Merge pull request #131 from rigdenlab/development

Version update

CHANGELOG.rst

@@ -2,6 +2,22 @@ Changelog
 =========
 
 
+0.4
+-----
+
+Added
+~~~~~
+- Added contact density, sequence hydrophobicity and MSA coverage tracks
+- Added support for trRosetta NPZ and MapPred residue distance formats
+- Added support of residue distance superposition
+
+Changed
+~~~~~
+- New heatmap color palette
+- Changed to vertical layout for verbose labels and increased verbosity
+- Parse PDB files as a residue distance format file
+
+
 0.3.2
 -----
 

app.py

@@ -6,7 +6,7 @@
 import logging
 import keydb
 import psycopg2
-from utils import callback_utils, data_utils, session_utils, app_utils, keydb_utils, plot_utils, UrlIndex
+from utils import callback_utils, data_utils, session_utils, app_utils, keydb_utils, plot_utils, cache_utils, UrlIndex
 from dash.dash import no_update
 import dash_bootstrap_components as dbc
 from dash.dependencies import Input, Output, State, ALL, MATCH
@@ -327,6 +327,8 @@ def upload_sequence(fname, fcontent, session_id):
         return no_update, None, components.SessionTimedOutModal()
     elif not callback_utils.ensure_triggered(trigger):
         return callback_utils.retrieve_sequence_fname(session_id, cache), None, None
+    elif not cache_utils.is_valid_fname(fname):
+        return no_update, no_update, components.InvalidFnameModal(fname)
 
     return data_utils.upload_sequence(fname, fcontent, session_id, cache, app.logger)
 
@@ -347,6 +349,8 @@ def upload_contact(fname, fcontent, input_format, fname_alerts, session_id):
         return no_update, None, components.SessionTimedOutModal()
     elif not callback_utils.ensure_triggered(trigger):
         return callback_utils.retrieve_contact_fnames(session_id, cache), None, None
+    elif not cache_utils.is_valid_fname(fname):
+        return no_update, no_update, components.InvalidFnameModal(fname)
 
     return data_utils.upload_dataset(fname, fcontent, input_format, fname_alerts, session_id, cache, app.logger,
                                      dataset=loaders.DatasetReference.CONTACT_MAP.value)
@@ -409,7 +413,7 @@ def javascript_exe_button(n_clicks, session_id):
     else:
         app.logger.info('Fetching example data')
         try:
-            session_utils.load_session('user_1', 35, session_id, cache, app.logger)
+            session_utils.load_session('user_1', 46, session_id, cache, app.logger)
         except (psycopg2.OperationalError, AttributeError) as e:
             app.logger.error('Unable to fetch example data: {}'.format(e))
             return no_update, components.ExampleSessionConnectionErrorModal(), no_update
@@ -450,8 +454,6 @@ def create_ConPlot(plot_click, refresh_click, factor, contact_marker_size, track
     if any([True for x in (factor, contact_marker_size, track_marker_size, track_separation) if x is None or x < 0]):
         app.logger.info('Session {} invalid display control value detected'.format(session_id))
         return no_update, components.InvalidInputModal(), no_update, no_update
-    elif superimpose and distance_matrix:
-        return no_update, components.InvalidSuperposeDistanceMatrixModal(), no_update, no_update
     elif superimpose and ('---' in cmap_selection or len(set(cmap_selection)) == 1):
         return no_update, components.InvalidMapSelectionModal(), no_update, no_update
 

components/__init__.py

@@ -3,11 +3,14 @@
 
 class UserReadableTrackNames(Enum):
     membranetopology = 'Membrane Topology'
+    msa = 'MSA Coverage'
     secondarystructure = 'Secondary Structure'
     disorder = 'Seq. Disorder'
     conservation = 'Seq. Conservation'
     custom = 'Custom Tracks'
     heatmap = 'Heatmap'
+    hydrophobicity = 'Hydrophobicity'
+    density = 'Contact density'
 
 
 class EmailIssueReference(Enum):
@@ -28,16 +31,21 @@ def SessionStoreModal(*args, **kwargs):
     return SessionStoreModal(*args, **kwargs)
 
 
+def InvalidFnameModal(*args, **kwargs):
+    from components.modals import InvalidFnameModal
+    return InvalidFnameModal(*args, **kwargs)
+
+
 def ExampleSessionConnectionErrorModal(*args, **kwargs):
     from components.modals import ExampleSessionConnectionErrorModal
 
     return ExampleSessionConnectionErrorModal(*args, **kwargs)
 
