001/* 002 * BioJava development code 003 * 004 * This code may be freely distributed and modified under the 005 * terms of the GNU Lesser General Public Licence. This should 006 * be distributed with the code. If you do not have a copy, 007 * see: 008 * 009 * http://www.gnu.org/copyleft/lesser.html 010 * 011 * Copyright for this code is held jointly by the individual 012 * authors. These should be listed in @author doc comments. 013 * 014 * For more information on the BioJava project and its aims, 015 * or to join the biojava-l mailing list, visit the home page 016 * at: 017 * 018 * http://www.biojava.org/ 019 * 020 */ 021package org.biojava.nbio.structure; 022 023import java.io.IOException; 024import java.util.Collections; 025import java.util.List; 026 027import org.biojava.nbio.structure.align.util.AtomCache; 028import org.biojava.nbio.structure.io.MMCIFFileReader; 029import org.biojava.nbio.structure.io.PDBFileReader; 030 031/** 032 * A class that provides static access methods for easy lookup of protein structure related components 033 * 034 * @author Andreas Prlic 035 * 036 * @since 3.0.5 037 */ 038public class StructureIO { 039 040 //private static final Logger logger = LoggerFactory.getLogger(StructureIO.class); 041 042 private static AtomCache cache ; 043 044 045 /** 046 * Loads a structure based on a name. Supported naming conventions are: 047 * 048 * <pre> 049 Formal specification for how to specify the <i>name</i>: 050 051 name := pdbID 052 | pdbID '.' chainID 053 | pdbID '.' range 054 | scopID 055 | biol 056 | pdp 057 range := '('? range (',' range)? ')'? 058 | chainID 059 | chainID '_' resNum '-' resNum 060 pdbID := [0-9][a-zA-Z0-9]{3} 061 chainID := [a-zA-Z0-9] 062 scopID := 'd' pdbID [a-z_][0-9_] 063 biol := 'BIO:' pdbID [:]? [0-9]+ 064 pdp := 'PDP:' pdbID[A-Za-z0-9_]+ 065 resNum := [-+]?[0-9]+[A-Za-z]? 066 067 068 Example structures: 069 1TIM #whole structure - asym unit 070 4HHB.C #single chain 071 4GCR.A_1-83 #one domain, by residue number 072 3AA0.A,B #two chains treated as one structure 073 d2bq6a1 #scop domain 074 BIO:1fah #biological assembly nr 1 for 1fah 075 BIO:1fah:0 #asym unit for 1fah 076 BIO:1fah:1 #biological assembly nr 1 for 1fah 077 BIO:1fah:2 #biological assembly nr 2 for 1fah 078 079 * </pre> 080 * 081 * With the additional set of rules: 082 * 083 * <ul> 084 * <li>If only a PDB code is provided, the whole structure will be return including ligands, but the first model only (for NMR). 085 * <li>Chain IDs are case sensitive, PDB ids are not. To specify a particular chain write as: 4hhb.A or 4HHB.A </li> 086 * <li>To specify a SCOP domain write a scopId e.g. d2bq6a1. Some flexibility can be allowed in SCOP domain names, see {@link #setStrictSCOP(boolean)}</li> 087 * <li>URLs are accepted as well</li> 088 * </ul> 089 * 090 * @param name 091 * @return a Structure object, or null if name appears improperly formated (eg too short, etc) 092 * @throws IOException The PDB file cannot be cached due to IO errors 093 * @throws StructureException The name appeared valid but did not correspond to a structure. 094 * Also thrown by some submethods upon errors, eg for poorly formatted subranges. 095 */ 096 public static Structure getStructure(String name) throws IOException, StructureException{ 097 098 checkInitAtomCache(); 099 100 // delegate this functionality to AtomCache... 101 102 return cache.getStructure(name); 103 104 } 105 106 107 private static void checkInitAtomCache() { 108 if ( cache == null){ 109 cache = new AtomCache(); 110 } 111 112 } 113 114 public static void setAtomCache(AtomCache c){ 115 cache = c; 116 } 117 118 public static AtomCache getAtomCache() { 119 return cache; 120 } 121 122 123 /** 124 * Returns the first biological assembly that is available for the given PDB id. 125 * <p> 126 * The output Structure will be different depending on the multiModel parameter: 127 * <li> 128 * the symmetry-expanded chains are added as new models, one per transformId. All original models but 129 * the first one are discarded. 