Merge pull request #127 from rigdenlab/development

FilomenoSanchez · web-flow · commit da508e235ac1 · 2021-02-11T10:49:42.000Z
Minor update
diff --git a/.docker/Dockerfile b/.docker/Dockerfile
@@ -1,9 +1,9 @@
-FROM centos:8 AS build
+FROM fedora:33 AS build
 RUN dnf update -y
 RUN dnf install curl gcc initscripts postgresql-server postgresql-contrib python3-devel python3-pip redis systemd  -y
 RUN mkdir /opt/conplot
 RUN curl https://codeload.github.com/rigdenlab/conplot/tar.gz/master | tar zx -C /opt/conplot/
 WORKDIR /opt/conplot/conplot-master
-RUN python3.6 -m pip install --upgrade pip
-RUN python3.6 -m pip install gevent
-RUN python3.6 -m pip install -r requirements.txt
+RUN python3.9 -m pip install --upgrade pip
+RUN python3.9 -m pip install gevent
+RUN python3.9 -m pip install -r requirements.txt
diff --git a/.github/workflows/main.yml b/.github/workflows/main.yml
@@ -23,17 +23,23 @@ jobs:
     steps:
       - name: Checkout repository
         uses: actions/checkout@v1
-      - name: Set up Python3.6 x64
+      - name: Set up Python3.9 x64
         uses: actions/setup-python@v1
         with:
-          python-version: 3.6
+          python-version: 3.9
           architecture: 'x64'
       - name: Install dependencies
         run: |
           python -m pip install --upgrade pip
           pip install -r requirements.txt
           pip install docker-py
+      - name: Start Redis Server
+        uses: supercharge/redis-github-action@1.2.0
+        with:
+          redis-version: 5
       - name: Run tests.py
+        env:
+          KEYDB_URL: $ {{ secrets.KEYDB_URL }}
         run: |
           python tests.py
   job_build:
diff --git a/CHANGELOG.rst b/CHANGELOG.rst
@@ -2,6 +2,21 @@ Changelog
 =========
 
 
+0.3.2
+-----
+
+Added
+~~~~~
+- Citation on home page
+- Added more exhaustive tests
+
+Changed
+~~~~~
+- Account recovery is automated: users will receive an automated email with instructions to reset password
+- Docker image now deployed on fedora 33 instead of CentOS 8
+- Users can upload both VFORMAT and HFORMAT psipred files instead of only VFORMAT
+
+
 0.3.1
 -----
 
diff --git a/README.md b/README.md
@@ -3,6 +3,7 @@
 [![Actions Status](https://github.com/rigdenlab/conplot/workflows/Test%20&%20Build/badge.svg)](https://github.com/rigdenlab/conplot/actions)
 [![Docker Automated build](https://img.shields.io/docker/automated/filosanrod/conplot)](https://hub.docker.com/r/filosanrod/conplot)
 [![RRID](https://img.shields.io/badge/RRID-SCR_019216-informational)](https://scicrunch.org/scicrunch/Resources/record/nlx_144509-1/SCR_019216/resolver)
+[![DOI](https://img.shields.io/badge/DOI-10.1093%2Fbioinformatics%2Fbtab049-blue.svg)](https://doi.org/10.1093/bioinformatics/btab049)
 
 ## About ConPlot
 
diff --git a/app.py b/app.py
@@ -43,7 +43,7 @@ def serve_layout():
         'routes_pathname_prefix': '/conplot/',
         'requests_pathname_prefix': '/conplot/',
     })
-keydb_pool = keydb_utils.create_pool()
+keydb_pool = keydb_utils.create_pool(os.environ.get('KEYDB_URL'))
 app.layout = serve_layout
 
 
diff --git a/components/listgrpoups.py b/components/listgrpoups.py
@@ -383,8 +383,8 @@ def PanelLayoutHelpList():
 
