Leave-One-Bacteria-Out evaluation of descriptor-based and PSE-based pipelines.

NIAID Data Ecosystem2026-05-02 收录

数据链接：

https://figshare.com/articles/dataset/Leave-One-Bacteria-Out_evaluation_of_descriptor-based_and_PSE-based_pipelines_/29249092 数据链接链接失效反馈

官方服务：

资源简介：

Leave-One-Bacteria-Out evaluation of descriptor-based and PSE-based pipelines.

创建时间：

2025-06-05

Datasets for: AmpHGT: Expanding Prediction of Antimicrobial Activity in Peptides Containing Non-Canonical Amino Acids Using multi-View Constrained Heterogeneous Graph Transformer

肽活性预测

非经典氨基酸肽

This repository contains datasets used in `AmpHGT: Expanding Prediction of Antimicrobial Activity in Peptides Containing Non-Canonical Amino Acids Using Multi-View Constrained Heterogeneous Graph Tran

Zenodo2025-05-17 更新50

Additional file 4 of Optimal selection of molecular descriptors for antimicrobial peptides classification: an evolutionary feature weighting approach

肽活性预测

生物信息学特征选择

Predictions of antibacterial activity for DAMPD_ANTIBACTERIAL. Evaluation of different models with DAMPD_ANTIBACTERIAL after applying the best compromise solutions and four machine learning algorithms

Figshare2018-09-24 更新50

PEP-1 Mutated Peptides and their Physicochemical Properties Determined through ToxinPred

肽活性预测

药物设计

All mutations of PEP-1 (uncapped) and their physicochemical properties as determined by ToxinPred. ToxinPred uses an SVM or SVM + Motif Based algorithm to generate all possible single mutated analogs

Zenodo2026-04-03 更新30

Additional file 3 of Optimal selection of molecular descriptors for antimicrobial peptides classification: an evolutionary feature weighting approach

肽活性预测

描述符优化

Predictions of antimicrobial activity for APD3_AMP. Evaluation of different models with APD3_AMP after applying the best compromise solutions and four machine learning algorithms. This file shows the

NIAID Data Ecosystem50

CpACpP: In Silico Cell-Penetrating Anticancer Peptide Prediction Using a Novel Bioinformatics Framework

肽活性预测

细胞穿透性预测

Cell-penetrating anticancer peptides (Cp-ACPs) are considered promising candidates in solid tumor and hematologic cancer therapies. Current approaches for the design and discovery of Cp-ACPs trust the

NIAID Data Ecosystem50

Leave-One-Bacteria-Out evaluation of descriptor-based and PSE-based pipelines.

资源简介：

相关数据集