Nicholas Ho

Hello! I'm Nicholas, a Computational Biology PhD student at Carnegie Mellon University, advised by Professor Jian Ma and Professor Eric Xing. My research is supported by the NSF Graduate Research Fellowship. I previously interned on the pretraining team in GenBio.AI.

I develop biological foundation models and study how their representations uncover new insights and improve counterfactual predictions.

Here are some highlights:

EMBER — Gene-centric foundation model for contextualized gene representations that support multigene perturbation prediction. (Video Explainer)
Cell Perturbation Benchmarking — Trained and evaluated diffusion, flow-matching, schrodinger-bridge and graph neural network models.
AIDO.Cell — Led a team for 600M-parameter single-cell foundation model for scaling pretraining with minimal priors.
AIDO.DNA — In charge of pretraining 7B-parameter genome foundation model on 256 A100 GPUs for variant effect prediction and sequence generation.
HEIMDALL — Examined how tokenizer design affects transfer learning in single-cell pretrained models.

Nicholas Ho playing with a yoyo on a rooftop

nzh [AT] cs.cmu.edu

I got some spatial transcriptomics and biophysics experience too. Feel free to reach out — I'm always happy to chat!

In my spare time I enjoy yoyoing.

Latest Posts

Soon!

Publications & Preprints

EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations

Nicholas Ho, Eric P. Xing, and Jian Ma

bioRxiv, 2026

DOI Bib HTML Code

@article{ho2026ember,
  title = {{EMBER: Contextualized gene representations enable compositional prediction across cellular perturbations}},
  author = {Ho, Nicholas and Xing, Eric P. and Ma, Jian},
  year = {2026},
  journal = {bioRxiv},
  doi = {10.64898/2026.10.28.762655},
  url = {https://doi.org/10.64898/2026.10.28.762655},
}

HEIMDALL: Disentangling Tokenizer Design for Robust Transfer in Single-Cell Foundation Models

Ellie Haber^*, Shahul Alam^*, Nicholas Ho^*, Renming Liu, Evan Trop, Shaoheng Liang, Muyu Yang, Spencer Krieger, and Jian Ma

Cell Genomics, 2026

Bib HTML

@article{haber2025heimdall,
  title = {{HEIMDALL: Disentangling Tokenizer Design for Robust Transfer in Single-Cell Foundation Models}},
  author = {Haber, Ellie and Alam, Shahul and Ho, Nicholas and Liu, Renming and Trop, Evan and Liang, Shaoheng and Yang, Muyu and Krieger, Spencer and Ma, Jian},
  year = {2026},
  journal = {Cell Genomics},
  url = {https://www.biorxiv.org/content/10.1101/2025.11.09.687403v3},
}

AIDO.Tissue: Spatial Cell-Guided Pretraining for Scalable Spatial Transcriptomics Foundation Model

Jing Gong^*, Yixuan Wang^*, Nicholas Ho, Xingyi Cheng, Le Song, and Eric Xing

In ICML 2025 Generative AI and Biology (GenBio) Workshop, 2025

Bib HTML

@inproceedings{gong2025aidotissue,
  title = {{AIDO.Tissue: Spatial Cell-Guided Pretraining for Scalable Spatial Transcriptomics Foundation Model}},
  author = {Gong, Jing and Wang, Yixuan and Ho, Nicholas and Cheng, Xingyi and Song, Le and Xing, Eric},
  year = {2025},
  booktitle = {ICML 2025 Generative AI and Biology (GenBio) Workshop},
  url = {https://www.biorxiv.org/content/10.1101/2025.07.04.663102v1},
}

Foundation Models Improve Perturbation Response Prediction

Elijah Cole, Geert-Jan Huizing, Sohan Addagudi, Nicholas Ho, Euxhen Hasanaj, Merel Kuijs, Toby Johnstone, Maria Carilli, Alec Davi, Caleb Ellington, Christoph Feinauer, Pan Li, Romain Menegaux, Shahin Mohammadi, Yanjun Shao, Josiah Zhang, Emma Lundberg, Le Song, Ziv Bar-Joseph, and Eric P. Xing

bioRxiv, 2026

Bib HTML

@article{cole2026perturbation,
  title = {{Foundation Models Improve Perturbation Response Prediction}},
  author = {Cole, Elijah and Huizing, Geert-Jan and Addagudi, Sohan and Ho, Nicholas and Hasanaj, Euxhen and Kuijs, Merel and Johnstone, Toby and Carilli, Maria and Davi, Alec and Ellington, Caleb and Feinauer, Christoph and Li, Pan and Menegaux, Romain and Mohammadi, Shahin and Shao, Yanjun and Zhang, Josiah and Lundberg, Emma and Song, Le and Bar-Joseph, Ziv and Xing, Eric P.},
  year = {2026},
  journal = {bioRxiv},
  url = {https://www.biorxiv.org/content/10.64898/2026.02.18.706454v2},
}

