面向生物医学数据的 AI

课题组发展适合生物医学数据结构的 AI 方法。此类数据通常具有异质性强、噪声高且受生物学约束等特点。我们关注深度学习、概率模型和新兴生成式方法，并将其应用于调控基因组学、单细胞轨迹推断、长读长变异解释和转化基因组学。

相关基础工作包括用于转录因子结合预测的 deep-learning imputation (Qin & Feng, 2017)、基于 Lisa 的整合式调控建模 (Qin et al., 2020)，以及用于高维多来源组学数据的统计整合方法 (Zang et al., 2016)。我们也参与单细胞分析开放问题的社区基准评测 (Luecken et al., 2025)，并参与发育轨迹和细胞命运推断综述 (Wang et al., 2021)，以确保方法能够与最强基线进行比较。

参考文献

2025

Nat Biotechnol

Defining and benchmarking open problems in single-cell analysis

Malte D Luecken, Scott Gigante, Daniel B Burkhardt, and 14 more authors

Nature Biotechnology, Jul 2025

DOI Bib HTML

@article{Luecken2025OpenProblems,
  title = {Defining and benchmarking open problems in single-cell analysis},
  author = {Luecken, Malte D and Gigante, Scott and Burkhardt, Daniel B and Cannoodt, Robrecht and Strobl, Daniel C and Markov, Nikolay S and Zappia, Luke and Palla, Giovanni and Lewis, Wesley and Dimitrov, Daniel and Vinyard, Michael E and Magruder, D S and Mueller, Michaela F and Andersson, Alma and Dann, Emma and Qin, Qian and others},
  journal = {Nature Biotechnology},
  volume = {43},
  number = {7},
  pages = {1035--1040},
  month = jul,
  year = {2025},
  doi = {10.1038/s41587-025-02694-w},
}

2021

Curr Opin Syst Biol

Current progress and potential opportunities to infer single-cell developmental trajectory and cell fate

L Wang, Q Zhang, Qian Qin, and 1 more author

Current Opinion in Systems Biology, 2021

DOI Bib

@article{Wang2021TrajectoryReview,
  title = {Current progress and potential opportunities to infer single-cell developmental trajectory and cell fate},
  author = {Wang, L and Zhang, Q and Qin, Qian and others},
  journal = {Current Opinion in Systems Biology},
  volume = {26},
  year = {2021},
  doi = {10.1016/j.coisb.2021.03.006}
}

2020

Genome Biol

Lisa: inferring transcriptional regulators through integrative modeling of public chromatin accessibility and ChIP-seq data

Qian Qin, J Fan, R Zheng, and 8 more authors

Genome Biology*Co-first authors , 2020

Bib HTML

@article{Qin2020Lisa,
  title = {{Lisa}: inferring transcriptional regulators through integrative modeling of public chromatin accessibility and {ChIP-seq} data},
  author = {Qin, Qian and Fan, J and Zheng, R and Wan, C and Mei, S and Wu, Q and Sun, H and Brown, M and Zhang, J and Meyer, C A and Liu, X S},
  journal = {Genome Biology},
  volume = {21},
  number = {1},
  pages = {32},
  year = {2020},
}

2017

PLoS Comput Biol

Imputation for transcription factor binding predictions based on deep learning

Qian Qin and Jianfeng Feng

PLoS Computational Biology, 2017

DOI Bib

@article{Qin2017DeepLearningTF,
  title = {Imputation for transcription factor binding predictions based on deep learning},
  author = {Qin, Qian and Feng, Jianfeng},
  journal = {PLoS Computational Biology},
  volume = {13},
  number = {2},
  pages = {e1005403},
  year = {2017},
  doi = {10.1371/journal.pcbi.1005403},
}

2016

Nat Commun

High-dimensional genomic data bias correction and data integration using MANCIE

C Zang, T Wang, K Deng, and 11 more authors

Nature Communications, 2016

Bib HTML

@article{Zang2016MANCIE,
  title = {High-dimensional genomic data bias correction and data integration using {MANCIE}},
  author = {Zang, C and Wang, T and Deng, K and Li, B and Hu, S and Qin, Qian and Xiao, T and Zhang, S and Meyer, C A and He, H H and Brown, M and Liu, J S and Xie, Y and Liu, X S},
  journal = {Nature Communications},
  volume = {7},
  pages = {11305},
  year = {2016},
}