def test_sifts_module(): failures = [] ddG_pdb_ids = ['107L','108L','109L','110L','111L','112L','113L','114L','115L','118L','119L','120L','122L','123L','125L','126L','127L','128L','129L','130L','131L','137L','149L','150L','151L','160L','161L','162L','163L','164L','165L','168L','169L','171L','172L','173L','190L','191L','192L','195L','196L','1A23','1A2I','1A2P','1A3Y','1A43','1A4Y','1A53','1A5E','1A70','1A7A','1A7H','1A7V','1AAL','1AAR','1AAZ','1ABE','1ACB','1ADO','1ADW','1AG2','1AG4','1AG6','1AIE','1AIN','1AJ3','1AJQ','1AKK','1AKM','1AM7','1AMQ','1ANF','1ANK','1ANT','1AO6','1AON','1AOZ','1APC','1APL','1APS','1AQH','1AR1','1ARR','1ATJ','1ATN','1AU1','1AUT','1AV1','1AVR','1AX1','1AXB','1AYE','1AYF','1AZP','1B0O','1B26','1B5M','1B8J','1BAH','1BAN','1BAO','1BCX','1BD8','1BET','1BF4','1BFM','1BGD','1BGL','1BJP','1BKE','1BKS','1BLC','1BMC','1BNI','1BNL','1BNS','1BNZ','1BOY','1BP2','1BPI','1BPL','1BPR','1BPT','1BRF','1BRG','1BRH','1BRI','1BRJ','1BRK','1BSA','1BSB','1BSC','1BSD','1BSE','1BSR','1BTA','1BTI','1BTM','1BUJ','1BVC','1BVU','1BZO','1C0L','1C17','1C2R','1C52','1C53','1C5G','1C6P','1C9O','1CAH','1CBW','1CDC','1CEA','1CEY','1CHK','1CHO','1CHP','1CLW','1CM7','1CMB','1CMS','1COA','1COK','1COL','1CPM','1CSP','1CTS','1CUN','1CUS','1CVW','1CX1','1CX8','1CYC','1CYO','1D0X','1D1G','1DAQ','1DDN','1DE3','1DEC','1DEQ','1DFO','1DFX','1DHN','1DIL','1DIV','1DJU','1DKG','1DKT','1DLC','1DM0','1DO9','1DPM','1DTD','1DTO','1DVC','1DVF','1DVV','1DXX','1DYA','1DYB','1DYC','1DYD','1DYE','1DYF','1DYG','1DYJ','1E21','1E6K','1E6L','1E6M','1E6N','1EDH','1EFC','1EG1','1EHK','1EKG','1EL1','1ELV','1EMV','1EQ1','1ERU','1ESF','1ETE','1EVQ','1EW4','1EXG','1EZA','1F88','1FAJ','1FAN','1FC1','1FEP','1FGA','1FKB','1FKJ','1FLV','1FMK','1FMM','1FNF','1FR2','1FRD','1FTG','1FTT','1FXA','1G6N','1G6V','1G6W','1GA0','1GAD','1GAL','1GAY','1GAZ','1GB0','1GB2','1GB3','1GB7','1GBX','1GD1','1GF8','1GF9','1GFA','1GFE','1GFG','1GFH','1GFJ','1GFK','1GFL','1GFR','1GFT','1GFU','1GFV','1GKG','1GLH','1GLM','1GOB','1GPC','1GQ2','1GRL','1GRX','1GSD','1GTM','1GTX','1GUY','1GXE','1H09','1H0C','1H2I','1H7M','1H8V','1HA4','1HCD','1HEM','1HEN','1HEO','1HEP','1HEQ','1HER','1HEV','1HFY','1HFZ','1HGH','1HGU','1HIB','1HIC','1HIO','1HIX','1HK0','1HME','1HML','1HNG','1HNL','1HOR','1HQK','1HTI','1HUE','1HXN','1HYN','1HYW','1HZ6','1I4N','1I5T','1IAR','1IC2','1IDS','1IFB','1IFC','1IGS','1IGV','1IHB','1IMQ','1INQ','1INU','1IO2','1IOB','1IOF','1IOJ','1IR3','1IRL','1IRO','1ISK','1IX0','1J0X','1J4S','1J7N','1JAE','1JBK','1JHN','1JIW','1JJI','1JKB','1JNK','1JTD','1JTG','1JTK','1K23','1K3B','1K40','1K9Q','1KA6','1KBP','1KDN','1KDU','1KDX','1KEV','1KFD','1KFW','1KJ1','1KKJ','1KTQ','1KUM','1KVA','1KVB','1KVC','1L00','1L02','1L03','1L04','1L05','1L06','1L07','1L08','1L09','1L10','1L11','1L12','1L13','1L14','1L15','1L16','1L17','1L18','1L19','1L20','1L21','1L22','1L23','1L24','1L33','1L34','1L36','1L37','1L38','1L40','1L41','1L42','1L43','1L44','1L45','1L46','1L47','1L48','1L49','1L50','1L51','1L52','1L53','1L54','1L55','1L56','1L57','1L59','1L60','1L61','1L62','1L63','1L65','1L66','1L67','1L68','1L69','1L70','1L71','1L72','1L73','1L74','1L75','1L76','1L77','1L85','1L86','1L87','1L88','1L89','1L90','1L91','1L92','1L93','1L94','1L95','1L96','1L97','1L98','1L99','1LAV','1LAW','1LBI','1LFO','1LHH','1LHI','1LHJ','1LHK','1LHL','1LHM','1LHP','1LLI','1LMB','1LOZ','1LPS','1LRA','1LRE','1LRP','1LS4','1LSN','1LUC','1LVE','1LYE','1LYF','1LYG','1LYH','1LYI','1LYJ','1LZ1','1M7T','1MAX','1MBD','1MBG','1MCP','1MGR','1MJC','1MLD','1MSI','1MUL','1MX2','1MX4','1MX6','1MYK','1MYL','1N02','1N0J','1NAG','1NM1','1NZI','1OA2','1OA3','1OCC','1OH0','1OIA','1OKI','1OLR','1OMU','1ONC','1OPD','1ORC','1OSA','1OSI','1OTR','1OUA','1OUB','1OUC','1OUD','1OUE','1OUF','1OUG','1OUH','1OUI','1OUJ','1OVA','1P2M','1P2N','1P2O','1P2P','1P2Q','1P3J','1PAH','1PBA','1PCA','1PDO','1PGA','1PHP','1PII','1PIN','1PK2','1PMC','1POH','1PPI','1PPN','1PPP','1PQN','1PRE','1PRR','1Q5Y','1QEZ','1QGV','1QHE','1QJP','1QK1','1QLP','1QLX','1QM4','1QND','1QQR','1QQV','1QT6','1QT7','1QU0','1QU7','1QUW','1R2R','1RBN','1RBP','1RBR','1RBT','1RBU','1RBV','1RCB','1RDA','1RDB','1RDC','1REX','1RGC','1RGG','1RH1','1RHD','1RHG','1RIL','1RIS','1RN1','1ROP','1RRO','1RTB','1RTP','1RX4','1S0W','1SAK','1SAP','1SCE','1SEE','1SFP','1SHF','1SHG','1SHK','1SMD','1SPD','1SPH','1SSO','1STF','1STN','1SUP','1SYC','1SYD','1SYE','1SYG','1T3A','1T7C','1T8L','1T8M','1T8N','1T8O','1TBR','1TCA','1TCY','1TEN','1TFE','1TGN','1THQ','1TI5','1TIN','1TIT','1TLA','1TML','1TMY','1TOF','1TPE','1TPK','1TTG','1TUP','1TUR','1U5P','1UBQ','1UCU','1UOX','1URK','1UW3','1UWO','1UZC','1V6S','1VAR','1VFB','1VIE','1VQA','1VQB','1VQC','1VQD','1VQE','1VQF','1VQG','1VQH','1VQI','1VQJ','1W3D','1W4E','1W4H','1W99','1WIT','1WLG','1WPW','1WQ5','1WQM','1WQN','1WQO','1WQP','1WQQ','1WQR','1WRP','1WSY','1XAS','1XY1','1Y4Y','1Y51','1YAL','1YAM','1YAN','1YAO','1YAP','1YAQ','1YCC','1YEA','1YGV','1YHB','1YMB','1YNR','1YPA','1YPB','1YPC','1YPI','1Z1I','1ZNJ','200L','206L','216L','217L','219L','221L','224L','227L','230L','232L','233L','235L','236L','237L','238L','239L','240L','241L','242L','243L','244L','246L','247L','253L','254L','255L','2A01','2A36','2ABD','2AC0','2ACE','2ACY','2ADA','2AFG','2AIT','2AKY','2ASI','2ATC','2B4Z','2BBM','2BQA','2BQB','2BQC','2BQD','2BQE','2BQF','2BQG','2BQH','2BQI','2BQJ','2BQK','2BQM','2BQN','2BQO','2BRD','2CBR','2CHF','2CI2','2CPP','2CRK','2CRO','2DQJ','2DRI','2EQL','2FAL','2FHA','2FX5','2G3P','2GA5','2GSR','2GZI','2HEA','2HEB','2HEC','2HED','2HEE','2HEF','2HIP','2HMB','2HPR','2IFB','2IMM','2L3Y','2L78','2LZM','2MBP','2MLT','2NUL','2OCJ','2PDD','2PEC','2PEL','2PRD','2Q98','2RBI','2RN2','2RN4','2SNM','2SOD','2TMA','2TRT','2TRX','2TS1','2WSY','2ZAJ','2ZTA','3BCI','3BCK','3BD2','3BLS','3CHY','3D2A','3ECA','3FIS','3HHR','3MBP','3PGK','3PRO','3PSG','3SSI','3TIM','3VUB','451C','487D','4BLM','4CPA','4GCR','4LYZ','4SGB','4TLN','4TMS','5AZU','5CPV','5CRO','5MDH','5PEP','6TAA','7AHL','7PTI','8PTI','8TIM','9INS','9PCY',] for no_xml_case in ['1GTX', '1SEE', '1UOX', '1WSY', '1YGV', '2MBP']: ddG_pdb_ids.remove(no_xml_case) for bad_sifts_mapping_case in ['1N02', '487D']: ddG_pdb_ids.remove(bad_sifts_mapping_case) for no_pdb_uniprot_mapping_case in ['2IMM']: ddG_pdb_ids.remove(no_pdb_uniprot_mapping_case) ddG_pdb_ids = ['1GTX', '1SEE', '1UOX', '1WSY', '1YGV', '2MBP'] ddG_pdb_ids = ['1N02', '487D'] + ['2IMM'] count = 1 num_cases = len(ddG_pdb_ids) for pdb_id in ddG_pdb_ids: try: print('Case %d/%d: %s' % (count, num_cases, pdb_id)) sifts_map = SIFTS.retrieve(pdb_id, cache_dir = cache_dir, acceptable_sequence_percentage_match = 80.0) except MissingSIFTSRecord: colortext.warning('No SIFTS XML exists for %s.' % pdb_id) except BadSIFTSMapping: colortext.warning('The SIFTS mapping for %s was considered a bad mapping at the time of writing.' % pdb_id) except NoSIFTSPDBUniParcMapping: colortext.warning('The SIFTS file for %s does not map to UniParc sequences at the time of writing.' % pdb_id) except Exception, e: colortext.warning(str(e)) colortext.error(traceback.format_exc()) failures.append(pdb_id) count += 1
def _get_ResultSetFilter_data(): s_module = "ddglib.ddgfilters" #clsmembers = inspect.getmembers(sys.modules[s_module], lambda member: member.__module__ == s_module and inspect.isclass) #clsmembers = inspect.getmembers(sys.modules[s_module], lambda member: member.inspect.isclass(member)) m_filters = [] m_resultsets = [] d_filters = {} s_module = "ddglib.ddgfilters" for m in inspect.getmembers(sys.modules[s_module]): o = m[1] if inspect.isclass(o) and o.__module__ == s_module: classnm = m[0] if classnm.find("Filter") != -1: d = {"name": classnm, "class": o} m_filters.append(d) d_filters[classnm] = d elif classnm.find("ResultSet") != -1: e_Filter = "%sFilter" % classnm[:classnm.find("ResultSet")] e_Filter = o.allowed_filters #"%sFilter" % classnm[:classnm.find("ResultSet")] m_resultsets.append({ "name": classnm, "class": o, "filter": e_Filter }) else: colortext.error("Unknown class '%s' found." % classnm) return m_filters, m_resultsets, d_filters
def match(self, other): ''' This is a noisy terminal-printing function at present since there is no need to make it a proper API function.''' colortext.message("FASTA Match") for frompdbID, fromchains in sorted(self.iteritems()): matched_pdbs = {} matched_chains = {} for fromchain, fromsequence in fromchains.iteritems(): for topdbID, tochains in other.iteritems(): for tochain, tosequence in tochains.iteritems(): if fromsequence == tosequence: matched_pdbs[topdbID] = matched_pdbs.get(topdbID, set()) matched_pdbs[topdbID].add(fromchain) matched_chains[fromchain] = matched_chains.get(fromchain, []) matched_chains[fromchain].append((topdbID, tochain)) foundmatches = [] colortext.printf(" %s" % frompdbID, color="silver") for mpdbID, mchains in matched_pdbs.iteritems(): if mchains == set(fromchains.keys()): foundmatches.append(mpdbID) colortext.printf(" PDB %s matched PDB %s on all chains" % (mpdbID, frompdbID), color="white") if foundmatches: for fromchain, fromsequence in fromchains.iteritems(): colortext.printf(" %s" % (fromchain), color = "silver") colortext.printf(" %s" % (fromsequence), color = self.unique_sequences[fromsequence]) mstr = [] for mchain in matched_chains[fromchain]: if mchain[0] in foundmatches: mstr.append("%s chain %s" % (mchain[0], mchain[1])) colortext.printf(" Matches: %s" % ", ".join(mstr)) else: colortext.error(" No matches found.")
