rbbt-dm 1.1.59 → 1.1.61

checksums.yaml

@@ -1,7 +1,7 @@
 ---
 SHA256:
-  metadata.gz: 1e001607266948a5221118c15d1fc95ed4266b0f8880b2fa628350d429ed3f7d
-  data.tar.gz: 1d56618e3039e1d99c8183aace2ae20e8cd3dafce0d574b5dbd49ce4f5a1ee14
+  metadata.gz: d24ba3529b0cd6c9470d87e9c947110a37e82f50345d8cf6242bd0cdee335afb
+  data.tar.gz: 8718681f7cd3bd48c4ad1c8f96ceaadd2cb737e8f6312b31549e1f9b25d0026c
 SHA512:
-  metadata.gz: d8d324c664257cb142ae7363de776ea7b6e367cd14c22026018c00de335bc3e35be428d00dad6d84a61c3f0874057612d1379e6839b1cea6fc312ea5d8e9a699
-  data.tar.gz: b2e52024a63f3105ac88ca1b471df0b69fe91237a1e3fa70185fc519e0740421c58755eb3560003c9f4e4f60b6479bf449fca7596684e3badba46e4ec242feee
+  metadata.gz: 452cfe66ec260c362290d7b1e119a246df32bd145ccc8942f625aa9ac8737d876344396fe2fe03a33ddfd8f7a31483cdaf9973ed3fa5f7f99447847f0cf9aa6f
+  data.tar.gz: 8c5911faac614b7a06a1d07d02dd2fed9ddf7049bc97d37303e612d764855714529be2d18c68ee7116fa3bae551fe94c696f8c45c908236e4bdeb2923829b3cb

data/lib/rbbt/matrix/barcode.rb

@@ -9,7 +9,7 @@ source('#{Rbbt.share.R['barcode.R'].find}')
 rbbt.GE.barcode.mode(#{ R.ruby2R self.data_file }, #{ R.ruby2R outfile }, #{ R.ruby2R factor })
     EOF
 
-    R.run(cmd)
+    R.run(cmd, :monitor => true)
   end
 
   def barcode_ruby(outfile, factor = 2)
@@ -55,7 +55,7 @@ source('#{Rbbt.share.R['barcode.R'].find}')
 rbbt.GE.activity_cluster(#{ R.ruby2R self.data_file }, #{ R.ruby2R outfile }, #{R.ruby2R key_field}, #{R.ruby2R clusters})
     EOF
 
-    R.run(cmd)
+    R.run(cmd, :monitor => true)
   end
 
 

data/lib/rbbt/matrix/differential.rb

@@ -1,4 +1,5 @@
 require 'rbbt/util/R'
+require 'rbbt/matrix'
 
 class RbbtMatrix
   def differential(main, contrast, path = nil)
@@ -31,9 +32,7 @@ class RbbtMatrix
         trend = false
         two_channel = false
       when 'fpkm'
-        log2 = true
-        trend = true
-        two_channel = false
+        type = "DESeq"
       when 'log2 ratio', 'transformed count'
         log2 = false
         trend = false
@@ -53,6 +52,7 @@ class RbbtMatrix
 source('#{Rbbt.share.R["MA.R"].find(:lib)}')
 
 data = rbbt.dm.matrix.differential(#{ R.ruby2R data_file }, 
+  type = #{R.ruby2R type},
   main = #{R.ruby2R(main_samples)}, 
   contrast = #{R.ruby2R(contrast_samples)}, 
   log2=#{ R.ruby2R log2 }, 

data/lib/rbbt/matrix.rb

@@ -140,6 +140,21 @@ class RbbtMatrix
     [main_samples, contrast_samples]
   end
 
+  def transpose(id = nil)
+    name = data_file =~ /:>/ ? File.basename(data_file) : data_file
+
+    file = Persist.persist(data_file, :tsv, :prefix => "Transpose", :check => [data_file],  :dir => RbbtMatrix.matrix_dir.values, :no_load => true) do
+
+      data = data_file.tsv(:cast => :to_f, :type => :double).transpose(id)
+
+      data.to_list{|v| v.length > 1 ? Misc.mean(v) : v }
+    end
+    subsets = self.subsets
+    matrix = RbbtMatrix.new file, labels, value_type, key_field, organism
+    matrix.subsets = subsets
+    matrix
+  end
+
   def to_average(identifiers = nil)
     name = data_file =~ /:>/ ? File.basename(data_file) : data_file
 

data/lib/rbbt/network/paths.rb

@@ -3,8 +3,16 @@ require 'fc'
 module Paths
 
   def self.dijkstra(adjacency, start_node, end_node = nil, max_steps = nil)
+
     return nil unless adjacency.include? start_node
 
