Fix spelling mistakes

examples/analysis/clustering_analysis.ipynb

@@ -20,7 +20,7 @@
      "metadata": {},
      "source": [
       "This tutorial describes how to run a cluster analysis, when the calculation was run with a ReplicaExchange protocol.\n",
-      "The clustering algorithm will create cluster.$index directories, therefore you may want to remove these directories everytime you rerun the calculation. The matrix calculation is very time consuming. The matrix can be saved in a file, in case you want to apply different clustering methods. In additio, one can run the calculation in parallel (you need the mpi4py python library installed).\n",
+      "The clustering algorithm will create cluster.$index directories, therefore you may want to remove these directories every time you rerun the calculation. The matrix calculation is very time consuming. The matrix can be saved in a file, in case you want to apply different clustering methods. In additio, one can run the calculation in parallel (you need the mpi4py python library installed).\n",
       "\n",
       "Paste the python code below in a file, and run it. (eg, imp/setup_environment.sh mpirun -np 8 python this_script.py)"
      ]
@@ -142,4 +142,4 @@
    "metadata": {}
   }
  ]
-}
+}

examples/analysis/sampling exhaustiveness analysis.ipynb

@@ -96,7 +96,7 @@
      "source": [
       "Last, setup the clustering. \n",
       "\n",
-      "`skip_clustering=True` it will actually not perform the clustering at all, but it will exctract the best scoring models\n",
+      "`skip_clustering=True` it will actually not perform the clustering at all, but it will extract the best scoring models\n",
       "\n",
       "`prefiltervalue=300` this value indicates the upper-bound score value. It is needed for memory efficiency.\n",
       "\n",
@@ -129,4 +129,4 @@
    "metadata": {}
   }
  ]
-}
+}

examples/cross-link/cross-link_ms-ambiguity.ipynb

@@ -234,7 +234,7 @@
       "# Compositional ambiguity occurs when identical copies of the same protein is present \n",
       "# in the sample, and we are not able to attribute the cross-link to one or the other copy.\n",
       "\n",
-      "# Furthermore, let's suppose to have already an indentification ambiguity, to complicate the example\n",
+      "# Furthermore, let's suppose to have already an identification ambiguity, to complicate the example\n",
       "# and see how the two ambiguities combine each other. See the data below, note that two crosslinks have the same \n",
       "# UniqueID\n",
       "\n",
@@ -412,4 +412,4 @@
    "metadata": {}
   }
  ]
-}
+}

pyext/src/analysis.py

@@ -450,7 +450,7 @@ def matrix_calculation(self, all_coords, template_coords, list_of_pairs):
                 template_rmsd, transformation = Ali.align()
 
                 # here we calculate the rmsd
-                # we will align two models based n the nuber of subunits provided
+                # we will align two models based on the number of subunits provided
                 # and transform coordinates of model 2 to model 1
                 coords_f1 = dict([(pr, all_coords[model_list_names[f1]][pr])
                                  for pr in rmsd_protein_names])
@@ -1308,11 +1308,11 @@ def get_subunit_coords(self, frame, align=0):
 
     def add_xlinks(
         self,
-        filname,
+        filename,
             identification_string='ISDCrossLinkMS_Distance_'):
         # 'ISDCrossLinkMS_Distance_interrb_6629-State:0-20:RPS30_218:eIF3j-1-1-0.1_None'
         self.xlinks = 1
-        data = open(filname)
+        data = open(filename)
         D = data.readlines()
         data.close()
 

pyext/src/io/crosslink.py

@@ -1337,7 +1337,7 @@ def __init__(self,CrossLinkDataBase,rmf_or_stat_handler):
         self.array_to_id={}
         self.id_to_array={}
 
