// looks for CO- SO- and PO- instances, neutralises the O
// returns the number of hits
int neutraliseCSPnegO(int structure) {
int query, matcher, matchIter, match, queryAtomIter, queryAtom; // Indigo objects that require freeing
query = indigoLoadSmartsFromString("[O-$(*[#6,#14,#15])]");
matcher = indigoSubstructureMatcher(structure, 0);
matchIter = indigoIterateMatches(matcher, query);
int numMatches = 0;
if (matchIter != -1) {
while (match = indigoNext(matchIter)) {
queryAtomIter = indigoIterateAtoms(query);
while (queryAtom = indigoNext(queryAtomIter))
{
int structureAtom = indigoMapAtom(match, queryAtom);
indigoSetCharge(structureAtom, 0);
indigoFree(queryAtom);
}
numMatches++;
indigoFree(queryAtomIter);
indigoFree(match);
}
}
indigoFree(matchIter);
indigoFree(matcher);
indigoFree(query);
return numMatches;
}
// looks for NH+ instances, neutralises the N
// returns the number of hits
int neutraliseNposH(int structure) {
int query, matcher, matchIter, match, queryAtomIter, queryAtom; // Indigo objects that require freeing
query = indigoLoadSmartsFromString("[#7+$(*[H])]"); // #7 means any nitrogen, aliphatic or aromatic
matcher = indigoSubstructureMatcher(structure, 0);
matchIter = indigoIterateMatches(matcher, query);
int numMatches = 0;
if (matchIter != -1) {
while (match = indigoNext(matchIter)) {
queryAtomIter = indigoIterateAtoms(query);
while (queryAtom = indigoNext(queryAtomIter))
{
int structureAtom = indigoMapAtom(match, queryAtom);
indigoSetCharge(structureAtom, 0);
indigoFree(queryAtom);
}
numMatches++;
indigoFree(queryAtomIter);
indigoFree(match);
}
}
indigoFree(matchIter);
indigoFree(matcher);
indigoFree(query);
return numMatches;
}
void _handleInputFile (const char *path, int structures)
{
if ((strlen(path) > 4 && strcmp(path + strlen(path) - 4, ".sdf") == 0) ||
(strlen(path) > 7 && strcmp(path + strlen(path) - 7, ".sdf.gz") == 0))
{
int item, iter = indigoIterateSDFile(path);
while ((item = indigoNext(iter)))
{
indigoArrayAdd(structures, item);
indigoFree(item);
}
indigoFree(iter);
}
else if ((strlen(path) > 4 && strcmp(path + strlen(path) - 4, ".rdf") == 0) ||
(strlen(path) > 7 && strcmp(path + strlen(path) - 7, ".rdf.gz") == 0))
{
int item, iter = indigoIterateRDFile(path);
while ((item = indigoNext(iter)))
{
indigoArrayAdd(structures, item);
indigoFree(item);
}
indigoFree(iter);
}
else if ((strlen(path) > 4 && strcmp(path + strlen(path) - 4, ".smi") == 0) ||
(strlen(path) > 7 && strcmp(path + strlen(path) - 7, ".smi.gz") == 0))
{
int item, iter = indigoIterateSmilesFile(path);
while ((item = indigoNext(iter)))
{
indigoArrayAdd(structures, item);
indigoFree(item);
}
indigoFree(iter);
}
else if ((strlen(path) > 4 && strcmp(path + strlen(path) - 4, ".cml") == 0))
{
int item, iter = indigoIterateCMLFile(path);
while ((item = indigoNext(iter)))
{
indigoArrayAdd(structures, item);
indigoFree(item);
}
indigoFree(iter);
}
else
{
int item = indigoLoadMoleculeFromFile(path);
indigoArrayAdd(structures, item);
indigoFree(item);
}
}
bool isOrganic(int structure) {
int atom, atomIter;
bool structureOrganic = true;
atomIter = indigoIterateAtoms(structure);
while(atom = indigoNext(atomIter)) {
bool atomOrganic = indigoAtomicNumber(atom) == 1 ||
