3 * Jalview - A Sequence Alignment Editor and Viewer ($$Version-Rel$$)
4 * Copyright (C) $$Year-Rel$$ The Jalview Authors
6 * This file is part of Jalview.
8 * Jalview is free software: you can redistribute it and/or
9 * modify it under the terms of the GNU General Public License
10 * as published by the Free Software Foundation, either version 3
11 * of the License, or (at your option) any later version.
13 * Jalview is distributed in the hope that it will be useful, but
14 * WITHOUT ANY WARRANTY; without even the implied warranty
15 * of MERCHANTABILITY or FITNESS FOR A PARTICULAR
16 * PURPOSE. See the GNU General Public License for more details.
18 * You should have received a copy of the GNU General Public License
19 * along with Jalview. If not, see <http://www.gnu.org/licenses/>.
20 * The Jalview Authors are detailed in the 'AUTHORS' file.
22 package jalview.ws.dbsources;
25 import java.io.FileInputStream;
26 import java.util.ArrayList;
27 import java.util.List;
30 import com.stevesoft.pat.Regex;
32 import jalview.api.FeatureSettingsModelI;
33 import jalview.bin.Console;
34 import jalview.datamodel.AlignmentAnnotation;
35 import jalview.datamodel.AlignmentI;
36 import jalview.datamodel.ContactMatrixI;
37 import jalview.datamodel.DBRefEntry;
38 import jalview.datamodel.PDBEntry;
39 import jalview.datamodel.SequenceFeature;
40 import jalview.datamodel.SequenceI;
41 import jalview.io.DataSourceType;
42 import jalview.io.FileFormat;
43 import jalview.io.FileFormatI;
44 import jalview.io.FormatAdapter;
45 import jalview.io.PDBFeatureSettings;
46 import jalview.util.MessageManager;
47 import jalview.util.Platform;
48 import jalview.ws.datamodel.alphafold.PAEContactMatrix;
49 import jalview.ws.utils.UrlDownloadClient;
55 public class EBIAlfaFold extends EbiFileRetrievedProxy
57 private static final String SEPARATOR = "|";
59 private static final String COLON = ":";
61 private static final int PDB_ID_LENGTH = 4;
63 private static String AF_VERSION = "2";
73 * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
76 public String getAccessionSeparator()
84 * @see jalview.ws.DbSourceProxy#getAccessionValidator()
87 public Regex getAccessionValidator()
89 Regex validator = new Regex("(AF-[A-Z]+[0-9]+[A-Z0-9]+-F1)");
90 validator.setIgnoreCase(true);
97 * @see jalview.ws.DbSourceProxy#getDbSource()
100 public String getDbSource()
108 * @see jalview.ws.DbSourceProxy#getDbVersion()
111 public String getDbVersion()
116 public static String getAlphaFoldCifDownloadUrl(String id, String vnum)
118 if (vnum == null || vnum.length() == 0)
122 return "https://alphafold.ebi.ac.uk/files/" + id + "-model_v" + vnum
126 public static String getAlphaFoldPaeDownloadUrl(String id, String vnum)
128 if (vnum == null || vnum.length() == 0)
132 return "https://alphafold.ebi.ac.uk/files/" + id
133 + "-predicted_aligned_error_v" + vnum + ".json";
139 * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
142 public AlignmentI getSequenceRecords(String queries) throws Exception
144 return getSequenceRecords(queries, null);
147 public AlignmentI getSequenceRecords(String queries, String retrievalUrl)
150 AlignmentI pdbAlignment = null;
153 if (queries.indexOf(COLON) > -1)
155 chain = queries.substring(queries.indexOf(COLON) + 1);
156 id = queries.substring(0, queries.indexOf(COLON));
163 if (!isValidReference(id))
166 "(AFClient) Ignoring invalid alphafold query: '" + id + "'");
170 String alphaFoldCif = getAlphaFoldCifDownloadUrl(id, AF_VERSION);
171 if (retrievalUrl != null)
173 alphaFoldCif = retrievalUrl;
178 File tmpFile = File.createTempFile(id, ".cif");
179 Console.debug("Retrieving structure file for " + id + " from "
181 UrlDownloadClient.download(alphaFoldCif, tmpFile);
183 // may not need this check ?
