="Hazal Timucin", email="hazal.timucin@med.uni-goettingen.de" },
@@ -31,7 +31,8 @@ dependencies = [
     "numpy",
     "pandas",
     "pyBigWig",
-    "tf-keras"
+    "tf-keras",
+    "tqdm"
 ]
 
 [project.urls]

{tfclass_predict-1.1.2 → tfclass_predict-1.1.4}/src/tfclass_predict/predictor.py

@@ -4,7 +4,7 @@ import numpy as np
 import pyBigWig as pbw
 import pandas as pd
 import os
-
+from tqdm import tqdm
 from .constants import MODELNAME, THRESHOLDS, TOKENIZERFOLDERNAME, K, CLASSMAPPING, WINDOWSIZE, BATCHSIZE
 from .sequence_processor import SequenceProcessor
 
@@ -78,7 +78,6 @@ class PredictorTFCPModel(Predictor):
         count_df = pd.DataFrame(count_mat.astype(int), columns=self.classmapping["Class"])
         return count_df
 
-# Currently under development 
 class PredictorPrecompiled(Predictor):
     """ Predictor class takes care about the prediction / model execution using the hg38 precompiled set"""
     def __init__(self, bed:pd.DataFrame, precompiled_file_path:str):
@@ -93,14 +92,15 @@ class PredictorPrecompiled(Predictor):
         count_mat = np.zeros(((end-start-WINDOWSIZE+1), len(self.tfbs_files)))
         for idx, tfclass_file in enumerate(self.tfbs_files):
             bb = pbw.open(tfclass_file)
-            print("Processing: {}".format(self.tfbs_files[idx].split(os.sep)[-1]))
-            if (end) < bb.chroms(chrom): # interval must be completely included
-                entries = bb.entries(chrom, start, end)
-                if entries:
-                    for entry in entries: 
-                        if entry[0] >= start and entry[1] <= end: # only fully included intervals
-                            i = entry[0]-start
-                            count_mat[i, idx] += 1
+            if (end) > bb.chroms(chrom): # interval must be completely included
+                end = bb.chroms(chrom)
+                
+            entries = bb.entries(chrom, start, end)
+            if entries:
+                for entry in entries: 
+                    if entry[0] >= start and entry[1] <= end: # only fully included intervals
+                        i = entry[0]-start
+                        count_mat[i, idx] += 1
         count_vec = np.sum(count_mat, axis=0)
         return count_vec
 
@@ -111,9 +111,13 @@ class PredictorPrecompiled(Predictor):
         :return: DataFrame of predicted TFBSs per region in BED file.
         """
 
+        print("Processing using precompiled data set!")
         count_mat = np.zeros((self.bed.shape[0], len(self.tfbs_files)))
-        for idx, row in self.bed.iterrows():
-            count_mat[idx, :] = self._predict_precompiled(row["chr"], row["start"], row["end"])
+
+        with tqdm(total=self.bed.shape[0], ncols=50) as pbar: 
+            for idx, row in self.bed.iterrows():
+                count_mat[idx, :] = self._predict_precompiled(row["chr"], row["start"], row["end"])
+                pbar.update(1)
         
         count_df = pd.DataFrame(count_mat.astype(int), columns=self.classmapping["Class"])
         return count_df

{tfclass_predict-1.1.2 → tfclass_predict-1.1.4/src/tfclass_predict.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: tfclass_predict
-Version: 1.1.2
+Version: 1.1.4
 Summary: tfclass_predict allows to estimate transcription factor bindingsites in the TFClass hierarchy.
 Author-email: Christian Ickes <christian.ickes@med.uni-goettingen.de>, Hazal Timucin <hazal.timucin@med.uni-goettingen.de>
 Project-URL: Homepage, https://gitlab.gwdg.de/hti/tfclass_dnabert
@@ -23,6 +23,7 @@ Requires-Dist: numpy
 Requires-Dist: pandas
 Requires-Dist: pyBigWig
 Requires-Dist: tf-keras
+Requires-Dist: tqdm
 Dynamic: license-file
 
 # TFClassPredict
@@ -53,7 +54,7 @@ Alternatively, the human genome (v38) and the TFClassPredict (TFCP) model can be
 
 [HG38](http://hgdownload.soe.ucsc.edu/goldenPath/hg38/bigZips/hg38.fa.gz) from UCSC
 
-[TFCP_model](https://owncloud.gwdg.de/index.php/s/kUqk2XXaC8bh8HM)
+[TFCP_model](https://owncloud.gwdg.de/index.php/s/QqfAJqcRYbnA5VZ)
 
 All downloads need to be **unzipped** so that the path to `TFCP_precompiled` directory or the path to the `hg38.fa` file and directory `TFCP_model` can be passed to the command-line tool or `PredictionManager`.
 

{tfclass_predict-1.1.2 → tfclass_predict-1.1.4}/src/tfclass_predict.egg-info/requires.txt

@@ -5,3 +5,4 @@ numpy
 pandas
 pyBigWig
 tf-keras
+tqdm