Merge pull request #19 from rigdenlab/dev

Colour schemes changed

conkit/applications/Bbcontacts.py

@@ -23,6 +23,10 @@ class BbcontactsCommandLine(AbstractCommandline):
     contacts between beta-strands by detecting patterns in matrices of
     predicted couplings. bbcontacts can make use of a secondary structure
     assignment or a secondary structure prediction.
+    
+    .. [#] Andreani J., Söding J. (2015). bbcontacts: prediction of beta-strand
+       pairing from direct coupling patterns. Bioinformatics 31(11), 1729-1737.
+
 
     Examples
     --------
@@ -45,9 +49,6 @@ class BbcontactsCommandLine(AbstractCommandline):
     <https://github.com/soedinglab/bbcontacts>`_, download the latest version
     and install it using python setup.py install.
 
-    .. [#] Andreani J., Söding J. (2015). bbcontacts: prediction of beta-strand
-       pairing from direct coupling patterns. Bioinformatics 31(11), 1729-1737.
-
     """
 
     def __init__(self, cmd="bbcontacts", **kwargs):

conkit/applications/CCMpred.py

@@ -22,6 +22,10 @@ class CCMpredCommandLine(AbstractCommandline):
     The CCMpred program is a very fast pseudo-likelihood maximisation
     implementation of covariance detection in a Multiple Sequence
     Alignment. This wrapper allows for easy-to-use Python implementation.
+    
+    .. [#] Seemayer S, Gruber M, Söding J (2014). CCMpred--fast and precise
+       prediction of protein residue-residue contacts from correlated mutations.
+       Bioinformatics 30(21), 3128-3130.
 
     Examples
     --------
@@ -38,10 +42,6 @@ class CCMpredCommandLine(AbstractCommandline):
     You would typically run the command line with :func:`ccmpred_cline` or via
     the Python subprocess module.
 
-    .. [#] Seemayer S, Gruber M, Söding J (2014). CCMpred--fast and precise
-       prediction of protein residue-residue contacts from correlated mutations.
-       Bioinformatics 30(21), 3128-3130.
-
     """
 
     def __init__(self, cmd="ccmpred", **kwargs):

conkit/applications/Cdhit.py

@@ -26,6 +26,13 @@ class CdhitCommandLine(AbstractCommandline):
     helps to significantly reduce the computational and manual efforts in
     many sequence analysis tasks and aids in understanding the data
     structure and correct the bias within a dataset.
+    
+    .. [#] Li W, Jaroszewski L, Godzik A(2001). Clustering of highly homologous sequences
+       to reduce thesize of large protein database. Bioinformatics 17, 282-283.
+
+    .. [#] Li W, Jaroszewski L, Godzik A (2002). Tolerating some redundancy significantly
+       speeds up clustering of large protein databases. Bioinformatics 18, 77-82.
+
 
     Examples
     --------
@@ -36,14 +43,6 @@ class CdhitCommandLine(AbstractCommandline):
     You would typically run the command line with :func:`cdhit_cline` or via
     the Python subprocess module.
 
-    Citations
-    ---------
-    .. [#] Li W, Jaroszewski L, Godzik A(2001). Clustering of highly homologous sequences
-       to reduce thesize of large protein database. Bioinformatics 17, 282-283.
-
-    .. [#] Li W, Jaroszewski L, Godzik A (2002). Tolerating some redundancy significantly
-       speeds up clustering of large protein databases. Bioinformatics 18, 77-82.
-
     """
 
     def __init__(self, cmd="cd-hit", **kwargs):

conkit/applications/HHblits.py

@@ -22,6 +22,12 @@ class HHblitsCommandLine(AbstractCommandline):
 
     The HHblits program is a homology detection tool by iterative HMM-HMM comparison.
 
+    .. [#] Alva V., Nam SZ., Söding J., Lupas AN. (2016). The MPI bioinformatics Toolkit as an
+       integrative platform for advanced protein sequence and structure analysis. Nucleic Acids Res. pii: gkw348.
+
+    .. [#] Remmert M., Biegert A., Hauser A., Söding J. (2011). HHblits: Lightning-fast iterative
+       protein sequence searching by HMM-HMM alignment. Nat Methods. 9(2):173-5.
+
     Examples
     --------
     To generate a Multiple Sequence Alignment, use:
@@ -36,12 +42,6 @@ class HHblitsCommandLine(AbstractCommandline):
     You would typically run the command line with :func:`hhblits_cline` or via
     the Python subprocess module.
 
