EPICv2 thyroid classifiers: invasiveness and driver group (CCR 2026), methscope random forests

EPICv2_thyroid_invasiveness.clfx (High/Low) and EPICv2_thyroid_driver.clfx
(BRAF V600E, DICER1, Kinase Fusion, Ras-like): the pediatric thyroid
carcinoma classifiers of Li et al. (CCR 2026) rebuilt with methscope's
random forest (classify-train --framework rf) on the 87 / 84 reference-
cohort primaries. Leave-one-out they match the published R forests (85.1%
vs 83.9%, 92.9% vs 95.2%); on the validation primaries 76.1% vs 75.0% and
80.5% vs 84.1%. Scored by a methscope with the rf framework.
SHA256SUMS adds the two files; README adds the EPICv2 fetch line.

.gitattributes

@@ -47,3 +47,5 @@ hg38_celltype_lite.clfx filter=lfs diff=lfs merge=lfs -text
 mm10_brain_full.clfx filter=lfs diff=lfs merge=lfs -text
 mm10_brain_lite.clfx filter=lfs diff=lfs merge=lfs -text
 mm10_41celltypes.msdref filter=lfs diff=lfs merge=lfs -text
+EPICv2_thyroid_invasiveness.clfx filter=lfs diff=lfs merge=lfs -text
+EPICv2_thyroid_driver.clfx filter=lfs diff=lfs merge=lfs -text

EPICv2_thyroid_driver.clfx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:28c9b38b464010b27675f18f27598f88eda16112471efc129b472d01c12849ec
+size 151891

EPICv2_thyroid_invasiveness.clfx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fad520429f53b959aae7f98945dabd908481209fd0e64073e9dbe3d38dfcf538
+size 144333

README.md

@@ -11,6 +11,7 @@ tags:
 - imputation
 - deconvolution
 - cell-type-annotation
+- infinium-array
 ---
 
 # MethScope — pretrained models
@@ -24,6 +25,7 @@ that carries its own feature definition, so a query `.cg` runs directly.
 ```sh
 methscope fetch hg38/models          # every human model, digest-checked
 methscope fetch mm10/models          # every mouse model
+methscope fetch EPICv2/models        # the EPICv2 array classifiers (pediatric thyroid)
 methscope fetch -c hg38/models/hg38_celltype_full.clfx   # one file, into the current dir
 ```
 

SHA256SUMS

@@ -1,6 +1,8 @@
 8f7f2d6d42f64daaba5bf9cede5146fa52c0f62b5c76b3d5c6680c5c7554b1b7  hg38_10k1.updecx
 a1aeaf7d62ec8546bd40963f2fe18dcb0bdb54360b64748c10fbd304816442d8  hg38_wg.updecx
 f25cc5317a892105a121300fef009e29e96677f9a43fd02c3b47a59bf64cd482  mm10_wg.updecx
+28c9b38b464010b27675f18f27598f88eda16112471efc129b472d01c12849ec  EPICv2_thyroid_driver.clfx
+fad520429f53b959aae7f98945dabd908481209fd0e64073e9dbe3d38dfcf538  EPICv2_thyroid_invasiveness.clfx
 4989d8178327e9a961a1834f53f68dd0e2ca7ce151959647fcbdc730d8e083ba  hg38_celltype_full.clfx
 a89214fe1a9a3a562eefeb2044eceac0509146df93296db3663abd5ca337b988  hg38_celltype_lite.clfx
 3d1618f6ca24d9a9d5b0fe1806673540515e5f6e7d7950e7c8873a85bb5c742b  hg38_sex.clfx