Subtype-MMCC: multimodal contrastive clustering approach for cancer subtype discovery with multi-omics data
Bibliographic record
Abstract
The diversity and complexity of cancer pose significant challenges in creating target treatment strategies. Identifying molecular subtypes of cancer is crucial for recognizing patients with distinct molecular profiles, thereby enhancing the accuracy of diagnosis, prognosis, and treatment decisions. With recent advancements in technology, there’s been a significant increase in the availability of multi-omics data, which is instrumental in the understanding of different cancer subtypes. However, accurately subtyping cancer is difficult due to the high dimensionality and heterogeneity of omics data. Current research in subtype identification often consolidates multi-omics data into a single dataset through simple concatenation and then employs machine learning models to derive a lower-dimensional representation, neglecting the unique distributions of different omics data types. Additionally, they separate representation learning and clustering into two stages, initially learning latent representations and then applying clustering algorithms, leading to suboptimal results due to overlooking the intrinsic clustering structures in the initial learning phase. To address these limitations, we propose a novel deep unsupervised learning model, Subtype-MMCC (Multi-modal Contrastive Clustering) that combines a multi-modal architecture with decoupled contrastive clustering to create an end-to-end framework. Tested on eight TCGA cancer datasets, Subtype-MMCC outperforms existing clustering methods, with its efficacy further validated by survival and clinical analysis outcomes.
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 | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".