indigoAtomicNumber(atom) == 6 ||
indigoAtomicNumber(atom) == 7 ||
indigoAtomicNumber(atom) == 8 ||
indigoAtomicNumber(atom) == 15 ||
indigoAtomicNumber(atom) == 16 ||
indigoAtomicNumber(atom) == 9 ||
indigoAtomicNumber(atom) == 17 ||
indigoAtomicNumber(atom) == 35 ||
indigoAtomicNumber(atom) == 53;
if(!atomOrganic) {
structureOrganic = false;
indigoFree(atom);
break;
}
indigoFree(atom);
}
indigoFree(atomIter);
return structureOrganic;
}
// returns the largest component within the structure (you need to free this returned object later)
// doesn't free structure
int pickLargestSubstructure(int structure) {
int componentIter, component, largestComponent; // Indigo objects that require freeing
componentIter = indigoIterateComponents(structure);
int maxAtoms = 0;
if (componentIter != -1) {
while (component = indigoNext(componentIter)) {
// if only one component
if (indigoIndex(component) == 0 && !indigoHasNext(componentIter))
{
indigoFree(componentIter);
return indigoClone(structure);
}
int currentComponent = indigoClone(component);
int numAtoms = indigoCountAtoms(currentComponent);
//Rprintf("Number of atoms: %d\n\n", numAtoms);
if (numAtoms>maxAtoms) {
maxAtoms = numAtoms;
largestComponent = indigoClone(currentComponent);
}
indigoFree(currentComponent);
indigoFree(component);
}
}
indigoFree(componentIter);
return largestComponent;
}
void resetIsotopes(int structure) {
int atom, atomIter;
atomIter = indigoIterateAtoms(structure);
while(atom = indigoNext(atomIter)) {
indigoResetIsotope(atom);
indigoFree(atom);
}
indigoFree(atomIter);
}
bool containsMoreThanX(int structure, int X, int atomicNumber) {
int count = 0;
int atom, atomIter;
atomIter = indigoIterateAtoms(structure);
while(atom = indigoNext(atomIter)) {
if(indigoAtomicNumber(atom)==atomicNumber) {
count++;
}
indigoFree(atom);
}
indigoFree(atomIter);
return count > X;
}
bool isAromatic(int structure) {
int bond, bondIter;
bool structureAromatic = false;
bondIter = indigoIterateBonds(structure);
while(bond = indigoNext(bondIter)) {
bool bondAromatic = (indigoBondOrder(bond) == 4);
if(bondAromatic) {
structureAromatic = true;
indigoFree(bond);
break;
}
indigoFree(bond);
}
indigoFree(bondIter);
return structureAromatic;
}
int _isMultipleCML (const char *filename, int *reaction)
{
int iter = indigoIterateCMLFile(filename);
*reaction = 0;
if (indigoHasNext(iter))
{
int item = indigoNext(iter);
if (strstr(indigoRawData(item), "<reaction") != NULL)
*reaction = 1;
if (indigoHasNext(iter))
{
indigoFree(item);
indigoFree(iter);
return 1;
}
indigoFree(item);
}
indigoFree(iter);
return 0;
}
int main (int argc, const char** argv)
{
int i;
int done_with_options = 0;
int approximate = 0;
int scaffold = 0;
int aromatic = 1;
const char *outfile_hl = 0;
const char *outfile_rg = 0;
const char *outfile_maxscaf = 0;
const char *outfile_allscafs = 0;
const char *outfile_scaf_r = 0;
int deco = 0;
int structures = 0;
indigoSetErrorHandler(onError, 0);
printf("R-Group deconvolution utility, powered by Indigo API version %s\n", indigoVersion());
structures = indigoCreateArray();
indigoSetOptionBool("treat-x-as-pseudoatom", 1);
indigoSetOptionBool("ignore-stereochemistry-errors", 1);
for (i = 1; i < argc; i++)
{
if (!done_with_options && argv[i][0] == '-')