def _get_ResultSetFilter_data(): s_module = "ddglib.ddgfilters" #clsmembers = inspect.getmembers(sys.modules[s_module], lambda member: member.__module__ == s_module and inspect.isclass) #clsmembers = inspect.getmembers(sys.modules[s_module], lambda member: member.inspect.isclass(member)) m_filters = [] m_resultsets = [] d_filters = {} s_module = "ddglib.ddgfilters" for m in inspect.getmembers(sys.modules[s_module]): o = m[1] if inspect.isclass(o) and o.__module__ == s_module: classnm = m[0] if classnm.find("Filter") != -1: d = {"name" : classnm, "class" : o} m_filters.append(d) d_filters[classnm] = d elif classnm.find("ResultSet") != -1: e_Filter = "%sFilter" % classnm[:classnm.find("ResultSet")] e_Filter = o.allowed_filters #"%sFilter" % classnm[:classnm.find("ResultSet")] m_resultsets.append({"name" : classnm, "class" : o, "filter" : e_Filter}) else: colortext.error("Unknown class '%s' found." % classnm) return m_filters, m_resultsets, d_filters
def __init__(self, user, host, db, passwd, port = 3306, socket = '/var/lib/mysql/mysql.sock'): try: self.db_interface = DatabaseInterface({}, isInnoDB=True, numTries=1, host=host, db=db, user=user, passwd=passwd, port=3306, unix_socket=socket, passwdfile=None, use_utf=False, use_locking=True) except Exception, e: colortext.error('An exception was thrown trying to connect to the database.') colortext.warning(str(e)) print(traceback.format_exc()) sys.exit(1)
def plot(self, table_name, RFunction, output_filename = None, filetype = "pdf"): '''Results is expect to be a list of dicts each of which has the keys ExperimentID and ddG.''' if (not self.analysis_tables) or (not table_name): raise Exception("There are no analysis tables to plot.") if not table_name in self.analysis_tables.keys(): raise Exception("The analysis table '%s' does not exist." % table_name) R_return_values = {} gplot = None analysis_table = self.analysis_tables[table_name] if self.quiet_level >= 3: print(table_name) print(RFunction) if len(analysis_table.points) == 1: raise Exception("The analysis table %s set only has one data point. At least two points are required." % table_name) else: inputfname = self.CreateCSVFile(table_name) if self.quiet_level >= 3: print(inputfname) try: if self.quiet_level >= 2: colortext.printf("Running %s." % RFunction) if output_filename: colortext.printf("Saving graph as %s with filename %s." % (filetype, output_filename)) output_fname = output_filename if not output_fname: output_fname = rosettahelper.writeTempFile(".", "") R_output = RFunction(inputfname, output_fname, filetype) R_return_values = RUtilities.parse_R_output(R_output) colortext.message(table_name) print(" %s" % str(RFunction)) for k, v in sorted(R_return_values.iteritems()): print(" %s: %s" % (str(k), str(v))) if not output_filename: contents = rosettahelper.readBinaryFile(output_fname) delete_file(output_fname) description = None for file_suffix, details in RFunctions.iteritems(): if details[1] == RFunction: description = details[0] assert(description) gplot = AnalysisObject(table_name, description, filetype, contents) else: gplot = output_filename except Exception, e: import traceback colortext.error(traceback.format_exc()) delete_file(inputfname) raise Exception(e) delete_file(inputfname)
def fix_1AYE_InputFiles(prediction_set): '''This is a once-off function which should only be run once per prediction set as each run changes the mutfile and this change should only occur once.''' import pickle ddGdb = ddgdbapi.ddGDatabase() BadPredictions = sorted(set([(r['PredictionID'], r['Status']) for r in ddGdb.execute_select(''' SELECT Prediction.ID AS PredictionID, Status FROM Prediction INNER JOIN UserDataSetExperiment ON UserDataSetExperiment.ID=Prediction.UserDataSetExperimentID WHERE PredictionSet=%s AND PDBFileID='1AYE' ''', parameters=(prediction_set,))])) BadPredictionIDs = sorted(set([r[0] for r in BadPredictions])) print(BadPredictions) num_active = len([r for r in BadPredictions if r[1] == 'active']) num_queued = len([r for r in BadPredictions if r[1] == 'queued']) statuses = sorted(set([r[1] for r in BadPredictions])) if ('active' in statuses) or ('queued' in statuses): colortext.error("Cannot proceed - there are %d active jobs and %d queued in the list that need to be fixed up. Stop the DDG scheduler, remove the queued constraint, and rerun this function. " % (num_active, num_queued)) if num_active: print("%d active jobs: %s" % (num_active, ", ".join([str(r[0]) for r in BadPredictions if r[1] == 'active']))) if num_queued: print("%d queued jobs: %s" % (num_queued, ", ".join([str(r[0]) for r in BadPredictions if r[1] == 'queued']))) return for PredictionID in BadPredictionIDs: r = ddGdb.execute_select("SELECT InputFiles FROM Prediction WHERE ID=%s", parameters=(PredictionID,)) assert(len(r) == 1) r = r[0] InputFiles = pickle.loads(r['InputFiles']) assert(InputFiles.keys() == ['MUTFILE']) mutfile = InputFiles['MUTFILE'] colortext.message("\n%d" % PredictionID) colortext.warning('original') print(mutfile) lines = mutfile.split("\n") assert(lines[0].startswith('total')) num_muts = int(lines[0][5:]) assert(lines[1] == str(num_muts)) for x in range(2, num_muts + 2): mutline = lines[x] tokens = mutline.split() tokens[1] = str(int(tokens[1]) - 1) lines[x] = " ".join(tokens) new_mutfile = "\n".join(lines) colortext.warning('fixed') print(new_mutfile) p = pickle.dumps({'MUTFILE' : new_mutfile})
def test_sequences(b, sequences): failed_cases = [] c = 0 for sequence in sequences: try: c += 1 colortext.message('\n{0}/{1}: {2}'.format(c, len(sequences), sequence)) hits = b.by_sequence(sequence) if hits: colortext.warning('{0} hits: {1}'.format(len(hits), ','.join(hits))) else: colortext.warning('No hits') except Exception, e: colortext.error('FAILED') failed_cases.append((sequence, str(e), traceback.format_exc()))
def updateEvents(self, calendar_id, newEvents): currentEvents = self.getEventsTable(calendar_id) #colortext.message(newEvents) #colortext.warning(currentEvents) # Events to remove toRemove = [] for startdateTitle, event in sorted(currentEvents.iteritems()): if event["title"].find("birthday") != -1: # Don't remove birthdays continue if newEvents.get(startdateTitle): newEvent = newEvents[startdateTitle] if newEvent["enddate"] == event["enddate"]: if event["location"].startswith(newEvent["location"]): if str(newEvent["title"]) == str(event["title"]): # Don't remove events which are in both newEvents and the calendar continue # Remove events which are on the calendar but not in newEvents toRemove.append(startdateTitle) # Events to add toAdd = [] for startdateTitle, event in sorted(newEvents.iteritems()): if currentEvents.get(startdateTitle): currentEvent = currentEvents[startdateTitle] if currentEvent["enddate"] == event["enddate"]: if currentEvent["location"].startswith(event["location"]): if str(currentEvent["title"]) == str(event["title"]): # Don't add events which are in both newEvents and the calendar continue # Add events which are in newEvents but not on the calendar toAdd.append(startdateTitle) if toRemove: colortext.error("Removing these %d events:" % len(toRemove)) for dtTitle in toRemove: colortext.warning(dtTitle) self.removeEvent(calendar_id, currentEvents[dtTitle]["event"].id) if toAdd: colortext.message("Adding these %d events:" % len(toAdd)) for dtTitle in toAdd: newEvent = newEvents[dtTitle] #print(dtTitle, newEvent) self.addNewEvent(calendar_id, dtTitle[0], newEvent["enddate"], newEvent["location"], newEvent["title"])
def test_pdb_files(b, pdb_ids): failed_cases = [] c = 0 for pdb_id in pdb_ids: try: c += 1 colortext.message('\n{0}/{1}: {2}'.format(c, len(pdb_ids), pdb_id)) hits = b.by_pdb(pdb_id) if hits: colortext.warning('{0} hits: {1}'.format(len(hits), ','.join(hits))) else: colortext.warning('No hits') except Exception, e: colortext.error('FAILED') failed_cases.append((pdb_id, str(e), traceback.format_exc()))
def prune(self, arbitrary_atom_serial_numbers, sidechain_atom_serial_numbers = set(), atoms_serial_numbers_to_keep_in_cutting = set(), keep_CA_in_cutting = True, generate_pymol_session = True, bonsai_label = 'Bonsai', cutting_label = 'Cutting', pymol_executable = 'pymol'): '''Returns the content of two PDB files and (optionally) a PyMOL session and associated script. The first returned PDB file ("bonsai") is missing the ATOM (and any related ANISOU) and HETATM records identified by atom_serial_numbers. The second returned PDB file ("cutting") only contains ATOM, ANISOU, and HETATM records which are identified by atom_serial_numbers. Both PDB objects contain all records from the original PDB which are not ATOM, ANISOU, or HETATM records. If keep_CA_in_cutting is set, the cutting will also contain the associated Calpha atoms. This is useful purely to visualize the cutting in the PyMOL session. If a PyMOL session is not to be generated, this option should be set to False. ''' bonsai = [] cutting = [] # Determine the set of sidechain residues in case keep_CA_in_cutting is True and we wish to keep those atoms in the cutting sidechain_residues = set() if keep_CA_in_cutting and sidechain_atom_serial_numbers: for line in self.indexed_lines: if line[0] == 'ATOM' and line[1] in sidechain_atom_serial_numbers: residue_id = line[3].residue.id() sidechain_residues.add(residue_id[0] + residue_id[1]) atom_serial_numbers_to_remove = arbitrary_atom_serial_numbers.union(sidechain_atom_serial_numbers) for line in self.indexed_lines: if line[0]: # record type PDB_line = line[2] if line[1] in atom_serial_numbers_to_remove: cutting.append(PDB_line) else: if atoms_serial_numbers_to_keep_in_cutting and int(PDB_line[6:11]) in atoms_serial_numbers_to_keep_in_cutting: cutting.append(PDB_line) elif keep_CA_in_cutting and PDB_line[21:27] in sidechain_residues and PDB_line[12:16] == ' CA ': cutting.append(PDB_line) bonsai.append(PDB_line) else: bonsai.append(line[1]) cutting.append(line[1]) bonsai_pdb_content = '\n'.join(bonsai) cutting_pdb_content = '\n'.join(cutting) PSE_file, PSE_script = None, None try: PSE_file, PSE_script = self.generate_pymol_session(bonsai_pdb_content, cutting_pdb_content, bonsai_label = bonsai_label, cutting_label = cutting_label, pymol_executable = pymol_executable, settings = {}) except Exception, e: colortext.error('Failed to generate the PyMOL session: "{0}"'.format(e))
def _generate_schema_diagram(self, show_fk_only): tempfiles = [] output_handle, sql_schema_filepath = open_temp_file('/tmp', ftype = 'w') tempfiles.append(sql_schema_filepath) try: #output_handle.write('%s\n\n' % self.db_schema) output_handle.write('%s\n\n' % self.sanitize_schema())#mysqldump_schema) output_handle.close() except: output_handle.close() try: png_handle, png_filepath = open_temp_file('/tmp', ftype = 'w') png_handle.close() tempfiles.append(png_filepath) c = [ "sqlt-diagram", "-d=MySQL", "-i=png", "-t=%s database on %s" % (self.db, self.host), "-o=%s" % png_filepath, "--color", sql_schema_filepath, ] if show_fk_only: # Useful to print a smaller schema of just the primary/foreign keys c.append("--show-fk-only") p = subprocess.Popen(c, stdout=subprocess.PIPE) stdout, stderr = p.communicate() if not p.returncode == 0: if stderr: raise colortext.Exception("Error - sqlt-diagram exited with %d: '%s'." % (p.returncode, stderr)) else: raise colortext.Exception("Error - sqlt-diagram exited with %d." % (p.returncode)) except Exception, e: colortext.error('Failed!') print(str(e))
def test_pdbml_speed(): test_cases = [ '1WSY', '1YGV', '487D', '1HIO', '1H38', '3ZKB', ] for test_case in test_cases: print("\n") colortext.message("Creating PDBML object for %s" % test_case) #PDBML.retrieve(test_case, cache_dir = cache_dir) print("") colortext.printf("Using the old minidom class", color = 'cyan') t1 = time.clock() p_minidom = PDBML_slow.retrieve(test_case, cache_dir = cache_dir) t2 = time.clock() colortext.message("Done in %0.2fs!" % (t2 - t1)) print("") colortext.printf("Using the new sax class", color = 'cyan') t1 = time.clock() p_sax = PDBML.retrieve(test_case, cache_dir = cache_dir) t2 = time.clock() colortext.message("Done in %0.2fs!" % (t2 - t1)) colortext.write("\nEquality test: ", color = 'cyan') try: assert(p_minidom.atom_to_seqres_sequence_maps.keys() == p_sax.atom_to_seqres_sequence_maps.keys()) for c, s_1 in p_minidom.atom_to_seqres_sequence_maps.iteritems(): s_2 = p_sax.atom_to_seqres_sequence_maps[c] assert(str(s_1) == str(s_2)) colortext.message("passed\n") except: colortext.error("failed\n")
def removeEvent(self, calendar_id, event_id): for i in range(3): try: assert(self.service.events().get(calendarId = self.configured_calendar_ids[calendar_id], eventId = event_id).execute()) self.service.events().delete(calendarId = self.configured_calendar_ids[calendar_id], eventId = event_id).execute() break except Exception, e: colortext.error("An error occurred:") colortext.error(e) colortext.error("Trying again.") time.sleep(2)
def addNewEvent(self, calendar_id, startdate, enddate, location, title): colortext.message("\nAdding %s on %s at %s" % (title, startdate, location)) #start_time = startdate.strftime('%Y-%m-%dT%H:%M:%S').isoformat() #end_time = enddate.strftime('%Y-%m-%dT%H:%M:%S').isoformat() start_time = startdate.isoformat() end_time = enddate.isoformat() loc = location if loc.startswith("Tahoe"): loc = "%s, 10 minutes outside Truckee, CA @ 39.328455,-120.184078" % loc else: if location.startswith("BH "): loc = "%s, Byers Hall" % loc loc = "%s, removeEvent/Mission Bay, San Francisco, CA @ 37.767952,-122.392214" % loc for i in range(3): try: self.service.events().insert( calendarId = self.configured_calendar_ids[calendar_id], body = { "start" : { "timeZone" : self.timezone_string, "dateTime" : start_time, }, "end" : { "timeZone" : self.timezone_string, "dateTime" : end_time, }, "location" : loc, "summary" : title, "description" : title }).execute() break except Exception, e: colortext.error("An error occurred:") colortext.error(traceback.format_exc()) colortext.error(e) colortext.error("Trying again.") time.sleep(2)