 def MandatoryInputHelpList():
     return html.Ul([
-        html.Li('FASTA file. This file should contain only one sequence, the one corresponding '
-                'with the structure of interest. If there are multiple sequences, ConPlot will '
+        html.Li('Sequence file. This should be a FASTA file containing only one sequence, the one '
+                'corresponding with the structure of interest. If there are multiple sequences, ConPlot will '
                 'only consider the first sequence present in the file. Please note that unlike '
                 'other types of input, only one sequence can be uploaded in each session at '
                 'any given time. If you want to upload a new sequence, that means you will '
diff --git a/components/modals.py b/components/modals.py
@@ -8,7 +8,7 @@ def MismatchModal(*args):
     return dbc.Modal([
         ModalHeader("Mismatch Detected"),
         dbc.ModalBody([
-            html.P("""We are having problems to match the uploaded sequence with the following prediction files. Please 
+            html.P("""We were unable to match the uploaded sequence with the following prediction files. Please 
                 ensure that these predictions correspond with the protein sequence in the uploaded FASTA file.""",
                    style={'text-align': "justify"}),
             html.Ul([html.Li('%s' % arg) for arg in args], id='mismatched-fnames-div')
@@ -20,7 +20,7 @@ def MismatchSequenceModal(*args):
     return dbc.Modal([
         ModalHeader("Sequence Mismatch"),
         dbc.ModalBody([
-            html.P("""We are having problems to match the uploaded sequence with contact maps in the following files. 
+            html.P("""We were unable to match the uploaded sequence with contact maps in the following files. 
             Please ensure that the provided the sequence corresponds with the structure in these contact maps.""",
                    style={'text-align': "justify"}),
             html.Ul([html.Li('File: %s' % arg) for arg in args], id='mismatched-maps-div')
@@ -112,7 +112,7 @@ def InvalidFormatModal():
             html.P("""The file you just attempted to upload does not comply with the file format guidelines. Make sure 
             that you are uploading the correct file and you have selected the correct format. If you are not sure about 
             how the file format looks like, you can read about each format on our help page. If you are sure that the 
-            format of your file is correct, please report the bug on the 'Contact' tab.""",
+            format of your file is correct, please report the bug on the 'Get in touch with us' tab.""",
                    style={'text-align': "justify"})
         ),
     ], id='invalid-input-modal', is_open=True)
diff --git a/layouts/help.py b/layouts/help.py
@@ -120,12 +120,6 @@ def Body(cache):
                                 'TIPS:',
                                 html.Ul([
                                     html.Br(),
-                                    html.Li(['PSIPRED server produces two output files that contain the same '
-                                             'information, but using different formats: a ',
-                                             html.I('.ss2'), ' file and a ', html.I('.horiz'),
-                                             ' file. ConPlot is only compatible with the ', html.I('ss2'),
-                                             ' format file, please do not attempt to uploade the ', html.I('.horiz'),
-                                             ' file.']),
                                     html.Li('You will not be able to upload a file until you first select its format '
                                             'in the dropdown selection menu.'),
                                     html.Li(['You can only upload one file at a time when you use the ',
diff --git a/layouts/home.py b/layouts/home.py
@@ -82,6 +82,19 @@ def Body():
                                 dbc.CardLink(html.U('help page'), href=UrlIndex.HELP.value),
                                 ' to read about how to use ConPlot and take advantage of its full potential!'
                             ], style={"font-size": "120%", "text-align": "justify"}),
+                            html.Br(),
+                            html.Br(),
+                            html.H4('Cite us', className="card-text", style={'text-align': "center"}),
+                            html.Hr(),
+                            html.Br(),
+                            html.P('If you found ConPlot useful for your work and you would like to cite us '
+                                   'please use the following reference:',
+                                   style={"font-size": "120%", "text-align": "justify"}),
+                            html.I('Sánchez Rodríguez, et al., ConPlot: Web-based application for the visualisation '
+                                   'of protein contact maps integrated with other data, Bioinformatics, 2021.',
+                                   style={"font-size": "120%", "text-align": "justify"}),
+                            html.Br(),
+                            html.A(html.I(html.U('DOI: 10.1093/bioinformatics/btab049')), href=UrlIndex.CITATION.value)
                         ]),
                     ]),
                 ], width=10)
diff --git a/loaders/tests/test_sequenceloader.py b/loaders/tests/test_sequenceloader.py
@@ -51,7 +51,7 @@ def test_2(self):
         self.assertIsNone(hydro_data)
         self.assertTrue(invalid)
 
-    def test_6(self):
+    def test_3(self):
         expected = [0.33, 0.22, 0.5, 0.12, -0.58, 1.14, -0.06, -0.81, 1.81, -0.69, -0.44, 0.43, -0.31, 0.19, 1.0, 0.33,
                     0.11, -0.53, -0.24, 0.23]
         seq = protein.letters
diff --git a/parsers/__init__.py b/parsers/__init__.py
@@ -7,6 +7,24 @@ def ConsurfParser(*args, **kwargs):
     return ConsurfParser(*args, **kwargs)
 
