miga-base 1.3.8.1 → 1.3.9.0

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
Files changed (52) hide show
  1. checksums.yaml +4 -4
  2. data/README.md +2 -2
  3. data/lib/miga/cli/action/add_result.rb +22 -1
  4. data/lib/miga/cli/action/browse/about.html +4 -2
  5. data/lib/miga/cli/action/doctor.rb +1 -1
  6. data/lib/miga/cli/action/download/gtdb.rb +1 -1
  7. data/lib/miga/cli/action/download/ncbi.rb +43 -68
  8. data/lib/miga/cli/action/download/seqcode.rb +1 -2
  9. data/lib/miga/cli/action/ncbi_get.rb +1 -8
  10. data/lib/miga/cli/action/wf.rb +15 -6
  11. data/lib/miga/cli/objects_helper.rb +3 -0
  12. data/lib/miga/cli/opt_helper.rb +8 -2
  13. data/lib/miga/common/net.rb +100 -18
  14. data/lib/miga/dataset/base.rb +40 -12
  15. data/lib/miga/dataset/hooks.rb +8 -0
  16. data/lib/miga/dataset/result/ignore.rb +14 -2
  17. data/lib/miga/dataset/type.rb +51 -0
  18. data/lib/miga/dataset.rb +3 -22
  19. data/lib/miga/json.rb +9 -0
  20. data/lib/miga/project/base.rb +15 -9
  21. data/lib/miga/project.rb +7 -1
  22. data/lib/miga/remote_dataset/base.rb +117 -36
  23. data/lib/miga/remote_dataset/download.rb +121 -54
  24. data/lib/miga/remote_dataset.rb +34 -13
  25. data/lib/miga/result/stats.rb +2 -0
  26. data/lib/miga/result/versions.rb +23 -0
  27. data/lib/miga/result.rb +7 -1
  28. data/lib/miga/taxonomy/base.rb +3 -2
  29. data/lib/miga/version.rb +2 -2
  30. data/scripts/assembly.bash +15 -1
  31. data/scripts/cds.bash +9 -3
  32. data/scripts/distances.bash +103 -5
  33. data/scripts/essential_genes.bash +14 -1
  34. data/scripts/mytaxa.bash +18 -3
  35. data/scripts/mytaxa_scan.bash +16 -3
  36. data/scripts/read_quality.bash +6 -2
  37. data/scripts/ssu.bash +19 -1
  38. data/scripts/stats.bash +9 -3
  39. data/scripts/taxonomy.bash +98 -2
  40. data/scripts/trimmed_fasta.bash +10 -2
  41. data/scripts/trimmed_reads.bash +26 -6
  42. data/test/dataset_test.rb +17 -2
  43. data/test/hook_test.rb +3 -2
  44. data/test/net_test.rb +21 -5
  45. data/test/project_test.rb +13 -0
  46. data/test/remote_dataset_test.rb +106 -7
  47. data/test/result_test.rb +47 -21
  48. data/test/taxonomy_test.rb +9 -3
  49. data/utils/distance/runner.rb +3 -1
  50. data/utils/distances.rb +1 -1
  51. data/utils/subclades.R +15 -8
  52. metadata +4 -2
data/utils/subclades.R CHANGED
@@ -116,7 +116,8 @@ subclade_clustering <- function (out_base, thr, ani.d, dist_rds) {
116
116
  say("Subsampling large collection")
117
117
  ids <- sample(labels(ani.d), nMax)
118
118
  ani.d.ori <- ani.d
119
- ani.d <- as.dist(as.matrix(ani.d)[ids, ids])
119
+ ani.d.m <- as.matrix(ani.d)
120
+ ani.d <- as.dist(ani.d.m[ids, ids])
120
121
  }
121
122
 
122
123
  # Silhouette
@@ -157,9 +158,10 @@ subclade_clustering <- function (out_base, thr, ani.d, dist_rds) {
157
158
  ani.d <- ani.d.ori
158
159
  # Find closest medoid for missing genomes
159
160
  missing <- labels(ani.d)[!labels(ani.d) %in% names(ani.types)]
160
- for (i in missing)
161
- ani.types[i] <- which.min(as.matrix(ani.d)[ani.medoids, i])
161
+ say("- Classify:", length(missing))
162
+ for (i in missing) ani.types[i] <- which.min(ani.d.m[ani.medoids, i])
162
163
  # Reorder
164
+ say("- Reorder and save")
163
165
  ani.types <- ani.types[labels(ani.d)]
164
166
  # Save missing genomes for inspection
165
167
  write.table(
@@ -190,11 +192,16 @@ subclade_clustering <- function (out_base, thr, ani.d, dist_rds) {
190
192
  # Generate graphic report
191
193
  say("Graphic report")
192
194
  pdf(paste(out_base, ".pdf", sep = ""), 7, 12)
193
- layout(matrix(c(rep(1:3, each = 2), 4:5), byrow = TRUE, ncol = 2))
194
- plot_distances(ani.d)
195
- plot_silhouette(k, s[1, ], s[2, ], ds, top.n)
196
- if (!is.huge) plot_clustering(ani.cl, ani.d, ani.types)
197
- if (!is.large) plot_tree(ani.ph, ani.types, ani.medoids)
195
+ if (is.huge) {
196
+ plot(NULL, axes = FALSE, xlab = '', ylab = '', xlim = 0:1, ylim = 0:1)
197
+ legend('center', legend = 'Dataset too large for graphical representation')
198
+ } else {
199
+ layout(matrix(c(rep(1:3, each = 2), 4:5), byrow = TRUE, ncol = 2))
200
+ plot_distances(ani.d)
201
+ plot_silhouette(k, s[1, ], s[2, ], ds, top.n)
202
+ plot_clustering(ani.cl, ani.d, ani.types)
203
+ if (!is.large) plot_tree(ani.ph, ani.types, ani.medoids)
204
+ }
198
205
  dev.off()
199
206
 
200
207
  # Save results
metadata CHANGED
@@ -1,14 +1,14 @@
1
1
  --- !ruby/object:Gem::Specification
2
2
  name: miga-base
3
3
  version: !ruby/object:Gem::Version
4
- version: 1.3.8.1
4
+ version: 1.3.9.0
5
5
  platform: ruby
6
6
  authors:
7
7
  - Luis M. Rodriguez-R
8
8
  autorequire:
9
9
  bindir: bin
10
10
  cert_chain: []
11
- date: 2023-07-05 00:00:00.000000000 Z
11
+ date: 2024-01-22 00:00:00.000000000 Z
12
12
  dependencies:
13
13
  - !ruby/object:Gem::Dependency
14
14
  name: daemons
@@ -218,6 +218,7 @@ files:
218
218
  - lib/miga/dataset/result/add.rb
219
219
  - lib/miga/dataset/result/ignore.rb
220
220
  - lib/miga/dataset/status.rb
221
+ - lib/miga/dataset/type.rb
221
222
  - lib/miga/json.rb
222
223
  - lib/miga/lair.rb
223
224
  - lib/miga/metadata.rb
@@ -235,6 +236,7 @@ files:
235
236
  - lib/miga/result/dates.rb
236
237
  - lib/miga/result/source.rb
237
238
  - lib/miga/result/stats.rb
239
+ - lib/miga/result/versions.rb
238
240
  - lib/miga/sqlite.rb
239
241
  - lib/miga/tax_dist.rb
240
242
  - lib/miga/tax_index.rb