def test_ddg_pdb_ids(): # Test set - 845 PDB IDs. A small number required manual intervention but most are parsed and mapped automatically. 5 needed to use the SIFTS mappings. ddG_pdb_ids = ['107L','108L','109L','110L','111L','112L','113L','114L','115L','118L','119L','120L','122L','123L','125L','126L','127L','128L','129L','130L','131L','137L','149L','150L','151L','160L','161L','162L','163L','164L','165L','168L','169L','171L','172L','173L','190L','191L','192L','195L','196L','1A23','1A2I','1A2P','1A3Y','1A43','1A4Y','1A53','1A5E','1A70','1A7A','1A7H','1A7V','1AAL','1AAR','1AAZ','1ABE','1ACB','1ADO','1ADW','1AG2','1AG4','1AG6','1AIE','1AIN','1AJ3','1AJQ','1AKK','1AKM','1AM7','1AMQ','1ANF','1ANK','1ANT','1AO6','1AON','1AOZ','1APC','1APL','1APS','1AQH','1AR1','1ARR','1ATJ','1ATN','1AU1','1AUT','1AV1','1AVR','1AX1','1AXB','1AYE','1AYF','1AZP','1B0O','1B26','1B5M','1B8J','1BAH','1BAN','1BAO','1BCX','1BD8','1BET','1BF4','1BFM','1BGD','1BGL','1BJP','1BKE','1BKS','1BLC','1BMC','1BNI','1BNL','1BNS','1BNZ','1BOY','1BP2','1BPI','1BPL','1BPR','1BPT','1BRF','1BRG','1BRH','1BRI','1BRJ','1BRK','1BSA','1BSB','1BSC','1BSD','1BSE','1BSR','1BTA','1BTI','1BTM','1BUJ','1BVC','1BVU','1BZO','1C0L','1C17','1C2R','1C52','1C53','1C5G','1C6P','1C9O','1CAH','1CBW','1CDC','1CEA','1CEY','1CHK','1CHO','1CHP','1CLW','1CM7','1CMB','1CMS','1COA','1COK','1COL','1CPM','1CSP','1CTS','1CUN','1CUS','1CVW','1CX1','1CX8','1CYC','1CYO','1D0X','1D1G','1DAQ','1DDN','1DE3','1DEC','1DEQ','1DFO','1DFX','1DHN','1DIL','1DIV','1DJU','1DKG','1DKT','1DLC','1DM0','1DO9','1DPM','1DTD','1DTO','1DVC','1DVF','1DVV','1DXX','1DYA','1DYB','1DYC','1DYD','1DYE','1DYF','1DYG','1DYJ','1E21','1E6K','1E6L','1E6M','1E6N','1EDH','1EFC','1EG1','1EHK','1EKG','1EL1','1ELV','1EMV','1EQ1','1ERU','1ESF','1ETE','1EVQ','1EW4','1EXG','1EZA','1F88','1FAJ','1FAN','1FC1','1FEP','1FGA','1FKB','1FKJ','1FLV','1FMK','1FMM','1FNF','1FR2','1FRD','1FTG','1FTT','1FXA','1G6N','1G6V','1G6W','1GA0','1GAD','1GAL','1GAY','1GAZ','1GB0','1GB2','1GB3','1GB7','1GBX','1GD1','1GF8','1GF9','1GFA','1GFE','1GFG','1GFH','1GFJ','1GFK','1GFL','1GFR','1GFT','1GFU','1GFV','1GKG','1GLH','1GLM','1GOB','1GPC','1GQ2','1GRL','1GRX','1GSD','1GTM','1GTX','1GUY','1GXE','1H09','1H0C','1H2I','1H7M','1H8V','1HA4','1HCD','1HEM','1HEN','1HEO','1HEP','1HEQ','1HER','1HEV','1HFY','1HFZ','1HGH','1HGU','1HIB','1HIC','1HIO','1HIX','1HK0','1HME','1HML','1HNG','1HNL','1HOR','1HQK','1HTI','1HUE','1HXN','1HYN','1HYW','1HZ6','1I4N','1I5T','1IAR','1IC2','1IDS','1IFB','1IFC','1IGS','1IGV','1IHB','1IMQ','1INQ','1INU','1IO2','1IOB','1IOF','1IOJ','1IR3','1IRL','1IRO','1ISK','1IX0','1J0X','1J4S','1J7N','1JAE','1JBK','1JHN','1JIW','1JJI','1JKB','1JNK','1JTD','1JTG','1JTK','1K23','1K3B','1K40','1K9Q','1KA6','1KBP','1KDN','1KDU','1KDX','1KEV','1KFD','1KFW','1KJ1','1KKJ','1KTQ','1KUM','1KVA','1KVB','1KVC','1L00','1L02','1L03','1L04','1L05','1L06','1L07','1L08','1L09','1L10','1L11','1L12','1L13','1L14','1L15','1L16','1L17','1L18','1L19','1L20','1L21','1L22','1L23','1L24','1L33','1L34','1L36','1L37','1L38','1L40','1L41','1L42','1L43','1L44','1L45','1L46','1L47','1L48','1L49','1L50','1L51','1L52','1L53','1L54','1L55','1L56','1L57','1L59','1L60','1L61','1L62','1L63','1L65','1L66','1L67','1L68','1L69','1L70','1L71','1L72','1L73','1L74','1L75','1L76','1L77','1L85','1L86','1L87','1L88','1L89','1L90','1L91','1L92','1L93','1L94','1L95','1L96','1L97','1L98','1L99','1LAV','1LAW','1LBI','1LFO','1LHH','1LHI','1LHJ','1LHK','1LHL','1LHM','1LHP','1LLI','1LMB','1LOZ','1LPS','1LRA','1LRE','1LRP','1LS4','1LSN','1LUC','1LVE','1LYE','1LYF','1LYG','1LYH','1LYI','1LYJ','1LZ1','1M7T','1MAX','1MBD','1MBG','1MCP','1MGR','1MJC','1MLD','1MSI','1MUL','1MX2','1MX4','1MX6','1MYK','1MYL','1N02','1N0J','1NAG','1NM1','1NZI','1OA2','1OA3','1OCC','1OH0','1OIA','1OKI','1OLR','1OMU','1ONC','1OPD','1ORC','1OSA','1OSI','1OTR','1OUA','1OUB','1OUC','1OUD','1OUE','1OUF','1OUG','1OUH','1OUI','1OUJ','1OVA','1P2M','1P2N','1P2O','1P2P','1P2Q','1P3J','1PAH','1PBA','1PCA','1PDO','1PGA','1PHP','1PII','1PIN','1PK2','1PMC','1POH','1PPI','1PPN','1PPP','1PQN','1PRE','1PRR','1Q5Y','1QEZ','1QGV','1QHE','1QJP','1QK1','1QLP','1QLX','1QM4','1QND','1QQR','1QQV','1QT6','1QT7','1QU0','1QU7','1QUW','1R2R','1RBN','1RBP','1RBR','1RBT','1RBU','1RBV','1RCB','1RDA','1RDB','1RDC','1REX','1RGC','1RGG','1RH1','1RHD','1RHG','1RIL','1RIS','1RN1','1ROP','1RRO','1RTB','1RTP','1RX4','1S0W','1SAK','1SAP','1SCE','1SEE','1SFP','1SHF','1SHG','1SHK','1SMD','1SPD','1SPH','1SSO','1STF','1STN','1SUP','1SYC','1SYD','1SYE','1SYG','1T3A','1T7C','1T8L','1T8M','1T8N','1T8O','1TBR','1TCA','1TCY','1TEN','1TFE','1TGN','1THQ','1TI5','1TIN','1TIT','1TLA','1TML','1TMY','1TOF','1TPE','1TPK','1TTG','1TUP','1TUR','1U5P','1UBQ','1UCU','1UOX','1URK','1UW3','1UWO','1UZC','1V6S','1VAR','1VFB','1VIE','1VQA','1VQB','1VQC','1VQD','1VQE','1VQF','1VQG','1VQH','1VQI','1VQJ','1W3D','1W4E','1W4H','1W99','1WIT','1WLG','1WPW','1WQ5','1WQM','1WQN','1WQO','1WQP','1WQQ','1WQR','1WRP','1WSY','1XAS','1XY1','1Y4Y','1Y51','1YAL','1YAM','1YAN','1YAO','1YAP','1YAQ','1YCC','1YEA','1YGV','1YHB','1YMB','1YNR','1YPA','1YPB','1YPC','1YPI','1Z1I','1ZNJ','200L','206L','216L','217L','219L','221L','224L','227L','230L','232L','233L','235L','236L','237L','238L','239L','240L','241L','242L','243L','244L','246L','247L','253L','254L','255L','2A01','2A36','2ABD','2AC0','2ACE','2ACY','2ADA','2AFG','2AIT','2AKY','2ASI','2ATC','2B4Z','2BBM','2BQA','2BQB','2BQC','2BQD','2BQE','2BQF','2BQG','2BQH','2BQI','2BQJ','2BQK','2BQM','2BQN','2BQO','2BRD','2CBR','2CHF','2CI2','2CPP','2CRK','2CRO','2DQJ','2DRI','2EQL','2FAL','2FHA','2FX5','2G3P','2GA5','2GSR','2GZI','2HEA','2HEB','2HEC','2HED','2HEE','2HEF','2HIP','2HMB','2HPR','2IFB','2IMM','2L3Y','2L78','2LZM','2MBP','2MLT','2NUL','2OCJ','2PDD','2PEC','2PEL','2PRD','2Q98','2RBI','2RN2','2RN4','2SNM','2SOD','2TMA','2TRT','2TRX','2TS1','2WSY','2ZAJ','2ZTA','3BCI','3BCK','3BD2','3BLS','3CHY','3D2A','3ECA','3FIS','3HHR','3K0NA_lin','3K0NB_lin','3K0On_lin','3MBP','3PGK','3PRO','3PSG','3SSI','3TIM','3VUB','451C','487D','4BLM','4CPA','4GCR','4LYZ','4SGB','4TLN','4TMS','5AZU','5CPV','5CRO','5MDH','5PEP','6TAA','7AHL','7PTI','8PTI','8TIM','9INS','9PCY',] print(len(ddG_pdb_ids)) fix_later = set([ # SELECT * FROM `Experiment` WHERE `PDBFileID` IN ('1OLR') # SELECT * FROM `DataSetDDG` WHERE `PDBFileID` IN ('1OLR') # SELECT * FROM `UserDataSetExperiment` WHERE `PDBFileID` IN ('1OLR') # SELECT * FROM `UserAnalysisSet` WHERE `PDB_ID` IN ('1OLR') ]) failed_cases = [] specific_cut_offs = { '1AR1' : (78, 76, 73.00), # Chain C has a Clustal Omega match at 77% '1BF4' : (80, 77, 87.00), # Chain A has a Clustal Omega match at 79% '1MCP' : (100, 98, 50.00), # Chain H has a Clustal Omega match at 100% but only half the chain '2ZAJ' : (75, 72, 70.00), # '1CPM' : (73, 71, 70.00), # } to_be_hardcoded = { # Special case: 1N02. This needs to be handled manually. # DBREF 1N02 A 1 3 UNP P81180 CVN_NOSEL 1 3 # DBREF 1N02 A 4 49 UNP P81180 CVN_NOSEL 54 992IMM # DBREF 1N02 A 50 54 UNP P81180 CVN_NOSEL 49 53 # DBREF 1N02 A 55 99 UNP P81180 CVN_NOSEL 4 48 # DBREF 1N02 A 100 101 UNP P81180 CVN_NOSEL 100 101 '1N02', ('2IMM'), # No PDB <-> UniProt mapping } test_these = [ '1KJ1' ] colortext.message('Testing %d PDB files for the DDG database.' % len(ddG_pdb_ids)) #start_x = 0 start_x = 0 for x in range(start_x, len(ddG_pdb_ids)): ddG_pdb_id = ddG_pdb_ids[x] if test_these and ddG_pdb_id not in test_these: continue if ddG_pdb_id not in fix_later: colortext.warning('Testing PDB file number %d: %s' % (x, ddG_pdb_id)) starting_clustal_cut_off = 100 min_clustal_cut_off = 71 acceptable_sequence_percentage_match = 80.0 if specific_cut_offs.get(ddG_pdb_id): starting_clustal_cut_off, min_clustal_cut_off, acceptable_sequence_percentage_match = specific_cut_offs[ddG_pdb_id] try: rr = ResidueRelatrix(ddG_pdb_id, rosetta_scripts_path, rosetta_database_path, starting_clustal_cut_off = starting_clustal_cut_off, min_clustal_cut_off = min_clustal_cut_off, acceptable_sequence_percentage_match = acceptable_sequence_percentage_match, cache_dir = '/home/oconchus/temp') except SpecificException: failed_cases.append((x, ddG_pdb_id, str(e))) else: colortext.warning('SKIPPING PDB file number %d: %s' % (x, ddG_pdb_id)) if failed_cases: colortext.error('Failed cases:') fcc = 0 for f in failed_cases: if fcc == 0: colortext.warning(str(f)) else: colortext.printf(str(f), color = 'cyan') fcc = (fcc + 1) % 2 print("failed_cases", failed_cases)
def generate_JSON_dataset(dataset_ID, pdb_data, pub_data): record_data = {} #1LRP #1LMB # 1 JSON object per dataset record failure_count = 0 records = ddGdb.execute_select('SELECT * FROM DataSetDDG WHERE DataSetID=%s', parameters=(dataset_ID,)) colortext.warning('Starting with %d records.' % (len(records))) mutation_count = {1:0, 2:0, 3:0, 4:0, 5:0} for r in records: mutation_is_reversed = r['MutationIsReversed'] == 1 d = dict( _DataSetDDGID = r['ID'], RecordID = r['RecordNumber'], AggregateType = r['AggregateType'], DDG = r['PublishedValue'], PDBFileID = r['PDBFileID'], DerivedMutation = mutation_is_reversed, ) # Parse PDB if not(cached_pdbs.get(r['PDBFileID'])): cached_pdbs[r['PDBFileID']] = PDB(ddGdb.execute_select('SELECT Content FROM PDBFile WHERE ID=%s', parameters=(r['PDBFileID'],))[0]['Content']) # Store PDB data PDBResolution = None, PDBMethodOfDetermination = None, try: PDBResolution = cached_pdbs[r['PDBFileID']].get_resolution() except: pass try: PDBMethodOfDetermination = cached_pdbs[r['PDBFileID']].get_techniques() except: pass pdb_data[r['PDBFileID']] = dict( Resolution = PDBResolution, MethodOfDetermination = PDBMethodOfDetermination, ) assay_DDGs = ddGdb.execute_select(''' SELECT * FROM DataSetDDGSource INNER JOIN ExperimentAssayDDG ON DataSetDDGSource.ExperimentAssayID = ExperimentAssayDDG.ExperimentAssayID AND DataSetDDGSource.Type = ExperimentAssayDDG.Type INNER JOIN ExperimentAssay ON ExperimentAssayDDG.ExperimentAssayID = ExperimentAssay.ID WHERE DataSetDDGID=%s''', parameters=(r['ID'],)) ExperimentID = set([a['ExperimentID'] for a in assay_DDGs]) if len(ExperimentID) != 1: colortext.message('%d records passed' % len(record_data)) # Cases where 1FLV and 1FTG need to be elided if sorted(ExperimentID) in ([113699, 113830], [113704, 113832], [113705, 113836]): ExperimentID = [sorted(ExperimentID)[0]] elif sorted(ExperimentID) in ([112149, 112591],): # ExperimentID is used below for mutation details but these agree in this case. 1LZ1, 2BQA ExperimentID = [sorted(ExperimentID)[0]] elif sorted(ExperimentID) in ( [112141, 112583L], [112136, 112578], [112137, 112579], [112142, 112584], [112139, 112581], [112140, 112582], [112146, 112588], [112147, 112589], [112148, 112590] ): # ExperimentID is used below for mutation details but these agree in this case. 1REX, 2BQA ExperimentID = [sorted(ExperimentID)[0]] elif sorted(ExperimentID) in ([112227, 112323], [112288, 113039], [111587, 112379]): # ExperimentID is used below for mutation details but these agree in this case. 2LZM, 1L63 ExperimentID = [sorted(ExperimentID)[0]] else: colortext.warning( '\n'.join(['%(PDBFileID)s %(Chain)s %(WildTypeAA)s %(ResidueID)s %(MutantAA)s' % rii for rii in ddGdb.execute_select(''' SELECT * FROM `ExperimentMutation` INNER JOIN Experiment ON Experiment.ID=ExperimentID WHERE `ExperimentID` IN (%s)''' % ','.join(map(str, ExperimentID)))])) pprint.pprint(r) colortext.error(map(int, ExperimentID)) #pprint.pprint(assay_DDGs) print(sorted(ExperimentID)) assert(len(ExperimentID) == 1) ExperimentID = ExperimentID.pop() d['_ExperimentID'] = ExperimentID experimental_DDGs = [] for a in assay_DDGs: experimental_DDGs.append(dict( DDG = a['Value'], DDGType = a['Type'], Publication = a['Publication'], LocationOfValueInPublication = a['LocationOfValueInPublication'], Temperature = a['Temperature'], pH= a['pH'], )) # Store Publication data pub_data[a['Publication']] = cached_publications[a['Publication']] d['ExperimentalDDGs'] = experimental_DDGs # Retrieve mutations mutation_records = ddGdb.execute_select('SELECT * FROM ExperimentMutation WHERE ExperimentID=%s ORDER BY ResidueID', parameters=(ExperimentID,)) if dataset_ID == "AlaScan-GPK_2014/09/25": assert(len(mutation_records) == 1) mutations = [] failed_check = False mutation_count[len(mutation_records)] += 1 for mutation in mutation_records: mutation_d = {} #if ExperimentID == 109911: # d['PDBFileID'] = '1WQ5' # Hack for one 1BKS case mutation_d['Chain'] = mutation['Chain'] mutation_d['ResidueID'] = mutation['ResidueID'] if mutation_is_reversed: mutation_d['MutantAA'] = mutation['WildTypeAA'] mutation_d['WildTypeAA'] = mutation['MutantAA'] else: mutation_d['WildTypeAA'] = mutation['WildTypeAA'] mutation_d['MutantAA'] = mutation['MutantAA'] if dataset_ID == "AlaScan-GPK_2014/09/25": if d['PDBFileID'] == '1LMB': mutation_d['Chain'] = '3' # Hack for the PDB replacement 1LRP (3.2A) -> 1LMB (1.8A) if d['PDBFileID'] == '1U5P' and int(mutation_d['ResidueID']) < 1600: mutation_d['ResidueID'] = str(int(mutation_d['ResidueID']) + 1762) # Hack for the PDB replacement 1AJ3, NMR -> 1U5P (2A) if dataset_ID == "Kellogg_10.1002/prot.22921_2010/12/03": if d['PDBFileID'] == '1U5P' and int(mutation_d['ResidueID']) < 1600: mutation_d['ResidueID'] = str(int(mutation_d['ResidueID']) + 1762) # Hack for the PDB replacement 1AJ3, NMR -> 1U5P (2A) mutated_residue = ddGdb.execute_select('SELECT * FROM PDBResidue WHERE PDBFileID=%s AND Chain=%s AND ResidueID=%s', parameters=(d['PDBFileID'], mutation_d['Chain'], ResidueID2String(mutation_d['ResidueID']))) if len(mutated_residue) == 0: colortext.warning('Skipping Experiment #%d (%s) in %s due to missing residue %s.' % (ExperimentID, d['PDBFileID'], dataset_ID, mutation_d['ResidueID'])) #print('SELECT * FROM PDBResidue WHERE PDBFileID=%s AND Chain=%s AND ResidueID=%s' % (d['PDBFileID'], mutation_d['Chain'], ResidueID2String(mutation_d['ResidueID']))) #pprint.pprint(d) #pprint.pprint(mutations) #pprint.pprint(mutation_d) #print(ExperimentID) #print(mutated_residue) #print(10*'*') #print('\n') failure_count += 1 failed_check = True break assert(len(mutated_residue) == 1) mutated_residue = mutated_residue[0] mutation_d['DSSPExposure'] = mutated_residue['MonomericExposure'] mutation_d['DSSPType'] = mutated_residue['MonomericDSSP'] mutation_d['DSSPSimpleSSType'] = dssp_elision.get(mutation_d['DSSPType']) assert(mutation_d['DSSPType'] != None) assert(mutation_d['DSSPSimpleSSType'] != None) mutations.append(mutation_d) if failed_check: print('FAILED CHECK') continue d['Mutations'] = mutations if dataset_ID == "Potapov_10.1093/protein/gzp030_2009/09/01": key = '%s_%s_%s' % (d['PDBFileID'], '+'.join(['%s:%s:%s' % (mutation_d['Chain'], mutation_d['ResidueID'].strip(), mutation_d['MutantAA']) for mutation_d in mutations]), d['RecordID']) else: key = '%s_%s' % (d['PDBFileID'], '+'.join(['%s:%s:%s' % (mutation_d['Chain'], mutation_d['ResidueID'].strip(), mutation_d['MutantAA']) for mutation_d in mutations])) if record_data.get(key): colortext.warning('KEY EXISTS: %s' % key) print('Existing record: %s' % pprint.pformat(record_data[key])) print('New record: %s' % pprint.pformat(d)) failure_count += 1 record_data[key] = d colortext.message('Mutation count') colortext.warning(pprint.pformat(mutation_count)) if failure_count > 0: colortext.error('Total length of dataset: %d. Failed on %d records.' % (len(record_data), failure_count)) else: colortext.message('Total length of dataset: %d. ' % (len(record_data))) record_list = [] for k, v in sorted(record_data.iteritems()): record_list.append(v) colortext.message('Adding dataset %s with %d records, %d PDB files, and %d references.' % (dataset_ID, len(record_list), len(pdb_data), len(pub_data))) JSON_datasets[dataset_ID]['data'] = record_list
