We read in input.scone.csv, which is our file modified (and renamed) from the get.marker.names() function. The K-nearest neighbor generation is derived from the Fast Nearest Neighbors (FNN) R package, within our function Fnn(), which takes as input the “input markers” to be used, along with the concatenated data previously generated, and the desired k. We advise the default selection to the total number of cells in the dataset divided by 100, as has been optimized on existing mass cytometry datasets. The output of this function is a matrix of each cell and the identity of its k-nearest neighbors, in terms of its row number in the dataset used here as input.
library(Sconify)
# Markers from the user-generated excel file
marker.file <- system.file('extdata', 'markers.csv', package = "Sconify")
markers <- ParseMarkers(marker.file)
# How to convert your excel sheet into vector of static and functional markers
markers## $input
## [1] "CD3(Cd110)Di" "CD3(Cd111)Di"
## [3] "CD3(Cd112)Di" "CD235-61-7-15(In113)Di"
## [5] "CD3(Cd114)Di" "CD45(In115)Di"
## [7] "CD19(Nd142)Di" "CD22(Nd143)Di"
## [9] "IgD(Nd145)Di" "CD79b(Nd146)Di"
## [11] "CD20(Sm147)Di" "CD34(Nd148)Di"
## [13] "CD179a(Sm149)Di" "CD72(Eu151)Di"
## [15] "IgM(Eu153)Di" "Kappa(Sm154)Di"
## [17] "CD10(Gd156)Di" "Lambda(Gd157)Di"
## [19] "CD24(Dy161)Di" "TdT(Dy163)Di"
## [21] "Rag1(Dy164)Di" "PreBCR(Ho165)Di"
## [23] "CD43(Er167)Di" "CD38(Er168)Di"
## [25] "CD40(Er170)Di" "CD33(Yb173)Di"
## [27] "HLA-DR(Yb174)Di"
##
## $functional
## [1] "pCrkL(Lu175)Di" "pCREB(Yb176)Di" "pBTK(Yb171)Di"
## [4] "pS6(Yb172)Di" "cPARP(La139)Di" "pPLCg2(Pr141)Di"
## [7] "pSrc(Nd144)Di" "Ki67(Sm152)Di" "pErk12(Gd155)Di"
## [10] "pSTAT3(Gd158)Di" "pAKT(Tb159)Di" "pBLNK(Gd160)Di"
## [13] "pP38(Tm169)Di" "pSTAT5(Nd150)Di" "pSyk(Dy162)Di"
## [16] "tIkBa(Er166)Di"# Get the particular markers to be used as knn and knn statistics input
input.markers <- markers[[1]]
funct.markers <- markers[[2]]
# Selection of the k. See "Finding Ideal K" vignette
k <- 30
# The built-in scone functions
wand.nn <- Fnn(cell.df = wand.combined, input.markers = input.markers, k = k)
# Cell identity is in rows, k-nearest neighbors are columns
# List of 2 includes the cell identity of each nn,
# and the euclidean distance between
# itself and the cell of interest
# Indices
str(wand.nn[[1]])## int [1:1000, 1:30] 660 570 342 898 835 943 61 673 771 362 ...wand.nn[[1]][1:20, 1:10]## [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
## [1,] 660 455 330 279 122 982 599 102 670 373
## [2,] 570 732 639 609 634 328 946 272 539 978
## [3,] 342 995 296 205 831 26 439 593 51 785
## [4,] 898 825 614 879 569 32 157 537 973 317
## [5,] 835 121 348 718 156 216 687 271 648 604
## [6,] 943 500 691 512 719 879 101 902 743 16
## [7,] 61 177 903 938 904 443 680 976 67 932
## [8,] 673 40 574 271 455 114 156 955 25 102
## [9,] 771 236 889 112 291 593 524 855 795 941
## [10,] 362 649 625 858 100 295 152 717 710 937
## [11,] 251 622 544 872 789 701 276 857 884 184
## [12,] 945 393 535 815 258 146 523 663 18 621
## [13,] 488 871 537 815 817 661 847 145 317 29
## [14,] 824 253 693 264 204 849 680 766 299 816
## [15,] 702 291 35 634 795 319 316 771 901 51
## [16,] 185 621 81 6 289 309 412 968 719 728
## [17,] 698 594 278 685 343 965 861 683 338 323
## [18,] 927 815 617 745 902 535 873 871 154 13
## [19,] 510 175 257 157 950 43 552 635 165 536
## [20,] 622 749 500 610 313 743 876 27 736 333# Distance
str(wand.nn[[2]])## num [1:1000, 1:30] 3.16 3.7 3.42 2.78 3.04 ...wand.nn[[2]][1:20, 1:10]## [,1] [,2] [,3] [,4] [,5] [,6] [,7]