-    .. [#]_ Alva V., Nam SZ., Söding J., Lupas AN. (2016). The MPI bioinformatics Toolkit as an
-       integrative platform for advanced protein sequence and structure analysis. Nucleic Acids Res. pii: gkw348.
-
-    .. [#]_ Remmert M., Biegert A., Hauser A., Söding J. (2011). HHblits: Lightning-fast iterative
-       protein sequence searching by HMM-HMM alignment. Nat Methods. 9(2):173-5.
-
     """
 
     def __init__(self, cmd="hhblits", **kwargs):

conkit/applications/HHfilter.py

@@ -19,6 +19,12 @@ class HHfilterCommandLine(AbstractCommandline):
 
     Filter an alignment by maximum sequence identity of match states and minimum coverage.
 
+    .. [#] Alva V., Nam SZ., Söding J., Lupas AN. (2016). The MPI bioinformatics Toolkit as an
+       integrative platform for advanced protein sequence and structure analysis. Nucleic Acids Res. pii: gkw348.
+
+    .. [#] Remmert M., Biegert A., Hauser A., Söding J. (2011). HHblits: Lightning-fast iterative
+       protein sequence searching by HMM-HMM alignment. Nat Methods. 9(2):173-5.
+
     Examples
     --------
     To generate a Multiple Sequence Alignment, use:
@@ -33,12 +39,6 @@ class HHfilterCommandLine(AbstractCommandline):
     You would typically run the command line with :func:`hhfilter_cline` or via
     the Python subprocess module.
 
-    .. [#]_ Alva V., Nam SZ., Söding J., Lupas AN. (2016). The MPI bioinformatics Toolkit as an
-       integrative platform for advanced protein sequence and structure analysis. Nucleic Acids Res. pii: gkw348.
-
-    .. [#]_ Remmert M., Biegert A., Hauser A., Söding J. (2011). HHblits: Lightning-fast iterative
-       protein sequence searching by HMM-HMM alignment. Nat Methods. 9(2):173-5.
-
     """
 
     def __init__(self, cmd='hhfilter', **kwargs):

conkit/applications/Jackhmmer.py

@@ -21,6 +21,9 @@ class JackhmmerCommandLine(AbstractCommandline):
     Jackhmmer is an algorithm that uses iterative searches a protein sequence
     against a protein sequence database to find sequence homologs.
 
+    .. [#] Johnson L. S., Eddy S. R., Portugaly E. (2010). Hidden Markov
+       Model Speed Heuristic and Iterative HMM Search Procedure. BMC Bioinformatics 11, 431.
+
     Examples
     --------
     To generate a Multiple Sequence Alignment, use:
@@ -35,9 +38,6 @@ class JackhmmerCommandLine(AbstractCommandline):
     You would typically run the command line with :func:`jackhmmer_cline` or via
     the Python subprocess module.
 
-    .. [#] Johnson L. S., Eddy S. R., Portugaly E. (2010). Hidden Markov
-       Model Speed Heuristic and Iterative HMM Search Procedure. BMC Bioinformatics 11, 431.
-
     """
 
     def __init__(self, cmd='jackhmmer', **kwargs):

conkit/applications/Psicov.py

@@ -21,6 +21,10 @@ class PsicovCommandLine(AbstractCommandline):
     The PSICOV program is a Accurate Contact Prediction from large
     protein alignments.
 
+    .. [#] Jones, D.T., Buchan, D.W., Cozzetto, D. & Pontil, M. (2012). PSICOV:
+       Precise structural contact prediction using sparse inverse covariance
+       estimation on large multiple sequence alignments. Bioinformatics. 28, 184-190.
+
     Examples
     --------
     To predict a contact map using a Multiple Sequence Alignment in
@@ -34,10 +38,6 @@ class PsicovCommandLine(AbstractCommandline):
     You would typically run the command line with :func:`psicov_cline` or via
     the Python subprocess module.
 
-    .. [#] Jones, D.T., Buchan, D.W., Cozzetto, D. & Pontil, M. (2012). PSICOV:
-       Precise structural contact prediction using sparse inverse covariance
-       estimation on large multiple sequence alignments. Bioinformatics. 28, 184-190.
-
     """
 
     def __init__(self, cmd='psicov', **kwargs):

conkit/constants.py

@@ -19,10 +19,3 @@
                 'PRO': 'P', 'PYL': 'O', 'SER': 'S', 'SEC': 'U', 'THR': 'T', 'TRP': 'W', 'TYR': 'Y', 'VAL': 'V', 
                 'ASX': 'B', 'GLX': 'Z', 'XAA': 'X', 'XLE': 'J'}
 
-# ================================================
-# Constants defining Contact().status color coding
-# ================================================
-TPCOLOR = '#2D9D00'     # color true positive
-FPCOLOR = '#AB0000'     # color false positive
-NTCOLOR = '#0482ff'     # color undefined
-RFCOLOR = '#B5B5B5'     # color structure

conkit/core/ContactFile.py

@@ -12,8 +12,6 @@
 class ContactFile(Entity):
     """A contact file object representing a single prediction file
 
-    Description
-    -----------
     The contact file class represents a data structure to hold all predictions
     with a single contact map file. It contains functions to store,
     manipulate and organise contact maps.

conkit/core/ContactMap.py

@@ -50,8 +50,6 @@ def __repr__(self):
 class ContactMap(Entity):
     """A contact map object representing a single prediction
 
-    Description
-    -----------
     The :obj:`ContactMap <conkit.core.ContactMap>` class represents a data structure to hold a single
     contact map prediction in one place. It contains functions to store,
     manipulate and organise :obj:`Contact <conkit.core.Contact>` instances.

conkit/core/Entity.py

@@ -13,8 +13,6 @@
 class Entity(object):
     """Base class for all entities used in this interface.
 