#sys.path.insert(0, "../..") sys.path.insert(0, "../updatedb") #sys.path.insert(0, '/home/oconchus/dev/') #sys.path.insert(0, "/home/oconchus/dev/klab") else: import klab import klab.colortext as colortext from ddglib.ppi_api import get_interface_with_config_file as get_ppi_interface_with_config_file # Set up database connection try: ppi_api = get_ppi_interface_with_config_file(host_config_name = 'kortemmelab') except: colortext.error('Database connection failed.') raise colortext.message('Connected to database.') # Pick a scoring method score_method_id = ppi_api.get_score_method_id('Rescore-Talaris2014', method_authors = 'kyle', method_type = 'ddg_monomer rescore') # Get the best structures for prediction 23849 wild_type_complexes = ppi_api.get_top_x_scores(23849, score_method_id, 'WildTypeComplex', 3, component = 'total', order_by = 'ASC') wild_type_filenames = [] for wtc in wild_type_complexes: wild_type_filenames.append([f for f in glob.glob('repacked_wt*_round_{0}.*'.format(wtc['StructureID']))][0]) print(wild_type_filenames)
def _create_intermediate_schema(self, tbl): code = (self.db_interface.execute("SHOW CREATE TABLE %s" % tbl)) assert(len(code) == 1) schema = code[0]['Create Table'] #colortext.message(tbl) #print(schema) #print(schema) fields = [f for f in map(string.strip, schema[schema.find('(') + 1:schema.find('PRIMARY KEY')].strip().split('\n')) if f.strip()] pk_fields = re.match('.*PRIMARY\s+KEY\s*[(](.*?)[)]\s*[,)].*', schema, re.DOTALL) assert(pk_fields) pk_fields = [s.strip() for s in pk_fields.group(1).replace('`', '').split(',') if s.strip()] #colortext.warning(fields) for f in fields: #print('') #colortext.message(f) if f.endswith(','): f = f[:-1] field_name = f.split()[0].replace('`', '') if f.split()[1].startswith('enum('): mtchs = re.match(".* (enum[(].*?[)])(.*)", f) assert(mtchs) #print('ENUM', mtchs.group(1)) field_type = mtchs.group(1) remaining_description = mtchs.group(2) else: field_type = f.split()[1] remaining_description = (' '.join(f.split()[2:])).strip() unicode_collation_or_character_set = False if remaining_description.find('utf') != -1: unicode_collation_or_character_set = True not_null = False if remaining_description.find('NOT NULL') != -1: not_null = True remaining_description = remaining_description.replace('NOT NULL', '').strip() default = False default_type = None default_value = None if remaining_description.find('default CURRENT_TIMESTAMP') != -1: default_type = 'TIMESTAMP' default_value = None remaining_description = remaining_description.replace('default CURRENT_TIMESTAMP', '') elif remaining_description.find('default NULL') != -1: default_type = 'null' default_value = None remaining_description = remaining_description.replace('default NULL', '') elif remaining_description.find('default') != -1: mtchs = re.match(".*default '(.*?)'.*", remaining_description) if mtchs: #print('mtchs', mtchs.group(1)) default_type = 'string' default_value = mtchs.group(1) remaining_description = remaining_description.replace("default '%s'" % default_value, "") else: colortext.error('Unexpected default value string: "{0}".'.format(remaining_description)) pass #mtchs = re.match(".*default (.*?)(\s.*)*$", remaining_description) #if mtchs: # print('mtchs non-string', mtchs.group(1)) # if mtchs.group(1) == 'NULL': # default_type = 'null' # default_value = None # remaining_description = remaining_description.replace('') comment = None mtchs = re.match(".*(COMMENT '.*?').*", remaining_description) if mtchs: comment = mtchs.group(1) remaining_description = remaining_description.replace(mtchs.group(1), "") remaining_description = remaining_description.strip() self.intermediate_schema[tbl] = self.intermediate_schema.get(tbl, []) self.intermediate_schema[tbl].append(IntermediateField(field_name, field_type, not_null = not_null, default_type = default_type, default_value = default_value, comment = comment, is_primary_key = field_name in pk_fields, unicode_collation_or_character_set = unicode_collation_or_character_set)) #print('field_name : %s' % field_name) #print('field_type : %s' % field_type) #print('not_null : %s' % not_null) if default_type != None: pass #print('default: %s, %s' % (default_type, default_value)) #print('comment : %s' % comment) if remaining_description: #colortext.error('remaining_description : %s' % remaining_description) pass
colortext.message('\n{0}/{1}: {2}'.format(c, len(pdb_ids), pdb_id)) hits = b.by_pdb(pdb_id) if hits: colortext.warning('{0} hits: {1}'.format(len(hits), ','.join(hits))) else: colortext.warning('No hits') except Exception, e: colortext.error('FAILED') failed_cases.append((pdb_id, str(e), traceback.format_exc())) if failed_cases: colortext.warning('*** These cases failed ***') for p in failed_cases: print('') colortext.pcyan(p[0]) colortext.error(p[1]) print(p[2]) print('') def test_sequences(b, sequences): failed_cases = [] c = 0 for sequence in sequences: try: c += 1 colortext.message('\n{0}/{1}: {2}'.format(c, len(sequences), sequence)) hits = b.by_sequence(sequence) if hits: colortext.warning('{0} hits: {1}'.format(len(hits), ','.join(hits))) else:
def _parse_PDB_mapping(self): entry_tag = self.entry_tag mapping = {} dbReference_tags = [child for child in entry_tag.childNodes if child.nodeType == child.ELEMENT_NODE and child.tagName == 'dbReference'] for t in dbReference_tags: db_type = t.getAttribute('type') assert(db_type) if db_type == 'PDB': pdb_id = t.getAttribute('id') assert(len(pdb_id) == 4) #print(pdb_id) method = None resolution = None chains = [] for p in t.getElementsByTagName('property'): if p.getAttribute('type') == 'method': method = p.getAttribute('value') elif p.getAttribute('type') == 'resolution': resolution = float(p.getAttribute('value')) elif p.getAttribute('type') == 'chains': chains_groups = [x.strip() for x in p.getAttribute('value').split(",") if x.strip()] for cg in chains_groups: cg_tokens = cg.split("=") assert(len(cg_tokens) == 2) chain_ids = cg_tokens[0].strip().split("/") for chain_id in chain_ids: assert(len(chain_id) == 1) #print(chain_id) range = cg_tokens[1].strip().split("-") assert(len(range) == 2) starting_index = None ending_index = None try: starting_index = int(range[0]) ending_index = int(range[1]) except: mmkey = "/".join(sorted(chain_ids)) if missing_mapping_for_AC_PDB_chains.get(self.UniProtAC, {}).get(pdb_id, {}).get(mmkey): starting_index, ending_index = missing_mapping_for_AC_PDB_chains.get(self.UniProtAC, {}).get(pdb_id, {}).get(mmkey) if not self.silent: colortext.error("Fixing starting_index, ending_index to %d, %d for PDB chains %s." % (starting_index, ending_index, str(chain_ids))) else: if not set(chain_ids) in broken_mapping_for_AC_PDB_chains.get(self.UniProtAC, {}).get(pdb_id, []): raise colortext.Exception("The starting index and ending index for %s, chains %s in UniProtKB AC entry %s is broken or missing. Fix the mapping or mark it as missing in uniprot_patches.py" % (pdb_id, ",".join(chain_ids), self.UniProtAC)) continue for chain_id in chain_ids: assert(len(chain_id) == 1) if fixed_mapping_for_AC_PDB_chains.get(self.UniProtAC, {}).get(pdb_id, {}).get(chain_id): fixed_chain_id = fixed_mapping_for_AC_PDB_chains.get(self.UniProtAC, {}).get(pdb_id, {}).get(chain_id) if not self.silent: colortext.error("Fixing PDB chain from %s to %s." % (chain_id, fixed_chain_id)) chain_id = fixed_chain_id chains.append((chain_id, starting_index, ending_index)) else: raise Exception("Unhandled dbReference property tag type.") if not method: temp_method = missing_AC_PDB_methods.get(self.UniProtAC, {}).get(pdb_id, []) if temp_method: method = temp_method[0] if not self.silent: colortext.error("Fixing method to %s for PDB %s." % (method, pdb_id)) if not chains: assert(pdb_id in broken_mapping_for_AC_PDB_chains.get(self.UniProtAC, {})) continue if not method and chains: raise colortext.Exception("Missing method and chains for %s in UniProtKB AC entry %s. Fix the mapping or mark it as missing in uniprot_patches.py" % (pdb_id, self.UniProtAC)) if not method in UniProtACEntry.sampling_methods.keys(): raise colortext.Exception("Unknown method '%s' found in UniProtKB AC entry %s." % (method, self.UniProtAC)) if method in ['X-ray'] and resolution: # resolution can be null e.g. in P00698 with 2A6U (POWDER DIFFRACTION) assert(pdb_id not in mapping) if pdb_id not in PDBs_marked_as_XRay_with_no_resolution: assert(resolution) mapping[pdb_id] = {'method' : method, 'resolution' : resolution, 'chains' : {}} import pprint for chain in chains: #assert(chain[0] not in mapping[pdb_id]['chains']) # todo: I disabled this when calling get_common_PDB_IDs as it hit the assertion while looking up 1REW with 4N1D. Is this assertion necessary? mapping[pdb_id]['chains'][chain[0]] = (chain[1], chain[2]) if False: for pdb_id, details in sorted(mapping.iteritems()): if not self.silent: colortext.message("%s, %s, %sA" % (str(pdb_id), str(details['method']), str(details['resolution']))) for chain, indices in sorted(details['chains'].iteritems()): if not self.silent: colortext.warning(" Chain %s: %s-%s" % (chain, str(indices[0]).rjust(5), str(indices[1]).ljust(5)))
average_time_taken = float(total_time_in_secs)/float(cases_computed or 1) estimate_remaining_time = number_of_cases_left * average_time_taken t.stop() colortext.printf("**Profile**", 'orange') print(t) colortext.message("Time taken for this case: %0.2fs." % t.sum()) colortext.message("Average time taken per case: %0.2fs." % average_time_taken) colortext.message("Estimated time remaining: %dh%dm%ds." % (int(estimate_remaining_time/3600), int((estimate_remaining_time/60) % 60), estimate_remaining_time % 60)) print("\n") #exF.close() colortext.printf("\nDone.", 'lightgreen') if failed_cases: colortext.error("Failed cases:\n[%s]" % ",".join(map(str, failed_cases))) #main(FixedIDs = [38766, 39738, 40379, 40381] + range(40610, 40611)) #main(FixedIDs = [39044]) #main(FixedIDs = [48898,49870,50948,51058,51059,52247,53633,53711]) convert_scores_to_json() print('here') FixedIDs = [76633] FixedIDs = [] main(FixedIDs = FixedIDs, radii = [8.0])
