数据集获取

git clone https://github.com/Sadik90/ACP-Dataset.git

curl -L -o repo.zip https://github.com/Sadik90/ACP-Dataset/archive/refs/heads/main.zip
unzip repo.zip

源站 README 摘录（使用方式）

ACP-Dataset

Release of Anticancer Peptide Dataset Integrated from Multiple Databases for Cancer Therapeutics Research
Introduction:
The release of the anticancer peptide dataset represents a significant advancement in cancer therapeutics research, aimed at facilitating the development of novel peptide-based treatments for various cancer types. This dataset is meticulously curated from multiple databases, including CancerPPD, APD3, LAMP, and UniProt, with a special focus on integrating peptides from non-secretory proteins as a negative dataset. By compiling diverse sources of peptide information, this dataset offers a comprehensive resource for researchers to explore the potential of peptides in cancer therapy.
Dataset Description:
The dataset comprises a diverse collection of anticancer peptides derived from various biological sources, encompassing different cancer types and stages. Each peptide is annotated with detailed information, including its sequence, origin, experimental evidence, and relevant references. Furthermore, the dataset includes a carefully curated set of non-secretory proteins, serving as a negative dataset for comparative analysis.
Integration with Cancer Genomic Datasets:
To enhance the utility of the anticancer peptide dataset, researchers can integrate it with cancer genomic datasets such as TCGA (The Cancer Genome Atlas) and Cancer Genome databases. By correlating peptide sequences with cancer subtypes and genomic alterations, researchers can identify potential therapeutic targets and elucidate the molecular mechanisms underlying cancer progression.
Potential Applications:
The integrated dataset enables researchers to explore various applications in cancer therapeutics, including:
Targeted Therapy: By combining peptide sequences with DNA methylation data, researchers can develop targeted therapies that exploit specific methylation patterns associated with cancer subtypes.
Splicing Therapy: Integration with alternate splicing data allows for the identification of splice variants associated with cancer progression, paving the way for splicing-based therapeutic interventions.
De Novo Peptide Design: Leveraging advanced generative models such as LSTM (Long Short-Term Memory), RNN (Recurrent Neural Network), VAE (Variational Autoencoder), and GAN (Generative Adversarial Network), researchers can generate novel anticancer peptides tailore

数据加载示例（表格/文本类）

import pandas as pd, glob, os

files = (glob.glob(os.path.join(path, "**", "*.csv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.tsv"), recursive=True)
       + glob.glob(os.path.join(path, "**", "*.xlsx"), recursive=True))
print("数据文件:", files)
df = pd.read_csv(files[0])
print(df.shape); print(df.columns.tolist()); print(df.head(3))

完整仓库：github.com/Sadik90/ACP-Dataset