 
-def InvalidSuperposeDistanceMatrixModal(*args, **kwargs):
-    from components.modals import InvalidSuperposeDistanceMatrixModal
+def InvalidSuperposeHeatmapModal(*args, **kwargs):
+    from components.modals import InvalidSuperposeHeatmapModal
 
-    return InvalidSuperposeDistanceMatrixModal(*args, **kwargs)
+    return InvalidSuperposeHeatmapModal(*args, **kwargs)
 
 
 def GdprPolicySectionOne(*args, **kwargs):

components/cards.py

@@ -308,17 +308,23 @@ def DisplayControlCard(available_tracks=None, selected_tracks=None, selected_cma
                             html.H5("Colour palettes", className="card-text", style={'text-align': "center"}),
                             html.Hr(),
                             html.Br(),
-                            ColorPaletteSelectionCard('membranetopology', selected_palettes[0]),
+                            ColorPaletteSelectionCard('density', selected_palettes[0]),
                             html.Br(),
-                            ColorPaletteSelectionCard('secondarystructure', selected_palettes[1]),
+                            ColorPaletteSelectionCard('custom', selected_palettes[1]),
                             html.Br(),
-                            ColorPaletteSelectionCard('disorder', selected_palettes[2]),
+                            ColorPaletteSelectionCard('heatmap', selected_palettes[2]),
                             html.Br(),
-                            ColorPaletteSelectionCard('conservation', selected_palettes[3]),
+                            ColorPaletteSelectionCard('hydrophobicity', selected_palettes[3]),
                             html.Br(),
-                            ColorPaletteSelectionCard('custom', selected_palettes[4]),
+                            ColorPaletteSelectionCard('membranetopology', selected_palettes[4]),
                             html.Br(),
-                            ColorPaletteSelectionCard('heatmap', selected_palettes[5]),
+                            ColorPaletteSelectionCard('msa', selected_palettes[5]),
+                            html.Br(),
+                            ColorPaletteSelectionCard('conservation', selected_palettes[6]),
+                            html.Br(),
+                            ColorPaletteSelectionCard('disorder', selected_palettes[7]),
+                            html.Br(),
+                            ColorPaletteSelectionCard('secondarystructure', selected_palettes[8]),
                             html.Br(),
                         ])
                     ]

components/inputgroups.py

@@ -3,7 +3,7 @@
 from loaders import AdditionalDatasetReference
 from parsers import ContactMapFormats, StructuralInformationFormats, DistanceInformationFormats
 from components import EmailIssueReference, UserReadableTrackNames
-from utils.plot_utils import PaletteDefaultLayout
+from utils.color_palettes import PaletteDefaultLayout
 from utils import UrlIndex
 
 

components/listgrpoups.py

@@ -94,7 +94,7 @@ def TutorialList():
             TutorialItem(idx=2, name='Compare a contact prediction with a PDB file'),
             TutorialItem(idx=3, name='Storing, loading and sharing a session'),
             TutorialItem(idx=4, name='Residue-Residue distance predictions'),
-            #TutorialItem(idx=5, name='Video tutorial')
+            # TutorialItem(idx=5, name='Video tutorial')
         ], style={'width': '75%'}
         ), justify='center', align='center')
 
@@ -397,9 +397,12 @@ def MandatoryInputHelpList():
                  html.Ul([
                      html.Li(['Residue Distance Prediction: these files contain information about real value distances '
                               'between residue pairs, and are rapidly replacing contact prediction maps in protein '
-                              'structure prediction pipelines. ConPlot currently supports CASP RR MODE 2 format, the '
-                              'specifications for this format can be found ',
-                              html.A(html.U('here'), href=UrlIndex.CASP14_RRFORMAT.value), '.']),
+                              'structure prediction pipelines. ConPlot currently supports three formats: CASP RR MODE '
+                              '2 format (read more ', html.A(html.U('here'), href=UrlIndex.CASP14_RRFORMAT.value),
+                              '), MapPred output files (get them ',
+                              html.A(html.U('here'), href=UrlIndex.MAPPRED_SERVER.value),
+                              ') and trRosetta npz files (get them ',
+                              html.A(html.U('here'), href=UrlIndex.TRROSETTA_SERVER.value), ').']),
                      html.Li(['Contact Maps: There are many formats used for such files, but ConPlot is able to parse '
                               'the most common ones. If you wish to upload a contact map file in a format not '
                               'supported by ConPlot, we suggest you take a look at ',
@@ -488,11 +491,14 @@ def PaletteItem(idx, name):
 def PaletteList():
     return dbc.Row(
         dbc.ListGroup([
-            PaletteItem(idx=1, name='Conservation'),
-            PaletteItem(idx=2, name='Custom files'),
-            PaletteItem(idx=3, name='Disorder'),
-            PaletteItem(idx=4, name='Membrane Topology'),
-            PaletteItem(idx=5, name='Secondary Structure'),
-            PaletteItem(idx=6, name='Heatmap')
+            PaletteItem(idx=1, name='Contact Density'),
+            PaletteItem(idx=2, name='Conservation'),
+            PaletteItem(idx=3, name='Custom files'),
+            PaletteItem(idx=4, name='Disorder'),
+            PaletteItem(idx=5, name='Membrane Topology'),
+            PaletteItem(idx=6, name='MSA Coverage'),
+            PaletteItem(idx=7, name='Secondary Structure'),
+            PaletteItem(idx=8, name='Hydrophobicity'),
+            PaletteItem(idx=9, name='Heatmap'),
         ], style={'width': '75%'}
         ), justify='center', align='center')

