Publications (previous 10 years)

Matching entries: 0

settings...

Reyes V and Marchand-Maillet S (2026), "Assessing the Quality of Dimensionality Reduction Methods Based on Fuzzy Simplicial Sets", In Similarity Search and Applications. Cham , pp. 85-93. Springer Nature Switzerland.

[Abstract] [BibTeX] [DOI]

Abstract: Dimensionality reduction (DR) methods are often used to unveil important information from a dataset. Most advanced DR algorithms are non-linear, presenting better performance in the result at the cost of a lower interpretability of whether the reduced dataset resembles the original one. While new methods for dimensionality reduction arise, UMAP is still more used than any other, for its great performance and solid theoretical foundations. As an embedding operation, DR methods induce a loss of information. Evaluation measures can be used in order to quantify the (local) faithfulness of the reduction. In this paper we propose using fuzzy simplicial sets (the cornerstone of UMAP) to develop evaluation measures. We demonstrate the usefulness of these measures in detecting unfaithfulness by revealing structural distortions, and identifying when the reduction falls below the intrinsic dimensionality.

BibTeX:

@inproceedings{reyes:sisap2025,
  author = {Reyes, Victor and Marchand-Maillet, Stephane},
  editor = {Amato, Giuseppe and Mic, Vladimir and Traina, Agma and Messina, Nicola and Amsaleg, Laurent and Guðmundsson, Gylfi Þór and Jónsson, Björn Þór and Vadicamo, Lucia},
  title = {Assessing the Quality of Dimensionality Reduction Methods Based on Fuzzy Simplicial Sets},
  booktitle = {Similarity Search and Applications},
  publisher = {Springer Nature Switzerland},
  year = {2026},
  pages = {85--93},
  doi = {10.1007/978-3-032-06069-3_7}
}

Bini L and Marchand-Maillet S (2025), "LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations", CoRR. Vol. abs/2506.13344

[BibTeX] [DOI] [URL]

BibTeX:

@article{bini:arxiv2025,
  author = {Lorenzo Bini and Stéphane Marchand-Maillet},
  title = {LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations},
  journal = {CoRR},
  year = {2025},
  volume = {abs/2506.13344},
  url = {https://doi.org/10.48550/arXiv.2506.13344},
  doi = {10.48550/ARXIV.2506.13344}
}

Bini L and Marchand-Maillet S (2025), "Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations", CoRR. Vol. abs/2506.20362

[BibTeX] [DOI] [URL]

BibTeX:

@article{bini:arxiv2025a,
  author = {Lorenzo Bini and Stéphane Marchand-Maillet},
  title = {Self-Supervised Graph Learning via Spectral Bootstrapping and Laplacian-Based Augmentations},
  journal = {CoRR},
  year = {2025},
  volume = {abs/2506.20362},
  url = {https://doi.org/10.48550/arXiv.2506.20362},
  doi = {10.48550/ARXIV.2506.20362}
}

Bini L and Marchand-Maillet S (2025), "LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations", In ICML'2025 + GenBio Workshop: The Second Workshop on Generative AI and Biology. Vancouver

[BibTeX] [DOI] [URL]

BibTeX:

@inproceedings{bini:genbio2025,
  author = {Lorenzo Bini and Stéphane Marchand-Maillet},
  title = {LapDDPM: A Conditional Graph Diffusion Model for scRNA-seq Generation with Spectral Adversarial Perturbations},
  booktitle = {ICML'2025 + GenBio Workshop: The Second Workshop on Generative AI and Biology},
  year = {2025},
  url = {https://doi.org/10.48550/arXiv.2506.13344},
  doi = {10.48550/ARXIV.2506.13344}
}

Liarou M, Matthes T and Marchand-Maillet S (2025), "TimeFlow: A Density-Driven Pseudotime Method for Flow Cytometry Data Analysis", Cytometry Part A. Vol. 107(4), pp. 233-247.

[Abstract] [BibTeX] [DOI] [URL]

Abstract: ABSTRACT Pseudotime methods order cells undergoing differentiation from the least to the most differentiated. We developed TimeFlow, a new method for computing pseudotime in multi-dimensional flow cytometry datasets. TimeFlow tracks the differentiation path of each cell on a graph by following smooth changes in the cell population density. To compute the probability density function of the cells, it uses a normalizing flow model. We profiled bone marrow samples from three healthy patients using a 20-color antibody panel for flow cytometry and prepared datasets that ranged from 5,000 to 600,000 cells and included monocytes, neutrophils, erythrocytes, and B-cells at various maturation stages. TimeFlow computed fine-grained pseudotime for all the datasets, and the cell orderings were consistent with prior knowledge of human hematopoiesis. Experiments showed its potential in generalizing across patients and unseen cell states. We compared our method to 11 other pseudotime methods using in-house and public datasets and found very good performance for both linear and branching trajectories. TimeFlow's pseudotemporal orderings are useful for modeling the dynamics of cell surface proteins along linear trajectories. The biologically meaningful results in branching trajectories suggest the possibility of future applications with automated cell lineage detection. Code is available at https://github.com/MargaritaLiarou1/TimeFlow and data at https://osf.io/ykue7/.

BibTeX:

@article{liarou:cytometry2025,
  author = {Liarou, Margarita and Matthes, Thomas and Marchand-Maillet, Stéphane},
  title = {TimeFlow: A Density-Driven Pseudotime Method for Flow Cytometry Data Analysis},
  journal = {Cytometry Part A},
  year = {2025},
  volume = {107},
  number = {4},
  pages = {233-247},
  url = {https://onlinelibrary.wiley.com/doi/abs/10.1002/cyto.a.24928},
  doi = {10.1002/cyto.a.24928}
}

Zheng Y, Bensahla A, Bjelogrlic M, Zaghir J, Turbe H, Bednarczyk L, Gaudet-Blavignac C, Ehrsam J, Marchand-Maillet S and Lovis C (2025), "A scoping review of self-supervised representation learning for clinical decision making using EHR categorical data", npj Digital Medicine., June, 2025. Vol. 8(1) Springer Science and Business Media LLC.

[BibTeX] [DOI]

BibTeX:

@article{zheng:njp2025,
  author = {Zheng, Yuanyuan and Bensahla, Adel and Bjelogrlic, Mina and Zaghir, Jamil and Turbe, Hugues and Bednarczyk, Lydie and Gaudet-Blavignac, Christophe and Ehrsam, Julien and Marchand-Maillet, Stéphane and Lovis, Christian},
  title = {A scoping review of self-supervised representation learning for clinical decision making using EHR categorical data},
  journal = {npj Digital Medicine},
  publisher = {Springer Science and Business Media LLC},
  year = {2025},
  volume = {8},
  number = {1},
  doi = {10.1038/s41746-025-01692-1}
}

Bini L, Mojarrad FN, Liarou M, Matthes T and Marchand-Maillet S (2024), "FlowCyt: A Comparative Study of Deep Learning Approaches for Multi-Class Classification in Flow Cytometry Benchmarking", CoRR. Vol. abs/2403.00024

[BibTeX] [DOI] [URL]

BibTeX:

@article{bini:arxiv2024a,
  author = {Lorenzo Bini and Fatemeh Nassajian Mojarrad and Margarita Liarou and Thomas Matthes and Stéphane Marchand-Maillet},
  title = {FlowCyt: A Comparative Study of Deep Learning Approaches for Multi-Class Classification in Flow Cytometry Benchmarking},
  journal = {CoRR},
  year = {2024},
  volume = {abs/2403.00024},
  url = {https://doi.org/10.48550/arXiv.2403.00024},
  doi = {10.48550/ARXIV.2403.00024}
}