greasycat/cpjump_m
收藏Hugging Face2026-03-08 更新2026-03-29 收录
下载链接:
https://hf-mirror.com/datasets/greasycat/cpjump_m
下载链接
链接失效反馈官方服务:
资源简介:
---
# For reference on dataset card metadata, see the spec: https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
# Doc / guide: https://huggingface.co/docs/hub/datasets-cards
{}
---
# CPJUMP Modified
<!-- Provide a quick summary of the dataset. -->
Modified/Extracted/Compressed Version of CPJUMP dataset created by (Chandrasekaran et al., 2024)
- Compression(JPEG 50) + 8Bit Conversion
- DINOv3 Large Extracted Feature Tokens
## Dataset Details
### Dataset Description
TBA
### Dataset Sources
<!-- Provide the basic links for the dataset. -->
- **Repository:** [Original Repo](https://github.com/jump-cellpainting/2024_Chandrasekaran_NatureMethods_CPJUMP1)
- **Paper:** (Chandrasekaran et al., 2024)
## Dataset Creation
### Curation Rationale
Original Dataset Size is over 3TB
Three million images and morphological profiles of cells treated with matched chemical and genetic perturbations
Srinivas Niranj Chandrasekaran, Beth A. Cimini, Amy Goodale, Lisa Miller, Maria Kost-Alimova, Nasim Jamali, John Doench, Briana Fritchman, Adam Skepner, Michelle Melanson, John Arevalo, Juan C. Caicedo, Daniel Kuhn, Desiree Hernandez, Jim Berstler, Hamdah Shafqat-Abbasi, David Root, Sussane Swalley, Shantanu Singh, Anne E. Carpenter
bioRxiv 2022.01.05.475090; doi: https://doi.org/10.1101/2022.01.05.475090
Now published in Nature Methods doi: 10.1038/s41592-024-02241-6
# 有关数据集卡片元数据的参考规范,请参阅:https://github.com/huggingface/hub-docs/blob/main/datasetcard.md?plain=1
# 文档/指南:https://huggingface.co/docs/hub/datasets-cards
{}
---
# CPJUMP 改良版
<!-- 请提供该数据集的简要概述。 -->
本数据集为Chandrasekaran等人(2024)所构建的CPJUMP数据集的改良、提取与压缩版本:
- 采用JPEG 50压缩方案与8位格式转换
- 提取了DINOv3 Large模型的特征Token(Token)
## 数据集详情
### 数据集描述
待补充(TBA)
### 数据集来源
<!-- 请提供该数据集的基础链接。 -->
- **仓库:** [原始仓库](https://github.com/jump-cellpainting/2024_Chandrasekaran_NatureMethods_CPJUMP1)
- **论文:** Chandrasekaran等人(2024)
## 数据集构建
### 筛选依据
原始数据集体量超过3TB,包含300万张图像以及经匹配化学与遗传扰动处理的细胞的形态学特征谱。
作者团队:Srinivas Niranj Chandrasekaran、Beth A. Cimini、Amy Goodale、Lisa Miller、Maria Kost-Alimova、Nasim Jamali、John Doench、Briana Fritchman、Adam Skepner、Michelle Melanson、John Arevalo、Juan C. Caicedo、Daniel Kuhn、Desiree Hernandez、Jim Berstler、Hamdah Shafqat-Abbasi、David Root、Sussane Swalley、Shantanu Singh、Anne E. Carpenter
该成果预印本发布于bioRxiv,编号2022.01.05.475090,DOI:https://doi.org/10.1101/2022.01.05.475090
后正式发表于《Nature Methods》期刊,DOI:10.1038/s41592-024-02241-6
提供机构:
greasycat



