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;
24 import jalview.api.FeatureSettingsModelI;
25 import jalview.bin.Cache;
26 import jalview.bin.Console;
27 import jalview.datamodel.AlignmentAnnotation;
28 import jalview.datamodel.AlignmentI;
29 import jalview.datamodel.ContactMatrix;
30 import jalview.datamodel.ContactMatrixI;
31 import jalview.datamodel.DBRefEntry;
32 import jalview.datamodel.DBRefSource;
33 import jalview.datamodel.PDBEntry;
34 import jalview.datamodel.PDBEntry.Type;
35 import jalview.datamodel.SequenceFeature;
36 import jalview.datamodel.SequenceI;
37 import jalview.datamodel.features.SequenceFeaturesI;
38 import jalview.io.DataSourceType;
39 import jalview.io.FileFormat;
40 import jalview.io.FileFormatI;
41 import jalview.io.FormatAdapter;
42 import jalview.io.PDBFeatureSettings;
43 import jalview.javascript.json.JSON;
44 import jalview.structure.StructureImportSettings;
45 import jalview.util.HttpUtils;
46 import jalview.util.MessageManager;
47 import jalview.util.Platform;
48 import jalview.ws.datamodel.alphafold.PAEContactMatrix;
49 import jalview.ws.ebi.EBIFetchClient;
50 import jalview.ws.utils.UrlDownloadClient;
52 import java.io.BufferedReader;
54 import java.io.FileInputStream;
55 import java.util.ArrayList;
56 import java.util.List;
59 import org.jmol.adapter.readers.simple.JSONReader;
61 import com.stevesoft.pat.Regex;
67 public class EBIAlfaFold extends EbiFileRetrievedProxy
69 private static final String SEPARATOR = "|";
71 private static final String COLON = ":";
73 private static final int PDB_ID_LENGTH = 4;
75 private static String AF_VERSION = "2";
85 * @see jalview.ws.DbSourceProxy#getAccessionSeparator()
88 public String getAccessionSeparator()
96 * @see jalview.ws.DbSourceProxy#getAccessionValidator()
99 public Regex getAccessionValidator()
101 Regex validator = new Regex("(AF-[A-Z]+[0-9]+[A-Z0-9]+-F1)");
102 validator.setIgnoreCase(true);
109 * @see jalview.ws.DbSourceProxy#getDbSource()
112 public String getDbSource()
120 * @see jalview.ws.DbSourceProxy#getDbVersion()
123 public String getDbVersion()
128 public static String getAlphaFoldCifDownloadUrl(String id, String vnum)
130 if (vnum == null || vnum.length() == 0)
134 return "https://alphafold.ebi.ac.uk/files/" + id + "-model_v" + vnum
138 public static String getAlphaFoldPaeDownloadUrl(String id, String vnum)
140 if (vnum == null || vnum.length() == 0)
144 return "https://alphafold.ebi.ac.uk/files/" + id
145 + "-predicted_aligned_error_v" + vnum + ".json";
151 * @see jalview.ws.DbSourceProxy#getSequenceRecords(java.lang.String[])
154 public AlignmentI getSequenceRecords(String queries) throws Exception
156 return getSequenceRecords(queries, null);
159 public AlignmentI getSequenceRecords(String queries, String retrievalUrl)
162 AlignmentI pdbAlignment = null;
165 if (queries.indexOf(COLON) > -1)
167 chain = queries.substring(queries.indexOf(COLON) + 1);
168 id = queries.substring(0, queries.indexOf(COLON));
175 if (!isValidReference(id))
178 "(AFClient) Ignoring invalid alphafold query: '" + id + "'");
182 String alphaFoldCif = getAlphaFoldCifDownloadUrl(id, AF_VERSION);
183 if (retrievalUrl != null)
185 alphaFoldCif = retrievalUrl;
190 File tmpFile = File.createTempFile(id, ".cif");
191 Console.debug("Retrieving structure file for "+id+" from "+alphaFoldCif);
192 UrlDownloadClient.download(alphaFoldCif, tmpFile);
194 // may not need this check ?