 
+def Ss2Parser(*args, **kwargs):
+    from parsers.ss2parser import Ss2Parser
+
+    return Ss2Parser(*args, **kwargs)
+
+
+def HorizParser(*args, **kwargs):
+    from parsers.horizparser import HorizParser
+
+    return HorizParser(*args, **kwargs)
+
+
+def guess_psipred_format(*args, **kwargs):
+    from parsers.psipredparser import guess_psipred_format
+
+    return guess_psipred_format(*args, **kwargs)
+
+
 def DistogramParser(*args, **kwargs):
     from parsers.distogramparser import DistogramParser
 
diff --git a/parsers/horizparser.py b/parsers/horizparser.py
@@ -0,0 +1,24 @@
+from parsers import SecondaryStructureStates
+from utils.exceptions import InvalidFormat
+
+
+def HorizParser(contents):
+    output = []
+
+    for line in contents:
+        if 'Pred: ' in line and line[0] != '#':
+            prediction = line.split()[-1]
+            for residue in prediction:
+                if residue == 'H':
+                    output.append(SecondaryStructureStates.HELIX.value)
+                elif residue == 'C':
+                    output.append(SecondaryStructureStates.COIL.value)
+                elif residue == 'E':
+                    output.append(SecondaryStructureStates.SHEET.value)
+                else:
+                    raise InvalidFormat('Invalid secondary structure element {}'.format(residue))
+
+    if not output:
+        raise InvalidFormat('Unable to parse prediction in psipred file')
+    else:
+        return output
diff --git a/parsers/psipredparser.py b/parsers/psipredparser.py
@@ -1,25 +1,18 @@
-from parsers import SecondaryStructureStates
+from parsers import HorizParser, Ss2Parser
 from utils.exceptions import InvalidFormat
 
 
-def PsipredParser(input):
-    contents = input.split('\n')
-    output = []
-
+def guess_psipred_format(contents):
     for line in contents:
-        line = line.split()
-        if len(line) != 6 or line[0] == '#':
-            continue
-        elif line[2] == 'H':
-            output.append(SecondaryStructureStates.HELIX.value)
-        elif line[2] == 'C':
-            output.append(SecondaryStructureStates.COIL.value)
-        elif line[2] == 'E':
-            output.append(SecondaryStructureStates.SHEET.value)
-        else:
-            raise InvalidFormat('Invalid secondary structure element {}'.format(line[2]))
+        if '# PSIPRED VFORMAT' in line:
+            return Ss2Parser
+        elif '# PSIPRED HFORMAT' in line:
+            return HorizParser
+
+    raise InvalidFormat('Unable to guess psipred file format')
 
-    if not output:
-        raise InvalidFormat('Unable to parse prediction in psipred file')
-    else:
-        return output
+
+def PsipredParser(input):
+    contents = input.split('\n')
+    parser = guess_psipred_format(contents)
+    return parser(contents)
diff --git a/parsers/ss2parser.py b/parsers/ss2parser.py
@@ -0,0 +1,24 @@
+from parsers import SecondaryStructureStates
+from utils.exceptions import InvalidFormat
+
+
+def Ss2Parser(contents):
+    output = []
+
+    for line in contents:
+        line = line.split()
+        if len(line) != 6 or line[0] == '#':
+            continue
+        elif line[2] == 'H':
+            output.append(SecondaryStructureStates.HELIX.value)
+        elif line[2] == 'C':
+            output.append(SecondaryStructureStates.COIL.value)
+        elif line[2] == 'E':
+            output.append(SecondaryStructureStates.SHEET.value)
+        else:
+            raise InvalidFormat('Invalid secondary structure element {}'.format(line[2]))
+
+    if not output:
+        raise InvalidFormat('Unable to parse prediction in psipred file')
+    else:
+        return output
diff --git a/parsers/tests/test_ccmpredparser.py b/parsers/tests/test_ccmpredparser.py
@@ -26,7 +26,7 @@ def test_1(self):
                           0.33913296461105347, 0.27737972140312195, 0.26654472947120667]
 
         output = CCMpredParser(dummy_prediction)
-        self.assertEquals(15, len(output))
+        self.assertEqual(15, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
diff --git a/parsers/tests/test_consurfparser.py b/parsers/tests/test_consurfparser.py
@@ -69,7 +69,7 @@ def test_1(self):
                     8, 6, 4, 6, 8, 8, 4, 9, 6, 4, 9, 9, 9, 7, 8, 9, 9, 4]
 
         output = ConsurfParser(dummy_prediction)
-        self.assertEquals(37, len(output))
+        self.assertEqual(37, len(output))
         self.assertListEqual(expected, output)
 
     def test_2(self):
diff --git a/parsers/tests/test_contactparser.py b/parsers/tests/test_contactparser.py
@@ -56,7 +56,7 @@ def test_3(self):
 
         output = ContactParser(dummy_prediction, 'BBCONTACTS')
 