Scaling Dense Representations for Single Cell with Transcriptome-Scale Context

Nicholas Ho, Caleb N. Ellington, Jinyu Hou, Sohan Addagudi, Shentong Mo, Tianhua Tao, Dian Li, Yonghao Zhuang, Hongyi Wang, Xingyi Cheng, Le Song, and Eric P. Xing

In NeurIPS Workshop on AI for New Drug Modalities, 2024

Bib HTML

@inproceedings{ho2024aidocell,
  title = {{Scaling Dense Representations for Single Cell with Transcriptome-Scale Context}},
  author = {Ho, Nicholas and Ellington, Caleb N. and Hou, Jinyu and Addagudi, Sohan and Mo, Shentong and Tao, Tianhua and Li, Dian and Zhuang, Yonghao and Wang, Hongyi and Cheng, Xingyi and Song, Le and Xing, Eric P.},
  year = {2024},
  booktitle = {NeurIPS Workshop on AI for New Drug Modalities},
  url = {https://www.biorxiv.org/content/10.1101/2024.11.28.625303v1},
}

Accurate and General DNA Representations Emerge from Genome Foundation Models at Scale

Caleb N. Ellington, Ning Sun, Nicholas Ho, Tianhua Tao, Sazan Mahbub, Dian Li, Yonghao Zhuang, Hongyi Wang, Le Song, and Eric P. Xing

In NeurIPS Workshop on AI for New Drug Modalities, 2024

Bib HTML

@inproceedings{ellington2024aidodna,
  title = {{Accurate and General DNA Representations Emerge from Genome Foundation Models at Scale}},
  author = {Ellington, Caleb N. and Sun, Ning and Ho, Nicholas and Tao, Tianhua and Mahbub, Sazan and Li, Dian and Zhuang, Yonghao and Wang, Hongyi and Song, Le and Xing, Eric P.},
  year = {2024},
  booktitle = {NeurIPS Workshop on AI for New Drug Modalities},
  url = {https://www.biorxiv.org/content/10.1101/2024.12.01.625444v1},
}

Multimodal AI predicts clinical outcomes of drug combinations from preclinical data

Yepeng Huang, Xiaorui Su, Varun Ullanat, Intae Moon, Ivy Liang, Lindsay Clegg, Damilola Olabode, Ruthie Johnson, Nicholas Ho, Megan Gibbs, Alexander Gusev, Bino John, and Marinka Zitnik

arXiv preprint, 2025

DOI Bib HTML Code

@article{huang2025madrigal,
  title = {{Multimodal AI predicts clinical outcomes of drug combinations from preclinical data}},
  author = {Huang, Yepeng and Su, Xiaorui and Ullanat, Varun and Moon, Intae and Liang, Ivy and Clegg, Lindsay and Olabode, Damilola and Johnson, Ruthie and Ho, Nicholas and Gibbs, Megan and Gusev, Alexander and John, Bino and Zitnik, Marinka},
  year = {2025},
  journal = {arXiv preprint},
  archiveprefix = {arXiv},
  doi = {10.48550/arXiv.2503.02781},
  url = {https://arxiv.org/abs/2503.02781},
}

Learning Free Energy Pathways through Reinforcement Learning of Adaptive Steered Molecular Dynamics

Nicholas Ho, John Kevin Cava, John Vant, Ankita Shukla, Jacob Miratsky, Pavan Turaga, Ross Maciejewski, and Abhishek Singharoy

In Machine Learning In Structural Biology (MLSB) Workshop at the 36th Conference on Neural Information Processing Systems, 2022

Bib HTML

@inproceedings{ho2022pathways,
  title = {{Learning Free Energy Pathways through Reinforcement Learning of Adaptive Steered Molecular Dynamics}},
  author = {Ho, Nicholas and Cava, John Kevin and Vant, John and Shukla, Ankita and Miratsky, Jacob and Turaga, Pavan and Maciejewski, Ross and Singharoy, Abhishek},
  year = {2022},
  booktitle = {Machine Learning In Structural Biology (MLSB) Workshop at the 36th Conference on Neural Information Processing Systems},
  url = {https://www.biorxiv.org/content/10.1101/2022.10.04.510845v1},
}