用于预测膀胱癌突变类型的多级集成模型

数据集获取（Figshare）

• 源站标题：A multilevel ensemble model for predicting mutation types in bladder cancer
• DOI：10.6084/m9.figshare.30723653.v1
• 发布日期：2025-11-26
• 文件数：7 个
• 文件总体积：111.96 KB
• 源站页面：https://tandf.figshare.com/articles/dataset/A_multilevel_ensemble_model_for_predicting_mutation_types_in_bladder_cancer/30723653

命令行下载

curl -L -o "Table S1- list of cell lines.docx" "https://ndownloader.figshare.com/files/59870387"
curl -L -o "Table S2- Sample of the Dataset Used.docx" "https://ndownloader.figshare.com/files/59870390"
curl -L -o "Table S3- Number of Observations for each Class.docx" "https://ndownloader.figshare.com/files/59870393"
curl -L -o "Table S4- Distribution of Classes after Splitting the Dataset.docx" "https://ndownloader.figshare.com/files/59870396"
curl -L -o "Table S5- P Values obtained from Chi-Square Test.docx" "https://ndownloader.figshare.com/files/59870399"
curl -L -o "Table S7- Hyperparameters for the Final ANN.docx" "https://ndownloader.figshare.com/files/59870402"
curl -L -o "Table S8- Confusion Matrix from the Predictions made by the ANN.docx" "https://ndownloader.figshare.com/files/59870405"

文件清单

• Table S1- list of cell lines.docx（17.45 KB）
• Table S2- Sample of the Dataset Used.docx（15.78 KB）
• Table S3- Number of Observations for each Class.docx（14.27 KB）
• Table S4- Distribution of Classes after Splitting the Dataset.docx（15.24 KB）
• Table S5- P Values obtained from Chi-Square Test.docx（15.19 KB）
• Table S7- Hyperparameters for the Final ANN.docx（18.89 KB）
• Table S8- Confusion Matrix from the Predictions made by the ANN.docx（15.15 KB）

文件总体积 111.96 KB（源站 API 实测）。

数据加载示例（图像类）

from PIL import Image
import glob, os

files = (glob.glob(os.path.join(path, "**", "*.png"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.jpg"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tif"), recursive=True))
print("图像文件数:", len(files))
img = Image.open(files[0]); print("尺寸/模式:", img.size, img.mode)

# torchvision Dataset 方式:
# from torchvision import datasets
# ds = datasets.ImageFolder(path)  # 要求 子目录=类别

目录组织与标注格式以源站说明和下载后实际文件为准。

数据说明

In urinary bladder cancer, early diagnosis plays a key role for effective patient management. Moreover, accurate prediction of genetic mutations plays a critical role in identifying biomarkers for prognosis and therapy.
Mutation types and other details were collected from publicly available datasets of human bladder cancer cell lines. A multilevel ensemble model was designed by integrating an Artificial Neural Network (ANN) with a Random Forest (RF) classifier. The model was trained and validated on DNA sequence data to predict mutation types, specifically base pair insertions and deletions. Performance was compared against traditional machine learning models including SVM, naive Bayes, and decision trees.
The proposed ensemble model achieved nearly 95% prediction accuracy, significantly outperforming conventional approaches. The integration of ANN and RF improved classification robustness and reliability in mutation type prediction. This study presents the development of a predictive model for mutation detection in bladder cancer using an AI-based approach.
This novel study highlights the potential of AI techniques for early detection of mutations in urinary bladder cancer. The highly accurate prediction capability of the developed model offers promise for identifying diagnostic and prognostic mutational landscapes to guide future therapeutic strategies.

许可

CC BY 4.0

引用

学术使用请引用 DOI 10.6084/m9.figshare.30723653.v1（source: https://tandf.figshare.com/articles/dataset/A_multilevel_ensemble_model_for_predicting_mutation_types_in_bladder_cancer/30723653）。