+    case end_node
+    when String
+      return nil unless adjacency.values.flatten.include? end_node
+    when Array
+      return nil unless (adjacency.values.flatten & end_node).any?
+    end
+
     active = FastContainers::PriorityQueue.new(:min)
     distances = Hash.new { 1.0 / 0.0 } 
     parents = Hash.new                 

data/lib/rbbt/vector/model/spaCy.rb

@@ -63,11 +63,16 @@ class SpaCyModel < VectorModel
       docs = []
       bar = bar(features.length, "Evaluating model")
       SpaCyModel.spacy do
+        gpu = Rbbt::Config.get('gpu_id', :spacy, :spacy_train, :default => 0)
+        gpu = gpu.to_i if gpu && gpu != ""
+        spacy.require_gpu(gpu) if gpu
         nlp = spacy.load("#{file}/model-best")
 
         docs = nlp.pipe(texts)
         RbbtPython.collect docs, :bar => bar do |d|
-          d.cats.sort_by{|l,v| v.to_f || 0 }.last.first
+          Misc.timeout_insist(20) do
+            d.cats.sort_by{|l,v| v.to_f || 0 }.last.first
+          end
         end
         #nlp.(docs).cats.collect{|cats| cats.sort_by{|l,v| v.to_f }.last.first }
         #Log::ProgressBar.with_bar texts.length, :desc => "Evaluating documents" do |bar|

data/share/R/MA.R

@@ -1,4 +1,4 @@
-rbbt.require('limma')
+rbbt.require('edgeR')
 
 #########################################################################
 # Model processing 
@@ -57,6 +57,33 @@ rbbt.dm.matrix.differential.limma.twoside <- function(expr, subset.main, subset.
     return(list(t= fit$t[,2], p.values= fit$p.value[,2]));
 }
 
+rbbt.dm.matrix.differential.DESeq <- function(expr, subset.main, subset.contrast) {
+    rbbt.require('DESeq2')
+    rbbt.require('HTSFilter')
+    rbbt.require('apeglm')
+
+    #expr[expr == 0] = NA
+    good.rows = apply(is.na(expr),1,sum) == 0
+    expr = expr[good.rows,]
+
+    condition_values = rep(c("contrast"), length(subset.contrast))
+    condition_values = c(condition_values, rep(c("condition"), length(subset.main)))
+    names = c(subset.contrast, subset.main)
+    conditions = data.frame(condition = factor(condition_values, levels=c("contrast", "condition")))
+    
+
+    expr = expr[,names]
+
+    dds <- DESeqDataSetFromMatrix(countData = round(expr), colData = conditions, design = ~ condition)
+    dds <- DESeq(dds)
+
+    filter <- HTSFilter(dds, s.len=25, plot=FALSE)$filteredData
+
+    res <- lfcShrink(filter, type="apeglm", coef="condition_condition_vs_contrast")
+
+    return(res)
+}
+
 
 rbbt.dm.matrix.guess.log2 <- function(m, two.channel){
     if (two.channel){
@@ -66,34 +93,24 @@ rbbt.dm.matrix.guess.log2 <- function(m, two.channel){
     }
 }
 
-rbbt.dm.matrix.differential <- function(file, main, contrast = NULL, log2 = FALSE, outfile = NULL, key.field = NULL, two.channel = NULL, namespace = NULL, eBayes.trend = FALSE){
-    if (is.null(namespace)) namespace = rbbt.default_code("Hsa")
-    data = data.matrix(rbbt.tsv(file));
-    dimnames = dimnames(data)
-    original.dimnames = dimnames;
-
-    dimnames[[1]] = make.names(dimnames[[1]])
-    dimnames[[2]] = make.names(dimnames[[2]])
-
-    dimnames(data) <- dimnames
-    main <- make.names(main);
-    contrast <- make.names(contrast);
-
-    data[data == 0] = NA
-    good.rows = apply(is.na(data),1,sum) != dim(data)[2]
-    data = data[good.rows,]
-
-    ids = rownames(data);
-    if (is.null(key.field)){ key.field = "ID" }
-
+rbbt.dm.matrix.differential.limma <- function(data, main, contrast=NULL, log2=NULL, two.channel=NULL, eBayes.trend=NULL){
     if (is.null(log2)){
       log2 = rbbt.dm.matrix.guess.log2(data, two.channel)
     }
 
     if (log2){
-       data = log2(data);
+       cutoff <- 1
+       drop <- which(apply(data, 1, max) < cutoff)
        min = min(data[data != -Inf])
        data[data == -Inf] = min
+       data <- DGEList(data)
+       data <- calcNormFactors(data)
+       data = cpm(data, log=TRUE, prior.count=3)
+       data <- data[-drop,]
+    }else{
+       data[data == 0] = NA
+       good.rows = apply(is.na(data),1,sum) != dim(data)[2]
+       data = data[good.rows,]
     }
 
     if (is.null(contrast)){
@@ -135,20 +152,50 @@ rbbt.dm.matrix.differential <- function(file, main, contrast = NULL, log2 = FALS
 
 
     if (! is.null(limma) && sum(is.na(limma$t)) != length(limma$t)){
+       ids = rownames(data)
        result = data.frame(ratio = ratio[ids], t.values = limma$t[ids], p.values = limma$p.values[ids])
        result["adjusted.p.values"] = p.adjust(abs(result$p.values), "fdr") * sign(result$p.values)
     }else{
        result = data.frame(ratio = ratio)
     }
 
