def knearest_tanimoto_search_symmetric(arena,
k=3,
threshold=0.7,
batch_size=100):
"""Search for the `k`-nearest hits in the `arena` at least `threshold` similar to the fingerprints in the arena
The computation can take a long time. Python won't check check for
a ^C until the function finishes. This can be irritating. Instead,
process only `batch_size` rows at a time before checking for a ^C.
The hits in the `SearchResults` are ordered by decreasing similarity score.
Example::
arena = chemfp.load_fingerprints("queries.fps")
results = chemfp.search.knearest_tanimoto_search_symmetric(arena, k=3, threshold=0.8)
for (query_id, hits) in zip(arena.ids, results):
print query_id, "->", ", ".join(("%s %.2f" % hit) for hit in hits.get_ids_and_scores())
:param arena: the set of fingerprints
:type arena: a FingerprintArena
:param k: the number of nearest neighbors to find.
:type k: positive integer
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:param include_lower_triangle:
if False, compute only the upper triangle, otherwise use symmetry to compute the full matrix
:type include_lower_triangle: boolean
:param batch_size: the number of rows to process before checking for a ^C
:type batch_size: integer
:returns: a SearchResults instance
"""
N = len(arena)
if batch_size <= 0:
raise ValueError("batch_size must be positive")
results = SearchResults(N, arena.arena_ids)
if N:
# Break it up into batch_size groups in order to let Python's
# interrupt handler check for a ^C, which is otherwise
# suppressed until the function finishes.
for query_start in xrange(0, N, batch_size):
query_end = min(query_start + batch_size, N)
_chemfp.knearest_tanimoto_arena_symmetric(
k, threshold, arena.num_bits, arena.start_padding,
arena.end_padding, arena.storage_size, arena.arena,
query_start, query_end, 0, N, arena.popcount_indices, results)
_chemfp.knearest_results_finalize(results, 0, N)
return results
def knearest_tanimoto_search_symmetric(arena, k=3, threshold=0.7, batch_size=100):
"""Search for the `k`-nearest hits in the `arena` at least `threshold` similar to the fingerprints in the arena
The computation can take a long time. Python won't check check for
a ^C until the function finishes. This can be irritating. Instead,
process only `batch_size` rows at a time before checking for a ^C.
The hits in the `SearchResults` are ordered by decreasing similarity score.
Example::
arena = chemfp.load_fingerprints("queries.fps")
results = chemfp.search.knearest_tanimoto_search_symmetric(arena, k=3, threshold=0.8)
for (query_id, hits) in zip(arena.ids, results):
print query_id, "->", ", ".join(("%s %.2f" % hit) for hit in hits.get_ids_and_scores())
:param arena: the set of fingerprints
:type arena: a FingerprintArena
:param k: the number of nearest neighbors to find.
:type k: positive integer
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:param include_lower_triangle:
if False, compute only the upper triangle, otherwise use symmetry to compute the full matrix
:type include_lower_triangle: boolean
:param batch_size: the number of rows to process before checking for a ^C
:type batch_size: integer
:returns: a SearchResults instance
"""
N = len(arena)
if batch_size <= 0:
raise ValueError("batch_size must be positive")
results = SearchResults(N, arena.arena_ids)
if N:
# Break it up into batch_size groups in order to let Python's
# interrupt handler check for a ^C, which is otherwise
# suppressed until the function finishes.
for query_start in xrange(0, N, batch_size):
query_end = min(query_start + batch_size, N)
_chemfp.knearest_tanimoto_arena_symmetric(
k, threshold, arena.num_bits,
arena.start_padding, arena.end_padding, arena.storage_size, arena.arena,
query_start, query_end, 0, N,
arena.popcount_indices,
results)
_chemfp.knearest_results_finalize(results, 0, N)
return results
def knearest_tanimoto_search_symmetric(arena, k, threshold):
N = len(arena)
results = SearchResults(N, arena.ids)
_chemfp.knearest_tanimoto_arena_symmetric(k, threshold, arena.num_bits,
arena.start_padding,
arena.end_padding,
arena.storage_size, arena.arena,
0, N, 0, N,
arena.popcount_indices, results)
_chemfp.knearest_results_finalize(results, 0, N)
return results
def knearest_tanimoto_search(query_arena, target_arena, k, threshold):
require_matching_sizes(query_arena, target_arena)
num_queries = len(query_arena)
results = SearchResults(num_queries, target_arena.ids)
_chemfp.knearest_tanimoto_arena(
k, threshold, target_arena.num_bits, query_arena.start_padding,
query_arena.end_padding, query_arena.storage_size, query_arena.arena,
query_arena.start, query_arena.end, target_arena.start_padding,
target_arena.end_padding, target_arena.storage_size,
target_arena.arena, target_arena.start, target_arena.end,
target_arena.popcount_indices, results, 0)
_chemfp.knearest_results_finalize(results, 0, num_queries)
return results
def knearest_tanimoto_search_fp(query_fp, target_arena, k, threshold):
require_matching_fp_size(query_fp, target_arena)
query_start_padding, query_end_padding, query_fp = _chemfp.align_fingerprint(
query_fp, target_arena.alignment, target_arena.storage_size)
if k < 0:
raise ValueError("k must be non-negative")
results = SearchResults(1)
_chemfp.knearest_tanimoto_arena(
k, threshold, target_arena.num_bits, query_start_padding,
query_end_padding, target_arena.storage_size, query_fp, 0, 1,
target_arena.start_padding, target_arena.end_padding,
target_arena.storage_size, target_arena.arena, target_arena.start,
target_arena.end, target_arena.popcount_indices, results, 0)
_chemfp.knearest_results_finalize(results, 0, 1)
return results[0]
def knearest_tanimoto_search_arena(query_arena,
target_arena,
k=3,
threshold=0.7):
"""Search for the `k` nearest hits in the `target_arena` at least `threshold` similar to the fingerprints in `query_arena`
The hits in the `SearchResults` are ordered by decreasing similarity score.
Example::
queries = chemfp.load_fingerprints("queries.fps")
targets = chemfp.load_fingerprints("targets.fps")
results = chemfp.search.knearest_tanimoto_search_arena(queries, targets, k=3, threshold=0.5)
for query_id, query_hits in zip(queries.ids, results):
if len(query_hits) >= 2:
print query_id, "->", ", ".join(query_hits.get_ids())
:param query_arena: The query fingerprints.
:type query_arena: a FingerprintArena
:param target_arena: The target fingerprints.
:type target_arena: a FingerprintArena
:param k: the number of nearest neighbors to find.
:type k: positive integer
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:returns: a SearchResults instance
"""
_require_matching_sizes(query_arena, target_arena)
num_queries = len(query_arena)
results = SearchResults(num_queries, target_arena.arena_ids)
_chemfp.knearest_tanimoto_arena(
k, threshold, target_arena.num_bits, query_arena.start_padding,
query_arena.end_padding, query_arena.storage_size, query_arena.arena,
query_arena.start, query_arena.end, target_arena.start_padding,
target_arena.end_padding, target_arena.storage_size,
target_arena.arena, target_arena.start, target_arena.end,
target_arena.popcount_indices, results, 0)
_chemfp.knearest_results_finalize(results, 0, num_queries)
return results
def knearest_tanimoto_search_arena(query_arena, target_arena, k=3, threshold=0.7):
"""Search for the `k` nearest hits in the `target_arena` at least `threshold` similar to the fingerprints in `query_arena`
The hits in the `SearchResults` are ordered by decreasing similarity score.
Example::
queries = chemfp.load_fingerprints("queries.fps")
targets = chemfp.load_fingerprints("targets.fps")
results = chemfp.search.knearest_tanimoto_search_arena(queries, targets, k=3, threshold=0.5)
for query_id, query_hits in zip(queries.ids, results):
if len(query_hits) >= 2:
print query_id, "->", ", ".join(query_hits.get_ids())
:param query_arena: The query fingerprints.