def check_failures(prediction_set): ddGdb = ddgdbapi.ddGDatabase() results_root = '/kortemmelab/shared/DDG/jobs' UserDataSetExperimentIDs = {} results = ddGdb.execute_select('''SELECT ID, ExperimentID FROM Prediction WHERE PredictionSet = %s AND STATUS = 'failed' ''', parameters=(prediction_set,)) reported_failures = [r['ID'] for r in results] for r in results: UserDataSetExperimentIDs[r['ID']] = r['ExperimentID'] print(UserDataSetExperimentIDs) print(len(UserDataSetExperimentIDs)) affected_subsets = {} actually_failed = [] did_not_fail = [] did_not_fail_but_have_many_residues = [] did_not_fail_but_has_a_troublesome_structure = [] large_proteins = set(['1FEP', '1W99']) troublesome_structures = set(['2IFB', '1FMK']) for PredictionID in reported_failures: print(PredictionID) zipfile_path = os.path.join(results_root, '%d.zip' % PredictionID) #try: z = zipfile.ZipFile(zipfile_path, 'r') #except: # colortext.error('MISSING FILE FOR %d' % PredictionID) # did_not_fail.append(PredictionID) # continue file_list = z.namelist() found_stdout = 0 found_stderr = 0 for f in file_list: if f.find('.cmd.o') != -1: found_stdout = 1 elif f.find('.cmd.e') != -1: found_stderr = 1 colortext.error(f) assert(found_stdout >= found_stderr) if found_stderr: assert(found_stderr == 1) colortext.error("Job #%d actually failed" % PredictionID) actually_failed.append(PredictionID) ExperimentID = UserDataSetExperimentIDs[PredictionID] sub_results = ddGdb.execute_select('''SELECT Subset FROM UserAnalysisSet WHERE ExperimentID = %s''', parameters=(ExperimentID,)) for sr in sub_results: print(sr['Subset']) affected_subsets[sr['Subset']] = affected_subsets.get(sr['Subset'], []) affected_subsets[sr['Subset']].append(PredictionID) else: PDBFileID = ddGdb.execute_select("SELECT UserDataSetExperiment.PDBFileID AS PDBFileID FROM Prediction INNER JOIN UserDataSetExperiment ON UserDataSetExperimentID=UserDataSetExperiment.ID WHERE Prediction.ID=%s", parameters=(PredictionID,))[0]['PDBFileID'] if PDBFileID in troublesome_structures: colortext.warning("Job #%d had not failed by the time it was terminated however it has a troublesome structure (%s)." % (PredictionID, PDBFileID)) did_not_fail_but_has_a_troublesome_structure.append(PredictionID) elif PDBFileID in large_proteins: colortext.warning("Job #%d had not failed by the time it was terminated however it has many residues (%s)." % (PredictionID, PDBFileID)) did_not_fail_but_have_many_residues.append(PredictionID) else: colortext.warning("Job #%d had not failed by the time it was terminated." % PredictionID) did_not_fail.append(PredictionID) colortext.message("*** Report ***") print('%d jobs were marked as failed.' % len(reported_failures)) colortext.warning('%d jobs were marked as failed but had not failed.' % len(did_not_fail)) colortext.warning('%d jobs were marked as failed and had not failed but had large chains.' % len(did_not_fail_but_have_many_residues)) colortext.warning('%d jobs were marked as failed and had not failed but have a troublesome structure.' % len(did_not_fail_but_has_a_troublesome_structure)) colortext.error('%d jobs were marked as failed and did fail.\n' % len(actually_failed)) if affected_subsets: print("The following subsets were affected") for k, v in affected_subsets.iteritems(): print("%s: %d records" % (k, len(v))) if did_not_fail: restart_jobs = ask_yes_no("Do you want to restart the jobs that did not actually fail?", default_value=False) if restart_jobs: for j in did_not_fail: r = ddGdb.execute("SELECT Status, AdminCommand FROM Prediction WHERE ID=%s", parameters=(j,)) assert(len(r) == 1) if r[0]['Status'] != 'failed' or r[0]['AdminCommand'] != 'restart': ddGdb.execute("UPDATE Prediction SET AdminCommand='restart' WHERE ID=%s", parameters=(j,)) if did_not_fail_but_have_many_residues: restart_jobs = ask_yes_no("Do you want to restart the jobs that did not actually fail but had large proteins?", default_value=False) if restart_jobs: for j in did_not_fail_but_have_many_residues: r = ddGdb.execute("SELECT Status, AdminCommand FROM Prediction WHERE ID=%s", parameters=(j,)) assert(len(r) == 1) if r[0]['Status'] != 'failed' or r[0]['AdminCommand'] != 'restart': ddGdb.execute("UPDATE Prediction SET AdminCommand='restart' WHERE ID=%s", parameters=(j,)) if did_not_fail_but_has_a_troublesome_structure: restart_jobs = ask_yes_no("Do you want to restart the jobs that did not actually fail but had troublesome structures?", default_value=False) if restart_jobs: for j in did_not_fail_but_has_a_troublesome_structure: r = ddGdb.execute("SELECT Status, AdminCommand FROM Prediction WHERE ID=%s", parameters=(j,)) assert(len(r) == 1) if r[0]['Status'] != 'failed' or r[0]['AdminCommand'] != 'restart': ddGdb.execute("UPDATE Prediction SET AdminCommand='restart' WHERE ID=%s", parameters=(j,)) for k, v in affected_subsets.iteritems(): see_errors = ask_yes_no("Do you want to see the stderr files for the jobs that did fail and affected %s?" % k, default_value=False) if see_errors: count = 1 for j in v: zipfile_path = os.path.join(results_root, '%d.zip' % j) z = zipfile.ZipFile(zipfile_path, 'r') file_list = z.namelist() colortext.error("\n[%d/%d] Prediction ID: %d" % (count, len(v), j)) PDBFileID = ddGdb.execute_select("SELECT UserDataSetExperiment.PDBFileID AS PDBFileID FROM Prediction INNER JOIN UserDataSetExperiment ON UserDataSetExperimentID=UserDataSetExperiment.ID WHERE Prediction.ID=%s", parameters=(j,)) assert(len(PDBFileID) == 1) PDBFileID = PDBFileID[0]['PDBFileID'] colortext.error("\nPDB ID: %s" % PDBFileID) for f in file_list: if f.find('.cmd.e') != -1: colortext.warning(f) print(z.open(f, 'r').read()[:300]) print("") count += 1
def classify_failures(prediction_set): ddGdb = ddgdbapi.ddGDatabase() results_root = '/kortemmelab/shared/DDG/jobs' UserDataSetExperimentIDs = {} results = ddGdb.execute_select('''SELECT ID, ExperimentID FROM Prediction WHERE PredictionSet = %s AND STATUS = 'failed' ''', parameters=(prediction_set,)) reported_failures = [r['ID'] for r in results] for r in results: UserDataSetExperimentIDs[r['ID']] = r['ExperimentID'] actually_failed = [] did_not_fail = [] for PredictionID in reported_failures: zipfile_path = os.path.join(results_root, '%d.zip' % PredictionID) #try: z = zipfile.ZipFile(zipfile_path, 'r') #except: # colortext.error('MISSING FILE FOR %d' % PredictionID) # continue file_list = z.namelist() found_stdout = 0 found_stderr = 0 for f in file_list: if f.find('.cmd.o') != -1: found_stdout = 1 elif f.find('.cmd.e') != -1: found_stderr = 1 assert(found_stdout >= found_stderr) if found_stderr: assert(found_stderr == 1) colortext.error("Job #%d actually failed" % PredictionID) actually_failed.append(PredictionID) else: colortext.warning("Job #%d had not failed by the time it was terminated." % PredictionID) did_not_fail.append(PredictionID) colortext.message("*** Report ***") print('%d jobs were marked as failed.' % len(reported_failures)) colortext.warning('%d jobs were marked as failed but had not failed.' % len(did_not_fail)) colortext.error('%d jobs were marked as failed and did fail.\n' % len(actually_failed)) pdb_details = {} failed_job_pdb_files = {} for failed_job in actually_failed: PDBFileID = ddGdb.execute_select("SELECT UserDataSetExperiment.PDBFileID AS PDBFileID FROM Prediction INNER JOIN UserDataSetExperiment ON UserDataSetExperimentID=UserDataSetExperiment.ID WHERE Prediction.ID=%s", parameters=(failed_job,))[0]['PDBFileID'] pdb_details[PDBFileID] = True failed_job_pdb_files[failed_job] = PDBFileID for pdb_id in pdb_details.keys(): pdb_details[pdb_id] = ddGdb.execute_select("SELECT Resolution, Techniques FROM PDBFile WHERE ID=%s", parameters=(pdb_id,))[0] pdb_details[pdb_id]['Chains'] = [r['Chain'] for r in ddGdb.execute_select("SELECT Chain FROM PDBChain WHERE PDBFileID=%s ORDER BY Chain", parameters=(pdb_id,))] pdb_details[pdb_id]['TotalJobs'] = ddGdb.execute_select("SELECT Count(ID) AS TotalJobs FROM UserDataSetExperiment WHERE PDBFileID=%s", parameters=(pdb_id,))[0]['TotalJobs'] hosts = {} failed_by_hessin = {} failed_by_residue_mismatch = {} failed_for_another_reason = {} missing_output = {} mutfiles = {} count = 1 for failed_job in actually_failed: mutfile = None colortext.message('Failed job %d of %d' % (count, failed_job)) zipfile_path = os.path.join(results_root, '%d.zip' % failed_job) found_output = False pdb_id = failed_job_pdb_files[failed_job] if os.path.exists(zipfile_path): z = zipfile.ZipFile(zipfile_path, 'r') file_list = z.namelist() for f in file_list: if f.find('.cmd.e') != -1: found_output = True stderr_contents = z.open(f, 'r').read() stdout_contents = z.open(f.replace('.cmd.e', '.cmd.o'), 'r').read() hosts[failed_job] = stdout_contents[stdout_contents.find('<host>') + 6:stdout_contents.find('</host>')].strip() if stderr_contents.find('HESSIN for (i,i):') != -1: assert(stderr_contents.find('G for (i):') != -1) print(stderr_contents[:120]) failed_by_hessin[pdb_id] = failed_by_hessin.get(pdb_id, []) failed_by_hessin[pdb_id].append(failed_job) colortext.error('HESSIN: %s' % pdb_id) elif stderr_contents.find('ERROR: pose.residue(resnum).name1() == wt') != -1: failed_by_residue_mismatch[pdb_id] = failed_by_residue_mismatch.get(pdb_id, []) failed_by_residue_mismatch[pdb_id].append(failed_job) colortext.error('MISMATCH') else: failed_for_another_reason[pdb_id] = failed_for_another_reason.get(pdb_id, []) failed_for_another_reason[pdb_id].append(failed_job) colortext.error('UNKNOWN') see_errors = ask_yes_no("Do you want to see the stderr files for prediction %d?" % failed_job, default_value=False) if see_errors: colortext.warning(f) print(stderr_contents[:300]) print("") if f.find('.mutfile') != -1: assert(mutfile == None) mutfile = z.open(f, 'r').read() mutfiles[failed_job] = mutfile if not found_output: missing_output[pdb_id] = missing_output.get(pdb_id, []) missing_output[pdb_id].append(failed_job) count += 1 colortext.message("*** Report ***") if missing_output: colortext.warning("Missing output: %d jobs" % sum([len(v) for k, v in missing_output.iteritems()])) for k, v in sorted(missing_output.iteritems()): print('%s: %d jobs - %s' % (k, len(v), ', '.join(map(str, sorted(v))))) if failed_by_hessin: colortext.warning("Failed Hessin: %d jobs" % sum([len(v) for k, v in failed_by_hessin.iteritems()])) for k, v in sorted(failed_by_hessin.iteritems()): if pdb_details[k]['Resolution'] != None: print('%s, %0.2fA, %s.' % (k, pdb_details[k]['Resolution'], pdb_details[k]['Techniques'].title())) else: print('%s, %s.' % (k, pdb_details[k]['Techniques'].title())) print('%d/%d jobs failed - %s\n' % (len(v), pdb_details[k]['TotalJobs'], ', '.join(map(str, sorted(v))))) for failed_id in sorted(v): mutations = ddGdb.execute_select("SELECT Prediction.ExperimentID, ExperimentMutation.* FROM Prediction INNER JOIN ExperimentMutation ON Prediction.ExperimentID=ExperimentMutation.ExperimentID WHERE Prediction.ID=%s", parameters=(failed_id,)) mut_str = ', '.join([('%s %s%s%s' % (m['Chain'], m['WildTypeAA'], m['ResidueID'], m['MutantAA'])) for m in mutations]) colortext.printf('%d: %s, experiment #%d. Host = %s' % (failed_id, mut_str, mutations[0]['ExperimentID'], hosts[failed_id]), 'orange') print('') print('') if failed_by_residue_mismatch: colortext.warning("Failed due to residue mismatch: %d jobs" % sum([len(v) for k, v in failed_by_residue_mismatch.iteritems()])) for k, v in sorted(failed_by_residue_mismatch.iteritems()): if pdb_details[k]['Resolution'] != None: colortext.printf('%s, %0.2fA, %s.' % (k, pdb_details[k]['Resolution'], pdb_details[k]['Techniques'].title()), 'cyan') else: colortext.printf('%s, %s.' % (k, pdb_details[k]['Techniques'].title()), 'cyan') print('%d/%d jobs failed - %s\n' % (len(v), pdb_details[k]['TotalJobs'], ', '.join(map(str, sorted(v))))) for failed_id in sorted(v): mutations = ddGdb.execute_select("SELECT ExperimentMutation.* FROM Prediction INNER JOIN ExperimentMutation ON Prediction.ExperimentID=ExperimentMutation.ExperimentID WHERE Prediction.ID=%s", parameters=(failed_id,)) mut_str = ', '.join([('%s %s%s%s' % (m['Chain'], m['WildTypeAA'], m['ResidueID'], m['MutantAA'])) for m in mutations]) colortext.printf('%d: %s' % (failed_id, mut_str), 'orange') print(mutfiles[failed_id]) print('') print('') if failed_for_another_reason: colortext.warning("Failed for an unknown reason: %d jobs" % sum([len(v) for k, v in failed_for_another_reason.iteritems()])) for k, v in sorted(failed_for_another_reason.iteritems()): if pdb_details[k]['Resolution'] != None: print('%s, %0.2fA, %s.' % (k, pdb_details[k]['Resolution'], pdb_details[k]['Techniques'].title())) else: print('%s, %s.' % (k, pdb_details[k]['Techniques'].title())) print('%d/%d jobs failed - %s\n' % (len(v), pdb_details[k]['TotalJobs'], ', '.join(map(str, sorted(v))))) print('%d jobs were marked as failed.' % len(reported_failures)) colortext.warning('%d jobs were marked as failed but had not failed.' % len(did_not_fail)) colortext.error('%d jobs were marked as failed and did fail.\n' % len(actually_failed))
def plot(self, table_name, RFunction, output_filename=None, filetype="pdf"): '''Results is expect to be a list of dicts each of which has the keys ExperimentID and ddG.''' if (not self.analysis_tables) or (not table_name): raise Exception("There are no analysis tables to plot.") if not table_name in self.analysis_tables.keys(): raise Exception("The analysis table '%s' does not exist." % table_name) R_return_values = {} gplot = None analysis_table = self.analysis_tables[table_name] if self.quiet_level >= 3: print(table_name) print(RFunction) if len(analysis_table.points) == 1: raise Exception( "The analysis table %s set only has one data point. At least two points are required." % table_name) else: inputfname = self.CreateCSVFile(table_name) if self.quiet_level >= 3: print(inputfname) try: if self.quiet_level >= 2: colortext.printf("Running %s." % RFunction) if output_filename: colortext.printf( "Saving graph as %s with filename %s." % (filetype, output_filename)) output_fname = output_filename if not output_fname: output_fname = rosettahelper.writeTempFile(".", "") R_output = RFunction(inputfname, output_fname, filetype) R_return_values = RUtilities.parse_R_output(R_output) colortext.message(table_name) print(" %s" % str(RFunction)) for k, v in sorted(R_return_values.iteritems()): print(" %s: %s" % (str(k), str(v))) if not output_filename: contents = rosettahelper.readBinaryFile(output_fname) delete_file(output_fname) description = None for file_suffix, details in RFunctions.iteritems(): if details[1] == RFunction: description = details[0] assert (description) gplot = AnalysisObject(table_name, description, filetype, contents) else: gplot = output_filename except Exception, e: import traceback colortext.error(traceback.format_exc()) delete_file(inputfname) raise Exception(e) delete_file(inputfname)
assert (len(loop_set) == 1) start_res = '{chainID}{resSeq:>4d}{iCode}'.format( **loop_set[0]['start']) end_res = '{chainID}{resSeq:>4d}{iCode}'.format( **loop_set[0]['stop']) success, result = get_pdb_contents_to_pose_residue_map( new_pdb_content, rosetta_scripts_binary, None, pdb_id=None, extra_flags= '-ignore_zero_occupancy false -ignore_unrecognized_res') if not success: colortext.error('Failed on {0}.'.format(pdb_prefix)) raise colortext.Exception('\n'.join(result)) else: if not start_res in result: raise colortext.Exception( 'Could not find the starting residue in the PDB -> Rosetta residue mapping.' ) elif not end_res in result: raise colortext.Exception( 'Could not find the starting residue in the PDB -> Rosetta residue mapping.' ) start_rosetta_res = result[start_res]['pose_residue_id'] end_rosetta_res = result[end_res]['pose_residue_id'] if not end_rosetta_res > start_rosetta_res: raise colortext.Exception( 'The end residue have a higher index number than the starting residue.'
