Merge remote-tracking branch 'upstream/master'

93663581 · John Chodera (MSKCC) · 94084151 · db272571 · 93663581 · 93663581
Commit 93663581 authored Feb 25, 2015 by John Chodera (MSKCC)
Showing with 84 additions and 72 deletions

.travis.yml
+8 -1

pdbfixer/__init__.py
+3 -1

pdbfixer/pdbfixer.py
+21 -23

pdbfixer/ui.py
+32 -28

pdbfixer/uiserver.py
+1 -1

tests/test_build_and_simulate.py
+17 -16

tests/test_removechains.py
+2 -2

No files found.
--- a/.travis.yml
+++ b/.travis.yml
 language: c
+env:
+    matrix:
+        - CONDA_PY=2.7
+        - CONDA_PY=3.3
+        - CONDA_PY=3.4
 install:
    - sudo apt-get update -qq
    - sudo apt-get install -qq python-dev python-pip python-yaml g++ ftp
    - sudo pip install conda eventlet
    - sudo conda init
    - conda config --add channels http://conda.binstar.org/omnia
-    - conda create --yes --name test nose setuptools numpy biopython pyflakes openmm
+    - conda create --yes --name test nose setuptools numpy biopython pyflakes openmm-dev
    - export PATH="$HOME/envs/test/bin/:$PATH"
 script:

--- a/pdbfixer/__init__.py
+++ b/pdbfixer/__init__.py
-from pdbfixer import PDBFixer
+from __future__ import absolute_import
+from .pdbfixer import PDBFixer
--- a/pdbfixer/pdbfixer.py
+++ b/pdbfixer/pdbfixer.py
@@ -6,7 +6,7 @@ Simbios, the NIH National Center for Physics-Based Simulation of
 Biological Structures at Stanford, funded under the NIH Roadmap for
 Medical Research, grant U54 GM072970. See https://simtk.org.
-Portions copyright (c) 2013-2014 Stanford University and the Authors.
+Portions copyright (c) 2013-2015 Stanford University and the Authors.
 Authors: Peter Eastman
 Contributors:
@@ -28,6 +28,7 @@ DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR
 OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE
 USE OR OTHER DEALINGS IN THE SOFTWARE.
 """
+from __future__ import absolute_import
 __author__ = "Peter Eastman"
 __version__ = "1.1"
@@ -207,7 +208,7 @@ class PDBFixer(object):
            self.source = url
            file = urlopen(url)
            # Read contents all at once and split into lines, since urlopen doesn't like it when we read one line at a time over the network.
-            contents = file.read()
+            contents = file.read().decode('utf-8')
            lines = contents.split('\n')
            file.close()
            structure = PdbStructure(lines)
@@ -221,7 +222,6 @@ class PDBFixer(object):
        self.pdb = app.PDBFile(structure)
        self.topology = self.pdb.topology
        self.positions = self.pdb.positions
-        self.structureChains = list(self.structure.iter_chains())
        # Load the templates.
@@ -462,7 +462,6 @@ class PDBFixer(object):
        modeller.delete(allChains[i] for i in chainIndices)
        self.topology = modeller.topology
        self.positions = modeller.positions
-        self.structureChains = [self.structureChains[i] for i in range(len(self.structureChains)) if i not in chainIndices]
        return
@@ -481,17 +480,17 @@ class PDBFixer(object):
        >>> missing_residues = fixer.missingResidues
        """
-        chains = [c for c in self.structureChains if any(atom.record_name == 'ATOM' for atom in c.iter_atoms())]
+        chains = [c for c in self.topology.chains() if len(list(c.residues())) > 0]
        chainWithGaps = {}
        # Find the sequence of each chain, with gaps for missing residues.
        for chain in chains:
-            minResidue = min(r.number for r in chain.iter_residues())
+            minResidue = min(int(r.id) for r in chain.residues())
-            maxResidue = max(r.number for r in chain.iter_residues())
+            maxResidue = max(int(r.id) for r in chain.residues())
            residues = [None]*(maxResidue-minResidue+1)
-            for r in chain.iter_residues():
+            for r in chain.residues():
-                residues[r.number-minResidue] = r.get_name()
+                residues[int(r.id)-minResidue] = r.name
            chainWithGaps[chain] = residues
        # Try to find the chain that matches each sequence.
@@ -500,7 +499,7 @@ class PDBFixer(object):
        chainOffset = {}
        for sequence in self.structure.sequences:
            for chain in chains:
-                if chain.chain_id != sequence.chain_id:
+                if chain.id != sequence.chain_id:
                    continue
                if chain in chainSequence:
                    continue
@@ -515,15 +514,15 @@ class PDBFixer(object):
        # Now build the list of residues to add.
        self.missingResidues = {}
-        for structChain, topChain in zip(self.structureChains, self.topology.chains()):
+        for chain in self.topology.chains():
-            if structChain in chainSequence:
+            if chain in chainSequence:
-                offset = chainOffset[structChain]
+                offset = chainOffset[chain]
-                sequence = chainSequence[structChain].residues
+                sequence = chainSequence[chain].residues
-                gappedSequence = chainWithGaps[structChain]
+                gappedSequence = chainWithGaps[chain]
                index = 0
                for i in range(len(sequence)):
                    if i < offset or i >= len(gappedSequence)+offset or gappedSequence[i-offset] is None:
-                        key = (topChain.index, index)
+                        key = (chain.index, index)
                        if key not in self.missingResidues:
                            self.missingResidues[key] = []
                        residueName = sequence[i]
@@ -556,16 +555,16 @@ class PDBFixer(object):
        # Now add ones based on MODRES records.
-        modres = dict(((m.chain_id, m.number, m.residue_name), m.standard_name) for m in self.structure.modified_residues)
+        modres = dict(((m.chain_id, str(m.number), m.residue_name), m.standard_name) for m in self.structure.modified_residues)
-        for structChain, topChain in zip(self.structureChains, self.topology.chains()):
+        for chain in self.topology.chains():
-            for structResidue, topResidue in zip(structChain.iter_residues(), topChain.residues()):
+            for residue in chain.residues():
-                key = (structChain.chain_id, structResidue.number, structResidue.name)
+                key = (chain.id, residue.id, residue.name)
                if key in modres:
                    replacement = modres[key]
                    if replacement == 'DU':
                        replacement = 'DT'
                    if replacement in self.templates:
-                        nonstandard[topResidue] = replacement
+                        nonstandard[residue] = replacement
        self.nonstandardResidues = [(r, nonstandard[r]) for r in sorted(nonstandard, key=lambda r: r.index)]
    def replaceNonstandardResidues(self):
@@ -1027,8 +1026,7 @@ class PDBFixer(object):
 def main():
    if len(sys.argv) < 2:
        # Display the UI.
+        from . import ui
-        import ui
        ui.launchUI()
    else:
        # Run in command line mode.

