Iss65

[zhiiiyang]

> tic()
> semi <- MLEcell::insitutype(counts = raw,
+                             neg = neg,
+                             bg = NULL,
+                             init_clust = NULL, n_clusts = c(2:4),
+                             fixed_profiles = CPA16_RNAseq,
+                             nb_size = 10,
+                             max_iters = 10,  # this is not enough
+                             method = "EM",
+                             n_phase1 = 1000,
+                             n_starts = 4,
+                             n_benchmark_cells = 500)
The following genes in the count data are missing from fixed_profiles and will be omitted: FHIT,ID2,KLRF1,NELL2,CTSD,CTSB,APOE,TRAT1,PLEK,DGKA,NCAM1,KLRD1,IRF8,TSPAN32,EEF1G,SPARC,CTSS,A2M,TC2N,FCRL3,SPON2
Selecting optimal number of clusters from a range of 2 - 4
Iteration Number 1
Iteration Number 2
12.09 cells per geometric bin.
Clustering with n_clust = 2
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
iter 7
iter 8
iter 9
iter 10
iter 11
iter 12
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
Clustering with n_clust = 3
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
iter 7
iter 8
iter 9
iter 10
iter 11
iter 12
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
Clustering with n_clust = 4
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
iter 7
iter 8
iter 9
iter 10
iter 11
iter 12
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
phase 1: random starts in 1000 cell subsets
Iteration Number 1
Iteration Number 2
Iteration Number 3
10.58 cells per geometric bin.
Iteration Number 1
Iteration Number 2
Iteration Number 3
10.58 cells per geometric bin.
Iteration Number 1
Iteration Number 2
Iteration Number 3
10.58 cells per geometric bin.
Iteration Number 1
Iteration Number 2
Iteration Number 3
10.58 cells per geometric bin.
Iteration Number 1
Iteration Number 2
12.09 cells per geometric bin.
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
iter 7
iter 8
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
iter 7
iter 8
iter 9
iter 10
iter 11
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
iter 7
iter 8
iter 9
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
phase 2: refining best random start in a 9986 cell subset
Iteration Number 1
Iteration Number 2
Iteration Number 3
Iteration Number 4
Iteration Number 5
Iteration Number 6
Iteration Number 7
Iteration Number 8
Iteration Number 9
Iteration Number 10
Iteration Number 11
Iteration Number 12
Iteration Number 13
Iteration Number 14
Iteration Number 15
Iteration Number 16
Iteration Number 17
Iteration Number 18
Iteration Number 19
Iteration Number 20
Iteration Number 21
Iteration Number 22
Iteration Number 23
Iteration Number 24
Iteration Number 25
Iteration Number 26
Iteration Number 27
Iteration Number 28
Iteration Number 29
Iteration Number 30
Iteration Number 31
Iteration Number 32
Iteration Number 33
Iteration Number 34
Iteration Number 35
Iteration Number 36
Iteration Number 37
Iteration Number 38
Iteration Number 39
Iteration Number 40
1.1 cells per geometric bin.
iter 1
iter 2
iter 3
iter 4
iter 5
iter 6
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
phase 3: finalizing clusters in a 9986 cell subset
Iteration Number 1
Iteration Number 2
Iteration Number 3
Iteration Number 4
Iteration Number 5
Iteration Number 6
Iteration Number 7
Iteration Number 8
Iteration Number 9
Iteration Number 10
Iteration Number 11
Iteration Number 12
Iteration Number 13
Iteration Number 14
Iteration Number 15
Iteration Number 16
Iteration Number 17
Iteration Number 18
Iteration Number 19
Iteration Number 20
Iteration Number 21
Iteration Number 22
Iteration Number 23
Iteration Number 24
Iteration Number 25
Iteration Number 26
Iteration Number 27
Iteration Number 28
Iteration Number 29
Iteration Number 30
Iteration Number 31
Iteration Number 32
Iteration Number 33
Iteration Number 34
Iteration Number 35
Iteration Number 36
Iteration Number 37
Iteration Number 38
Iteration Number 39
Iteration Number 40
1.1 cells per geometric bin.
iter 1
iter 2
iter 3
Converged: <= 0.01% of cell type assignments changed in the last iteration.
==========================================================================
phase 4: classifying all 9986 cells

mean(semi$clust == celltype) [1] 0.4419187