Figure 5 from DeePathNet: A Transformer-Based Deep Learning Model Integrating Multiomic Data with Cancer Pathways

<p>Performance evaluation of breast cancer subtype classification. <b>A,</b> Model evaluation by cross-validation. The <i>x</i>-axis represents the macro-average <i>F</i><sub>1</sub>-score, and the <i>y</i>-axis represents accuracy. &...

Full description

Saved in:
Bibliographic Details
Main Author: Zhaoxiang Cai (20445441) (author)
Other Authors: Rebecca C. Poulos (20445444) (author), Adel Aref (20445447) (author), Phillip J. Robinson (20445450) (author), Roger R. Reddel (15031827) (author), Qing Zhong (20445453) (author)
Published: 2024
Subjects:
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:<p>Performance evaluation of breast cancer subtype classification. <b>A,</b> Model evaluation by cross-validation. The <i>x</i>-axis represents the macro-average <i>F</i><sub>1</sub>-score, and the <i>y</i>-axis represents accuracy. <b>B,</b> Radar chart showing the model ranks across the set of four metrics. A larger enclosed area represents better classification performance. <b>C,</b> Performance metrics showing generalization errors for DeePathNet and random forest when using CPTAC data as the independent test set for validation. <b>D,</b> Confusion matrix showing generalization errors when using CPTAC data as the independent test set for validation. Statistics are annotated in the same way as described in <a href="#fig4" target="_blank">Fig. 4C</a>.</p>