GENE_FAMILY: AP2

MODEL: FEEDFORWARD_k2

Model Architecture

Model: "FEEDFORWARD_k2"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ dense (Dense)                        │ (None, 256)                 │         113,152 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout (Dropout)                    │ (None, 256)                 │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_1 (Dense)                      │ (None, 128)                 │          32,896 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_1 (Dropout)                  │ (None, 128)                 │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_2 (Dense)                      │ (None, 64)                  │           8,256 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_2 (Dropout)                  │ (None, 64)                  │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_3 (Dense)                      │ (None, 32)                  │           2,080 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_3 (Dropout)                  │ (None, 32)                  │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_4 (Dense)                      │ (None, 1)                   │              33 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
 Total params: 469,253 (1.79 MB)
 Trainable params: 156,417 (611.00 KB)
 Non-trainable params: 0 (0.00 B)
 Optimizer params: 312,836 (1.19 MB)

Learning Curve

Learning Curve

Class Distribution

       Count  Percentage
class                   
1       4461       50.16
0       4433       49.84

Additional Metrics

  • Total Samples: 8894
  • Imbalance Ratio: 1.01

Classification Report

              precision    recall  f1-score   support

     Class 0     0.9782    0.9617    0.9699       887
     Class 1     0.9625    0.9787    0.9705       892

    accuracy                         0.9702      1779
   macro avg     0.9704    0.9702    0.9702      1779
weighted avg     0.9703    0.9702    0.9702      1779

Metrics

  • True Positives (TP): 873
  • True Negatives (TN): 853
  • False Positives (FP): 34
  • False Negatives (FN): 19

Confusion Matrix

Confusion Matrix
MODEL: FEEDFORWARD_k3

Model Architecture

Model: "FEEDFORWARD_k3"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ dense_5 (Dense)                      │ (None, 256)                 │       2,278,144 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_4 (Dropout)                  │ (None, 256)                 │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_6 (Dense)                      │ (None, 128)                 │          32,896 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_5 (Dropout)                  │ (None, 128)                 │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_7 (Dense)                      │ (None, 64)                  │           8,256 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_6 (Dropout)                  │ (None, 64)                  │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_8 (Dense)                      │ (None, 32)                  │           2,080 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_7 (Dropout)                  │ (None, 32)                  │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_9 (Dense)                      │ (None, 1)                   │              33 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
 Total params: 6,964,229 (26.57 MB)
 Trainable params: 2,321,409 (8.86 MB)
 Non-trainable params: 0 (0.00 B)
 Optimizer params: 4,642,820 (17.71 MB)

Learning Curve

Learning Curve

Class Distribution

       Count  Percentage
class                   
1       4461       50.16
0       4433       49.84

Additional Metrics

  • Total Samples: 8894
  • Imbalance Ratio: 1.01

Classification Report

              precision    recall  f1-score   support

     Class 0     0.9754    0.9820    0.9787       887
     Class 1     0.9819    0.9753    0.9786       892

    accuracy                         0.9786      1779
   macro avg     0.9787    0.9786    0.9786      1779
weighted avg     0.9787    0.9786    0.9786      1779

Metrics

  • True Positives (TP): 870
  • True Negatives (TN): 871
  • False Positives (FP): 16
  • False Negatives (FN): 22

Confusion Matrix

Confusion Matrix
MODEL: FEEDFORWARD_k4

Model Architecture

Model: "FEEDFORWARD_k4"
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓
┃ Layer (type)                         ┃ Output Shape                ┃         Param # ┃
┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩
│ dense_10 (Dense)                     │ (None, 256)                 │      38,890,240 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_8 (Dropout)                  │ (None, 256)                 │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_11 (Dense)                     │ (None, 128)                 │          32,896 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_9 (Dropout)                  │ (None, 128)                 │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_12 (Dense)                     │ (None, 64)                  │           8,256 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dropout_10 (Dropout)                 │ (None, 64)                  │               0 │
├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤
│ dense_13 (Dense)                     │ (None, 1)                   │              65 │
└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘
 Total params: 116,794,373 (445.54 MB)
 Trainable params: 38,931,457 (148.51 MB)
 Non-trainable params: 0 (0.00 B)
 Optimizer params: 77,862,916 (297.02 MB)

Learning Curve

Learning Curve

Class Distribution

       Count  Percentage
class                   
1       4461       50.16
0       4433       49.84

Additional Metrics

  • Total Samples: 8894
  • Imbalance Ratio: 1.01

Classification Report

              precision    recall  f1-score   support

     Class 0     0.9744    0.9887    0.9815       887
     Class 1     0.9886    0.9742    0.9814       892

    accuracy                         0.9815      1779
   macro avg     0.9815    0.9815    0.9814      1779
weighted avg     0.9816    0.9815    0.9814      1779

Metrics

  • True Positives (TP): 869
  • True Negatives (TN): 877
  • False Positives (FP): 10
  • False Negatives (FN): 23

Confusion Matrix

Confusion Matrix