#11 · Single-cell
Transcriptomic models are evaluated by transfer design, calibration and identifiability
The dominant thread is that the validation design is itself under test. The HNSCC Elastic Net is trained on GDSC cell lines and checked on TCGA-HNSC and GSE65858. The source-selection study asks whether baseline transcriptomic similarity ranks source contexts beyond tissue lineage for held-out drug responses. ssGSEA3.0 replaces feature-label permutation with feature-level bootstrap resampling to improve significance calibration. The decidualization work uses identifiability-aware models, simulations and GEO re-analysis to separate temporal delay from amplitude loss. The glioma reanalysis of 252,106 cells examines whether response direction is coherent across malignant states. The COPD network CNN nominates biomarker candidates tested on public transcriptomic data, but the excerpt reports no performance figures, so it fits this thread only loosely.
Preprints
Network-guided identification of candidate biomarkers for COPD-associated comorbidities using deep learning and real-world transcriptomic data
CNN functional-distance model on a protein network nominates COPD-comorbidity biomarker candidates, tested on public transcriptomic data.
Predicting Pathway Dependency in Head and Neck Squamous Cell Carcinoma from Hallmark Transcriptomic Features
Transcriptome-based Elastic Net framework inferring Hallmark pathway dependency in HNSCC from GDSC cell lines, validated on TCGA-HNSC and GSE65858 with HPV and…
Transcriptomic similarity guides source selection beyond tissue lineage
Tests whether baseline transcriptomic similarity ranks source contexts for predicting held-out drug responses; ranking adds signal beyond tissue matching…
ssGSEA3.0: Feature-Level Bootstrap Resampling for Robust Assessment of Statistical Significance
ssGSEA3.0 replaces feature-label permutation with feature-level bootstrap resampling for per-sample pathway and PTM-SEA significance, improving calibration and…
Single-cell geometry of drug responses across malignant glioma states
Reanalyzes a public scRNA-seq drug-treated glioma slice dataset (252,106 cells) and finds response direction is reproducibly coherent across glioma states and…
Evaluating the Identifiability of Temporal Delay and Response Attenuation in Endometrial Decidualization
Identifiability-aware models separate temporal delay from amplitude loss in endometrial transcriptomic responses, with simulations and GEO re-analysis.
Topic history
| Date | Rank |
|---|---|
| #11 | |
| #12 | |
| #8 | |
| #17 | |
| #28 | |
| #26 | |
| #11 | |
| #26 | |
| #38 | |
| #31 | |
| #35 | |
| #37 | |
| #2 | |
| #4 | |
| #2 | |
| #6 | |
| #2 | |
| #2 | |
| #1 | |
| #34 | |
| #24 | |
| #22 | |
| #25 | |
| #27 | |
| #26 | |
| #19 | |
| #19 | |
| #26 | |
| #36 | |
| #27 | |
| #30 | |
| #33 | |
| #9 | |
| #21 | |
| #17 | |
| #21 | |
| #9 | |
| #5 | |
| #6 | |
| #18 | |
| #22 | |
| #38 | |
| #18 | |
| #23 | |
| #27 | |
| #33 | |
| #32 | |
| #32 | |
| #40 |