def end_document(self): assert(self.counters['entry'] == 1) residue_count = 0 residues_matched = {} residues_encountered = set() atom_to_uniparc_residue_map = {} atom_to_seqres_residue_map = {} seqres_to_uniparc_residue_map = {} UniProtACs = set() for r in self.residues: if r.UniProtAC: UniProtACs.add(r.UniProtAC) ACC_to_UPARC_mapping = uniprot_map('ACC', 'UPARC', list(UniProtACs), cache_dir = self.cache_dir) assert(sorted(ACC_to_UPARC_mapping.keys()) == sorted(list(UniProtACs))) for k, v in ACC_to_UPARC_mapping.iteritems(): assert(len(v) == 1) ACC_to_UPARC_mapping[k] = v[0] map_chains = set() for r in self.residues: if not(r.PDBResidueID.isalnum() and int(r.PDBResidueID.isalnum()) < 0): # These are not valid PDB residue IDs - the SIFTS XML convention sometimes assigns negative residue IDs to unobserved residues before the first ATOM record # (only if the first residue ID is 1?) pass # Store the PDB->UniProt mapping if r.has_pdb_to_uniprot_mapping(): UniProtAC = r.UniProtAC UniParcID = ACC_to_UPARC_mapping[UniProtAC] self.uniparc_ids.add(UniParcID) full_pdb_residue_ID = r.get_pdb_residue_id() PDBChainID = r.PDBChainID map_chains.add(PDBChainID) residues_matched[PDBChainID] = residues_matched.get(PDBChainID, 0) if not r.WasNotObserved: # Do not add ATOM mappings when the ATOM data does not exist if r.has_pdb_to_uniprot_mapping(): atom_to_uniparc_residue_map[PDBChainID] = atom_to_uniparc_residue_map.get(PDBChainID, {}) atom_to_uniparc_residue_map[PDBChainID][full_pdb_residue_ID] = (UniParcID, r.UniProtResidueIndex) atom_to_seqres_residue_map[PDBChainID] = atom_to_seqres_residue_map.get(PDBChainID, {}) atom_to_seqres_residue_map[PDBChainID][full_pdb_residue_ID] = r.PDBeResidueID if r.has_pdb_to_uniprot_mapping(): seqres_to_uniparc_residue_map[PDBChainID] = seqres_to_uniparc_residue_map.get(PDBChainID, {}) seqres_to_uniparc_residue_map[PDBChainID][r.PDBeResidueID] = (UniParcID, r.UniProtResidueIndex) # Make sure we only have at most one match per PDB residue assert(full_pdb_residue_ID not in residues_encountered) residues_encountered.add(full_pdb_residue_ID) # Count the number of exact sequence matches PDBResidue3AA = r.PDBResidue3AA pdb_residue_type = residue_type_3to1_map.get(PDBResidue3AA) or self.modified_residues.get(PDBResidue3AA) or protonated_residue_type_3to1_map.get(PDBResidue3AA) or non_canonical_amino_acids.get(PDBResidue3AA) if r.has_pdb_to_uniprot_mapping(): if pdb_residue_type == r.UniProtResidue1AA: residues_matched[PDBChainID] += 1 residue_count += 1 # Create the SequenceMaps for c in map_chains: if residues_matched[c] > 0: # 1IR3 has chains A, # Chain A has mappings from atom and seqres (PDBe) residues to UniParc as usual # Chain B (18 residues long) has mappings from atom to seqres residues but not to UniParc residues self.atom_to_uniparc_sequence_maps[c] = PDBUniParcSequenceMap.from_dict(atom_to_uniparc_residue_map[c]) self.seqres_to_uniparc_sequence_maps[c] = PDBUniParcSequenceMap.from_dict(seqres_to_uniparc_residue_map[c]) self.atom_to_seqres_sequence_maps[c] = SequenceMap.from_dict(atom_to_seqres_residue_map[c]) # Check the match percentage total_residues_matched = sum([residues_matched[c] for c in residues_matched.keys()]) if total_residues_matched == 0: if self.pdb_id and self.pdb_id in NoSIFTSPDBUniParcMappingCases: if self.require_uniprot_residue_mapping: raise NoSIFTSPDBUniParcMapping('The PDB file %s has a bad or missing SIFTS mapping at the time of writing.' % self.pdb_id) else: colortext.error('Warning: The PDB file %s has a a bad or missing SIFTS mapping at the time of writing so there is no PDB -> UniProt residue mapping.' % self.pdb_id) else: if self.require_uniprot_residue_mapping: raise Exception('No residue information matching PDB residues to UniProt residues was found.') else: colortext.error('Warning: No residue information matching PDB residues to UniProt residues was found.') else: percentage_matched = float(total_residues_matched)*100.0/float(residue_count) if percentage_matched < self.acceptable_sequence_percentage_match: if self.pdb_id and self.pdb_id in BadSIFTSMappingCases: raise BadSIFTSMapping('The PDB file %s has a known bad SIFTS mapping at the time of writing.' % self.pdb_id) else: raise Exception('Expected %.2f%% sequence match on matched residues but the SIFTS results only gave us %.2f%%.' % (self.acceptable_sequence_percentage_match, percentage_matched)) # Merge the ranges for the region mappings i.e. so [1-3],[3-86] becomes [1-86] region_mapping = self.region_mapping for chain_id, chain_details in region_mapping.iteritems(): for dbSource, source_details in chain_details.iteritems(): for dbAccessionId, range_list in source_details.iteritems(): source_details[dbAccessionId] = merge_range_pairs(range_list) # Check to see if the expected numbering schemes hold for k, v in expected_residue_numbering_schemes.iteritems(): if self.region_map_coordinate_systems.get(k): assert(self.region_map_coordinate_systems[k] == set([v])) pfam_scop_mapping = {} scop_pfam_mapping = {} for chain_id, chain_details in region_mapping.iteritems(): if chain_details.get('Pfam') and chain_details.get('SCOP'): for pfamAccessionId, pfam_range_lists in chain_details['Pfam'].iteritems(): pfam_residues = parse_range(','.join(['%d-%d' % (r[0], r[1]) for r in pfam_range_lists])) for scopAccessionId, scop_range_lists in chain_details['SCOP'].iteritems(): scop_residues = parse_range(','.join(['%d-%d' % (r[0], r[1]) for r in scop_range_lists])) num_same_residues = len(set(pfam_residues).intersection(set(scop_residues))) if num_same_residues > 10: Pfam_match_quality = float(num_same_residues) / float(len(pfam_residues)) SCOP_match_quality = float(num_same_residues) / float(len(scop_residues)) if (Pfam_match_quality >= self.domain_overlap_cutoff) or (SCOP_match_quality >= self.domain_overlap_cutoff): pfam_scop_mapping[pfamAccessionId] = pfam_scop_mapping.get(pfamAccessionId, DomainMatch(pfamAccessionId, 'Pfam')) pfam_scop_mapping[pfamAccessionId].add(scopAccessionId, 'SCOP', SCOP_match_quality) scop_pfam_mapping[scopAccessionId] = scop_pfam_mapping.get(scopAccessionId, DomainMatch(scopAccessionId, 'SCOP')) scop_pfam_mapping[scopAccessionId].add(pfamAccessionId, 'Pfam', Pfam_match_quality) self.pfam_scop_mapping = pfam_scop_mapping self.scop_pfam_mapping = scop_pfam_mapping self._validate()
def format(self, abbreviate_journal = True, abbreviate_author_names = True, show_year = True, html = True, allow_errors = False): raise Exception('This function is deprecated in favor of PublicationInterface.to_string. Some functionality needs to be added to that function e.g. ReferralURL_link.') if self.errors and not allow_errors: if not self.quiet: colortext.error("There were parsing errors: %s" % self.errors) return None # Abbreviate the journal name journal = self.journal if abbreviate_journal and self.publication_type != "CHAP": journal = publication_abbreviations.get(self.journal, self.journal) # Abbreviate the authors' names authors_str = None if abbreviate_author_names: authors_str = ", ".join(self.get_author_names_in_short_format()) else: raise Exception("This code needs to be written with whatever is needed.") # Create string for the publication year year_str = "" if show_year: year_str = ", %s" % self.year ReferralURL_link = "" if self.ReferralURL: ReferralURL_link = " <a class='publist' href='%s'>[free download]</a>" % self.ReferralURL titlesuffix = '.' if self.publication_type == "CHAP": titlesuffix = " in" # The entry format is fixed. This could be passed as a variable for different styles. entry = "" if self.volume: entry = self.volume if self.subtitle: entry += " (%s)" % self.subtitle if self.issue: entry += "(%s)" % self.issue pagerange = PublicationInterface.get_page_range_in_abbreviated_format(self.startpage, self.endpage) if pagerange: entry += ":%s" % pagerange else: if self.startpage and self.endpage and self.startpage.isdigit() and self.endpage.isdigit(): if self.subtitle: entry = " (%s)" % self.subtitle pagerange = PublicationInterface.get_page_range_in_abbreviated_format(self.startpage, self.endpage) if pagerange: entry += ":%s" % pagerange s = ['%s. ' % authors_str] if html: if self.doi: s.append('%s%s %s %s%s.' % (self.title, titlesuffix, self.journal, entry, year_str)) s.append('doi: <a class="publication_doi" href="http://dx.doi.org/%s">%s</a>''' % (self.doi, self.doi)) s.append(ReferralURL_link) elif self.url: s.append('<a class="publication_link" href="%s">%s</a>%s' % (self.url, self.title, titlesuffix)) s.append('%s %s%s.' % (self.journal, entry, year_str)) s.append(ReferralURL_link) else: s.append('%s%s %s %s%s.' % (self.title, titlesuffix, self.journal, entry, year_str)) s.append(ReferralURL_link) else: s.append('%s%s %s %s%s.' % (self.title, titlesuffix, self.journal, entry, year_str)) if self.doi: s.append('doi: %s' % self.doi) elif self.url: s.append('url: %s' % self.url) return " ".join(s)
#print('comment : %s' % comment) if remaining_description: #colortext.error('remaining_description : %s' % remaining_description) pass #print('\n') if __name__ == '__main__': script_name = sys.argv[0] args = sys.argv[1:] if 4 > len(args) or len(args) > 6: print('Usage : %s [user] [host] [db] [passwd]' % script_name) print('Optional arguments: %s [user] [host] [db] [passwd] [port] [socket]' % script_name) else: user = args[0] host = args[1] db = args[2] passwd = args[3] port = 3306 socket = '/var/lib/mysql/mysql.sock' if len(args) == 6: socket = args[5] if len(args) >= 5: try: port = int(args[4]) except: colortext.error('Error: Port must be a numeric string.') sys.exit(1) sc = MySQLSchemaConverter(user, host, db, passwd, port, socket) sc.get_sqlalchemy_schema()
def determine_structure_scores(DDG_api, skip_if_we_have_pairs = 50): pp = pprint.PrettyPrinter(indent=4) ddGdb = DDG_api.ddGDB ddGdb_utf = ddgdbapi.ddGDatabase(use_utf = True) # Get the list of completed prediction set completed_prediction_sets = get_completed_prediction_sets(DDG_api) print(completed_prediction_sets) # Create the mapping from the old score types to the ScoreMethod record IDs ScoreMethodMap = {} results = ddGdb_utf.execute('SELECT * FROM ScoreMethod') for r in results: if r['MethodName'] == 'Global' and r['MethodType'] == 'Protocol 16': ScoreMethodMap[("kellogg", "total")] = r['ID'] if r['Authors'] == 'Noah Ollikainen': if r['MethodName'] == 'Local' and r['MethodType'] == 'Position' and r['Parameters'] == u'8Å radius': ScoreMethodMap[("noah_8,0A", "positional")] = r['ID'] if r['MethodName'] == 'Local' and r['MethodType'] == 'Position (2-body)' and r['Parameters'] == u'8Å radius': ScoreMethodMap[("noah_8,0A", "positional_twoscore")] = r['ID'] if r['MethodName'] == 'Global' and r['MethodType'] == 'By residue' and r['Parameters'] == u'8Å radius': ScoreMethodMap[("noah_8,0A", "total")] = r['ID'] # For each completed prediction set, determine the structure scores for prediction_set in completed_prediction_sets: #if prediction_set not in ['Ubiquitin scan: UQ_con_yeast p16']: # continue predictions = ddGdb.execute('SELECT ID, ddG, Scores, status, ScoreVersion FROM Prediction WHERE PredictionSet=%s ORDER BY ID', parameters=(prediction_set,)) num_predictions = len(predictions) # Pass #1: Iterate over all Predictions and make sure that they gave completed and contain all the scores we expect colortext.message('Prediction set: %s' % prediction_set) colortext.warning('Checking that all data exists...') for prediction in predictions: #assert(prediction['status'] == 'done') PredictionID = prediction['ID'] if PredictionID != 72856: continue global_scores = pickle.loads(prediction['ddG']) assert(global_scores) assert(prediction['ScoreVersion'] == 0.23) if not prediction['Scores']: raise Exception("This prediction needs to be scored with Noah's method.") gs2 = json.loads(prediction['Scores']) if True not in set([k.find('noah') != -1 for k in gs2['data'].keys()]): raise Exception("This prediction needs to be scored with Noah's method.") assert (gs2['data']['kellogg'] == global_scores['data']['kellogg']) # Pass #2: Iterate over all completed Predictions with null StructureScores. # For each Prediction, determine and store the structure scores count = 0 for prediction in predictions: count += 1 PredictionID = prediction['ID'] colortext.message('%s: %d of %d (Prediction #%d)' % (prediction_set, count, num_predictions, PredictionID)) #if PredictionID != 72856: #if PredictionID < 73045: continue if prediction['status'] == 'failed': colortext.error('Skipping failed prediction %d.' % PredictionID) continue if prediction['status'] == 'queued': colortext.warning('Skipping queued prediction %d.' % PredictionID) continue if prediction['status'] == 'postponed': colortext.printf('Skipping postponed prediction %d.' % PredictionID, 'cyan') continue # Store the ensemble scores try: global_scores = json.loads(prediction['Scores'])['data'] except: raise colortext.Exception("Failed reading the Scores field's JSON object. The Prediction