:type query_arena: a FingerprintArena
:param target_arena: The target fingerprints.
:type target_arena: a FingerprintArena
:param k: the number of nearest neighbors to find.
:type k: positive integer
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:returns: a SearchResults instance
"""
_require_matching_sizes(query_arena, target_arena)
num_queries = len(query_arena)
results = SearchResults(num_queries, target_arena.arena_ids)
_chemfp.knearest_tanimoto_arena(
k, threshold, target_arena.num_bits,
query_arena.start_padding, query_arena.end_padding,
query_arena.storage_size, query_arena.arena, query_arena.start, query_arena.end,
target_arena.start_padding, target_arena.end_padding,
target_arena.storage_size, target_arena.arena, target_arena.start, target_arena.end,
target_arena.popcount_indices,
results, 0)
_chemfp.knearest_results_finalize(results, 0, num_queries)
return results
def knearest_tanimoto_search_fp(query_fp, target_arena, k=3, threshold=0.7):
"""Search for `k`-nearest hits in `target_arena` which are at least `threshold` similar to `query_fp`
The hits in the `SearchResults` are ordered by decreasing similarity score.
Example::
query_id, query_fp = chemfp.load_fingerprints("queries.fps")[0]
targets = chemfp.load_fingerprints("targets.fps")
print list(chemfp.search.knearest_tanimoto_search_fp(query_fp, targets, k=3, threshold=0.0))
:param query_fp: the query fingerprint
:type query_fp: a byte string
:param target_arena: the target arena
:type target_fp: a FingerprintArena
:param k: the number of nearest neighbors to find.
:type k: positive integer
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:returns: a SearchResult
"""
_require_matching_fp_size(query_fp, target_arena)
query_start_padding, query_end_padding, query_fp = _chemfp.align_fingerprint(
query_fp, target_arena.alignment, target_arena.storage_size)
if k < 0:
raise ValueError("k must be non-negative")
results = SearchResults(1, target_arena.arena_ids)
_chemfp.knearest_tanimoto_arena(
k, threshold, target_arena.num_bits,
query_start_padding, query_end_padding, target_arena.storage_size, query_fp, 0, 1,
target_arena.start_padding, target_arena.end_padding,
target_arena.storage_size, target_arena.arena, target_arena.start, target_arena.end,
target_arena.popcount_indices,
results, 0)
_chemfp.knearest_results_finalize(results, 0, 1)
return results[0]
def knearest_tanimoto_search_fp(query_fp, target_arena, k=3, threshold=0.7):
"""Search for `k`-nearest hits in `target_arena` which are at least `threshold` similar to `query_fp`
The hits in the `SearchResults` are ordered by decreasing similarity score.
Example::
query_id, query_fp = chemfp.load_fingerprints("queries.fps")[0]
targets = chemfp.load_fingerprints("targets.fps")
print list(chemfp.search.knearest_tanimoto_search_fp(query_fp, targets, k=3, threshold=0.0))
:param query_fp: the query fingerprint
:type query_fp: a byte string
:param target_arena: the target arena
:type target_fp: a FingerprintArena
:param k: the number of nearest neighbors to find.
:type k: positive integer
:param threshold: The minimum score threshold.
:type threshold: float between 0.0 and 1.0, inclusive
:returns: a SearchResult
"""
_require_matching_fp_size(query_fp, target_arena)
query_start_padding, query_end_padding, query_fp = _chemfp.align_fingerprint(
query_fp, target_arena.alignment, target_arena.storage_size)
if k < 0:
raise ValueError("k must be non-negative")
results = SearchResults(1, target_arena.arena_ids)
_chemfp.knearest_tanimoto_arena(
k, threshold, target_arena.num_bits, query_start_padding,
query_end_padding, target_arena.storage_size, query_fp, 0, 1,
target_arena.start_padding, target_arena.end_padding,
target_arena.storage_size, target_arena.arena, target_arena.start,
target_arena.end, target_arena.popcount_indices, results, 0)
_chemfp.knearest_results_finalize(results, 0, 1)
return results[0]