-    Description
-    -----------
     It handles the storage of data. It also provides a high-efficiency
     methods to allow fast lookup and iterations of each entity. It also
     provides a hierarchical structure to remember parent and child

conkit/core/SequenceFile.py

@@ -22,8 +22,6 @@
 class SequenceFile(Entity):
     """A sequence file object representing a single sequence file
 
-    Description
-    -----------
     The :obj:`SequenceFile <conkit.core.SequenceFile>` class represents a data structure to hold
     :obj:`Sequence <conkit.core.Sequence>` instances in a single sequence file. It contains
     functions to store and analyze sequences.

conkit/io/JonesIO.py

@@ -16,8 +16,6 @@
 class JonesIO(_SequenceFileParser):
     """Parser class for Jones sequence files
 
-    Description
-    -----------
     This format is a "new" definition of sequence-only records.
 
     It assumes that there are no comments, headers or any other

conkit/io/PconsIO.py

@@ -33,8 +33,6 @@
 class PconsParser(_ContactFileParser):
     """Class to parse a Pcons output
 
-    Description
-    -----------
     This module can be used to parse all versions of the
     Pcons programs, i.e. PconsC, PconsC2, and PconsC3.
 

conkit/plot/ContactMapChordPlot.py

@@ -13,18 +13,28 @@
 import numpy
 
 from conkit.plot._Figure import Figure
-from conkit.plot._plottools import points_on_circle
+from conkit.plot._plottools import ColorDefinitions, points_on_circle
 
 
 class ContactMapChordFigure(Figure):
     """A Figure object specifically for a Contact Map chord diagram
 
-    Description
-    -----------
     This figure will illustrate the contacts linking the residues
     in the target sequence. This plot is a very common representation
     of contacts. With this figure, you can illustrate intra-molecular.
 
+    Color scheme: 
+    
+    ==========  ===========   ==========  ===========  ==========  ===========  ==========  ===========  ==========  ===========
+    Amino acid  Hex code      Amino acid  Hex code     Amino acid  Hex code     Amino acid  Hex code     Amino acid  Hex code
+    ==========  ===========   ==========  ===========  ==========  ===========  ==========  ===========  ==========  ===========
+    Ala         ``#882D17``   Arg         ``#B3446C``  Asn         ``#F99379``  Asp         ``#875692``  Cys         ``#F3C300`` 
+    Gln         ``#F6A600``   Glu         ``#F38400``  Gly         ``#BE0032``  His         ``#C2B280``  Ile         ``#848482``
+    Leu         ``#E68FAC``   Lys         ``#008856``  Met         ``#0067A5``  Phe         ``#A1CAF1``  Pro         ``#604E97``
+    Ser         ``#DCD300``   Thr         ``#8DB600``  Trp         ``#E25822``  Tyr         ``#2B3D26``  Val         ``#654522``
+    Unk         ``#000000``
+    ==========  ===========   ==========  ===========  ==========  ===========  ==========  ===========  ==========  ===========
+
     Attributes
     ----------
     hierarchy : :obj:`ContactMap <conkit.core.ContactMap>`
@@ -37,14 +47,6 @@ class ContactMapChordFigure(Figure):
     >>> conkit.plot.ContactMapChordFigure(cmap)
 
     """
-    AA_ENCODING = {
-        'A': '#882D17', 'C': '#F3C300', 'D': '#875692', 'E': '#F38400',
-        'F': '#A1CAF1', 'G': '#BE0032', 'H': '#C2B280', 'I': '#848482',
-        'K': '#008856', 'L': '#E68FAC', 'M': '#0067A5', 'N': '#F99379',
-        'P': '#604E97', 'Q': '#F6A600', 'R': '#B3446C', 'S': '#DCD300',
-        'T': '#8DB600', 'V': '#654522', 'W': '#E25822', 'Y': '#2B3D26',
-        'X': '#000000'
-    }
 
     def __init__(self, hierarchy, **kwargs):
         """A new contact map plot
@@ -120,11 +122,11 @@ def _draw(self):
         residue_data = residue_data.reshape(self_data.T[0].shape[0] * 2, 2)
 