Status is %(status)s. The Scores field is: '%(Scores)s'." % prediction) for score_type, inner_data in global_scores.iteritems(): for inner_score_type, data in inner_data.iteritems(): components = {} if score_type == 'kellogg' and inner_score_type == 'total': components = data['components'] ddG = data['ddG'] elif score_type == 'noah_8,0A' and inner_score_type == 'positional': ddG = data['ddG'] elif score_type == 'noah_8,0A' and inner_score_type == 'positional_twoscore': ddG = data['ddG'] elif score_type == 'noah_8,0A' and inner_score_type == 'total': ddG = data['ddG'] else: continue raise Exception('Unhandled score types: "%s", "%s".' % (score_type, inner_score_type)) ScoreMethodID = ScoreMethodMap[(score_type, inner_score_type)] new_record = dict( PredictionID = PredictionID, ScoreMethodID = ScoreMethodID, ScoreType = 'DDG', StructureID = -1, # This score is for the Prediction rather than a structure DDG = ddG, ) assert(not(set(components.keys()).intersection(set(new_record.keys())))) new_record.update(components) ddGdb.insertDictIfNew('PredictionStructureScore', new_record, ['PredictionID', 'ScoreMethodID', 'ScoreType', 'StructureID']) if skip_if_we_have_pairs != None: # Skip this case if we have a certain number of existing records (much quicker since we do not have to extract the binary) num_wt = ddGdb.execute_select("SELECT COUNT(ID) AS NumRecords FROM PredictionStructureScore WHERE PredictionID=%s AND ScoreType='WildType'", parameters=(PredictionID,))[0]['NumRecords'] num_mut = ddGdb.execute_select("SELECT COUNT(ID) AS NumRecords FROM PredictionStructureScore WHERE PredictionID=%s AND ScoreType='Mutant'", parameters=(PredictionID,))[0]['NumRecords'] print(num_wt, num_mut) if num_wt == num_mut and num_mut == skip_if_we_have_pairs: continue # Store the ddg_monomer scores for each structure grouped_scores = DDG_api.get_ddg_monomer_scores_per_structure(PredictionID) for structure_id, wt_scores in sorted(grouped_scores['WildType'].iteritems()): new_record = dict( PredictionID = PredictionID, ScoreMethodID = ScoreMethodMap[("kellogg", "total")], ScoreType = 'WildType', StructureID = structure_id, DDG = None, ) new_record.update(wt_scores) ddGdb.insertDictIfNew('PredictionStructureScore', new_record, ['PredictionID', 'ScoreMethodID', 'ScoreType', 'StructureID']) for structure_id, wt_scores in sorted(grouped_scores['Mutant'].iteritems()): new_record = dict( PredictionID = PredictionID, ScoreMethodID = ScoreMethodMap[("kellogg", "total")], ScoreType = 'Mutant', StructureID = structure_id, DDG = None, ) new_record.update(wt_scores) ddGdb.insertDictIfNew('PredictionStructureScore', new_record, ['PredictionID', 'ScoreMethodID', 'ScoreType', 'StructureID']) # Test to make sure that we can pick a best pair of structures (for generating a PyMOL session) assert(DDG_api.determine_best_pair(PredictionID) != None)
def import_mutageneses(): setup_mutations_dataframe() ppi_api = get_ppi_api() complex_definitions = json.loads(read_file('tinas_complexes.json')) # Determine the mapping from PDB ID to complex ID pdb_id_to_database_id = {} for index, r in mutations_dataframe.iterrows(): pdb_id = r['pdb'] db_id = complex_definitions[pdb_id]['Structure']['db_id'] if pdb_id_to_database_id.get(pdb_id): assert(pdb_id_to_database_id[pdb_id] == db_id) pdb_id_to_database_id[pdb_id] = db_id pdb_id_to_complex_id = {} for pdb_id, db_id in sorted(pdb_id_to_database_id.iteritems()): results = ppi_api.DDG_db.execute_select('SELECT DISTINCT PPComplexID, SetNumber FROM PPIPDBPartnerChain WHERE PDBFileID=%s', parameters=(db_id,)) assert(len(results) == 1) pdb_id_to_complex_id[pdb_id] = dict(PPComplexID = results[0]['PPComplexID'], SetNumber = results[0]['SetNumber']) pdb_residues = {} for db_id in pdb_id_to_database_id.values(): pdb_residues[db_id] = {} for r in ppi_api.DDG_db.execute_select('SELECT Chain, ResidueID, ResidueAA FROM PDBResidue WHERE PDBFileID=%s', parameters=(db_id,)): pdb_residues[db_id][r['Chain']] = pdb_residues[db_id].get(r['Chain'], {}) pdb_residues[db_id][r['Chain']][r['ResidueID']] = r['ResidueAA'] assert(len(pdb_id_to_complex_id) == 15) user_data_set_text_id = 'RAN-GSP' ppi_api.add_user_dataset('oconchus', user_data_set_text_id, "Tina's dataset for RAN/GSP1 complexes.") user_dataset_cases = [] for index, r in mutations_dataframe.iterrows(): pdb_id = r['pdb'] database_pdb_id = pdb_id_to_database_id[pdb_id] dataset_id = index pdb_id = r['pdb'] complex_definition = complex_definitions[pdb_id] # all the mutations are on chain1 (which is always chain A) chain_id = 'A' residue_id = str(r['pdb_res_num']) wildtype_aa = pdb_residues[database_pdb_id][chain_id][PDB.ResidueID2String(residue_id)] mutant_aa = r['mutation'] assert(wildtype_aa != mutant_aa) case_details = dict( # These records are used to create a PPMutagenesis record and the associated mutagenesis details Mutagenesis = dict( RecognizableString = 'TinaGSP_{0}'.format(dataset_id), PPComplexID = pdb_id_to_complex_id[pdb_id]['PPComplexID'], ), Mutations = [ # There is one dict per mutation dict( MutagenesisMutation = dict( # PPMutagenesisID will be filled in when the PPMutagenesis record is created. RecordKey = '{0} {1}{2}{3}'.format(chain_id, wildtype_aa, residue_id.strip(), mutant_aa), ProteinID = None, # todo ResidueIndex = None, # todo WildTypeAA = wildtype_aa, MutantAA = mutant_aa, ), MutagenesisPDBMutation = dict( # PPMutagenesisID and PPMutagenesisMutationID will be filled in when the PPMutagenesisMutation record is created. # PPComplexID is taken from the PPMutagenesis section. WildTypeAA and MutantAA are taken from the PPMutagenesisMutation section. SetNumber = pdb_id_to_complex_id[pdb_id]['SetNumber'], PDBFileID = database_pdb_id, Chain = chain_id, ResidueID = residue_id, ), ), ], # This field is used to create the UserPPDataSetExperiment record. All other fields can be derived from the above. # Note: We use the human-readable label here. The database ID is retrieved using e.g. ppi_api.get_defined_user_datasets()[<UserDataSetTextID>]['ID'] UserDataSetTextID = user_data_set_text_id, ) user_dataset_cases.append(case_details) colortext.porange('Creating the UserDataSet cases') user_dataset_name_to_id_map = {} tsession = ppi_api.get_session(new_session = True) try: for user_dataset_case in user_dataset_cases: ppi_api.add_user_dataset_case(tsession, user_dataset_case, user_dataset_name_to_id_map = user_dataset_name_to_id_map) print('\n\nSuccess') tsession.commit() #tsession.rollback() tsession.close() except Exception, e: colortext.error('\n\nFailure: An error occurred.') colortext.warning(str(e)) colortext.warning(traceback.format_exc()) tsession.rollback() tsession.close()
def main(FixedIDs = [], radii = [6.0, 7.0, 8.0, 9.0]): max_processors = get_number_of_processors() rescore_process_file = "/tmp/klab_rescore.txt" parser = OptionParser() parser.add_option("-n", "--numprocesses", default=1, type='int', dest="num_processes", help="The number of processes used for the rescoring. The cases are split according to this number.", metavar="NUM_PROCESSES") parser.add_option("-p", "--process", default=1, type='int', dest="process", help="The ID of this process. This should be an integer between 1 and the number of processes used for the rescoring.", metavar="PROCESS_ID") parser.add_option("-d", "--delete", action="store_true", dest="delete", help="Delete the process tracking file %s." % rescore_process_file) parser.add_option("-s", "--set", type='string', dest="prediction_set", help="The prediction set to rescore.") (options, args) = parser.parse_args() if options.delete and os.path.exists(rescore_process_file): print("Removing %s." % rescore_process_file) os.remove(rescore_process_file) num_processes = options.num_processes prediction_set = options.prediction_set process_id = options.process for i in FixedIDs: assert(type(i) == type(1)) # SELECT * FROM `Prediction` WHERE `PredictionSet`= 'RosCon2013_P16_score12prime' AND Status='done' LIMIT 1 # Check prediction set if not prediction_set: raise colortext.Exception("A prediction set must be specified.") else: if FixedIDs: results = ddGdb.execute("SELECT DISTINCT PredictionSet FROM Prediction WHERE ID IN (%s)" % ",".join(map(str, FixedIDs))) if len(results) != 1: raise colortext.Exception("Error: The fixed IDs cover %d different prediction sets." % len(results)) else: results = ddGdb.execute("SELECT ID FROM PredictionSet WHERE ID=%s", parameters=(prediction_set,)) if not results: raise colortext.Exception("The prediction set '%s' does not exist in the database." % prediction_set) if num_processes < 1: raise colortext.Exception("At least 1 processor must be used.") if num_processes > max_processors: raise colortext.Exception("Only %d processors/cores were detected. Cannot run with %d processes." % (max_processors, num_processes)) if num_processes > (max_processors * 0.75): colortext.warning("Warning: Using %d processors/cores out of %d which is %0.2f%% of the total available." % (num_processes, max_processors, (100.0*float(num_processes)/float(max_processors)))) if not(1 <= process_id <= min(max_processors, num_processes)): raise colortext.Exception("The process ID %d must be between 1 and the number of processes, %d." % (process_id, num_processes)) if os.path.exists(rescore_process_file): lines = readFileLines(rescore_process_file) idx = lines[0].find("numprocesses") if idx == -1: raise Exception("Badly formatted %s." % rescore_process_file) existing_num_processes = int(lines[0][idx+len("numprocesses"):]) if existing_num_processes != num_processes: raise colortext.Exception("You specified the number of processes to be %d but %s already specifies it as %d." % (num_processes, rescore_process_file, existing_num_processes)) for line in [line for line in lines[1:] if line.strip()]: idx = line.find("process") if idx == -1: raise colortext.Exception("Badly formatted %s. Line is '%s'." % (rescore_process_file, line)) existing_process = int(line[idx+len('process'):]) if process_id == existing_process: raise colortext.Exception("Process %d is already logged as running. Check if this is so and edit %s." % (process_id, rescore_process_file)) F = open(rescore_process_file, 'a') F.write("process %d\n" % process_id) F.close() else: F = open(rescore_process_file, 'w') F.write("numprocesses %d\n" % num_processes) F.write("process %d\n" % process_id) F.close() output_dir = os.path.join('rescoring', str(process_id)) if not(os.path.exists(output_dir)): os.makedirs(output_dir) abs_output_dir = os.path.abspath(os.path.join(os.getcwd(), output_dir)) print("Running process in %s.\n" % abs_output_dir) ReallyFixedIDs = False results = ddGdb.execute("SELECT ID, ExperimentID, Scores FROM Prediction WHERE PredictionSet=%s AND Status='done' AND ScoreVersion <> %s", parameters=(prediction_set, float(current_score_revision),)) if not(FixedIDs) and results: raise WrongScoreRevisionException("Score versions found which are not %s. Need to update table structure." % current_score_revision) else: # Hacky way to run multiple processes if ReallyFixedIDs: num_to_score = len(remaining_unscored) num_for_this_to_score = num_to_score / num_processes IDs_to_score = remaining_unscored[(process_id-1) * num_for_this_to_score : (process_id) * num_for_this_to_score] results = ddGdb.execute("SELECT ID, ExperimentID, Scores, UserDataSetExperimentID FROM Prediction WHERE ID IN (%s)" % (",".join(map(str, IDs_to_score)))) elif FixedIDs: results = ddGdb.execute("SELECT ID, ExperimentID, Scores, UserDataSetExperimentID FROM Prediction WHERE ID IN (%s) AND MOD(ID,%s)=%s" % (",".join(map(str, FixedIDs)), num_processes,process_id-1)) else: results = ddGdb.execute("SELECT ID, ExperimentID, Scores, UserDataSetExperimentID FROM Prediction WHERE PredictionSet=%s AND Status='done' AND ScoreVersion=%s AND MOD(ID,%s)=%s", parameters=(prediction_set, float(current_score_revision),num_processes,process_id-1)) count = 0 cases_computed = 0 total_time_in_secs = 0 number_of_cases_left = len(results) * len(radii) failed_cases = [] colortext.printf("Rescoring %d predictions over %d radii...