## [1,] 3.163055 3.674974 3.678692 3.994928 4.009643 4.103495 4.125000
## [2,] 3.699966 3.845257 4.089461 4.091291 4.095246 4.108874 4.369179
## [3,] 3.419116 3.626014 4.277316 4.286301 4.339516 4.430295 4.484132
## [4,] 2.781732 2.935804 3.051874 3.129580 3.131815 3.139441 3.237568
## [5,] 3.037948 3.302855 3.344558 3.382285 3.419764 3.453594 3.460411
## [6,] 2.567725 2.732229 2.764853 2.769046 2.769133 2.776092 2.826313
## [7,] 3.442041 3.701995 3.819065 3.840330 3.879517 3.939425 4.036865
## [8,] 2.485762 3.154017 3.372972 3.429964 3.506096 3.527210 3.660883
## [9,] 3.896089 4.161308 4.428155 4.444999 4.664446 4.706743 4.726543
## [10,] 4.108895 4.257397 4.360755 4.365505 4.437687 4.477520 4.479676
## [11,] 4.371005 4.375177 4.386573 4.437174 4.471504 4.510921 4.542604
## [12,] 3.044497 3.169950 3.223405 3.246766 3.289788 3.454380 3.476104
## [13,] 2.289549 2.710660 2.767685 2.817048 2.916928 2.946039 2.967586
## [14,] 3.556735 3.630682 3.632301 3.712904 3.761041 3.784941 3.871217
## [15,] 3.708601 3.884775 3.960447 4.028409 4.073326 4.124767 4.156030
## [16,] 2.850939 2.880144 2.919602 2.931802 2.976749 2.977181 2.977382
## [17,] 3.906039 4.012393 4.072270 4.079715 4.573888 4.690086 4.867458
## [18,] 2.394399 2.778345 2.788882 2.839030 2.921404 2.997739 3.024625
## [19,] 2.739680 2.799856 2.948125 3.093891 3.114458 3.164888 3.190506
## [20,] 3.527260 3.536258 3.538865 3.552419 3.559358 3.615154 3.740749
## [,8] [,9] [,10]
## [1,] 4.149065 4.161751 4.203414
## [2,] 4.382126 4.465774 4.502410
## [3,] 4.564862 4.712444 4.769048
## [4,] 3.261503 3.294610 3.320959
## [5,] 3.573983 3.624240 3.653846
## [6,] 2.873548 2.892904 2.931802
## [7,] 4.076319 4.077486 4.215599
## [8,] 3.669237 3.707808 3.742693
## [9,] 4.804098 4.834206 4.856048
## [10,] 4.490707 4.491358 4.515552
## [11,] 4.587073 4.636025 4.638315
## [12,] 3.569579 3.627767 3.635642
## [13,] 3.100222 3.107892 3.144814
## [14,] 3.882875 3.926375 3.960578
## [15,] 4.221158 4.396115 4.490877
## [16,] 3.087312 3.092471 3.129033
## [17,] 4.877204 5.018824 5.072023
## [18,] 3.142601 3.287488 3.322590
## [19,] 3.239989 3.242177 3.256460
## [20,] 3.816203 3.823781 3.869796This function iterates through each KNN, and performs a series of calculations. The first is fold change values for each maker per KNN, where the user chooses whether this will be based on medians or means. The second is a statistical test, where the user chooses t test or Mann-Whitney U test. I prefer the latter, because it does not assume any properties of the distributions. Of note, the p values are adjusted for false discovery rate, and therefore are called q values in the output of this function. The user also inputs a threshold parameter (default 0.05), where the fold change values will only be shown if the corresponding statistical test returns a q value below said threshold. Finally, the “multiple.donor.compare” option, if set to TRUE will perform a t test based on the mean per-marker values of each donor. This is to allow the user to make comparisons across replicates or multiple donors if that is relevant to the user’s biological questions. This function returns a matrix of cells by computed values (change and statistical test results, labeled either marker.change or marker.qvalue). This matrix is intermediate, as it gets concatenated with the original input matrix in the post-processing step (see the relevant vignette). We show the code and the output below. See the post-processing vignette, where we show how this gets combined with the input data, and additional analysis is performed.