130 * </li> 131 * <li> 132 * as original with symmetry-expanded chains added with renamed chain ids and names (in the form 133 * originalAsymId_transformId and originalAuthId_transformId) 134 * </li> 135 * <p> 136 * For more documentation on quaternary structures see: 137 * {@link http://pdb101.rcsb.org/learn/guide-to-understanding-pdb-data/biological-assemblies} 138 * 139 * 140 * @param pdbId 141 * @param multiModel if true the output Structure will be a multi-model one with one transformId per model, 142 * if false the outputStructure will be as the original with added chains with renamed asymIds (in the form originalAsymId_transformId and originalAuthId_transformId). 143 * @return a Structure object or null if that assembly is not available 144 * @throws StructureException 145 * @throws IOException 146 */ 147 public static Structure getBiologicalAssembly(String pdbId, boolean multiModel) throws IOException, StructureException{ 148 149 checkInitAtomCache(); 150 151 pdbId = pdbId.toLowerCase(); 152 153 Structure s = cache.getBiologicalAssembly(pdbId, multiModel); 154 155 return s; 156 } 157 158 /** 159 * Returns the first biological assembly that is available for the given PDB id, 160 * using multiModel={@value AtomCache#DEFAULT_BIOASSEMBLY_STYLE} 161 * <p> 162 * For more documentation on quaternary structures see: 163 * {@link http://pdb101.rcsb.org/learn/guide-to-understanding-pdb-data/biological-assemblies} 164 * 165 * 166 * @param pdbId 167 * @return a Structure object or null if that assembly is not available 168 * @throws StructureException 169 * @throws IOException 170 */ 171 public static Structure getBiologicalAssembly(String pdbId) throws IOException, StructureException{ 172 return getBiologicalAssembly(pdbId, AtomCache.DEFAULT_BIOASSEMBLY_STYLE); 173 } 174 175 /** 176 * Returns the biological assembly for the given PDB id and bioassembly identifier. 177 * <p> 178 * The output Structure will be different depending on the multiModel parameter: 179 * <li> 180 * the symmetry-expanded chains are added as new models, one per transformId. All original models but 181 * the first one are discarded. 182 * </li> 183 * <li> 184 * as original with symmetry-expanded chains added with renamed chain ids and names (in the form 185 * originalAsymId_transformId and originalAuthId_transformId) 186 * </li> 187 * @param pdbId 188 * @param biolAssemblyNr - the ith biological assembly that is available for a PDB ID (we start counting at 1, 0 represents the asym unit). 189 * @param multiModel if true the output Structure will be a multi-model one with one transformId per model, 190 * if false the outputStructure will be as the original with added chains with renamed asymIds (in the form originalAsymId_transformId and originalAuthId_transformId). 191 * @return a Structure object or null if that assembly is not available 192 * @throws StructureException if there is no bioassembly available for given biolAssemblyNr or some other problems encountered while loading it 193 * @throws IOException 194 */ 195 public static Structure getBiologicalAssembly(String pdbId, int biolAssemblyNr, boolean multiModel) throws IOException, StructureException { 196 197 checkInitAtomCache(); 198 199 pdbId = pdbId.toLowerCase(); 200 201 Structure s = cache.getBiologicalAssembly(pdbId, biolAssemblyNr, multiModel); 202 203 return s; 204 } 205 206 /** 207 * Returns the biological assembly for the given PDB id and bioassembly identifier, 208 * using multiModel={@value AtomCache#DEFAULT_BIOASSEMBLY_STYLE} 209 * @param pdbId 210 * @param biolAssemblyNr - the ith biological assembly that is available for a PDB ID (we start counting at 1, 0 represents the asym unit). 