Evaluating multiple next-generation sequencing derived tumor features to accurately predict DNA mismatch repair status
Bibliographic record
Abstract
Abstract Identifying tumor DNA mismatch repair deficiency (dMMR) is important for precision medicine. We assessed tumor features, individually and in combination, in whole-exome sequenced (WES) colorectal cancers (CRCs) and in panel sequenced CRCs, endometrial cancers (ECs) and sebaceous skin tumors (SSTs) for their accuracy in detecting dMMR. CRCs (n=300) with WES, where MMR status was determined by immunohistochemistry, were assessed for microsatellite instability (MSMuTect, MANTIS, MSIseq, MSISensor), COSMIC tumor mutational signatures (TMS) and somatic mutation counts. A 10-fold cross-validation approach (100 repeats) evaluated the dMMR prediction accuracy for 1) individual features, 2) Lasso statistical model and 3) an additive feature combination approach. Panel sequenced tumors (29 CRCs, 22 ECs, 20 SSTs) were assessed for the top performing dMMR predicting features/models using these three approaches. For WES CRCs, 10 features provided >80% dMMR prediction accuracy, with MSMuTect, MSIseq, and MANTIS achieving ≥99% accuracy. The Lasso model achieved 98.3%. The additive feature approach with ≥3/6 of MSMuTect, MANTIS, MSIseq, MSISensor, INDEL count or TMS ID2+ID7 achieved 99.7% accuracy. For the panel sequenced tumors, the additive feature combination approach of ≥3/6 achieved accuracies of 100%, 95.5% and 100%, for CRCs, ECs, and SSTs, respectively. The microsatellite instability calling tools performed well in WES CRCs, however, an approach combining tumor features may improve dMMR prediction in both WES and panel sequenced data across tissue types.
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 | 0.005 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.000 | 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".