Donor-Aware scRNA-seq Benchmarks for IBD Classification
Donor-level disease classification from single-cell RNA sequencing (scRNA-seq) requires strict donor-aware cross-validation: naive pipelines that split cells randomly conflate training and test donors, inflating reported performance through pseudoreplication. We present a donor-aware benchmark evaluating three feature representations across two independent IBD cohorts: centered log-ratio (CLR) transformed cell-type composition, GatedStructuralCFN dependency embeddings, and scVI variational autoencoder latent embeddings. The cohorts are the SCP259 ulcerative colitis atlas (UC vs. Healthy, n=30 donors, 51 cell types) and the Kong 2023 Crohn's disease atlas (CD vs. Healthy, n=71 donors, 55-68 cell types across three intestinal regions). Compartment-stratified CLR composition achieves AUROC 0.956 +/- 0.061 on SCP259; GatedStructuralCFN on the same features achieves 0.978 +/- 0.050. In the Kong cohort, CFN achieves its best performance in the colon region (0.960 +/- 0.055 after feature filtering), exceeding linear CLR (0.900 +/- 0.100), while terminal ileum classification is dominated by linear models (CatBoost CLR 0.967 +/- 0.075 vs. CFN 0.811 +/- 0.164). Cross-dataset transfer (CD->UC, four shared cell types) achieves AUC 0.833 with XGBoost CLR; the reverse direction performs at chance. CFN edge stability analysis shows that compartment-wise composition eliminates spurious unit-sum-induced instability present in global composition (Jaccard 0.026 vs. top-20 recurrence 1.0). CFN shows a consistent numerical advantage over linear models in the colon region of CD (AUROC 0.960 vs. 0.900), though no inter-method comparison reached statistical significance at n<=34 donors per region. Compartment-aware feature construction is critical for both classification performance and structural interpretability. Code: https://github.com/Jonathan-321/sfn-scrna-study
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Single-Cell RNA-seq Synthesis with Latent Diffusion Model
The single-cell RNA sequencing (scRNA-seq) technology enables researchers to study complex biological systems and diseases with high resolution. The central challenge is synthesizing enough scRNA-seq samples; insufficien…
scRNA-seq Data Clustering by Cluster-aware Iterative Contrastive Learning
Single-cell RNA sequencing (scRNA-seq) enables researchers to analyze gene expression at single-cell level. One important task in scRNA-seq data analysis is unsupervised clustering, which helps identify distinct cell typ…
ClusteringContrastive LearningRepresentation LearningZero-Shot Quantization via Weight-Space Arithmetic
We show that robustness to post-training quantization (PTQ) is a transferable direction in weight space. We call this direction the quantization vector: extracted from a donor task by simple weight-space arithmetic, it c…
Image ClassificationOptimizing Donor Outreach for Blood Collection Sessions: A Scalable Decision Support Framework
Blood donation centers face challenges in matching supply with demand while managing donor availability. Although targeted outreach is important, it can cause donor fatigue via over-solicitation. Effective recruitment re…
Closed-Loop Design of Proton Donors for Lithium-Mediated Ammonia Synthesis with Interpretable Models and Molecular Machine Learning
In this work, we experimentally determined the efficacy of several classes of proton donors for lithium-mediated electrochemical nitrogen reduction in a tetrahydrofuran-based electrolyte, an attractive alternative method…
ClassificationDeep LearningGeneral Classification