VParka commited on
Commit
1d88d38
·
verified ·
1 Parent(s): cb5929b

Upload README.md via DNA Console (Portable Version)

Browse files
Files changed (1) hide show
  1. README.md +6 -6
README.md CHANGED
@@ -7,12 +7,12 @@ tags:
7
  library_name: sklearn
8
  ---
9
 
10
- # BioGuard DNA Classifier Ensemble (Portable v1.1)
11
 
12
  This repository contains a dual-model ensemble for DNA sequence analysis and virus classification, optimized for **portability and zero-dependency loading**.
13
 
14
  > [!NOTE]
15
- > **Version 1.1 Update**: This version has been refactored to decouple the models from custom feature extraction classes. It uses a raw scikit-learn format for maximum compatibility.
16
 
17
  ## 🧬 Models Included
18
 
@@ -23,16 +23,16 @@ This repository hosts two distinct models specialized for different aspects of g
23
  * **Purpose**: General-purpose synthetic vs. biological sequence classification.
24
  * **Architecture**: Random Forest (sklearn) with biological feature extraction (k-mers, GC content, etc.).
25
  * **Performance (Test Set)**:
26
- * **Accuracy**: 89.4%
27
- * **F1 Score**: 89.4%
28
 
29
  ### 2. **ViralBoost** (GradientBoostingClassifier)
30
  * **File**: `sequence_model.joblib`
31
  * **Purpose**: Specific virus type identification (Influenza A, Norovirus, etc.) based on sequence signatures.
32
  * **Architecture**: Gradient Boosting (sklearn) trained on real-world viral sequences.
33
  * **Performance (Test Set)**:
34
- * **Accuracy**: 99.4%
35
- * **F1 Score**: 99.4%
36
  * **Classes**: Other, Influenza A, Chicken anemia virus, Norovirus, Influenza B
37
 
38
  ## 🚀 Usage
 
7
  library_name: sklearn
8
  ---
9
 
10
+ # BioGuard DNA Classifier Ensemble (Portable v1.3)
11
 
12
  This repository contains a dual-model ensemble for DNA sequence analysis and virus classification, optimized for **portability and zero-dependency loading**.
13
 
14
  > [!NOTE]
15
+ > **Version 1.3 Update**: This version has been fully refactored to remove all custom class dependencies from `.joblib` files. Feature extraction is now strictly handled via source code.
16
 
17
  ## 🧬 Models Included
18
 
 
23
  * **Purpose**: General-purpose synthetic vs. biological sequence classification.
24
  * **Architecture**: Random Forest (sklearn) with biological feature extraction (k-mers, GC content, etc.).
25
  * **Performance (Test Set)**:
26
+ * **Accuracy**: 88.9%
27
+ * **F1 Score**: 89.2%
28
 
29
  ### 2. **ViralBoost** (GradientBoostingClassifier)
30
  * **File**: `sequence_model.joblib`
31
  * **Purpose**: Specific virus type identification (Influenza A, Norovirus, etc.) based on sequence signatures.
32
  * **Architecture**: Gradient Boosting (sklearn) trained on real-world viral sequences.
33
  * **Performance (Test Set)**:
34
+ * **Accuracy**: 99.3%
35
+ * **F1 Score**: 99.3%
36
  * **Classes**: Other, Influenza A, Chicken anemia virus, Norovirus, Influenza B
37
 
38
  ## 🚀 Usage