Absolute Assignment of Breast Cancer Intrinsic Molecular Subtype
Bibliographic record
Abstract
BACKGROUND: Massively parallel gene expression profiling has provided a more objective, molecular-level characterization of breast cancer subtypes. Several bioinformatics tools are available to infer patient subtype from a gene expression profile including the well-studied PAM50. The specific algorithmic methods used in these tools require access to a broad patient dataset. The choice of subtype for an individual is determined relative to all other patients across the panel, making subtypes heavily dependent on the composition of the dataset. Our aim was to develop a bioinformatics approach assigning absolute breast cancer subtypes, independent of dataset composition. METHODS: Using a dataset of 4924 breast cancer patients, we defined a new bioinformatics approach: Absolute Intrinsic Molecular Subtyping (AIMS) that assigns subtype from a gene expression profile for an individual sample without the need for a large, diverse, and normalized dataset. We evaluated the agreement of AIMS with PAM50 and compared subtype assignment and prognostic value of the subtypes. We assessed AIMS' robustness using a benchmark set of tests including subtype reproducibility between technologies, gene removal, and normal gene expression contamination, and compared it with PAM50. All statistical tests, except where noted, were two-sided. RESULTS: AIMS vastly agreed with PAM50, with 76% and 77% agreement for cross validation and the test set, respectively, and the prognostic capacity of the intrinsic subtypes was preserved. AIMS is fully stable, and its absolute nature enables its use on a wide range of datasets and technologies, including RNA-seq. CONCLUSIONS: The instability of a breast cancer subtyping scheme like PAM50 could have important consequences in clinical management of patients. AIMS is a fully stable and robust subtyping scheme that recapitulates PAM50.
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 | 0.005 | 0.013 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| 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".