wand.scone <- SconeValues(nn.matrix = wand.nn,
cell.data = wand.combined,
scone.markers = funct.markers,
unstim = "basal")
wand.scone## # A tibble: 1,000 x 34
## `pCrkL(Lu175)Di… `pCREB(Yb176)Di… `pBTK(Yb171)Di.… `pS6(Yb172)Di.I…
## <dbl> <dbl> <dbl> <dbl>
## 1 0.964 0.945 0.877 0.947
## 2 0.998 1 0.490 1
## 3 0.998 0.945 0.397 0.980
## 4 0.998 0.972 0.889 0.986
## 5 0.998 0.945 0.864 1
## 6 0.998 0.945 0.940 0.947
## 7 0.998 1 0.541 0.980
## 8 0.998 0.945 0.919 0.947
## 9 0.998 0.945 0.998 0.947
## 10 0.998 0.931 0.515 0.982
## # … with 990 more rows, and 30 more variables:
## # `cPARP(La139)Di.IL7.qvalue` <dbl>, `pPLCg2(Pr141)Di.IL7.qvalue` <dbl>,
## # `pSrc(Nd144)Di.IL7.qvalue` <dbl>, `Ki67(Sm152)Di.IL7.qvalue` <dbl>,
## # `pErk12(Gd155)Di.IL7.qvalue` <dbl>,
## # `pSTAT3(Gd158)Di.IL7.qvalue` <dbl>, `pAKT(Tb159)Di.IL7.qvalue` <dbl>,
## # `pBLNK(Gd160)Di.IL7.qvalue` <dbl>, `pP38(Tm169)Di.IL7.qvalue` <dbl>,
## # `pSTAT5(Nd150)Di.IL7.qvalue` <dbl>, `pSyk(Dy162)Di.IL7.qvalue` <dbl>,
## # `tIkBa(Er166)Di.IL7.qvalue` <dbl>, `pCrkL(Lu175)Di.IL7.change` <dbl>,
## # `pCREB(Yb176)Di.IL7.change` <dbl>, `pBTK(Yb171)Di.IL7.change` <dbl>,
## # `pS6(Yb172)Di.IL7.change` <dbl>, `cPARP(La139)Di.IL7.change` <dbl>,
## # `pPLCg2(Pr141)Di.IL7.change` <dbl>, `pSrc(Nd144)Di.IL7.change` <dbl>,
## # `Ki67(Sm152)Di.IL7.change` <dbl>, `pErk12(Gd155)Di.IL7.change` <dbl>,
## # `pSTAT3(Gd158)Di.IL7.change` <dbl>, `pAKT(Tb159)Di.IL7.change` <dbl>,
## # `pBLNK(Gd160)Di.IL7.change` <dbl>, `pP38(Tm169)Di.IL7.change` <dbl>,
## # `pSTAT5(Nd150)Di.IL7.change` <dbl>, `pSyk(Dy162)Di.IL7.change` <dbl>,
## # `tIkBa(Er166)Di.IL7.change` <dbl>, IL7.fraction.cond.2 <dbl>,
## # density <dbl>If one wants to export KNN data to perform other statistics not available in this package, then I provide a function that produces a list of each cell identity in the original input data matrix, and a matrix of all cells x features of its KNN.
I also provide a function to find the KNN density estimation independently of the rest of the “scone.values” analysis, to save time if density is all the user wants. With this density estimation, one can perform interesting analysis, ranging from understanding phenotypic density changes along a developmental progression (see post-processing vignette for an example), to trying out density-based binning methods (eg. X-shift). Of note, this density is specifically one divided by the aveage distance to k-nearest neighbors. This specific measure is related to the Shannon Entropy estimate of that point on the manifold (https://hal.archives-ouvertes.fr/hal-01068081/document).