--- a/pdbfixer/ui.py
+++ b/pdbfixer/ui.py
-import simtk.openmm.app as app
+from __future__ import absolute_import
-from simtk.openmm.app.internal.pdbstructure import PdbStructure
-import simtk.unit as unit
-from pdbfixer import PDBFixer, substitutions, proteinResidues, dnaResidues, rnaResidues
-import uiserver
 import webbrowser
 import os.path
-import gzip
 import time
-from io import BytesIO
+import simtk.openmm.app as app
+import simtk.unit as unit
+from .pdbfixer import PDBFixer, proteinResidues, dnaResidues, rnaResidues
+from . import uiserver
 try:
    from urllib.request import urlopen
    from io import StringIO
@@ -27,7 +29,7 @@ def loadImageFile(name):
    if name not in cachedImages:
        imagePath = os.path.join(os.path.dirname(__file__), 'images')
        file = os.path.join(imagePath, name)
-        cachedImages[name] = open(file).read()
+        cachedImages[name] = open(file, 'rb').read()
    return cachedImages[name]
 def controlsCallback(parameters, handler):
@@ -53,13 +55,21 @@ def startPageCallback(parameters, handler):
    global fixer
    if 'type' in parameters:
        if parameters.getfirst('type') == 'local':
-            fixer = PDBFixer(file=parameters['pdbfile'].value.decode().splitlines())
+            fixer = PDBFixer(pdbfile=parameters['pdbfile'].value.decode().splitlines())
+            fixer.source = parameters['pdbfile'].filename
        else:
            id = parameters.getfirst('pdbid')
            try:
                fixer = PDBFixer(pdbid=id)
-            except:
+            except Exception as e:
-                handler.sendResponse(header+"Unable to download the PDB file. This may indicate an invalid PDB identifier, or an error in network connectivity."+loadHtmlFile("error.html"))
+                import traceback
+                print(traceback.format_exc())
+                handler.sendResponse(
+                    header + "<p>Unable to download the PDB file. " +
+                    "This may indicate an invalid PDB identifier, " +
+                    "or an error in network connectivity.</p>" +
+                    "<p>{}</p>".format(e) +
+                    loadHtmlFile("error.html"))
        displayDeleteChainsPage()
 def deleteChainsPageCallback(parameters, handler):
@@ -73,7 +83,7 @@ def addResiduesPageCallback(parameters, handler):
    for i, key in enumerate(keys):
        if 'add'+str(i) not in parameters:
            del fixer.missingResidues[key]
-    displayMissingAtomsPage()
+    displayConvertResiduesPage()
 def convertResiduesPageCallback(parameters, handler):
    for i in range(len(fixer.nonstandardResidues)):
@@ -134,7 +144,7 @@ def displayDeleteChainsPage():
            content = "DNA"
        else:
            content = ', '.join(set(residues))
-        table += '    <tr><td>%d</td><td>%d</td><td>%s</td><td><input type="checkbox" name="include%d" checked></td></tr>\n' % (chain.index+1, len(residues), content, i)
+        table += '    <tr><td>%s</td><td>%d</td><td>%s</td><td><input type="checkbox" name="include%d" checked></td></tr>\n' % (chain.id, len(residues), content, i)
    uiserver.setContent(header+loadHtmlFile("removeChains.html") % (numChains, table))
 def displayAddResiduesPage():
@@ -144,14 +154,16 @@ def displayAddResiduesPage():
        displayConvertResiduesPage()
        return
    table = ""
+    chains = list(fixer.topology.chains())
    for i, key in enumerate(sorted(fixer.missingResidues)):