         #     - compute a default color list
-        color_codes = dict([(k, ContactMapChordFigure.AA_ENCODING['X']) for k in self_data_range])
+        color_codes = dict([(k, ColorDefinitions.AA_ENCODING['X']) for k in self_data_range])
 
         #     - fill default dict with data we have
         for k, v in numpy.vstack({tuple(row) for row in residue_data}):
-            color_codes[int(k)] = ContactMapChordFigure.AA_ENCODING[v]
+            color_codes[int(k)] = ColorDefinitions.AA_ENCODING[v]
 
         #     - create a color list
         colors = [color_codes[k] for k in sorted(color_codes.keys())]

conkit/plot/ContactMapPlot.py

@@ -12,15 +12,13 @@
 import matplotlib.pyplot
 import numpy
 
-from conkit import constants
 from conkit.plot._Figure import Figure
+from conkit.plot._plottools import ColorDefinitions
 
 
 class ContactMapFigure(Figure):
     """A Figure object specifically for a Contact Map
 
-    Description
-    -----------
     This figure will illustrate the contacts in a contact
     map. This plot is a very common representation of contacts.
     With this figure, you can illustrate either your contact 
@@ -138,7 +136,7 @@ def _draw(self):
             else:
                 reference_data = numpy.asarray([(c.res1_seq, c.res2_seq)
                                                 for c in self._reference if c.is_true_positive])
-            reference_colors = [constants.RFCOLOR for _ in range(len(reference_data))]
+            reference_colors = [ColorDefinitions.STRUCTURAL for _ in range(len(reference_data))]
             ax.scatter(reference_data.T[0], reference_data.T[1], color=reference_colors,
                        s=10, marker='o', edgecolor='none', linewidths=0.0)
             ax.scatter(reference_data.T[1], reference_data.T[0], color=reference_colors,
@@ -197,15 +195,15 @@ def _draw(self):
 
         # Create a custom legend
         if self._reference:
-            tp_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=constants.TPCOLOR,
+            tp_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=ColorDefinitions.MATCH,
                                                  marker='o', linestyle='', label='Match')
-            fp_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=constants.FPCOLOR,
+            fp_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=ColorDefinitions.MISMATCH,
                                                  marker='o', linestyle='', label='Mismatch')
-            rf_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=constants.RFCOLOR,
+            rf_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=ColorDefinitions.STRUCTURAL,
                                                  marker='o', linestyle='', label='Structural')
             artists = [tp_artist, fp_artist, rf_artist]
         else:
-            nt_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=constants.NTCOLOR,
+            nt_artist = matplotlib.pyplot.Line2D((0, 1), (0, 0), color=ColorDefinitions.NEUTRAL,
                                                  marker='o', linestyle='', label='Contact')
             artists = [nt_artist]
         ax.legend(handles=artists, numpoints=1, fontsize=10, bbox_to_anchor=(0., 1.02, 1., .102),
@@ -222,8 +220,7 @@ def _draw(self):
     def _determine_color(h):
         """Determine the color of the contacts in order"""
         return [
-            constants.TPCOLOR if contact.is_true_positive
-            else constants.FPCOLOR if contact.is_false_positive
-            else constants.NTCOLOR
-            for contact in h
+            ColorDefinitions.MATCH if contact.is_true_positive
+            else ColorDefinitions.MISMATCH if contact.is_false_positive
+            else ColorDefinitions.NEUTRAL for contact in h
         ]

conkit/plot/PrecisionEvaluationPlot.py

@@ -12,13 +12,12 @@
 import numpy
 
 from conkit.plot._Figure import Figure
+from conkit.plot._plottools import ColorDefinitions
 
 
 class PrecisionEvaluationFigure(Figure):
     """A Figure object specifically for a Precision evaluation.
 
-    Description
-    -----------
     This figure will illustrate the precision scores of a contact
     map at different precision scores. These can be determined at
     various start and end points with different stepwise increases
@@ -168,12 +167,12 @@ def _draw(self):
         fig, ax = matplotlib.pyplot.subplots()
 
         # Add indicator lines for clarity of data
-        ax.axhline(0.5, color='#008E00', linestyle='-',  label='50% Precision')
+        ax.axhline(0.5, color=ColorDefinitions.PRECISION50, linestyle='-',  label='50% Precision')
         if self.min_cutoff <= 1.0:
-            ax.axvline(1.0, color='#BDBDBD', linestyle='--', label='Factor L')
+            ax.axvline(1.0, color=ColorDefinitions.FACTOR1, linestyle='--', label='Factor L')
 
         # Add data points itself
-        ax.plot(factors, precisions, color='#000000', marker='o', markersize=5, linestyle='-',
+        ax.plot(factors, precisions, color=ColorDefinitions.GENERAL, marker='o', markersize=5, linestyle='-',
                 label='Precision score')
 
         # Prettify the plot