| 项目编号 |
PRJCA028510 |
| 项目标题 |
PEAKFORMER: Transformer-based Precise Peak Identification and Quantification Tool |
| 涉及领域 |
Medical |
| 数据类型 |
metabolomics
|
| 物种名称 |
Homo sapiens
|
| 描述信息 |
We developed PeakFormer, a deep learning method based on object detection designed to detect complete peak signals. Our algorithm harnesses the capabilities of transformers, training on over 20,000 annotated EIC and ensuring unique predictions through bipartite matching. Without retraining, PeakFormer achieves over 90% accuracy in distinguishing true and false peaks on the EVA dataset. We performed interpretability analysis of the encoder and decoder using visualization techniques. |
| 样品范围 |
clinical cohorts |
| 发布日期 |
2024-07-25 |
| 项目资金来源 |
| 机构 |
项目类型 |
授权项目ID |
授权项目名称 |
| National Natural Science Foundation of China (NSFC)
|
Major Research Plan
|
91957120
|
Based on spalial melabolomics, the metabolic mode of aldose reductase inpromoting the occurence and development of liver cancer was investigated
|
| National Natural Science Foundation of China (NSFC)
|
General Program
|
21974114
|
Mass specrometry-based immunometabolic landscape analysis of lung metastases in breast cancer
|
|
|
| 提交者 |
Shuhai
Lin (shuhai@xmu.edu.cn)
|
| 提交单位 |
Xiamen University |
| 提交日期 |
2024-07-25 |
