BiocNeighbors 1.22.0
The BiocNeighbors package implements a few algorithms for exact nearest neighbor searching:
Both KMKNN and VP-trees involve a component of randomness during index construction, though the k-nearest neighbors result is fully deterministic1 Except in the presence of ties, see ?"BiocNeighbors-ties"
for details..
The most obvious application is to perform a k-nearest neighbors search. We’ll mock up an example here with a hypercube of points, for which we want to identify the 10 nearest neighbors for each point.
nobs <- 10000
ndim <- 20
data <- matrix(runif(nobs*ndim), ncol=ndim)
The findKNN()
method expects a numeric matrix as input with data points as the rows and variables/dimensions as the columns.
We indicate that we want to use the KMKNN algorithm by setting BNPARAM=KmknnParam()
(which is also the default, so this is not strictly necessary here).
We could use a VP tree instead by setting BNPARAM=VptreeParam()
.
fout <- findKNN(data, k=10, BNPARAM=KmknnParam())
head(fout$index)
## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
## [1,] 1989 4622 8618 2158 7879 2133 9013 9508 4499 5229
## [2,] 4794 2009 6091 4188 7004 7215 9857 2796 3660 9161
## [3,] 7830 3666 2945 4592 7275 3335 1716 1889 5439 9718
## [4,] 8439 5358 7958 4857 6985 6399 6370 2443 195 830
## [5,] 3889 1124 5754 6799 7697 5520 9800 9926 2738 9240
## [6,] 5991 6412 5266 775 3885 6310 3578 4606 9008 3014
head(fout$distance)
## [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## [1,] 1.0097842 1.0227242 1.0275769 1.0369262 1.0564901 1.0822241 1.0903339
## [2,] 0.8701481 0.9319641 0.9348332 0.9844711 1.0252510 1.0303986 1.0325786
## [3,] 0.7910433 0.8477791 0.8976068 0.9115301 0.9490122 0.9499254 0.9516261
## [4,] 0.9264327 0.9326880 0.9717430 0.9931083 1.0444846 1.0664840 1.0695115
## [5,] 0.8315563 0.8344440 0.8452555 0.8651816 0.8747433 0.9340461 0.9385280
## [6,] 0.7639928 0.8173307 0.8219567 0.8996072 0.9188609 0.9191398 0.9250174
## [,8] [,9] [,10]
## [1,] 1.0947257 1.1138215 1.1281925
## [2,] 1.0334664 1.0475224 1.0774493
## [3,] 0.9990428 1.0041717 1.0050663
## [4,] 1.0747146 1.0776285 1.0778396
## [5,] 0.9424983 0.9426294 0.9727308
## [6,] 0.9263940 0.9375396 0.9443515
Each row of the index
matrix corresponds to a point in data
and contains the row indices in data
that are its nearest neighbors.
For example, the 3rd point in data
has the following nearest neighbors:
fout$index[3,]
## [1] 7830 3666 2945 4592 7275 3335 1716 1889 5439 9718
… with the following distances to those neighbors:
fout$distance[3,]
## [1] 0.7910433 0.8477791 0.8976068 0.9115301 0.9490122 0.9499254 0.9516261
## [8] 0.9990428 1.0041717 1.0050663
Note that the reported neighbors are sorted by distance.
Another application is to identify the k-nearest neighbors in one dataset based on query points in another dataset. Again, we mock up a small data set:
nquery <- 1000
ndim <- 20
query <- matrix(runif(nquery*ndim), ncol=ndim)
We then use the queryKNN()
function to identify the 5 nearest neighbors in data
for each point in query
.
qout <- queryKNN(data, query, k=5, BNPARAM=KmknnParam())
head(qout$index)
## [,1] [,2] [,3] [,4] [,5]
## [1,] 9010 9330 1883 9571 8936
## [2,] 1242 1502 4466 3303 6279
## [3,] 5867 6335 2119 3411 7181
## [4,] 4554 1357 3309 6206 1565
## [5,] 6028 1151 2490 821 6469
## [6,] 5165 7568 8421 1632 6761
head(qout$distance)
## [,1] [,2] [,3] [,4] [,5]
## [1,] 0.8425451 0.8884211 0.9081493 0.9326827 0.9341941
## [2,] 0.9518900 0.9574701 0.9744274 0.9783393 0.9979423
## [3,] 0.8600595 0.9278923 0.9574250 0.9704132 0.9881491
## [4,] 0.9573079 0.9713062 0.9997422 1.0025234 1.0665254
## [5,] 0.8129505 0.8139442 0.8182734 0.8732380 0.8733563
## [6,] 0.9073574 0.9250673 0.9812302 0.9813518 1.0058444
Each row of the index
matrix contains the row indices in data
that are the nearest neighbors of a point in query
.
