Conference
Influence of Gender-Specific Data Imbalance on scGPT Fine-Tuning for Single-Cell Genomics
| Title: | Influence of Gender-Specific Data Imbalance on scGPT Fine-Tuning for Single-Cell Genomics |
|---|---|
| Authors: | Al Amin, Mohammad Aman Ullah, Filienko, Daniil, Qin, Hong |
| Source: | Computer Science Faculty Publications |
| Publisher Information: | ODU Digital Commons |
| Publication Year: | 2025 |
| Collection: | Old Dominion University: ODU Digital Commons |
| Subject Terms: | Artificial intelligence—Sex differences, Bias in artificial intelligence, Big data—Sex differences, Bioinformatics, Cell populations—Sex differences, Cells—Classification—Data processing, Computational biology, Data imbalance (Machine learning), Gene expression—Analysis, Genomics—Data processing, Health disparities—Sex factors, Hematopoietic cells—Classification, Immune system—Sex differences, Machine learning—Sex differences, Medical informatics—Moral and ethical aspects, Monocytes—Sex differences, Natural killer cells—Sex differences, Precision medicine—Sex differences, Sex differences (Biology), Sex factors in disease, Single-cell RNA sequencing, T cells—Sex differences, Transformers (Machine learning), Artificial Intelligence and Robotics, Bioethics and Medical Ethics, Genetics and Genomics |
| Description: | The transformer-based foundation model scGPT has demonstrated strong capabilities in analyzing high-dimensional single-cell RNA sequencing data. However, the impact of demographic factors, particularly gender, on model performance remains insufficiently understood. Gender is known to influence cell type compositions in the immune system. Here, using the gender-sensitive cell type composition in immune system, we comprehensively evaluate how the gender-sensitive imbalance of training data influences the performance of scGPT in cell type predictions. We fine-tune scGPT on male-only, female-only, and mixed-gender subsets from two large-scale datasets containing immune cells. We use a logit difference to measure the confidence gap between the true label and the actual model prediction. The confidence gap is zero for perfect classifications and negative for incorrect predictions. We find that training and testing configurations with aligned gender distributions generally show higher prediction confidence, while mismatched gender during training and testing, especially when training excludes one gender, leads to substantial confidence drops. We also find that training with mixed-gender data promotes more balanced generalization, but does not eliminate all biases. We conclude that gender-specific data imbalance, represented by immune cell type subpopulation variation between women and men, can influence fine-tuning of scGPT and its performance in cell type classification, highlighting the importance of addressing such demographic biases in biomedical AI models. |
| Document Type: | conference object |
| Language: | unknown |
| Relation: | https://digitalcommons.odu.edu/computerscience_fac_pubs/419; https://doi.org/10.1609/aaaiss.v7i1.36914 |
| DOI: | 10.1609/aaaiss.v7i1.36914 |
| Availability: | https://digitalcommons.odu.edu/computerscience_fac_pubs/419 https://doi.org/10.1609/aaaiss.v7i1.36914 |
| Rights: | © 2023, Association for the Advancement of Artificial Intelligence. All rights reserved. "In the Returned Rights section of the AAAI copyright form, authors are specifically granted back the right to use their own papers for noncommercial uses, such as inclusion in their dissertations or the right to deposit their own papers in their institutional repositories, provided there is proper attribution. The published version is not available for posting outside the AAAI Digital Library." |
| Accession Number: | edsbas.D7EC9F01 |
| Database: | BASE |
| DOI: | 10.1609/aaaiss.v7i1.36914 |
|---|