Correct publication references, input guidance and output units

README.md

@@ -9,7 +9,7 @@ tags:
 
 # tagemortality
 
-Elastic Net over 10,487 mouse-Entrez genes, multispecies multi-tissue, scaleddiff variant. Cohort-relative: predict_age runs the tAge cohort preprocessing on the raw RNA-seq counts itself, so a prediction is a hazard shift against the reference group rather than an absolute risk. Name the cohort's species with a 0/1 column among var_names (mouse, rat, macaque or human; absent or all-zero means mouse) and the samples to centre against with a truthy adata.obs["tage_reference_group"] (absent centres on the whole cohort); at least two samples are needed. The published pipeline's SimpleImputer, mean-only StandardScaler and pass-through SelectKBest are folded into the packaged linear layer, and the imputer medians are carried as reference_values so a gene the sample does not measure contributes its training median. Output is log10(hazard ratio) -- base 10, not the natural log the 'log hazard' unit label usually implies -- and unlike the chronological clocks it is never rescaled by species maximum lifespan, so it is directly comparable across species. Released under the MGB Open Access License 1.0: non-commercial academic research use only.
+Elastic Net over 10,487 mouse-Entrez genes, multispecies multi-tissue, scaleddiff variant. Cohort-relative: predict_age runs the tAge cohort preprocessing on the raw RNA-seq counts itself, so a prediction is a hazard shift against the reference group rather than an absolute risk. Name the cohort's species with a 0/1 column among var_names (mouse, rat, macaque or human; absent or all-zero means mouse) and the samples to centre against with a truthy adata.obs["tage_reference_group"] (absent centres on the whole cohort); at least two samples are needed. The published pipeline's SimpleImputer, mean-only StandardScaler and pass-through SelectKBest are folded into the packaged linear layer, and the imputer medians are carried as reference_values so a gene the sample does not measure contributes its training median. Output is log10(hazard ratio), using the base-10 logarithm -- and unlike the chronological clocks it is never rescaled by species maximum lifespan, so it is directly comparable across species. Released under the MGB Open Access License 1.0: non-commercial academic research use only.
 
 Model weights retain the original authors' terms; the pyaging software license does not relicense them. These weights are restricted to research use under the authors' terms.
 

config.json

@@ -10,7 +10,7 @@
  "last_author": "Vadim N. Gladyshev",
  "model_type": "elastic net regression",
  "n_features": 10487,
- "notes": "Elastic Net over 10,487 mouse-Entrez genes, multispecies multi-tissue, scaleddiff variant. Cohort-relative: predict_age runs the tAge cohort preprocessing on the raw RNA-seq counts itself, so a prediction is a hazard shift against the reference group rather than an absolute risk. Name the cohort's species with a 0/1 column among var_names (mouse, rat, macaque or human; absent or all-zero means mouse) and the samples to centre against with a truthy adata.obs[\"tage_reference_group\"] (absent centres on the whole cohort); at least two samples are needed. The published pipeline's SimpleImputer, mean-only StandardScaler and pass-through SelectKBest are folded into the packaged linear layer, and the imputer medians are carried as reference_values so a gene the sample does not measure contributes its training median. Output is log10(hazard ratio) -- base 10, not the natural log the 'log hazard' unit label usually implies -- and unlike the chronological clocks it is never rescaled by species maximum lifespan, so it is directly comparable across species. Released under the MGB Open Access License 1.0: non-commercial academic research use only.",
+ "notes": "Elastic Net over 10,487 mouse-Entrez genes, multispecies multi-tissue, scaleddiff variant. Cohort-relative: predict_age runs the tAge cohort preprocessing on the raw RNA-seq counts itself, so a prediction is a hazard shift against the reference group rather than an absolute risk. Name the cohort's species with a 0/1 column among var_names (mouse, rat, macaque or human; absent or all-zero means mouse) and the samples to centre against with a truthy adata.obs[\"tage_reference_group\"] (absent centres on the whole cohort); at least two samples are needed. The published pipeline's SimpleImputer, mean-only StandardScaler and pass-through SelectKBest are folded into the packaged linear layer, and the imputer medians are carried as reference_values so a gene the sample does not measure contributes its training median. Output is log10(hazard ratio), using the base-10 logarithm -- and unlike the chronological clocks it is never rescaled by species maximum lifespan, so it is directly comparable across species. Released under the MGB Open Access License 1.0: non-commercial academic research use only.",
  "platform": [
   "RNA-seq"
  ],
@@ -28,7 +28,7 @@
   "mortality"
  ],
  "unit": [
-  "log hazard"
+  "log10 hazard ratio"
  ],
  "version": "0.5.7",
  "year": 2026

tagemortality.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9376fe7efab1bcf4d7dbaa2b32da893ca6a4ea3b3c50f0f56825e6ecba1e589f
-size 355157
+oid sha256:88e5411ef60061baf946431bc18491915562a3f26bdc4f9b71848e81647713b9
+size 355093