Posts by Collection

portfolio

scPEFT: Parameter Efficient Fine-Tuning single-cell Large Language Models

Published: January 14, 2026

A framework that efficiently calibrates general scLLMs for out-of-context use cases

pathCLIP: Detection of genes and gene relations from biological pathway figures through image-text contrastive learning

Published: January 14, 2026

A pathway figure curation system for identifying genes and gene relations from pathway figures.

RESEPT: a deep-learning framework for characterizing and visualizing tissue architecture from spatially resolved transcriptomics

Published: January 14, 2026

a deep-learning framework for characterizing and visualizing tissue architecture from spatially resolved transcriptomics

publications

MusiteDeep: a deep-learning based webserver for protein post-translational modification site prediction and visualization

Published in Nucleic Acids Research, 2020

A deep-learning framework for protein PTM and binding site prediction and visualization.

Citation: Duolin Wang, Dongpeng Liu, Jiakang Yuchi, Fei He, Yuexu Jiang, Siteng Cai, Jingyi Li, Dong Xu. "MusiteDeep: a deep-learning based webserver for protein post-translational modification site prediction and visualization". Nucleic Acids Research, Volume 48, Issue W1, 02 July 2020, Pages W140–W146
Download Paper

Identifying Genes and Their Interactions from Pathway Figures and Text in Biomedical Articles

Published in 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021

utilizing prompt-based learning to adapt the state-of-the-art image segmentation foundation model Segment Anything Model (SAM) for cryo-EM.

Citation: F. He et al., "Identifying Genes and Their Interactions from Pathway Figures and Text in Biomedical Articles." 2021 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2021. 398-405
Download Paper

Define and visualize pathological architectures of human tissues from spatially resolved transcriptomics using deep learning

Published in Computational and Structural Biotechnology Journal, 2022

A deep-learning framework for characterizing and visualizing tissue architecture from spatially resolved transcriptomics.

Citation: Chang, Yuzhou, Fei He, Juexin Wang, Shuo Chen, Jingyi Li, Jixin Liu, Yang Yu et al. "Define and visualize pathological architectures of human tissues from spatially resolved transcriptomics using deep learning." Computational and structural biotechnology journal 20 (2022): 4600-4617.
Download Paper

Meta-learning for T cell receptor binding specificity and beyond

Published in Nature Machine Intelligence, 2023

Comment on a new approach that uses meta-learning to improve predictions for binding to peptides for which no or little binding data exists.

Citation: Wang, D., He, F., Yu, Y. et al. "Meta-learning for T cell receptor binding specificity and beyond". Nature Machine Intelligence 5, 337–339 (2023).
Download Paper

pathclip: Detection of genes and gene relations from biological pathway figures through image-text contrastive learning

Published in IEEE Journal of Biomedical and Health Informatics, 2024

A pathway figure curation system for identifying genes and gene relations from pathway figures.

Citation: F. He et al., "pathCLIP: Detection of Genes and Gene Relations From Biological Pathway Figures Through Image-Text Contrastive Learning,". IEEE Journal of Biomedical and Health Informatics, vol. 28, no. 8, pp. 5007-5019
Download Paper

Adapting Segment Anything Model (SAM) through Prompt-based Learning for Enhanced Protein Identification in Cryo-EM Micrographs

Published in 2024 IEEE International Conference on Medical Artificial Intelligence (MedAI), 2024

utilizing prompt-based learning to adapt the state-of-the-art image segmentation foundation model Segment Anything Model (SAM) for cryo-EM.

Citation: F. He et al., "Adapting Segment Anything Model (SAM) through Prompt-based Learning for Enhanced Protein Identification in Cryo-EM Micrographs." 2024 IEEE International Conference on Medical Artificial Intelligence (MedAI), 2024, 9-20
Download Paper

Predicting the location of coordinated metal ion-ligand binding sites using geometry-aware graph neural networks

Published in Computational and Structural Biotechnology Journal, 2024

A novel structure-based method that transforms the 3-dimensional structure of a protein into a point cloud representation and then designs a geometry-aware graph neural network to learn the local structural properties of each amino acid residue under specific ligand-binding supervision.

Citation: Essien, Clement, Ning Wang, Yang Yu, Salhuldin Alqarghuli, Yongfang Qin, Negin Manshour, Fei He, and Dong Xu. "Predicting the location of coordinated metal ion-ligand binding sites using geometry-aware graph neural networks." Computational and Structural Biotechnology Journal 27 (2025): 137-148.
Download Paper