K-nearest neighbors:

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"           "CD3(Cd112)Di"          
##  [4] "CD235-61-7-15(In113)Di" "CD3(Cd114)Di"           "CD45(In115)Di"         
##  [7] "CD19(Nd142)Di"          "CD22(Nd143)Di"          "IgD(Nd145)Di"          
## [10] "CD79b(Nd146)Di"         "CD20(Sm147)Di"          "CD34(Nd148)Di"         
## [13] "CD179a(Sm149)Di"        "CD72(Eu151)Di"          "IgM(Eu153)Di"          
## [16] "Kappa(Sm154)Di"         "CD10(Gd156)Di"          "Lambda(Gd157)Di"       
## [19] "CD24(Dy161)Di"          "TdT(Dy163)Di"           "Rag1(Dy164)Di"         
## [22] "PreBCR(Ho165)Di"        "CD43(Er167)Di"          "CD38(Er168)Di"         
## [25] "CD40(Er170)Di"          "CD33(Yb173)Di"          "HLA-DR(Yb174)Di"       
## 
## $functional
##  [1] "pCrkL(Lu175)Di"  "pCREB(Yb176)Di"  "pBTK(Yb171)Di"   "pS6(Yb172)Di"   
##  [5] "cPARP(La139)Di"  "pPLCg2(Pr141)Di" "pSrc(Nd144)Di"   "Ki67(Sm152)Di"  
##  [9] "pErk12(Gd155)Di" "pSTAT3(Gd158)Di" "pAKT(Tb159)Di"   "pBLNK(Gd160)Di" 
## [13] "pP38(Tm169)Di"   "pSTAT5(Nd150)Di" "pSyk(Dy162)Di"   "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] 311 669 564 685 920 139 976 319 805 192 ...
wand.nn[[1]][1:20, 1:10]
##       [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8] [,9] [,10]
##  [1,]  311  846  515  196  163  571  182  169  139   138
##  [2,]  669  840   63  321   81  859  114   50  410   925
##  [3,]  564  357 1000  964  438  239  662  456  649   836
##  [4,]  685  575   68  294  977  954  800  366  614   469
##  [5,]  920  458  844  501  197  811  125  268  159    20
##  [6,]  139  196  571   90  747  970  809    1  876   301
##  [7,]  976  252  385  322  537  265  840  323  270   410
##  [8,]  319  189  416  264   88  513   63  825  944   488
##  [9,]  805  312  636  886  402   17  931  776  437   606
## [10,]  192  179  197  419  976  766  339  546   44   669
## [11,]  622  602  934  787  439  734  143  187  870   133
## [12,]  282  975  277  265  533  593  384  644  560   246
## [13,]  677  464  974  489  951   67  908  201  320   970
## [14,]  142  276  443  264  815  637  439  585  326   746
## [15,]  930  820  554  577   76  529  200  452  905   168
## [16,]  934  959  791  874  143  356  584  547  269   260
## [17,]  402  965  805    9  404  568  752  310  804   541
## [18,]  998  603  783  925  770  317  181  360  753   374
## [19,]  519  484  227  113  844  246  842  419  252   728
## [20,]  728  519  844  449  125  421  599  298  303   410
# Distance
str(wand.nn[[2]])
##  num [1:1000, 1:30] 3.17 2.61 5.29 3.65 3.17 ...
wand.nn[[2]][1:20, 1:10]
##           [,1]     [,2]     [,3]     [,4]     [,5]     [,6]     [,7]     [,8]
##  [1,] 3.171068 3.481178 3.600803 3.817606 3.921847 3.947861 3.960518 4.009307
##  [2,] 2.614026 2.804278 3.086236 3.138471 3.197036 3.274039 3.438990 3.492433
##  [3,] 5.288472 5.367204 6.070138 6.219095 6.235203 6.346594 6.353196 6.417676
##  [4,] 3.654436 3.799726 3.855296 4.044009 4.097500 4.127788 4.154500 4.163842
##  [5,] 3.172684 3.211234 3.333152 3.351309 3.481355 3.615715 3.643893 3.675832
##  [6,] 4.088346 4.125997 4.186742 4.189745 4.224849 4.270545 4.344830 4.352267
##  [7,] 3.285076 3.380446 3.427433 3.555003 3.608696 3.615235 3.722028 3.757769
##  [8,] 3.950426 3.982444 3.983523 4.271339 4.306284 4.319607 4.352936 4.358861
##  [9,] 3.029227 3.067163 3.284825 3.308825 3.321665 3.378611 3.514371 3.548801
## [10,] 3.607652 3.618035 3.666589 3.672020 3.809696 3.970047 4.213986 4.283156
## [11,] 2.407407 2.815737 2.827644 2.844380 2.919770 2.949460 3.015529 3.017756
## [12,] 4.579636 4.691063 4.721317 4.751897 4.814718 4.837764 4.871265 4.883767
## [13,] 4.699835 5.174059 5.298123 5.399836 5.488858 5.559348 5.650207 5.677497
## [14,] 3.356851 3.359119 3.494441 3.786363 3.876545 4.081137 4.158189 4.189339
## [15,] 4.065915 4.497995 4.535445 4.667527 4.684504 4.724088 4.912392 4.980528
## [16,] 4.241486 4.397172 4.398451 4.412831 4.415038 4.419607 4.506987 4.588290
## [17,] 3.056717 3.066980 3.145096 3.378611 3.543692 3.579748 3.679669 3.708573
## [18,] 2.907041 3.102249 3.157273 3.246241 3.253448 3.269542 3.311457 3.327819
## [19,] 3.017974 3.268297 3.320573 3.381191 3.481008 3.627836 3.677416 3.701739
## [20,] 3.036677 3.241655 3.253749 3.273673 3.316434 3.324695 3.335381 3.563293
##           [,9]    [,10]
##  [1,] 4.019552 4.033075
##  [2,] 3.496222 3.507000
##  [3,] 6.489301 6.611625
##  [4,] 4.192262 4.214410
##  [5,] 3.695514 3.719047
##  [6,] 4.403568 4.440960
##  [7,] 3.770940 3.786052
##  [8,] 4.391597 4.401570
##  [9,] 3.585331 3.608424
## [10,] 4.288488 4.352584
## [11,] 3.068766 3.071325
## [12,] 4.920338 4.940955
## [13,] 5.684162 5.699640
## [14,] 4.216063 4.236636
## [15,] 4.990545 5.145195
## [16,] 4.669358 4.690217
## [17,] 3.709851 3.711832
## [18,] 3.346413 3.357396
## [19,] 3.745634 3.759993
## [20,] 3.564146 3.665252