\n" % (len(results), len(radii)), 'lightgreen') for r in results: t = Timer() t.add('Preamble') inner_count = 0 mutations = ddGdb.execute('SELECT * FROM ExperimentMutation WHERE ExperimentID=%s', parameters=(r['ExperimentID'],)) mutation_str = ', '.join(['%s %s%s%s' % (m['Chain'], m['WildTypeAA'], m['ResidueID'], m['MutantAA']) for m in mutations]) extracted_data = False details = ddGdb.execute_select('SELECT Prediction.ID, PDBFileID, Chain FROM Prediction INNER JOIN Experiment ON Prediction.ExperimentID=Experiment.ID INNER JOIN ExperimentChain ON Prediction.ExperimentID=ExperimentChain.ExperimentID WHERE Prediction.ID=%s', parameters=(r['ID'],)) details = ddGdb.execute_select('SELECT Prediction.ID, PDBFileID, Chain FROM Prediction INNER JOIN Experiment ON Prediction.ExperimentID=Experiment.ID INNER JOIN ExperimentChain ON Prediction.ExperimentID=ExperimentChain.ExperimentID WHERE Prediction.ID=%s', parameters=(r['ID'],)) colortext.message("Prediction: %d, %s chain %s. Mutations: %s. Experiment ID #%d. UserDataSetExperimentID #%d." % (details[0]['ID'], details[0]['PDBFileID'], details[0]['Chain'], mutation_str, r['ExperimentID'], r['UserDataSetExperimentID'])) experiment_pdbID = ddGdb.execute('SELECT PDBFileID FROM Experiment WHERE ID=%s', parameters=(r['ExperimentID'],))[0]['PDBFileID'] print('Experiment PDB file ID = %s' % experiment_pdbID) pdbID = ddGdb.execute('SELECT UserDataSetExperiment.PDBFileID FROM Prediction INNER JOIN UserDataSetExperiment ON UserDataSetExperimentID=UserDataSetExperiment.ID WHERE Prediction.ID=%s', parameters=(r['ID'],))[0]['PDBFileID'] print('UserDataSetExperiment PDB file ID = %s' % pdbID) count += 1 if True:#len(mutations) == 1: timestart = time.time() #mutation = mutations[0] dbchains = sorted(set([mutation['Chain'] for mutation in mutations])) # todo: note: assuming monomeric structures here assert(len(dbchains) == 1) dbchain = dbchains[0] #mutantaa = mutation['MutantAA'] ddG_dict = json.loads(r['Scores']) kellogg_ddG = ddG_dict['data']['kellogg']['total']['ddG'] #assert(ddG_dict['version'] == current_score_revision) all_done = True for radius in radii: score_name = ('noah_%0.1fA' % radius).replace(".", ",") if not(ddG_dict['data'].get(score_name)): all_done = False else: cases_computed += 1 number_of_cases_left -= 1 if all_done: print('Prediction %d: done.' % r["ID"]) continue # Extract data t.add('Grab data') #archivefile = None #prediction_data_path = ddGdb.execute('SELECT Value FROM _DBCONSTANTS WHERE VariableName="PredictionDataPath"')[0]['Value'] #job_data_path = os.path.join(prediction_data_path, '%d.zip' % r['ID']) #print(job_data_path) #assert(os.path.exists(job_data_path)) #archivefile = readBinaryFile(job_data_path) archivefile = DDG_interface.getData(r['ID']) zipfilename = os.path.join(output_dir, "%d.zip" % r['ID']) F = open(zipfilename, "wb") F.write(archivefile) F.close() t.add('Extract data') zipped_content = zipfile.ZipFile(zipfilename, 'r', zipfile.ZIP_DEFLATED) tmpdir = None repacked_files = [] mutant_files = [] rosetta_resids = [] try: tmpdir = makeTemp755Directory(output_dir) highestIndex = -1 foundResfile = False foundMutfile = False presumed_mutation = None for fname in sorted(zipped_content.namelist()): if fname.endswith(".pdb"): if fname.startswith("%s/mut_" % r['ID']) or fname.startswith("%s/repacked_" % r['ID']): structnum = int(fname[fname.rindex('_')+1:-4]) if fname.startswith("%s/mut_" % r['ID']): if presumed_mutation: assert(presumed_mutation == os.path.split(fname)[1].split('_')[1]) else: presumed_mutation = os.path.split(fname)[1].split('_')[1] newfname = 'mutant_%02d' % structnum if fname.startswith("%s/repacked_" % r['ID']): newfname = 'repacked_%02d' % structnum highestIndex = max(highestIndex, structnum) newfilepath = os.path.join(tmpdir, newfname) writeFile(newfilepath, zipped_content.read(fname)) if fname.startswith("%s/mut_" % r['ID']): mutant_files.append(newfilepath) if fname.startswith("%s/repacked_" % r['ID']): repacked_files.append(newfilepath) #elif fname.startswith("%s/%s-%s" % (r['ID'],r['ExperimentID'],pdbID)) or fname.startswith("%s/repacked_" % r['ID']): # writeFile(os.path.join(tmpdir, '%s.pdb' % pdbID), zipped_content.read(fname)) if fname.startswith("%s/%s-%s.resfile" % (r['ID'],r['ExperimentID'],experiment_pdbID)): raise Exception('This case needs to be updated (see the mutfile section below). We mainly use mutfiles now so I did not update this section.') foundResfile = True lines = zipped_content.read(fname).split("\n") assert(len(lines) == 3) assert(lines[0] == "NATAA") assert(lines[1] == "start") resfile_mutation = lines[2].split(" ") assert(len(resfile_mutation) == 4) rosetta_resid = resfile_mutation[0] rosetta_chain = resfile_mutation[1] rosetta_mutaa = resfile_mutation[3] assert(mutantaa == rosetta_mutaa) assert(dbchain == rosetta_chain) assert(resfile_mutation[2] == 'PIKAA') assert(len(rosetta_mutaa) == 1) if fname.startswith("%s/%s-%s.mutfile" % (r['ID'],r['ExperimentID'],experiment_pdbID)): foundMutfile = True lines = zipped_content.read(fname).split("\n") assert(lines[0].startswith('total ')) num_mutations = int(lines[0][6:]) assert(lines[1] == str(num_mutations)) # todo: note: assuming monomeric structures here rosetta_chain = ddGdb.execute("SELECT Chain FROM ExperimentChain WHERE ExperimentID=%s", parameters=(r['ExperimentID'],)) assert(len(rosetta_chain) == 1) rosetta_chain = rosetta_chain[0]['Chain'] resfile_mutations = lines[2:] for resfile_mutation in resfile_mutations: resfile_mutation = resfile_mutation.split(" ") assert(len(resfile_mutation) == 3) rosetta_resids.append(resfile_mutation[1]) rosetta_mutaa = resfile_mutation[2] assert(dbchain == rosetta_chain) assert(len(rosetta_mutaa) == 1) # Make sure the wtaa->mutantaa types match the structures assert(not(foundResfile)) if not foundMutfile: raise Exception('This case needs to be updated (see the mutfile section below). This was added as a hack for cases where I did not store the mutfile so I did not update this section.') input_files = ddGdb.execute_select('SELECT InputFiles FROM Prediction WHERE ID=%s', parameters=(r['ID'],)) assert(len(input_files) == 1) lines = pickle.loads(input_files[0]['InputFiles'])['MUTFILE'].split("\n") #lines = regenerate_mutfile(r['ID']).split("\n") assert(len(lines) == 3) assert(lines[0] == "total 1") assert(lines[1] == "1") resfile_mutation = lines[2].split(" ") assert(len(resfile_mutation) == 3) rosetta_resid = resfile_mutation[1] rosetta_chain = ddGdb.execute("SELECT Chain FROM ExperimentChain WHERE ExperimentID=%s", parameters=(r['ExperimentID'],)) assert(len(rosetta_chain) == 1) rosetta_chain = rosetta_chain[0]['Chain'] rosetta_mutaa = resfile_mutation[2] assert(dbchain == rosetta_chain) assert(len(rosetta_mutaa) == 1) assert("%s%s%s" % (resfile_mutation[0], resfile_mutation[1], resfile_mutation[2]) == presumed_mutation) fullresids = [] for rosetta_resid in rosetta_resids: fullresid = None if rosetta_resid.isdigit(): fullresid = '%s%s%s ' % (rosetta_chain, (4-len(rosetta_resid)) * ' ', rosetta_resid) else: assert(False) fullresid = '%s%s%s' % (rosetta_chain, (5-len(rosetta_resid)) * ' ', rosetta_resid) fullresids.append(fullresid) resultst1 = ddGdb.execute_select("SELECT ExperimentID, UserDataSetExperimentID FROM Prediction WHERE ID=%s", parameters = (r['ID'],)) assert(len(resultst1) == 1) ExperimentIDt1 = resultst1[0]['ExperimentID'] UserDataSetExperimentIDt1 = resultst1[0]['UserDataSetExperimentID'] if UserDataSetExperimentIDt1: resultst2 = ddGdb.execute_select("SELECT PDBFileID FROM UserDataSetExperiment WHERE ID=%s", parameters = (UserDataSetExperimentIDt1,)) else: resultst2 = ddGdb.execute_select("SELECT PDBFileID FROM Experiment WHERE ID=%s", parameters = (ExperimentIDt1,)) assert(len(resultst2) == 1) prediction_PDB_ID = resultst2[0]['PDBFileID'] if False and prediction_PDB_ID not in ['1TEN', '1AYE', '1H7M'] + ['1A2P', '1BNI', '1STN']: for fullresid in fullresids: wtaa = None for m in mutations: # Hack for ub_RPN13 if prediction_PDB_ID == 'ub_RPN13' and m['Chain'] == fullresid[0] and m['ResidueID'] == str(int(fullresid[1:].strip()) - 109): wtaa = m['WildTypeAA'] # Hack for ub_RPN13_yeast elif prediction_PDB_ID == 'uby_RPN13' and m['Chain'] == fullresid[0] and m['ResidueID'] == str(int(fullresid[1:].strip()) - 109): wtaa = m['WildTypeAA'] # Hack for ub_OTU elif prediction_PDB_ID == 'ub_OTU' and m['Chain'] == fullresid[0] and m['ResidueID'] == str(int(fullresid[1:].strip()) - 172): wtaa = m['WildTypeAA'] # Hack for ub_OTU_yeast elif prediction_PDB_ID == 'uby_OTU' and m['Chain'] == fullresid[0] and m['ResidueID'] == str(int(fullresid[1:].strip()) - 172): wtaa = m['WildTypeAA'] # Hack for ub_UQcon elif prediction_PDB_ID == 'ub_UQcon' and m['Chain'] == fullresid[0] and m['ResidueID'] == str(int(fullresid[1:].strip()) + 213): # starts at 501 wtaa = m['WildTypeAA'] # Hack for uby_UQcon elif prediction_PDB_ID == 'uby_UQcon' and m['Chain'] == fullresid[0] and m['ResidueID'] == str(int(fullresid[1:].strip()) - 287): wtaa = m['WildTypeAA'] elif m['Chain'] == fullresid[0] and m['ResidueID'] == fullresid[1:].strip(): wtaa = m['WildTypeAA'] if (wtaa == None): colortext.error(prediction_PDB_ID) colortext.error('wtaa == None') colortext.error('fullresid = %s' % str(fullresid)) colortext.error(str(mutations)) colortext.warning([rosetta_resid.strip() for rosetta_resid in rosetta_resids]) #sys.exit(0) assert(wtaa != None) assert(PDB.from_filepath(repacked_files[0]).get_residue_id_to_type_map()[fullresid] == wtaa) #assert(PDB(mutant_files[0]).get_residue_id_to_type_map()[fullresid] == mutantaa) for radius in radii: score_name = ('noah_%0.1fA' % radius).replace(".", ",") if ddG_dict['data'].get(score_name): print('Radius %0.1f: done.' % radius) continue cases_computed += 1 number_of_cases_left -= 1 t.add('Radius %0.3f: repacked' % radius) colortext.printf("Prediction ID: %d. Calculating radius %0.1f. Calculation #%d of %d." % (r['ID'], radius, cases_computed, len(results) * len(radii)), 'orange') repacked_score = NoahScore() repacked_score.calculate(repacked_files, rosetta_chain, sorted([rosetta_resid.strip() for rosetta_resid in rosetta_resids]), radius = radius) colortext.message("Repacked") print(repacked_score) t.add('Radius %0.3f: mutant' % radius) mutant_score = NoahScore() mutant_score.calculate(mutant_files, rosetta_chain, sorted([rosetta_resid.strip() for rosetta_resid in rosetta_resids]), radius = radius) colortext.printf("Mutant", color = 'cyan') print(mutant_score) t.add('Radius %0.3f: postamble' % radius) colortext.printf("ddG", color = 'lightpurple') ddg_score = repacked_score.ddg(mutant_score) print(ddg_score) colortext.printf("Liz's ddG", color = 'yellow') print("Total score: %0.3f" % kellogg_ddG) ddG_dict['version'] = '0.23' if ddG_dict['version'] == '0.1': ddG_dict['version'] = '0.21' ddG_dict['data'] = { 'kellogg' : { 'total' : ddG_dict['data'], }, 'noah': { 'total' : {'ddG' : ddg_score.total}, 'positional' : {'ddG' : ddg_score.positional}, 'positional_twoscore' : {'ddG' : ddg_score.positional_twoscore}, }, } elif ddG_dict['version'] == '0.2': ddG_dict['version'] = '0.21' ddG_dict['data']['noah']['total']['ddG'] = ddg_score.total ddG_dict['data']['noah']['positional']['ddG'] = ddg_score.positional ddG_dict['data']['noah']['positional_twoscore']['ddG'] = ddg_score.positional_twoscore elif ddG_dict['version'] == '0.22': ddG_dict['data'][score_name] = {'total' : {}, 'positional' : {}, 'positional_twoscore' : {}} ddG_dict['data'][score_name]['total']['ddG'] = ddg_score.total ddG_dict['data'][score_name]['positional']['ddG'] = ddg_score.positional ddG_dict['data'][score_name]['positional_twoscore']['ddG'] = ddg_score.positional_twoscore elif ddG_dict['version'] == '0.23': ddG_dict['data'][score_name] = {'total' : {}, 'positional' : {}, 'positional_twoscore' : {}} ddG_dict['data'][score_name]['total']['ddG'] = ddg_score.total ddG_dict['data'][score_name]['positional']['ddG'] = ddg_score.positional ddG_dict['data'][score_name]['positional_twoscore']['ddG'] = ddg_score.positional_twoscore jsonified_ddG = json.dumps(ddG_dict) ddGdb.execute('UPDATE Prediction SET Scores=%s WHERE ID=%s', parameters=(jsonified_ddG, r['ID'],)) t.add('Cleanup') shutil.rmtree(tmpdir) os.remove(zipfilename) except Exception, e: print("Exception! In prediction %d" % r['ID'], str(e)) failed_cases.append(r['ID']) import traceback print(traceback.format_exc()) if tmpdir: shutil.rmtree(tmpdir) total_time_in_secs += t.sum() average_time_taken = float(total_time_in_secs)/float(cases_computed or 1) estimate_remaining_time = number_of_cases_left * average_time_taken t.stop() colortext.printf("**Profile**", 'orange') print(t) colortext.message("Time taken for this case: %0.2fs." % t.sum()) colortext.message("Average time taken per case: %0.2fs." % average_time_taken) colortext.message("Estimated time remaining: %dh%dm%ds." % (int(estimate_remaining_time/3600), int((estimate_remaining_time/60) % 60), estimate_remaining_time % 60)) print("\n")
try: print('Case %d/%d: %s' % (count, num_cases, pdb_id)) sifts_map = SIFTS.retrieve(pdb_id, cache_dir = cache_dir, acceptable_sequence_percentage_match = 80.0) except MissingSIFTSRecord: colortext.warning('No SIFTS XML exists for %s.' % pdb_id) except BadSIFTSMapping: colortext.warning('The SIFTS mapping for %s was considered a bad mapping at the time of writing.' % pdb_id) except NoSIFTSPDBUniParcMapping: colortext.warning('The SIFTS file for %s does not map to UniParc sequences at the time of writing.' % pdb_id) except Exception, e: colortext.warning(str(e)) colortext.error(traceback.format_exc()) failures.append(pdb_id) count += 1 if failures: colortext.error('Failures: %d/%d' % (len(failures), num_cases)) for f in failures: colortext.warning(f) def test_pdbml_speed(): test_cases = [ '1WSY', '1YGV', '487D', '1HIO', '1H38', '3ZKB', ] for test_case in test_cases: print("\n")