{
if (strcmp(argv[i], "--") == 0)
done_with_options = 1;
else if (strcmp(argv[i], "-h") == 0 ||
strcmp(argv[i], "-?") == 0 ||
strcmp(argv[i], "/?") == 0 ||
strcmp(argv[i], "-help") == 0 ||
strcmp(argv[i], "--help") == 0)
{
_printHelpMessage();
return 0;
}
else if (strcmp(argv[i], "-a") == 0)
approximate = 1;
else if (strcmp(argv[i], "-l") == 0)
{
if (++i == argc)
{
fprintf(stderr, "expecting filename after -l\n");
return -1;
}
scaffold = indigoLoadMoleculeFromFile(argv[i]);
}
else if (strcmp(argv[i], "-o") == 0)
{
if (++i == argc)
{
fprintf(stderr, "expecting filename after -o\n");
return -1;
}
outfile_hl = argv[i];
}
else if (strcmp(argv[i], "-r") == 0)
{
if (++i == argc)
{
fprintf(stderr, "expecting filename after -r\n");
return -1;
}
outfile_rg = argv[i];
}
else if (strcmp(argv[i], "-s") == 0)
{
if (++i == argc)
{
fprintf(stderr, "expecting filename after -s\n");
return -1;
}
outfile_maxscaf = argv[i];
}
else if (strcmp(argv[i], "-sr") == 0)
{
if (++i == argc)
{
fprintf(stderr, "expecting filename after -sr\n");
return -1;
}
outfile_scaf_r = argv[i];
}
else if (strcmp(argv[i], "-S") == 0)
{
if (++i == argc)
{
fprintf(stderr, "expecting filename after -S\n");
return -1;
}
outfile_allscafs = argv[i];
}
else if (strcmp(argv[i], "-na") == 0)
aromatic = 0;
else
{
fprintf(stderr, "Unknown option: %s", argv[i]);
_printHelpMessage();
return -1;
}
}
else
{
char dirname[1024];
char errbuf[1024];
const char *filename = 0;
int k;
for (k = (int)strlen(argv[i]) - 1; k >= 0; k--)
if (argv[i][k] == '/' || argv[i][k] == '\\')
break;
if (k == -1)
strncpy(dirname, ".", sizeof(dirname));
else if (k == 0)
{
dirname[0] = argv[i][0];
dirname[1] = 0;
}
else if (k == strlen(argv[i]) - 1)
{
fprintf(stderr, "can not handle filenames ending with a slash\n");
return -1;
}
else if (k > sizeof(dirname) - 1)
{
fprintf(stderr, "filename too long\n");
return -1;
}
else
{
memcpy(dirname, argv[i], k);
dirname[k] = 0;
}
_replaceSlashes(dirname);
filename = argv[i] + k + 1;
{
OsDirIter dir_iter;
int rc = osDirSearch(dirname, filename, &dir_iter);
if (rc == OS_DIR_OK)
{
int count = 0;
while ((rc = osDirNext(&dir_iter)) == OS_DIR_OK)
{
_replaceSlashes(dir_iter.path);
_handleInputFile(dir_iter.path, structures);
count++;
}
if (rc != OS_DIR_END)
{
fprintf(stderr, "%s\n", osDirLastError(errbuf, sizeof(errbuf)));
return -1;
}
if (count == 0)
{
fprintf(stderr, "can not find %s in directory %s\n", filename, dirname);
return -1;
}
}
else
{
fprintf(stderr, "%s\n", osDirLastError(errbuf, sizeof(errbuf)));
return -1;
}
}
}
}
if (indigoCount(structures) < 1)
{
fprintf(stderr, "no input structures\n");
_printHelpMessage();
return -1;
}
printf("got %d input structures\n", indigoCount(structures));
indigoSetOptionBool("deconvolution-aromatization", aromatic);
if (scaffold == 0)
{
printf("calculating scaffold... ");
fflush(stdout);
if (approximate)
scaffold = indigoExtractCommonScaffold(structures, "approximate");
else
scaffold = indigoExtractCommonScaffold(structures, "exact");
printf("done\n");
fflush(stdout);
}
if (outfile_maxscaf != 0)
{
printf("saving the scaffold to %s\n", outfile_maxscaf);
indigoSaveMolfileToFile(scaffold, outfile_maxscaf);
}
if (outfile_allscafs != 0)
{