components/modals.py

@@ -60,12 +60,12 @@ def InvalidMapSelectionModal():
     ], id='invalid-map-selection-modal', is_open=True)
 
 
-def InvalidSuperposeDistanceMatrixModal():
+def InvalidSuperposeHeatmapModal():
     return dbc.Modal([
         ModalHeader("Invalid Input"),
         dbc.ModalBody([
-            html.P("""Superposition of heatmaps is not supported yet!""",
-                   style={'text-align': "justify"})
+            html.P("""Superposition of residue contact predictions is not supported while the heatmap mode is 
+            activated.""", style={'text-align': "justify"})
         ]),
     ], id='invalid-map-selection-modal', is_open=True)
 
@@ -101,6 +101,16 @@ def InvalidInputModal():
     ], id='invalid-input-modal', is_open=True)
 
 
+def InvalidFnameModal(fname):
+    return dbc.Modal([
+        ModalHeader("Invalid file name"),
+        dbc.ModalBody(
+            html.P("""Sorry but we cannot process files named '{}'. You will need to rename your file.""".format(fname),
+                   style={'text-align': "justify"})
+        ),
+    ], id='invalid-fname-modal', is_open=True)
+
+
 def SessionTimedOutModal():
     return dbc.Modal([
         ModalHeader("Session timed-out"),

layouts/help.py

@@ -10,12 +10,15 @@ def Body(cache):
             html.Br(),
             html.Br(),
             html.Br(),
-            components.PaletteModal('conservation', 1),
-            components.PaletteModal('custom', 2),
-            components.PaletteModal('disorder', 3),
-            components.PaletteModal('membranetopology', 4),
-            components.PaletteModal('secondarystructure', 5),
-            components.PaletteModal('heatmap', 6),
+            components.PaletteModal('density', 1),
+            components.PaletteModal('conservation', 2),
+            components.PaletteModal('custom', 3),
+            components.PaletteModal('disorder', 4),
+            components.PaletteModal('membranetopology', 5),
+            components.PaletteModal('msa', 6),
+            components.PaletteModal('secondarystructure', 7),
+            components.PaletteModal('hydrophobicity', 8),
+            components.PaletteModal('heatmap', 9),
             components.GdprPolicyModal(),
             components.TutorialOneModal(),
             components.TutorialTwoModal(),

loaders/__init__.py

@@ -1,30 +1,50 @@
 from enum import Enum
 import base64
+from parsers import HydrophobicityStates
 
 
 class DatasetReference(Enum):
     SEQUENCE = 'sequence'
+    HYDROPHOBICITY = 'hydrophobicity'
     CONTACT_MAP = 'contact'
+    CONTACT_DENSITY = 'density'
     MEMBRANE_TOPOLOGY = 'membranetopology'
     SECONDARY_STRUCTURE = 'secondarystructure'
     CONSERVATION = 'conservation'
     DISORDER = 'disorder'
     CUSTOM = 'custom'
+    MSA = 'msa'
 
     @classmethod
     def exclude_seq(cls):
         for item in cls:
-            if item.value != 'sequence':
+            if item.value != 'sequence' and item.value != 'hydrophobicity':
                 yield item
 
 
 class AdditionalDatasetReference(Enum):
+    A3M = DatasetReference.MSA.value
     TOPCONS = DatasetReference.MEMBRANE_TOPOLOGY.value
     PSIPRED = DatasetReference.SECONDARY_STRUCTURE.value
     IUPRED = DatasetReference.DISORDER.value
     CONSURF = DatasetReference.CONSERVATION.value
     CUSTOM = DatasetReference.CUSTOM.value
 