-        self.assertEquals(6, len(output))
+        self.assertEqual(6, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
@@ -79,7 +79,7 @@ def test_4(self):
         expected_score = [0, 0, 0, 0, 0, 0, 0, 0, 0, 0]
 
         output = ContactParser(dummy_prediction, 'COMSAT')
-        self.assertEquals(10, len(output))
+        self.assertEqual(10, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
@@ -102,7 +102,7 @@ def test_5(self):
                           0.9883262, 0.98828995]
 
         output = ContactParser(dummy_prediction, 'EVFOLD')
-        self.assertEquals(10, len(output))
+        self.assertEqual(10, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
@@ -125,7 +125,7 @@ def test_6(self):
                           0.9883262, 0.98828995]
 
         output = ContactParser(dummy_prediction, 'FLIB')
-        self.assertEquals(10, len(output))
+        self.assertEqual(10, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
@@ -148,7 +148,7 @@ def test_7(self):
                           0.9883262, 0.98828995]
 
         output = ContactParser(dummy_prediction, 'PCONS')
-        self.assertEquals(10, len(output))
+        self.assertEqual(10, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
@@ -171,7 +171,7 @@ def test_8(self):
                           0.9883262, 0.98828995]
 
         output = ContactParser(dummy_prediction, 'FREECONTACT')
-        self.assertEquals(10, len(output))
+        self.assertEqual(10, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
diff --git a/parsers/tests/test_customparser.py b/parsers/tests/test_customparser.py
@@ -21,7 +21,7 @@ def test_1(self):
                     5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 5, 3, 3, 'NAN', 8, 9, 'NAN', 1, 1, 1, 1, 'NAN']
 
         output = CustomParser(dummy_prediction)
-        self.assertEquals(46, len(output))
+        self.assertEqual(46, len(output))
         self.assertListEqual(expected, output)
 
     def test_2(self):
diff --git a/parsers/tests/test_distogramparser.py b/parsers/tests/test_distogramparser.py
@@ -35,7 +35,7 @@ def test_1(self):
 
         output = DistogramParser(dummy_prediction)
 
-        self.assertEquals('DISTO', output.pop(-1))
+        self.assertEqual('DISTO', output.pop(-1))
         self.assertEqual(12, len(output))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
diff --git a/parsers/tests/test_iupredparser.py b/parsers/tests/test_iupredparser.py
@@ -39,7 +39,7 @@ def test_1(self):
         ]
 
         output = IupredParser(dummy_prediction)
-        self.assertEquals(10, len(output))
+        self.assertEqual(10, len(output))
         self.assertListEqual(expected, output)
 
     def test_2(self):
diff --git a/parsers/tests/test_pdbparser.py b/parsers/tests/test_pdbparser.py
@@ -30,8 +30,8 @@ def test_1(self):
         expected_score = [0.934108, 0.920229]
 
         output = PDBParser(dummy_prediction)
-        self.assertEquals(3, len(output))
-        self.assertEquals('PDB', output.pop(-1))
+        self.assertEqual(3, len(output))
+        self.assertEqual('PDB', output.pop(-1))
         self.assertListEqual(expected_res1, [contact[0] for contact in output])
         self.assertListEqual(expected_res2, [contact[1] for contact in output])
         self.assertListEqual(expected_score, [contact[2] for contact in output])
diff --git a/parsers/tests/test_psipredparser.py b/parsers/tests/test_psipredparser.py
diff --git a/parsers/tests/test_topconsparser.py b/parsers/tests/test_topconsparser.py
diff --git a/utils/__init__.py b/utils/__init__.py
diff --git a/utils/cache_utils.py b/utils/cache_utils.py
diff --git a/utils/keydb_utils.py b/utils/keydb_utils.py
diff --git a/utils/tests/test_cache_utils.py b/utils/tests/test_cache_utils.py
diff --git a/utils/tests/test_keydb_utils.py b/utils/tests/test_keydb_utils.py
