Update README.md

README.md

@@ -12,17 +12,13 @@ tags:
 
 # Cherimoya Accessibility aTlas (CATv1)
 
-This is the first release of the **Cherimoya Accessibility aTlas (CATv1)**: a collection of over 1,000 Cherimoya models trained on DNase-seq and ATAC-seq experiments from the ENCODE Project. Cherimoya models are state-of-the-art predictors of local chromatin accessibility, mapping a DNA sequence to a base-resolution accessibility profile together with its total read count.
+This is the first release of the **Cherimoya Accessibility aTlas (CATv1)**: a collection of over 7,500 Cherimoya models trained on DNase-seq and ATAC-seq experiments from the ENCODE Project. This release covers **1,518 ENCODE experiments** (1,149 DNase-seq and 369 ATAC-seq). Every experiment is trained and evaluated across **5 folds** (`fold_0`–`fold_4`) of a chromosome-held-out cross-validation. Each model predicts accessibility for a **single experiment**, so download only the model(s) you need.
 
-This release covers **1,518 ENCODE experiments** (1,149 DNase-seq and 369 ATAC-seq). Every experiment is trained and evaluated across **5 folds** (`fold_0`–`fold_4`) of a chromosome-held-out cross-validation. Each model predicts accessibility for a **single experiment**, so download only the model(s) you need.
+Each Cherimoya model is a compact residual convolutional network (~0.6M parameters; 9 layers, 128 filters) in the BPNet / ChromBPNet family. It takes a one-hot DNA sequence of `in_window=2114` bp and produces two outputs over the central `out_window=1000` bp: a **profile** head (base-resolution logits, shape `(N, 1, 1000)`) describing the shape of the accessibility signal, and a **log count** head (log total counts, shape `(N, 1)`) describing the overall magnitude. The published checkpoints are the exponential-moving-average (EMA) shadow weights selected on validation performance.
 
-## Model description
+Models are trained on the human genome (**GRCh38 / hg38**) against the observed ENCODE accessibility signal for each experiment. Training loci are the experiment's peak regions plus GC-matched background (non-peak) negatives, with ENCODE blacklist regions excluded. The five folds partition the genome by chromosome, so for every fold the validation and test chromosomes are held out of training; reported metrics are **validation-set** performance, not the test set.
 
-Each Cherimoya model is a compact residual convolutional network (~0.6M parameters; 9 layers, 128 filters) in the BPNet / ChromBPNet family. It takes a one-hot DNA sequence of `in_window=2114` bp and produces two outputs over the central `out_window=1000` bp: a **profile** head (base-resolution logits, shape `(N, 1, 1000)`) describing the shape of the accessibility signal, and a **count** head (log total counts, shape `(N, 1)`) describing the overall magnitude. The published checkpoints are the exponential-moving-average (EMA) shadow weights selected on validation performance.
-
-## Training data
-
-Models are trained on the human genome (**GRCh38 / hg38**) against the observed ENCODE accessibility signal for each experiment. Training loci are the experiment's peak regions plus GC-matched background (non-peak) negatives, with ENCODE blacklist regions excluded. The five folds partition the genome by chromosome, so for every fold the validation chromosomes are held out of training; reported metrics are therefore **validation-set** performance, not a separate test set.
+See https://github.com/jmschrei/cherimoya for more details on the Cherimoya model.
 
 ## Repository layout