Finding scone values:

This 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 × 34
##    pCrkL(Lu175…¹ pCREB…² pBTK(…³ pS6(Y…⁴ cPARP…⁵ pPLCg…⁶ pSrc(…⁷ Ki67(…⁸ pErk1…⁹
##            <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>
##  1         0.996       1   0.963   0.976   1       0.849   0.931   0.992   1    
##  2         0.994       1   0.878   0.995   0.938   0.849   0.993   0.992   1    
##  3         0.943       1   0.878   1       0.932   1       0.943   0.992   1    
##  4         0.996       1   0.878   1       1       0.797   0.931   0.992   1    
##  5         0.982       1   0.963   0.976   0.932   0.976   0.925   0.992   0.998
##  6         1           1   0.949   0.996   1       0.797   0.946   0.992   1    
##  7         0.939       1   0.878   0.976   0.989   0.794   0.981   0.992   0.977
##  8         0.982       1   0.878   1       1       0.895   0.944   0.894   0.977
##  9         0.982       1   0.963   0.714   0.989   0.960   0.931   0.997   0.977
## 10         0.943       1   0.975   0.976   0.984   0.834   0.992   0.920   0.977
## # … with 990 more rows, 25 more variables: `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>, …

For programmers: performing additional per-KNN statistics

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 × 51
##    CD3(Cd110)…¹ CD3(C…² CD3(C…³ CD235…⁴ CD3(C…⁵ CD45(…⁶ CD19(…⁷ CD22(…⁸ IgD(Nd…⁹
##           <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>   <dbl>    <dbl>
##  1     -0.157   -0.0810 -0.163  -0.0833  0.511     2.87   0.301  1.15   -0.0625 
##  2      0.00900 -0.242  -0.198  -0.0516  0.0926    2.50   2.33  -0.0390  0.486  
##  3     -0.224   -0.501  -0.133  -0.477  -0.678     3.49   2.08   1.02   -0.138  
##  4     -0.208   -0.0944 -0.163  -0.440  -0.0278    1.83   1.26  -0.250  -0.00915
##  5     -0.402   -0.356  -0.397  -0.883  -0.497     3.13   2.61   1.11   -0.103  
##  6     -0.231   -0.449  -0.894   0.285  -0.401     3.14   2.03   1.79   -0.0556 
##  7     -0.398   -0.252  -0.830  -0.816  -0.492     3.06   1.97   1.36   -0.369  
##  8     -0.255   -0.0930 -0.0922  0.367  -0.0480    2.39   0.337  0.254   0.860  
##  9     -0.144   -0.0808 -0.103  -1.13   -0.181     2.49   2.42   0.273  -0.336  
## 10     -0.218   -0.0910 -0.198   0.145  -0.417     3.08   2.56   1.07   -0.0836 
## # … with 20 more rows, 42 more variables: `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>, …
# 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] 0.242 0.285 0.152 0.231 0.262 ...