+    @classmethod
+    def include_hydrophobicity(cls):
+        new_enum = Enum('AdditionalDatasetReference', {
+            'A3M': DatasetReference.MSA.value,
+            'TOPCONS': DatasetReference.MEMBRANE_TOPOLOGY.value,
+            'PSIPRED': DatasetReference.SECONDARY_STRUCTURE.value,
+            'IUPRED': DatasetReference.DISORDER.value,
+            'CONSURF': DatasetReference.CONSERVATION.value,
+            'CUSTOM': DatasetReference.CUSTOM.value,
+            'HYDROPHOBICITY': DatasetReference.HYDROPHOBICITY.value
+        })
+
+        for item in new_enum:
+            yield item
+
 
 def decode_raw_file(raw_file):
     content_type, content_string = raw_file.split(',')
@@ -43,3 +63,84 @@ def SequenceLoader(*args, **kwargs):
     from loaders.sequenceloader import SequenceLoader
 
     return SequenceLoader(*args, **kwargs)
+
+
+STATES = {
+    DatasetReference.MEMBRANE_TOPOLOGY.value: {
+        1: 'INSIDE',
+        2: 'OUTSIDE',
+        3: 'INSERTED'
+    },
+    DatasetReference.CONSERVATION.value: {
+        1: 'VARIABLE_1',
+        2: 'VARIABLE_2',
+        3: 'VARIABLE_3',
+        4: 'AVERAGE_4',
+        5: 'AVERAGE_5',
+        6: 'AVERAGE_6',
+        7: 'CONSERVED_7',
+        8: 'CONSERVED_8',
+        9: 'CONSERVED_9'
+    },
+    DatasetReference.CUSTOM.value: {
+        1: 'CUSTOM_1',
+        2: 'CUSTOM_2',
+        3: 'CUSTOM_3',
+        4: 'CUSTOM_4',
+        5: 'CUSTOM_5',
+        6: 'CUSTOM_6',
+        7: 'CUSTOM_7',
+        8: 'CUSTOM_8',
+        9: 'CUSTOM_9',
+        10: 'CUSTOM_10',
+        11: 'CUSTOM_11',
+        'NAN': 'CUSTOM_NAN'
+    },
+    DatasetReference.DISORDER.value: {
+        1: 'DISORDER',
+        2: 'ORDER'
+    },
+    DatasetReference.SECONDARY_STRUCTURE.value: {
+        1: 'HELIX',
+        2: 'COIL',
+        3: 'SHEET'
+    },
+    DatasetReference.HYDROPHOBICITY.value: {
+        0: 'HYDROPATHY_0',
+        1: 'HYDROPATHY_1',
+        2: 'HYDROPATHY_2',
+        3: 'HYDROPATHY_3',
+        4: 'HYDROPATHY_4',
+        5: 'HYDROPATHY_5',
+        6: 'HYDROPATHY_6',
+        7: 'HYDROPATHY_7',
+        8: 'HYDROPATHY_8',
+        9: 'HYDROPATHY_9',
+        10: 'HYDROPATHY_10'},
+    DatasetReference.CONTACT_DENSITY.value: {
+        0: 'CONTACT_DENSITY_0',
+        1: 'CONTACT_DENSITY_1',
+        2: 'CONTACT_DENSITY_2',
+        3: 'CONTACT_DENSITY_3',
+        4: 'CONTACT_DENSITY_4',
+        5: 'CONTACT_DENSITY_5',
+        6: 'CONTACT_DENSITY_6',
+        7: 'CONTACT_DENSITY_7',
+        8: 'CONTACT_DENSITY_8',
+        9: 'CONTACT_DENSITY_9',
+        10: 'CONTACT_DENSITY_10',
+    },
+    DatasetReference.MSA.value: {
+        0: 'MSA_COVERAGE_0',
+        1: 'MSA_COVERAGE_1',
+        2: 'MSA_COVERAGE_2',
+        3: 'MSA_COVERAGE_3',
+        4: 'MSA_COVERAGE_4',
+        5: 'MSA_COVERAGE_5',
+        6: 'MSA_COVERAGE_6',
+        7: 'MSA_COVERAGE_7',
+        8: 'MSA_COVERAGE_8',
+        9: 'MSA_COVERAGE_9',
+        10: 'MSA_COVERAGE_10',
+    }
+}