Accurate and Efficient Phylogenetic Inference through End-To-End Deep Learning
文献类型：期刊论文
| 作者 | Zhang, Xinru2,3; Ding, Shizhe2,3; Yu, Chungong1,2,3; Zhao, Jianquan2,3; Bu, Dongbo1,2,3 |
| 刊名 | MOLECULAR BIOLOGY AND EVOLUTION
 |
| 出版日期 | 2025-11-01 |
| 卷号 | 42期号:11页码:14 |
| 关键词 | phylogenetic inference phylogenetic tree deep learning |
| ISSN号 | 0737-4038 |
| DOI | 10.1093/molbev/msaf260 |
| 英文摘要 | Accurate phylogenetic inference is crucial for understanding evolutionary relationships among species. Deep learning technique has been introduced for phylogenetic inference; however, the existing deep learning-based approaches either suffer from limited accuracy as they split inference into several disjoint stages, or exhibit low efficiency and hardly apply to the cases with over 20 species. Here, we present an accurate and efficient approach to phylogenetic inference. Our approach, called NeuralNJ, employs an end-to-end framework that directly constructs phylogenetic trees from the input taxa, thus effectively avoiding the inaccuracy incurred by the split inference stages. The key innovation of NeuralNJ lies in its learnable neighbor joining mechanism, which iteratively joins neighbors guided by learned priority scores and thereby achieves accurate tree reconstruction. The inference accuracy is further enhanced through incorporating reinforcement learning-based tree search. Using both simulated and empirical data as representatives, we demonstrate that NeuralNJ can effectively infer phylogenetic tree with improved computational efficiency and reconstruction accuracy. The study paves the way to accurate and efficient phylogenetic inference for hundreds of taxa in complex evolutionary scenarios. |
| 资助项目 | National Natural Science Foundation of China[32271297] ; National Natural Science Foundation of China[82130055] ; National Key Research and Development Program of China[2024YFC3405500] |
| WOS研究方向 | Biochemistry & Molecular Biology ; Evolutionary Biology ; Genetics & Heredity |
| 语种 | 英语 |
| WOS记录号 | WOS:001615870300001 |
| 出版者 | OXFORD UNIV PRESS |
| 源URL | [http://119.78.100.204/handle/2XEOYT63/43095]  |
| 专题 | 中国科学院计算技术研究所 |
| 通讯作者 | Ding, Shizhe; Bu, Dongbo |
| 作者单位 | 1.Henan Acad Sci, Cent China Artificial Intelligence Res Inst, Zhengzhou 450046, Peoples R China 2.Chinese Acad Sci, Inst Comp Technol, SKLP, Beijing 100190, Peoples R China 3.Univ Chinese Acad Sci, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Zhang, Xinru,Ding, Shizhe,Yu, Chungong,et al. Accurate and Efficient Phylogenetic Inference through End-To-End Deep Learning[J]. MOLECULAR BIOLOGY AND EVOLUTION,2025,42(11):14. |
| APA | Zhang, Xinru,Ding, Shizhe,Yu, Chungong,Zhao, Jianquan,&Bu, Dongbo.(2025).Accurate and Efficient Phylogenetic Inference through End-To-End Deep Learning.MOLECULAR BIOLOGY AND EVOLUTION,42(11),14. |
| MLA | Zhang, Xinru,et al."Accurate and Efficient Phylogenetic Inference through End-To-End Deep Learning".MOLECULAR BIOLOGY AND EVOLUTION 42.11(2025):14. |
入库方式： OAI收割
来源：计算技术研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。