I use this metric to avoid the unusual properties of the volume of a sphere as it increases in dimensions (https://en.wikipedia.org/wiki/Volume_of_an_n-ball). This being said, one can modify this vector to be such a density estimation (example http://www.cs.haifa.ac.il/~rita/ml_course/lectures_old/KNN.pdf), by treating the distance to knn as the radius of a n-dimensional sphere and incoroprating said volume accordingly.
An individual with basic programming skills can iterate through these elements to perform the statistics of one’s choosing. Examples would include per-KNN regression and classification, or feature imputation. The additional functionality is shown below, with the example knn.list in the package being the first ten instances:
# Constructs KNN list, computes KNN density estimation
wand.knn.list <- MakeKnnList(cell.data = wand.combined, nn.matrix = wand.nn)
wand.knn.list[[8]]## # A tibble: 30 x 51
## `CD3(Cd110)Di` `CD3(Cd111)Di` `CD3(Cd112)Di` `CD235-61-7-15(…
## <dbl> <dbl> <dbl> <dbl>
## 1 -0.131 -0.106 -0.294 0.683
## 2 -0.506 -0.686 -1.31 -0.265
## 3 0.540 -0.181 0.0845 0.266
## 4 -0.254 -0.193 -0.121 -0.267
## 5 -0.258 -0.304 -0.192 -0.370
## 6 -0.263 -0.0122 -0.107 0.281
## 7 -0.113 -0.176 0.456 -0.695
## 8 -0.00923 -0.0951 -0.0519 -0.802
## 9 -0.213 0.314 -0.206 -0.502
## 10 -0.156 -0.380 -0.384 0.721
## # … with 20 more rows, and 47 more variables: `CD3(Cd114)Di` <dbl>,
## # `CD45(In115)Di` <dbl>, `CD19(Nd142)Di` <dbl>, `CD22(Nd143)Di` <dbl>,
## # `IgD(Nd145)Di` <dbl>, `CD79b(Nd146)Di` <dbl>, `CD20(Sm147)Di` <dbl>,
## # `CD34(Nd148)Di` <dbl>, `CD179a(Sm149)Di` <dbl>, `CD72(Eu151)Di` <dbl>,
## # `IgM(Eu153)Di` <dbl>, `Kappa(Sm154)Di` <dbl>, `CD10(Gd156)Di` <dbl>,
## # `Lambda(Gd157)Di` <dbl>, `CD24(Dy161)Di` <dbl>, `TdT(Dy163)Di` <dbl>,
## # `Rag1(Dy164)Di` <dbl>, `PreBCR(Ho165)Di` <dbl>, `CD43(Er167)Di` <dbl>,
## # `CD38(Er168)Di` <dbl>, `CD40(Er170)Di` <dbl>, `CD33(Yb173)Di` <dbl>,
## # `HLA-DR(Yb174)Di` <dbl>, Time <dbl>, Cell_length <dbl>,
## # `cPARP(La139)Di` <dbl>, `pPLCg2(Pr141)Di` <dbl>,
## # `pSrc(Nd144)Di` <dbl>, `pSTAT5(Nd150)Di` <dbl>, `Ki67(Sm152)Di` <dbl>,
## # `pErk12(Gd155)Di` <dbl>, `pSTAT3(Gd158)Di` <dbl>,
## # `pAKT(Tb159)Di` <dbl>, `pBLNK(Gd160)Di` <dbl>, `pSyk(Dy162)Di` <dbl>,
## # `tIkBa(Er166)Di` <dbl>, `pP38(Tm169)Di` <dbl>, `pBTK(Yb171)Di` <dbl>,
## # `pS6(Yb172)Di` <dbl>, `pCrkL(Lu175)Di` <dbl>, `pCREB(Yb176)Di` <dbl>,
## # `DNA1(Ir191)Di` <dbl>, `DNA2(Ir193)Di` <dbl>,
## # `Viability1(Pt195)Di` <dbl>, `Viability2(Pt196)Di` <dbl>,
## # wanderlust <dbl>, condition <chr># Finds the KNN density estimation for each cell, ordered by column, in the
# original data matrix
wand.knn.density <- GetKnnDe(nn.matrix = wand.nn)
str(wand.knn.density)## num [1:1000] 0.235 0.221 0.21 0.294 0.263 ...