Update README.md

README.md

@@ -1,3 +1,44 @@
----
-license: mit
----
+---
+language: 
+  - en
+
+license: mit
+tags:
+  - biology
+  - genomics
+  - transcriptomics
+  - cancer
+  - bulk-rnaseq
+  - foundation-model
+  - masked-reconstruction
+  - performer
+  - gcn
+  - pytorch
+
+library_name: pytorch
+pipeline_tag: feature-extraction
+
+model_name: CancerTranscriptome-Mini-48M
+model_type: transformer
+
+datasets:
+  - ARCHS4
+
+papers:
+  - https://doi.org/10.1101/2025.06.11.659222
+
+authors:
+  - name: Walter Alvarado
+    affiliation: NASA Ames Research Center
+    github: https://github.com/alwalt
+
+model_size:
+  total_params: 48336162
+
+description: >
+  CancerTranscriptome-Mini-48M is a small, proof-of-concept BulkFormer-inspired model
+  trained on cancer-only bulk RNA-seq (ARCHS4, TCGA, GEO). It integrates ESM2 gene
+  identity embeddings, Rotary Expression Embeddings (REE), GCN message passing, local
+  bin-based Performer attention, and global Performer attention. This model is designed
+  as a research prototype showing that BulkFormer-like architectures can be trained and
+  used end-to-end on a single consumer GPU.