Abstract 4279: Method for identifying microsatellite instability high DNA abnormality samples
Bibliographic record
Abstract
Abstract Introduction: Tissue samples with high microsatellite instability (MSI-H) can be indicators of cancerous tumors that are sensitive to certain types of cancer treatments (e.g., immune modulation-checkpoint inhibitor treatment). MSI-H regions can be identified with Polymerase Chain Reaction (PCR) based assays and next-generation sequencing (NGS). However, these MS regions are susceptible to PCR and sequencing errors. We developed a computational method for detecting microsatellite instability high (MSI-H) tumors using next-generation sequencing (NGS) data to accurately identify true MSI-H samples from MS-Stable samples based on an analysis of these MS regions. Methods: We developed a method for classifying a tissue sample as being microsatellite instability high (MSI-H) without using normal tissue from the same person which doubles the sequencing cost. Furthermore, the algorithm was designed for amplicon targeted assays where it is not always feasible to choose the most predictive MS sites. The machine learning classifier (ML) algorithm is a random forest algorithm with a training set of known MSI-H and MS-Stable samples to learn the relationship between the MSI status and the distribution of repeats in microsatellite regions of genomes using 21 MS loci. A negative control was used to normalize the ML features and therefore reduce the effects of PCR and sequencing errors in noisy MS sites. Results: The MSI detection algorithm was validated in analytical and clinical samples achieving an accuracy greater than 98%. Analytical samples consist of commercial reference standard samples and well characterized FFPE treated cell-lines. Clinical samples consists of clinical FFPE tumor samples from cancer patients that were orthogonally validated using immunohistochemistry (expression of mismatch repair genes, i.e., MMRnormal vs MMRd) on tumor tissue and/or the Promega MSI PCR using matched tumor/normal. All experiments were performed in the Imagia Canexia Health CAP, CLIA, DAP certified laboratory using the Find It assay standard operating procedures for detecting genomic mutations in solid tumor tissue. Conclusions: The MSI detection algorithm can accurately identify samples with MSI-H tumors. When used in a clinical setting, these patients can then be directed to treatments such as immune-checkpoint inhibitors. Citation Format: Dilmi Perera, Sahand Khakabi, Ka Mun Nip, Sonal Brahmbatt, Adrian Kense, Kevin Tam, David Mulder, Melissa McConechy, David Huntsman, Ruth Miller, Rosalía Aguirre-Hernández. Method for identifying microsatellite instability high DNA abnormality samples. [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 4279.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.007 | 0.009 |
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".