int output = indigoWriteFile(outfile_allscafs);
int allscafs = indigoAllScaffolds(scaffold);
int item, iter = indigoIterateArray(allscafs);
printf("saving all obtained scaffolds (%d total) to %s\n",
indigoCount(allscafs), outfile_allscafs);
while ((item = indigoNext(iter)))
{
indigoSdfAppend(output, item);
indigoFree(item);
}
indigoFree(iter);
indigoFree(output);
}
if (outfile_hl == 0 && outfile_rg == 0 && outfile_scaf_r == 0)
{
printf("none of -o, -r, -sr specified, nothing left to do\n");
return 0;
}
printf("decomposing the structures... ");
fflush(stdout);
deco = indigoDecomposeMolecules(scaffold, structures);
printf("done\n");
fflush(stdout);
if (outfile_scaf_r != 0)
{
int sr = indigoDecomposedMoleculeScaffold(deco);
indigoLayout(sr);
printf("saving the scaffold with R-sites to %s\n", outfile_scaf_r);
indigoSaveMolfileToFile(sr, outfile_scaf_r);
}
if (outfile_hl != 0)
{
int output = indigoWriteFile(outfile_hl);
int item, iter = indigoIterateDecomposedMolecules(deco);
printf("saving the highlighted structures to %s\n", outfile_hl);
while ((item = indigoNext(iter)))
{
indigoSdfAppend(output, indigoDecomposedMoleculeHighlighted(item));
indigoFree(item);
}
indigoFree(iter);
indigoFree(output);
}
if (outfile_rg != 0)
{
int output = indigoWriteFile(outfile_rg);
int item, iter = indigoIterateDecomposedMolecules(deco);
printf("saving the structures with R-groups to %s\n", outfile_rg);
while ((item = indigoNext(iter)))
{
indigoSdfAppend(output, indigoDecomposedMoleculeWithRGroups(item));
indigoFree(item);
}
indigoFree(iter);
indigoFree(output);
}
return 0;
};
int main (int argc, char *argv[])
{
Params p;
int obj = -1, reader = -1, writer = -1;
int i = 0;
char number[100];
char outfilename[4096];
const char *id;
p.width =
p.height =
p.bond =
p.mode = -1;
p.id =
p.string_to_load =
p.file_to_load = NULL;
p.hydro_set =
p.query_set =
p.smarts_set = 0;
p.aromatization = NONE;
p.comment_field = NULL;
p.comment = NULL;
p.comment_name = 0;
if (argc <= 2)
USAGE();
indigoSetErrorHandler(onError, 0);
indigoSetOption("ignore-stereochemistry-errors", "on");
if (parseParams(&p, argc, argv) < 0)
return -1;
p.out_ext = OEXT_OTHER;
if (strcmp(p.outfile_ext, "mol") == 0)
p.out_ext = OEXT_MOL;
else if (strcmp(p.outfile_ext, "sdf") == 0)
p.out_ext = OEXT_SDF;
else if (strcmp(p.outfile_ext, "rxn") == 0)
p.out_ext = OEXT_RXN;
else if (strcmp(p.outfile_ext, "rdf") == 0)
p.out_ext = OEXT_RDF;
else if (strcmp(p.outfile_ext, "cml") == 0)
p.out_ext = OEXT_CML;
// guess whether to layout or render by extension
p.action = ACTION_LAYOUT;
if (p.out_ext == OEXT_OTHER) {
indigoSetOption("render-output-format", p.outfile_ext);
p.action = ACTION_RENDER;
}
// read in the input
reader = (p.file_to_load != NULL) ? indigoReadFile(p.file_to_load) : indigoReadString(p.string_to_load);
if (p.mode == MODE_SINGLE_MOLECULE) {
if (p.id != NULL)
ERROR("on single input, setting '-id' is not allowed\n");
if (p.out_ext == OEXT_RXN)
ERROR("reaction output specified for molecule input\n");
if (p.smarts_set)
obj = indigoLoadSmarts(reader);
else if (p.query_set)
obj = indigoLoadQueryMolecule(reader);
else
obj = indigoLoadMolecule(reader);
_prepare(obj, p.aromatization);
if (p.action == ACTION_LAYOUT) {
indigoLayout(obj);