For example, the 3rd point in query
has the following nearest neighbors in data
:
qout$index[3,]
## [1] 5867 6335 2119 3411 7181
… with the following distances to those neighbors:
qout$distance[3,]
## [1] 0.8600595 0.9278923 0.9574250 0.9704132 0.9881491
Again, the reported neighbors are sorted by distance.
Users can perform the search for a subset of query points using the subset=
argument.
This yields the same result as but is more efficient than performing the search for all points and subsetting the output.
findKNN(data, k=5, subset=3:5)
## $index
## [,1] [,2] [,3] [,4] [,5]
## [1,] 7830 3666 2945 4592 7275
## [2,] 8439 5358 7958 4857 6985
## [3,] 3889 1124 5754 6799 7697
##
## $distance
## [,1] [,2] [,3] [,4] [,5]
## [1,] 0.7910433 0.8477791 0.8976068 0.9115301 0.9490122
## [2,] 0.9264327 0.9326880 0.9717430 0.9931083 1.0444846
## [3,] 0.8315563 0.8344440 0.8452555 0.8651816 0.8747433
If only the indices are of interest, users can set get.distance=FALSE
to avoid returning the matrix of distances.
This will save some time and memory.
names(findKNN(data, k=2, get.distance=FALSE))
## [1] "index"
It is also simple to speed up functions by parallelizing the calculations with the BiocParallel framework.
library(BiocParallel)
out <- findKNN(data, k=10, BPPARAM=MulticoreParam(3))
For multiple queries to a constant data
, the pre-clustering can be performed in a separate step with buildIndex()
.
The result can then be passed to multiple calls, avoiding the overhead of repeated clustering2 The algorithm type is automatically determined when BNINDEX
is specified, so there is no need to also specify BNPARAM
in the later functions..
pre <- buildIndex(data, BNPARAM=KmknnParam())
out1 <- findKNN(BNINDEX=pre, k=5)
out2 <- queryKNN(BNINDEX=pre, query=query, k=2)
The default setting is to search on the Euclidean distance.
Alternatively, we can use the Manhattan distance by setting distance="Manhattan"
in the BiocNeighborParam
object.
out.m <- findKNN(data, k=5, BNPARAM=KmknnParam(distance="Manhattan"))
Advanced users may also be interested in the raw.index=
argument, which returns indices directly to the precomputed object rather than to data
.
This may be useful inside package functions where it may be more convenient to work on a common precomputed object.
sessionInfo()
## R version 4.4.0 beta (2024-04-15 r86425 ucrt)
## Platform: x86_64-w64-mingw32/x64
## Running under: Windows Server 2022 x64 (build 20348)
##
## Matrix products: default
##
##
## locale:
## [1] LC_COLLATE=C
## [2] LC_CTYPE=English_United States.utf8
## [3] LC_MONETARY=English_United States.utf8
## [4] LC_NUMERIC=C
## [5] LC_TIME=English_United States.utf8
##
## time zone: America/New_York
## tzcode source: internal
##
## attached base packages:
## [1] stats graphics grDevices utils datasets methods base
##
## other attached packages:
## [1] BiocParallel_1.38.0 BiocNeighbors_1.22.0 knitr_1.46
## [4] BiocStyle_2.32.0
##
## loaded via a namespace (and not attached):
## [1] cli_3.6.2 rlang_1.1.3 xfun_0.43
## [4] jsonlite_1.8.8 S4Vectors_0.42.0 htmltools_0.5.8.1
## [7] stats4_4.4.0 sass_0.4.9 rmarkdown_2.26
## [10] grid_4.4.0 evaluate_0.23 jquerylib_0.1.4
## [13] fastmap_1.1.1 yaml_2.3.8 lifecycle_1.0.4
## [16] bookdown_0.39 BiocManager_1.30.22 compiler_4.4.0
## [19] codetools_0.2-20 Rcpp_1.0.12 lattice_0.22-6
## [22] digest_0.6.35 R6_2.5.1 parallel_4.4.0
## [25] bslib_0.7.0 Matrix_1.7-0 tools_4.4.0
## [28] BiocGenerics_0.50.0 cachem_1.0.8
Wang, X. 2012. “A Fast Exact k-Nearest Neighbors Algorithm for High Dimensional Search Using k-Means Clustering and Triangle Inequality.” Proc Int Jt Conf Neural Netw 43 (6): 2351–8.
Yianilos, P. N. 1993. “Data Structures and Algorithms for Nearest Neighbor Search in General Metric Spaces.” In SODA, 93:311–21. 194.