Update README.md

README.md

@@ -1,3 +1,71 @@
----
-license: apache-2.0
----
+Here’s a **descriptive yet concise README** for your hierarchical VCF mutation embedding model, suitable for Hugging Face, GitHub, or documentation purposes:
+
+---
+
+# GvEM - Genomic Variant Embedding Model
+
+**HierarchicalVCF** is a PyTorch-based deep learning model designed to embed and model genomic mutation data from VCF (Variant Call Format) files using a biologically-informed hierarchy:
+**Pathway → Chromosome → Gene → Mutations**
+
+This model enables:
+
+* Pathway-aware embedding of genomic variants.
+* Learning from multi-level hierarchies of mutation context.
+* Generalization across diseases and datasets via scalable, modular design.
+
+---
+
+## Hierarchy of input data
+
+   example_data = {
+        'sample1': {
+            'pathway1': {
+                'chr1': {
+                    'gene1': [
+                        {
+                            'impact': 'HIGH',
+                            'reference': 'A',
+                            'alternate': 'T'
+                        }
+                    ]
+                }
+            }
+        }
+    }
+
+---
+
+## Features
+
+* ✅ **VCF Parser**: Converts standard VCF files into a hierarchical JSON-like structure.
+* ✅ **MutationEmbedder**: Learns embeddings for categorical mutation features (scalable).
+* ✅ **GeneEncoder**: Processes lists of mutations using Transformer and heirarchical attention to get gene-level representations.
+* ✅ **ChromosomeEncoder**: Aggregates gene encodings.
+* ✅ **PathwayEncoder**: Aggregates chromosome encodings to yield final sample representation.
+* ✅ **Scalable**: Easily extensible to new fields or biological groupings.
+* ✅ **HuggingFace Compatible**: Designed for sharing and experimentation on the 🤗 Hub.
+
+---
+
+## Use Cases
+
+* Variant-based disease classification (e.g., cancer, rare diseases, ASD)
+* Multi-omics fusion models (tabular + image + VCF)
+* Knowledge-driven mutation impact modeling
+* Transfer learning across genomic datasets
+
+---
+
+## 📂 Folder Structure
+
+```
+HierarchicalVCF/
+├── vcf_parser.py        # Parses VCF files into hierarchical format
+├── model.py             # Model components (MutationEmbedder, encoders, classification head)
+├── tokenizer.py         # Vocabulary tokenizer for categorical fields
+├── VCFDataset.py        # Torch dataset compiler
+├── train.py             # Sample training pipeline
+├── README.md            # This file
+```
+
+## MODEL STILL UNDER DEVELOPMENT