211 * @return a Structure object or null if that assembly is not available 212 * @throws StructureException if there is no bioassembly available for given biolAssemblyNr or some other problems encountered while loading it 213 * @throws IOException 214 */ 215 public static Structure getBiologicalAssembly(String pdbId, int biolAssemblyNr) throws IOException, StructureException { 216 return getBiologicalAssembly(pdbId, biolAssemblyNr, AtomCache.DEFAULT_BIOASSEMBLY_STYLE); 217 } 218 219 220 /** 221 * Returns all biological assemblies for the given PDB id. 222 * <p> 223 * The output Structure will be different depending on the multiModel parameter: 224 * <li> 225 * the symmetry-expanded chains are added as new models, one per transformId. All original models but 226 * the first one are discarded. 227 * </li> 228 * <li> 229 * as original with symmetry-expanded chains added with renamed chain ids and names (in the form 230 * originalAsymId_transformId and originalAuthId_transformId) 231 * </li> 232 * If only one biological assembly is required use {@link #getBiologicalAssembly(String)} or {@link #getBiologicalAssembly(String, int)} instead. 233 * @param pdbId 234 * @param multiModel if true the output Structure will be a multi-model one with one transformId per model, 235 * if false the outputStructure will be as the original with added chains with renamed asymIds (in the form originalAsymId_transformId and originalAuthId_transformId). 236 * @return 237 * @throws IOException 238 * @throws StructureException 239 * @since 5.0 240 */ 241 public static List<Structure> getBiologicalAssemblies(String pdbId, boolean multiModel) throws IOException, StructureException { 242 243 checkInitAtomCache(); 244 245 pdbId = pdbId.toLowerCase(); 246 247 List<Structure> s = cache.getBiologicalAssemblies(pdbId, multiModel); 248 249 return s; 250 251 } 252 253 /** 254 * Returns all biological assemblies for the given PDB id, 255 * using multiModel={@value AtomCache#DEFAULT_BIOASSEMBLY_STYLE} 256 * <p> 257 * If only one biological assembly is required use {@link #getBiologicalAssembly(String)} or {@link #getBiologicalAssembly(String, int)} instead. 258 * @param pdbId 259 * @return 260 * @throws IOException 261 * @throws StructureException 262 * @since 5.0 263 */ 264 public static List<Structure> getBiologicalAssemblies(String pdbId) throws IOException, StructureException { 265 return getBiologicalAssemblies(pdbId, AtomCache.DEFAULT_BIOASSEMBLY_STYLE); 266 } 267 268 269 private static final String FILE_SEPARATOR = System.getProperty("file.separator"); 270 271 /** 272 * Utility method to set the location where PDB files can be found 273 * 274 * @param pathToPDBFiles 275 */ 276 public static void setPdbPath(String pathToPDBFiles){ 277 278 if ( ! pathToPDBFiles.endsWith(FILE_SEPARATOR)) 279 pathToPDBFiles += FILE_SEPARATOR; 280 } 281 282 283 public static enum StructureFiletype { 284 PDB( (new PDBFileReader()).getExtensions()), 285 CIF( new MMCIFFileReader().getExtensions()), 286 UNKNOWN(Collections.<String>emptyList()); 287 288 private List<String> extensions; 289 /** 290 * @param extensions List of supported extensions, including leading period 291 */ 292 private StructureFiletype(List<String> extensions) { 293 this.extensions = extensions; 294 } 295 /** 296 * @return a list of file extensions associated with this type 297 */ 298 public List<String> getExtensions() { 299 return extensions; 300 } 301 } 302 303 /** 304 * Attempts to guess the type of a structure file based on the extension 305 * @param filename 306 * @return 307 */ 308 public static StructureFiletype guessFiletype(String filename) { 309 String lower = filename.toLowerCase(); 310 for(StructureFiletype type : StructureFiletype.values()) { 311 for(String ext : type.getExtensions()) { 312 if(lower.endsWith(ext.toLowerCase())) { 313 return type; 314 } 315 } 316 } 317 return StructureFiletype.UNKNOWN; 318 } 319}