        residues = fixer.missingResidues[key]
-        chain = fixer.structureChains[key[0]]
+        chain = chains[key[0]]
-        if key[1] < len(chain.residues):
+        chainResidues = list(chain.residues())
-            offset = chain.residues[key[1]].number-len(residues)-1
+        if key[1] < len(chainResidues):
+            offset = int(chainResidues[key[1]].id)-len(residues)-1
        else:
-            offset = chain.residues[-1].number
+            offset = int(chainResidues[-1].id)
-        table += '    <tr><td>%d</td><td>%d to %d</td><td>%s</td><td><input type="checkbox" name="add%d" checked></td></tr>\n' % (key[0]+1, offset+1, offset+len(residues), ', '.join(residues), i)
+        table += '    <tr><td>%s</td><td>%d to %d</td><td>%s</td><td><input type="checkbox" name="add%d" checked></td></tr>\n' % (chain.id, offset+1, offset+len(residues), ', '.join(residues), i)
    uiserver.setContent(header+loadHtmlFile("addResidues.html") % table)
 def displayConvertResiduesPage():
@@ -160,10 +172,6 @@ def displayConvertResiduesPage():
    if len(fixer.nonstandardResidues) == 0:
        displayMissingAtomsPage()
        return
-    indexInChain = {}
-    for structChain, topChain in zip(fixer.structureChains, fixer.topology.chains()):
-        for structResidue, topResidue in zip(structChain.iter_residues(), topChain.residues()):
-            indexInChain[topResidue] = structResidue.number
    table = ''
    nucleotides = ['DA', 'DC', 'DG', 'DT', 'A', 'C', 'G', 'T']
    for i in range(len(fixer.nonstandardResidues)):
@@ -178,7 +186,7 @@ def displayConvertResiduesPage():
            if res == replaceWith:
                selected = ' selected'
            options += '<option value="%s"%s>%s</option>' % (res, selected, res)
-        table += '    <tr><td>%d</td><td>%s %d</td><td><select name="residue%d">%s</select></td><td><input type="checkbox" name="convert%d" checked></td></tr>\n' % (residue.chain.index+1, residue.name, indexInChain[residue], i, options, i)
+        table += '    <tr><td>%s</td><td>%s %s</td><td><select name="residue%d">%s</select></td><td><input type="checkbox" name="convert%d" checked></td></tr>\n' % (residue.chain.id, residue.name, residue.id, i, options, i)
    uiserver.setContent(header+loadHtmlFile("convertResidues.html") % table)
 def displayMissingAtomsPage():
@@ -190,10 +198,6 @@ def displayMissingAtomsPage():
        fixer.addMissingAtoms()
        displayAddHydrogensPage()
        return
-    indexInChain = {}
-    for structChain, topChain in zip(fixer.structureChains, fixer.topology.chains()):
-        for structResidue, topResidue in zip(structChain.iter_residues(), topChain.residues()):
-            indexInChain[topResidue] = structResidue.number
    table = ""
    for residue in allResidues:
        atoms = []
@@ -201,7 +205,7 @@ def displayMissingAtomsPage():
            atoms.extend(atom.name for atom in fixer.missingAtoms[residue])
        if residue in fixer.missingTerminals:
            atoms.extend(atom for atom in fixer.missingTerminals[residue])
-        table += '    <tr><td>%d</td><td>%s %d</td><td>%s</td></tr>\n' % (residue.chain.index+1, residue.name, indexInChain[residue], ', '.join(atoms))
+        table += '    <tr><td>%s</td><td>%s %s</td><td>%s</td></tr>\n' % (residue.chain.id, residue.name, residue.id, ', '.join(atoms))
    uiserver.setContent(header+loadHtmlFile("addHeavyAtoms.html") % table)
 def displayAddHydrogensPage():