-        print("computing distances fro all crosslinks and all structures")
+        print("computing distances for all crosslinks and all structures")
         for i in self.prots[::10]:
             self.compute_distances()
             for key,xl in enumerate(self.CrossLinkDataBase):

pyext/src/macros.py

@@ -1710,7 +1710,7 @@ def clustering(self,
                     rmsd_coordinates)
 
             if self.rank == 0:
-                # save needed informations in external files
+                # save needed information in external files
                 self.save_objects(
                     [best_score_feature_keyword_list_dict,
                      rmf_file_name_index_dict],
@@ -1745,7 +1745,7 @@ def clustering(self,
                 self.cluster_obj.save_distance_matrix_file(file_name=distance_matrix_file)
 
 # ------------------------------------------------------------------------
-# Alteratively, load the distance matrix from file and cluster that
+# Alternatively, load the distance matrix from file and cluster that
 # ------------------------------------------------------------------------
         else:
             if self.rank==0:
@@ -1765,7 +1765,7 @@ def clustering(self,
             self.comm.Barrier()
 
 # ------------------------------------------------------------------------
-# now save all informations about the clusters
+# now save all information about the clusters
 # ------------------------------------------------------------------------
 
         if self.rank == 0:
@@ -2789,7 +2789,7 @@ def rmsd(self,metric=IMP.atom.get_rmsd):
 
     def set_reference(self,reference,cluster):
         """
-        Fix the reference structure for structural alignment, rmsd and chain assignemnt
+        Fix the reference structure for structural alignment, rmsd and chain assignment
         @param reference can be either "Absolute" (cluster center of the first cluster)
                         or Relative (cluster center of the current cluster)
         """
@@ -2804,7 +2804,7 @@ def set_reference(self,reference,cluster):
 
     def apply_molecular_assignments(self, n1):
         """
-        compute the molecular assignemnts between multiple copies
+        compute the molecular assignments between multiple copies
         of the same sequence. It changes the Copy index of Molecules
         """
         d1=self.stath1[n1]

pyext/src/nonmantained.py

@@ -202,7 +202,7 @@ def destroy_residues(self, segments):
                                               segment[1] + 1)))
                 for p in s.get_selected_particles():
                     if IMP.core.RigidMember.get_is_setup(p):
-                        print("MultipleStates: one particle was not destroied because it was a RigidMember.")
+                        print("MultipleStates: one particle was not destroyed because it was a RigidMember.")
                     else:
                         # destroy the residue and the associated atom
                         a = IMP.atom.Atom(p)
@@ -354,7 +354,7 @@ def destroy_everything_but_the_residues(self, segments):
             for p in IMP.atom.get_leaves(prot):
                 if p not in pstokeep:
                     if IMP.core.RigidMember.get_is_setup(p):
-                        print("MultipleStates: one particle was not destroied because it was a RigidMember.")
+                        print("MultipleStates: one particle was not destroyed because it was a RigidMember.")
                     else:
                         # destroy the residue and the associated atom
                         a = IMP.atom.Atom(p).get_parent()
@@ -584,7 +584,7 @@ def read_pdbs(self, list_pdb_file):
         if the pdbs are given a individual strings, it will read the
         pdbs and give the chain name as specified in the pdb
         If it s a tuple like (filename,chainname) it will read
-        the pdb and assing a name chainname
+        the pdb and assign a name chainname
         to the chain"""
 
         # create an empty hierarchy
@@ -673,7 +673,7 @@ def shuffle_configuration(self, bounding_box_length):
         "shuffle configuration, used to restart the optimization"
         "it only works if rigid bodies were initialized"
         if len(self.rigid_bodies) == 0:
-            print("MultipleStates: rigid bodies were not intialized")
+            print("MultipleStates: rigid bodies were not initialized")
         hbbl = bounding_box_length / 2
         for rbl in self.rigid_bodies:
             for rb in rbl:
@@ -708,10 +708,10 @@ def calculate_drms(self):
         # calculate DRMSD matrix
 
         if len(self.xyzmodellist) == 0:
-            print("MultipleStates: hierarchies were not intialized")
+            print("MultipleStates: hierarchies were not initialized")
 
         if len(self.xyzreflist) == 0:
-            print("MultipleStates: reference hierarchies were not intialized")
+            print("MultipleStates: reference hierarchies were not initialized")
 
         drmsd = {}
         for i in range(len(self.xyzreflist)):
@@ -1233,7 +1233,7 @@ def __init__(self, prots,
         # this map is used in the new cross-link file reader
         #{"Nsp1":"A","Nup82":"B"} etc.
         self.mbpnc = map_between_protein_names_and_chains
-        # check whther the file was initialized
+        # check whether the file was initialized
 