184 file = tmpFile.getAbsolutePath();
190 pdbAlignment = importDownloadedStructureFromUrl(alphaFoldCif, tmpFile,
191 id, chain, getDbSource(), getDbVersion());
193 if (pdbAlignment == null || pdbAlignment.getHeight() < 1)
195 throw new Exception(MessageManager.formatMessage(
196 "exception.no_pdb_records_for_chain", new String[]
197 { id, ((chain == null) ? "' '" : chain) }));
200 // import PAE as contact matrix - assume this will work if there was a
202 File pae = File.createTempFile(id, "pae_json");
203 String paeURL = getAlphaFoldPaeDownloadUrl(id, AF_VERSION);
205 if (retrievalUrl != null)
207 // manufacture the PAE url from a url like ...-model-vN.cif
208 paeURL = retrievalUrl.replace("model", "predicted_aligned_error")
209 .replace(".cif", ".json");
211 Console.debug("Downloading pae from " + paeURL + " to "
212 + pae.toString() + "");
216 UrlDownloadClient.download(paeURL, pae);
217 if (!importPaeJSONAsContactMatrix(pdbAlignment, pae))
219 Console.warn("Couln't import contact matrix from " + paeURL
220 + " (stored in " + pae.toString() + ")");
222 } catch (Exception pae_ex)
224 Console.debug("Couldn't download PAE", pae_ex);
227 } catch (Exception ex) // Problem parsing PDB file
235 private boolean importPaeJSONAsContactMatrix(AlignmentI pdbAlignment,
236 File pae) throws Exception
238 FileInputStream pae_input = new FileInputStream(pae);
240 List<Object> pae_obj = (List<Object>) Platform.parseJSON(pae_input);
245 ContactMatrixI matrix = new PAEContactMatrix(
246 pdbAlignment.getSequenceAt(0),
247 (Map<String, Object>) pae_obj.get(0));
249 pdbAlignment.getSequenceAt(0)
250 .addAlignmentAnnotation(pdbAlignment.addContactList(matrix));
255 * general purpose structure importer - designed to yield alignment useful for
256 * transfer of annotation to associated sequences
258 * @param alphaFoldCif
267 public static AlignmentI importDownloadedStructureFromUrl(
268 String alphaFoldCif, File tmpFile, String id, String chain,
269 String dbSource, String dbVersion) throws Exception
271 String file = tmpFile.getAbsolutePath();
272 // todo get rid of Type and use FileFormatI instead?
273 FileFormatI fileFormat = FileFormat.MMCif;
274 AlignmentI pdbAlignment = new FormatAdapter().readFile(tmpFile,
275 DataSourceType.FILE, fileFormat);
276 if (pdbAlignment != null)
278 List<SequenceI> toremove = new ArrayList<SequenceI>();
279 for (SequenceI pdbcs : pdbAlignment.getSequences())
283 for (PDBEntry pid : pdbcs.getAllPDBEntries())
285 if (pid.getFile() == file)
287 chid = pid.getChainCode();
291 if (chain == null || (chid != null && (chid.equals(chain)
292 || chid.trim().equals(chain.trim())
293 || (chain.trim().length() == 0 && chid.equals("_")))))
295 // FIXME seems to result in 'PDB|1QIP|1qip|A' - 1QIP is redundant.
296 // TODO: suggest simplify naming to 1qip|A as default name defined
297 pdbcs.setName(id + SEPARATOR + pdbcs.getName());
298 // Might need to add more metadata to the PDBEntry object
301 * PDBEntry entry = new PDBEntry(); // Construct the PDBEntry
302 * entry.setId(id); if (entry.getProperty() == null)
303 * entry.setProperty(new Hashtable());
304 * entry.getProperty().put("chains", pdbchain.id + "=" +
305 * sq.getStart() + "-" + sq.getEnd());
306 * sq.getDatasetSequence().addPDBId(entry);
309 // We make a DBRefEtntry because we have obtained the PDB file from
312 // JBPNote - PDB DBRefEntry should also carry the chain and mapping
314 if (dbSource != null)
316 DBRefEntry dbentry = new DBRefEntry(dbSource,
318 dbVersion, (chid == null ? id : id + chid));
320 pdbcs.addDBRef(dbentry);
321 // update any feature groups
322 List<SequenceFeature> allsf = pdbcs.getFeatures()
324 List<SequenceFeature> newsf = new ArrayList<SequenceFeature>();
325 if (allsf != null && allsf.size() > 0)
327 for (SequenceFeature f : allsf)
329 if (file.equals(f.getFeatureGroup()))
331 f = new SequenceFeature(f, f.type, f.begin, f.end, id,
336 pdbcs.setSequenceFeatures(newsf);
342 // mark this sequence to be removed from the alignment
343 // - since it's not from the right chain
347 // now remove marked sequences
348 for (SequenceI pdbcs : toremove)
350 pdbAlignment.deleteSequence(pdbcs);
351 if (pdbcs.getAnnotation() != null)
353 for (AlignmentAnnotation aa : pdbcs.getAnnotation())
355 pdbAlignment.deleteAnnotation(aa);
366 * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
369 public boolean isValidReference(String accession)
371 Regex r = getAccessionValidator();
372 return r.search(accession.trim());
379 public String getTestQuery()
381 return "AF-O15552-F1";
385 public String getDbName()
387 return "ALPHAFOLD"; // getDbSource();
397 * Returns a descriptor for suitable feature display settings with
399 * <li>ResNums or insertions features visible</li>
400 * <li>insertions features coloured red</li>
401 * <li>ResNum features coloured by label</li>
402 * <li>Insertions displayed above (on top of) ResNums</li>
406 public FeatureSettingsModelI getFeatureColourScheme()
408 return new PDBFeatureSettings();