if (p.out_ext == OEXT_MOL)
indigoSaveMolfileToFile(obj, p.outfile);
else
indigoSaveCmlToFile(obj, p.outfile);
} else {
_setComment(obj, &p);
renderToFile(obj, p.outfile);
}
} else if (p.mode == MODE_SINGLE_REACTION) {
if (p.id != NULL)
ERROR("on single input, setting '-id' is not allowed\n");
if (p.out_ext == OEXT_MOL)
ERROR("molecule output specified for reaction input\n");
if (p.smarts_set)
obj = indigoLoadReactionSmarts(reader);
else if (p.query_set)
obj = indigoLoadQueryReaction(reader);
else
obj = indigoLoadReaction(reader);
_prepare(obj, p.aromatization);
if (p.action == ACTION_LAYOUT) {
indigoLayout(obj);
if (p.out_ext == OEXT_CML)
indigoSaveCmlToFile(obj, p.outfile);
else
indigoSaveRxnfileToFile(obj, p.outfile);
} else {
_setComment(obj, &p);
renderToFile(obj, p.outfile);
}
} else {
int item;
int have_percent_s = (strstr(p.outfile, "%s") != NULL);
if (p.mode == MODE_MULTILINE_SMILES)
obj = indigoIterateSmiles(reader);
else if (p.mode == MODE_SDF)
obj = indigoIterateSDF(reader);
else if (p.mode == MODE_MULTIPLE_CML)
obj = indigoIterateCML(reader);
else if (p.mode == MODE_RDF)
obj = indigoIterateRDF(reader);
else {
fprintf(stderr, "internal error: wrong branch\n");
return -1;
}
if ((p.out_ext == OEXT_MOL || p.out_ext == OEXT_RXN || p.out_ext == OEXT_OTHER) && !have_percent_s)
ERROR("on multiple output, output file name must have '%%s'\n");
if (p.out_ext == OEXT_SDF || p.out_ext == OEXT_RDF ||
(p.out_ext == OEXT_CML && !have_percent_s))
{
writer = indigoWriteFile(p.outfile);
if (p.out_ext == OEXT_RDF)
indigoRdfHeader(writer);
if (p.out_ext == OEXT_CML)
indigoCmlHeader(writer);
}
i = -1;
while ((item = indigoNext(obj))) {
int rc;
++i;
if (writer > 0)
printf("saving item #%d... ", i);
else
{
if (p.id) {
if (!indigoHasProperty(item, p.id)) {
fprintf(stderr, "item #%d does not have %s, skipping\n", i, p.id);
continue;
}
id = indigoGetProperty(item, p.id);
snprintf(outfilename, sizeof(outfilename), p.outfile, id);
} else {
snprintf(number, sizeof(number), "%d", i);
snprintf(outfilename, sizeof(outfilename), p.outfile, number);
}
printf("saving %s... ", outfilename);
}
indigoSetErrorHandler(0, 0);
if (_prepare(item, p.aromatization) < 0)
{
printf("%s\n", indigoGetLastError());
indigoSetErrorHandler(onError, 0);
continue;
}
if (p.action == ACTION_LAYOUT)
{
if (indigoLayout(item) < 0)
{
printf("%s\n", indigoGetLastError());
indigoSetErrorHandler(onError, 0);
continue;
}
}
if (writer > 0) {
if (p.out_ext == OEXT_SDF)
rc = indigoSdfAppend(writer, item);
else if (p.out_ext == OEXT_RDF)
rc = indigoRdfAppend(writer, item);
else
rc = indigoCmlAppend(writer, item);
} else {
if (p.action == ACTION_LAYOUT) {
if (p.out_ext == OEXT_MOL)
rc = indigoSaveMolfileToFile(item, outfilename);
else if (p.out_ext == OEXT_RXN)
rc = indigoSaveRxnfileToFile(item, outfilename);
else
ERROR("extension unexpected");
} else {
_setComment(item, &p);
rc = indigoRenderToFile(item, outfilename);
}
}
if (rc < 0)
{
printf("%s\n", indigoGetLastError());
indigoSetErrorHandler(onError, 0);
continue;
}
indigoFree(item);
indigoSetErrorHandler(onError, 0);
printf("\n");
}
if (writer > 0)
{
if (p.out_ext == OEXT_CML)
indigoCmlFooter(writer);
indigoFree(writer);
}
}
indigoFree(reader);
indigoFree(obj);
return 0;
}