195 file = tmpFile.getAbsolutePath();
201 pdbAlignment = importDownloadedStructureFromUrl(alphaFoldCif, tmpFile,
202 id, chain, getDbSource(), getDbVersion());
204 if (pdbAlignment == null || pdbAlignment.getHeight() < 1)
206 throw new Exception(MessageManager.formatMessage(
207 "exception.no_pdb_records_for_chain", new String[]
208 { id, ((chain == null) ? "' '" : chain) }));
211 // import PAE as contact matrix - assume this will work if there was a
213 File pae = File.createTempFile(id, "pae_json");
214 String paeURL = getAlphaFoldPaeDownloadUrl(id, AF_VERSION);
216 if (retrievalUrl != null)
218 // manufacture the PAE url from a url like ...-model-vN.cif
219 paeURL = retrievalUrl.replace("model","predicted_aligned_error").replace(".cif",".json");
221 Console.debug("Downloading pae from " + paeURL
222 + " to " + pae.toString() + "");
225 UrlDownloadClient.download(paeURL, pae);
226 if (!importPaeJSONAsContactMatrix(pdbAlignment, pae))
228 Console.warn("Couln't import contact matrix from " + paeURL
229 + " (stored in " + pae.toString() + ")");
231 } catch (Exception pae_ex) {
232 Console.debug("Couldn't download PAE",pae_ex);
235 } catch (Exception ex) // Problem parsing PDB file
243 private boolean importPaeJSONAsContactMatrix(AlignmentI pdbAlignment,
244 File pae) throws Exception
246 FileInputStream pae_input = new FileInputStream(pae);
248 List<Object> pae_obj = (List<Object>) Platform
249 .parseJSON(pae_input);
254 ContactMatrixI matrix = new PAEContactMatrix(
255 pdbAlignment.getSequenceAt(0), (Map<String, Object>)pae_obj.get(0));
257 pdbAlignment.getSequenceAt(0).addAlignmentAnnotation(pdbAlignment.addContactList(matrix));
262 * general purpose structure importer - designed to yield alignment useful for
263 * transfer of annotation to associated sequences
265 * @param alphaFoldCif
274 public static AlignmentI importDownloadedStructureFromUrl(
275 String alphaFoldCif, File tmpFile, String id, String chain,
276 String dbSource, String dbVersion) throws Exception
278 String file = tmpFile.getAbsolutePath();
279 // todo get rid of Type and use FileFormatI instead?
280 FileFormatI fileFormat = FileFormat.MMCif;
281 AlignmentI pdbAlignment = new FormatAdapter().readFile(tmpFile,
282 DataSourceType.FILE, fileFormat);
283 if (pdbAlignment != null)
285 List<SequenceI> toremove = new ArrayList<SequenceI>();
286 for (SequenceI pdbcs : pdbAlignment.getSequences())
290 for (PDBEntry pid : pdbcs.getAllPDBEntries())
292 if (pid.getFile() == file)
294 chid = pid.getChainCode();
298 if (chain == null || (chid != null && (chid.equals(chain)
299 || chid.trim().equals(chain.trim())
300 || (chain.trim().length() == 0 && chid.equals("_")))))
302 // FIXME seems to result in 'PDB|1QIP|1qip|A' - 1QIP is redundant.
303 // TODO: suggest simplify naming to 1qip|A as default name defined
304 pdbcs.setName(id + SEPARATOR + pdbcs.getName());
305 // Might need to add more metadata to the PDBEntry object
308 * PDBEntry entry = new PDBEntry(); // Construct the PDBEntry
309 * entry.setId(id); if (entry.getProperty() == null)
310 * entry.setProperty(new Hashtable());
311 * entry.getProperty().put("chains", pdbchain.id + "=" +
312 * sq.getStart() + "-" + sq.getEnd());
313 * sq.getDatasetSequence().addPDBId(entry);
316 // We make a DBRefEtntry because we have obtained the PDB file from
319 // JBPNote - PDB DBRefEntry should also carry the chain and mapping
321 if (dbSource != null)
323 DBRefEntry dbentry = new DBRefEntry(dbSource,
325 dbVersion, (chid == null ? id : id + chid));
327 pdbcs.addDBRef(dbentry);
328 // update any feature groups
329 List<SequenceFeature> allsf = pdbcs.getFeatures()
331 List<SequenceFeature> newsf = new ArrayList<SequenceFeature>();
332 if (allsf != null && allsf.size() > 0)
334 for (SequenceFeature f : allsf)
336 if (file.equals(f.getFeatureGroup()))
338 f = new SequenceFeature(f, f.type, f.begin, f.end, id,
343 pdbcs.setSequenceFeatures(newsf);
349 // mark this sequence to be removed from the alignment
350 // - since it's not from the right chain
354 // now remove marked sequences
355 for (SequenceI pdbcs : toremove)
357 pdbAlignment.deleteSequence(pdbcs);
358 if (pdbcs.getAnnotation() != null)
360 for (AlignmentAnnotation aa : pdbcs.getAnnotation())
362 pdbAlignment.deleteAnnotation(aa);
373 * @see jalview.ws.DbSourceProxy#isValidReference(java.lang.String)
376 public boolean isValidReference(String accession)
378 Regex r = getAccessionValidator();
379 return r.search(accession.trim());
386 public String getTestQuery()
388 return "AF-O15552-F1";
392 public String getDbName()
394 return "ALPHAFOLD"; // getDbSource();
404 * Returns a descriptor for suitable feature display settings with
406 * <li>ResNums or insertions features visible</li>
407 * <li>insertions features coloured red</li>
408 * <li>ResNum features coloured by label</li>
409 * <li>Insertions displayed above (on top of) ResNums</li>
413 public FeatureSettingsModelI getFeatureColourScheme()
415 return new PDBFeatureSettings();