Merge pull request #23 from MannLabs/development

fix tests

directlfq/dashboard_parts.py

@@ -148,19 +148,19 @@ def __init__(self):
         self.path_protein_groups_file = pn.widgets.TextInput(
             name='(optional) If you are using MaxQuant evidence.txt or peptides.txt files, you can add the link to the corresponding proteinGroups.txt file (will improve peptide-to-protein mapping)',
             placeholder='(optional) Enter the whole path to the MaxQuant proteinGroups.txt file',
-            default = None,
+            value = None,
             width=900,
             sizing_mode='stretch_width',
             margin=(15, 15, 0, 15)
         )
 
         ## optional files
 
-        self.additional_headers_title = pn.pane.Markdown('* Add the names of columns that you want to keep in the directLFQ output file, separated by semicolons. Note that some basic additional columns such as gene names are always added to the output table by default.\nWARNING: Take care that columns you add are not ambigous. For example, adding the peptide sequence column will not work, because there are multiple peptide sequences per protein.')
+        self.additional_headers_title = pn.pane.Markdown('* Add the names of columns that you want to keep in the directLFQ output file, separated by semicolons. Note that some basic additional columns such as gene names are always added to the output table by value.\nWARNING: Take care that columns you add are not ambigous. For example, adding the peptide sequence column will not work, because there are multiple peptide sequences per protein.')
         self.additional_headers = pn.widgets.TextInput(
             name='',
             placeholder='(optional) Enter the names of columns that you want to keep',
-            default = None,
+            value = None,
             #width=900,
             #sizing_mode='stretch_width',
             #margin=(15, 15, 0, 15)
@@ -169,7 +169,7 @@ def __init__(self):
         self.protein_subset_for_normalization_title = pn.pane.Markdown('* Specify a list of proteins (no header, seperated by linebreaks) that you want to use for normalization. This could for example be a list of housekeeping proteins:')
         self.protein_subset_for_normalization_file = pn.widgets.TextInput(
             name='',
-            default = None,
+            value = None,
             placeholder='(optional) Enter the whole path to the protein list file',
             width=900,
             sizing_mode='stretch_width',
@@ -179,7 +179,7 @@ def __init__(self):
         self.yaml_filt_dict_title = pn.pane.Markdown('* In case you want to define specific filters in addition to the standard filters, you can add a yaml file where the filters are defined (see GitHub docs).')
         self.yaml_filt_dict_path = pn.widgets.TextInput(
             name='',
-            default = None,
+            value = None,
             placeholder='(optional) Enter the whole path to the yaml file with the filters',
             width=900,
             sizing_mode='stretch_width',

directlfq/test_utils.py

@@ -0,0 +1,60 @@
+import numpy as np
+import pandas as pd
+
+from  numpy.random import MT19937
+from numpy.random import RandomState, SeedSequence
+
+class ProteinProfileGenerator():
+    def __init__(self, peptide_profiles):
+        self._peptide_profiles = peptide_profiles
+
+        self.protein_profile_dataframe = None
+        self._generate_protein_profile_dataframe()
+
+    def _generate_protein_profile_dataframe(self):
+        collected_profiles = [x.peptide_profile_vector for x in self._peptide_profiles]
+        protnames_for_index = [x.protein_name for x in self._peptide_profiles]
+        pepnames_for_index = [f'{idx}' for idx in range(len(self._peptide_profiles))]
+        self.protein_profile_dataframe = pd.DataFrame(collected_profiles,index=[protnames_for_index, pepnames_for_index])
+        self.protein_profile_dataframe.index.names = ['protein', 'ion']
+        self.protein_profile_dataframe = np.log2(self.protein_profile_dataframe.replace(0, np.nan))
+
+
+
+class PeptideProfile():
+    def __init__(self, protein_name, fraction_zeros_in_profile, systematic_peptide_shift, add_noise, num_samples = 20, min_intensity = 1e6, max_intensity = 1e10):
+
+
+        self._fraction_zeros_in_profile = fraction_zeros_in_profile
+        self._systematic_peptide_shift = systematic_peptide_shift
+        self._add_noise = add_noise
+        self._min_intensity = min_intensity
+        self._max_intensity = max_intensity
+        self._num_samples = num_samples
+
+        self.protein_name = protein_name
+        self.peptide_profile_vector = []
+        self._define_peptide_profile_vector()
+
+    def _define_peptide_profile_vector(self):
+        self.peptide_profile_vector = self._get_single_peptide_profile_template()
+        self._scale_profile_vector()
+        if self._add_noise:
+            self._apply_poisson_noise_to_profilevector()
+        self._add_zeros_to_profilevector()
+
+    def _get_single_peptide_profile_template(self):
+        rs = RandomState(MT19937(SeedSequence(42312)))
+        return rs.randint(low=self._min_intensity, high=self._max_intensity,size=self._num_samples)
+
+    def _scale_profile_vector(self):
+        self.peptide_profile_vector = self.peptide_profile_vector*self._systematic_peptide_shift
+
+    def _apply_poisson_noise_to_profilevector(self):
+        self.peptide_profile_vector = np.random.poisson(lam=self.peptide_profile_vector, size=len(self.peptide_profile_vector))
+
+    def _add_zeros_to_profilevector(self):
+        num_elements_to_set_zero = int(self._num_samples*self._fraction_zeros_in_profile)
+        idxs_to_set_zero = np.random.choice(self._num_samples,size=num_elements_to_set_zero, replace=False)
+        self.peptide_profile_vector[idxs_to_set_zero] = 0
+

misc/loose_pip_install.sh

@@ -1,5 +1,5 @@
 conda create -n directlfq python=3.8 -y
 conda activate directlfq
-pip install -e '../.[development, gui]'
+pip install -e '../.[development-stable, gui]'
 directlfq
 conda deactivate