-    rownames(result) <- original.dimnames[[1]][good.rows]
+    rownames(result) <- rownames(data)
+    result = result[!is.na(result$ratio),]
+
+    return(result)
+}
+
+rbbt.dm.matrix.differential <- function(file, main, contrast = NULL, type = 'limma', log2 = FALSE, outfile = NULL, key.field = NULL, two.channel = NULL, namespace = NULL, eBayes.trend = FALSE){
+    data = data.matrix(rbbt.tsv(file));
+    dimnames = dimnames(data)
+
+    original.dimnames = dimnames;
+
+    #dimnames[[1]] = make.names(dimnames[[1]])
+    dimnames[[2]] = make.names(dimnames[[2]])
+
+    dimnames(data) <- dimnames
+    main <- make.names(main);
+
+    if (! is.null(contrast)){
+        contrast <- make.names(contrast);
+    }
+
+    if (type == 'limma')
+        result = rbbt.dm.matrix.differential.limma(data, main, contrast, log2, two.channel, eBayes.trend)
+    else
+        result = rbbt.dm.matrix.differential.DESeq(data, main, contrast)
+
+    if (is.null(outfile)){
+        return(result);
+    }else{
+        if (is.null(key.field)){ key.field = "ID" }
+        if (is.null(namespace)) namespace = rbbt.default_code("Hsa")
+
+        rbbt.tsv.write(outfile, result, key.field, paste(":type=:list#:cast=:to_f#:namespace=", namespace, "#comment=Negative values mark downregulation", sep=""));
+        return(NULL);
+    }
 
-   if (is.null(outfile)){
-       return(result);
-   }else{
-       rbbt.tsv.write(outfile, result, key.field, paste(":type=:list#:cast=:to_f#:namespace=", namespace, "#comment=Negative values mark downregulation", sep=""));
-       return(NULL);
-   }
 }
 
 

data/share/R/barcode.R

@@ -66,17 +66,21 @@ rbbt.GE.barcode.mode <- function(matrix_file, output_file, sd.factor = 2, key.fi
 rbbt.GE.activity_cluster <- function(matrix_file, output_file, key.field = "ID", clusters = c(2,3)){
 
     rbbt.require('mclust')
+    rbbt.require('R.utils')
 
     data = rbbt.tsv.numeric(matrix_file)
 
-    classes = apply(data,1,function(row){
+    classes = apply(data, 1, function(row){
                     row.na = is.na(row)
                     clust = rep(NA, length(row))
-                    if (sum(row.na) <= length(row) - 5){
+                    rbbt.log(str(row))
+                    if (sum(row.na) <= length(row) - 5 && length(unique(row[!row.na])) > 4){
                         clust[!row.na] = densityMclust(row[!row.na], prior=priorControl(), G=clusters)$classification
+                        rbbt.log(str(clust))
                     }
                     clust
     })
+    rbbt.log("DONE")
 
     classes = data.frame(t(classes))
 

data/test/rbbt/network/test_paths.rb

@@ -21,6 +21,26 @@ N4 N5
 
     path = Paths.dijkstra(network, start_node, [end_node])
     assert_equal %w(N1 N2 N4 N5), path.reverse
+
+    path = Paths.dijkstra(network, start_node, end_node)
+    assert_equal %w(N1 N2 N4 N5), path.reverse
+  end
+
+  def test_dijsktra_missing
+    network_txt=<<-EOF
+#: :sep=/\s/#:type=:flat
+#Start End
+N1 N2
+N2 N3 N4
+N4 N5
+    EOF
+    network = TSV.open(StringIO.new(network_txt))
+
+    start_node = "N1"
+    end_node = "M5"
+
+    path = Paths.dijkstra(network, start_node, [end_node])
+    assert_nil path
   end
 
   def test_weighted_dijsktra

metadata

@@ -1,14 +1,14 @@
 --- !ruby/object:Gem::Specification
 name: rbbt-dm
 version: !ruby/object:Gem::Version
-  version: 1.1.59
+  version: 1.1.61
 platform: ruby
 authors:
 - Miguel Vazquez
 autorequire: 
 bindir: bin
 cert_chain: []
-date: 2022-07-29 00:00:00.000000000 Z
+date: 2022-11-07 00:00:00.000000000 Z
 dependencies:
 - !ruby/object:Gem::Dependency
   name: rbbt-util