     #-------------------------------
     def get_crosslinker_dict(self, typeofprofile="gofr"):
@@ -1930,7 +1930,7 @@ def __init__(self, m, prots,
         # this map is used in the new cross-link file reader
         #{"Nsp1":"A","Nup82":"B"} etc.
         self.mbpnc = map_between_protein_names_and_chains
-        # check whther the file was initialized
+        # check whether the file was initialized
 
     def create_psi(self, index, value):
         if value is None:
@@ -2407,7 +2407,7 @@ def __init__(self, prot, restraints_file, TruncatedHarmonic=True):
 
             # part1=[]
             # part2=[]
-            # this list contain the list of simmetric pairs to avoid
+            # this list contain the list of symmetric pairs to avoid
             # duplications
 
             # this is the map between particle pairs and the restraints (there
@@ -2422,7 +2422,7 @@ def __init__(self, prot, restraints_file, TruncatedHarmonic=True):
                 print("WARNING> residue %d of chain %s and residue %d of chain %s belong to the same rigid body" % (r1, c1, r2, c2))
                 continue
 
-                # this list contain the list of simmetric pairs to avoid
+                # this list contain the list of symmetric pairs to avoid
                 # duplications
             if (p1, p2, crosslinker) in addedd_pairs_list:
                 print("WARNING> pair %d %s %d %s already there" % (r1, c1, r2, c2))

pyext/src/output.py

@@ -406,7 +406,7 @@ def init_rmf(self, name, hierarchies, rs=None, geometries=None, listofobjects=No
         This function initialize an RMF file
 
         @param name          the name of the RMF file
-        @param hierarchies   the hiearchies to be included (it is a list)
+        @param hierarchies   the hierarchies to be included (it is a list)
         @param rs            optional, the restraint sets (it is a list)
         @param geometries    optional, the geometries (it is a list)
         @param listofobjects optional, the list of objects for the stat (it is a list)

pyext/src/process_output.py

@@ -100,7 +100,7 @@
 # print the queried fields
 if not result.fields is None:
     field_list = []
-    # check whether the fields exist and convert them to best maching existing
+    # check whether the fields exist and convert them to best matching existing
     # field names
     for field in result.fields:
         found_entries = difflib.get_close_matches(
@@ -168,7 +168,7 @@
     f.close()
 
 if (not result.search_field is None) and (not result.search_value is None):
-    # check whether the fields exist and convert them to best maching existing
+    # check whether the fields exist and convert them to best matching existing
     # field names
     found_entries = difflib.get_close_matches(
         result.search_field,
@@ -203,7 +203,7 @@
     f.close()
 
 if not result.print_raw_number is None:
-    # check whether the fields exist and convert them to best maching existing
+    # check whether the fields exist and convert them to best matching existing
     # field names
     f = open(result.filename, "r")
     line_number = 0

pyext/src/process_output_rmf.py

@@ -67,7 +67,7 @@
 # print the queried fields
 if not result.fields is None:
     field_list = []
-    # check whether the fields exist and convert them to best maching existing
+    # check whether the fields exist and convert them to best matching existing
     # field names
     for field in result.fields:
         found_entries = difflib.get_close_matches(

pyext/src/representation.py

@@ -102,7 +102,7 @@ def __init__(self, model, upperharmonic=True, disorderedlength=True):
         self._non_modeled_components = {}
 
