Elucidating tumor heterogeneity from spatially resolved transcriptomics data by multi-view graph collaborative learning
Bibliographic record
Abstract
Abstract Spatially resolved transcriptomics (SRT) technology enables us to gain novel insights into tissue architecture and cell development, especially tumors. However, the lack of effective methods for exploiting biological contexts (e.g., global position information) and multi-view features has severely hindered the disentangling ability for tissue heterogeneity. Here, we proposed stMVC, a multi-view graph collaborative learning model that integrates histology, gene expression, spatial location, and biological contexts in analyzing SRT data by attention. Specifically, stMVC adopting semi-supervised graph attention autoencoder separately learns view-specific representations for each of two graphs, i.e., histological similarity graph by visual features and spatial location graph by physical coordinates, and then simultaneously integrates two-view graphs for robust representations via learning weights of different views with attention in a semi-supervision manner from biological contexts. Benchmark studies of stMVC on 12 slices from the human cortex, demonstrate its superior capability in detecting tissue structure, visualizing trajectory relationships between different layers, and denoising data. In particular, in the breast cancer study, stMVC identified new disease-related cell-states and their transition cell-states, which were further validated by the functional and survival analysis of independent clinical data. Those results not only provided novel biological insights into tumor heterogeneity but also demonstrated clinical and prognostic applications from SRT data. The software is available at https://github.com/cmzuo11/stMVC.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".