--- a/pdbfixer/uiserver.py
+++ b/pdbfixer/uiserver.py
@@ -46,7 +46,7 @@ class _Handler(BaseHTTPRequestHandler):
        self.send_header("Content-type", type)
        self.send_header("Content-length", str(len(response)))
        self.end_headers()
-        if sys.version_info.major > 2:
+        if sys.version_info.major > 2 and isinstance(response, str):
            response = bytes(response, 'UTF-8')
        self.wfile.write(response)

--- a/tests/test_build_and_simulate.py
+++ b/tests/test_build_and_simulate.py
+from __future__ import print_function
 import pdbfixer
 import simtk.openmm 
@@ -79,7 +80,7 @@ def simulate(pdbcode, pdb_filename):
    del context, integrator
-    print "Simulation completed: potential = %.3f kcal/mol" % potential
+    print("Simulation completed: potential = %.3f kcal/mol" % potential)
    return
@@ -105,8 +106,8 @@ def test_build_and_simulate():
    failures = list()
    for pdbcode in pdbcodes_to_build:
-        print "------------------------------------------------"
+        print("------------------------------------------------")
-        print pdbcode
+        print(pdbcode)
        output_pdb_filename = 'output.pdb'
@@ -152,14 +153,14 @@ def test_build_and_simulate():
        except Watchdog:
            message = "timed out in stage %s" % stage
-            print message
+            print(message)
            failures.append((pdbcode, Exception(message)))
        except Exception as e:
-            print "EXCEPTION DURING BUILD"
+            print("EXCEPTION DURING BUILD")
            #import traceback
            #print traceback.print_exc()
-            print str(e)
+            print(str(e))
            failures.append((pdbcode, e))
        watchdog.stop()
@@ -173,14 +174,14 @@ def test_build_and_simulate():
            except Watchdog:
                message = "timed out in simulation"
-                print message
+                print(message)
                failures.append((pdbcode, Exception(message)))
            except Exception as e:
-                print "EXCEPTION DURING SIMULATE"
+                print("EXCEPTION DURING SIMULATE")
                #import traceback
                #print traceback.print_exc()
-                print str(e)
+                print(str(e))
                failures.append((pdbcode, e))
            watchdog.stop()
@@ -189,21 +190,21 @@ def test_build_and_simulate():
        # Clean up.
        os.remove(output_pdb_filename)
-    print "------------------------------------------------"
+    print("------------------------------------------------")
    if len(failures) != 0:
-        print ""
+        print("")
-        print "SUMMARY OF FAILURES:"
+        print("SUMMARY OF FAILURES:")
-        print ""
+        print("")
        for failure in failures:
            (pdbcode, exception) = failure
-            print "%6s : %s" % (pdbcode, str(exception))
+            print("%6s : %s" % (pdbcode, str(exception)))
-        print ""
+        print("")
        raise Exception("Build test failed on one or more PDB files.")
    else:
-        print "All tests succeeded."
+        print("All tests succeeded.")
 if __name__ == '__main__':
    test_build_and_simulate()
--- a/tests/test_removechains.py
+++ b/tests/test_removechains.py
@@ -9,7 +9,7 @@ def remove_chain_ids_and_verify(pdbid, chain_ids_to_remove, expected_chain_ids_r
    # Remove specified chains.
    fixer.removeChains(chainIds=chain_ids_to_remove)
    # Check to make sure asserted chains remain.
-    chain_ids_remaining = [c.chain_id for c in fixer.structureChains]
+    chain_ids_remaining = [c.id for c in fixer.topology.chains()]
    assert_items_equal(chain_ids_remaining, expected_chain_ids_remaining)
 def test_removechain_ids():
@@ -25,7 +25,7 @@ def remove_chain_indices_and_verify(pdbid, chain_indices_to_remove, expected_cha
    # Remove specified chains.
    fixer.removeChains(chainIndices=chain_indices_to_remove)
    # Check to make sure asserted chains remain.
-    chain_ids_remaining = [c.chain_id for c in fixer.structureChains]
+    chain_ids_remaining = [c.id for c in fixer.topology.chains()]
    assert_items_equal(chain_ids_remaining, expected_chain_ids_remaining)
 def test_removechain_indices():