         # this flag uses either harmonic (False) or upperharmonic (True)
-        # in the intra-pair connectivity restraint. Harmonic is used whe you want to
+        # in the intra-pair connectivity restraint. Harmonic is used when you want to
         # remove the intra-ev term from energy calculations, e.g.:
         # upperharmonic=False
         # ip=self.get_connected_intra_pairs()
@@ -1428,7 +1428,7 @@ def shuffle_configuration(
             hierarchies_excluded_from_collision = []
 
         if len(self.rigid_bodies) == 0:
-            print("shuffle_configuration: rigid bodies were not intialized")
+            print("shuffle_configuration: rigid bodies were not initialized")
 
         gcpf = IMP.core.GridClosePairsFinder()
         gcpf.set_distance(cutoff)

pyext/src/restraints/npc.py

@@ -9,7 +9,7 @@
 the xy plane and centered at the origin. Individual proteins
 (or parts of proteins, such as the N- or C- termini) are then localized to
 different regions of the complex (e.g. near the membrane or pore, or on
-the nuclear or cytoplasmic side) by simple restraints on ther Cartesian
+the nuclear or cytoplasmic side) by simple restraints on their Cartesian
 coordinates.
 """
 

pyext/src/restraints/saxs.py

@@ -37,7 +37,7 @@ def __init__(self, input_objects, saxs_datafile, weight=1.0,
         @param label Label for the restraint in outputs
 
         @param maxq - maximum q value that the restraint will be evaluated at
-                        Default vaules for ff_type = ALL_ATOMS : 0.5. HEAVY_ATOMS : 0.4,
+                        Default values for ff_type = ALL_ATOMS : 0.5. HEAVY_ATOMS : 0.4,
                         CA_ATOMS and RESIDUES = 0.15. These values were eyeballed
                         by comparing ALL_ATOM calculated SAXS profiles to those calculated
                         with the reduced representations, so could be improved.
@@ -251,7 +251,7 @@ def get_output(self):
 
     @staticmethod
     def _logspace(a, b, num=100):
-        """Mimick numpy's logspace function"""
+        """Mimic numpy's logspace function"""
         for i in range(num):
             val = a + float(b - a) / float(num - 1) * i
             yield 10 ** val

pyext/src/tools.py

@@ -1648,12 +1648,12 @@ def input_adaptor(stuff,
     else:
         stuff = [stuff]
 
-    # check that it is a hierarchy homogenously:
+    # check that it is a hierarchy homogeneously:
     try:
         is_hierarchy=all(IMP.atom.Hierarchy.get_is_setup(s) for s in stuff)
     except NotImplementedError:
         is_hierarchy=False
-    # get the other types homogenously
+    # get the other types homogeneously
     is_system=False
     is_state=False
     is_molecule=False
@@ -2016,7 +2016,7 @@ def shuffle_configuration(objects,
     else:
         raise Exception("Could not find any particles in the hierarchy")
     if len(rigid_bodies) == 0:
-        print("shuffle_configuration: rigid bodies were not intialized")
+        print("shuffle_configuration: rigid bodies were not initialized")
 
     ### gather all particles
     gcpf = IMP.core.GridClosePairsFinder()

pyext/src/topology/__init__.py

@@ -127,7 +127,7 @@ def read_sequences(self,fasta_fn,name_map=None):
 
 
 class TopologyReader(object):
-    """Automatically setup Sytem and Degrees of Freedom with a formatted text file.
+    """Automatically setup System and Degrees of Freedom with a formatted text file.
     The file is read in and each part of the topology is stored as a
     ComponentTopology object for input into IMP::pmi1::macros::BuildSystem.
     The topology file should be in a simple pipe-delimited format:

test/test_stopwatch.py

@@ -15,7 +15,7 @@ def mocked_object(parent, objname, replacement):
 
 def get_times(outkey, *args, **kwargs):
     """Get a sequence of times by calling Stopwatch repeatedly. Ensure that
-       times are reliable by overridding time.clock() to always return whole
+       times are reliable by overriding time.clock() to always return whole
        seconds."""
     class MockClock(object):
         count = 0