Abstract 3364: Diagnosing Li-Fraumeni syndrome from the somatic genome
Bibliographic record
Abstract
Abstract Background: Li-Fraumeni syndrome (LFS) is a hereditary cancer predisposition syndrome caused by germline mutations in the tumor suppressor gene TP53. LFS is estimated to occur in 1:1000 - 1:5000 people and is associated with a 80% lifetime cancer risk. This syndrome is diagnosed using familial cancer history and germline TP53 sequencing; however, clinical heterogeneity and variants of unknown significance limit diagnostic precision. Accurate diagnosis is imperative to implement surveillance for secondary malignancies and familial genetic testing. Methods: We hypothesized that LFS cancers evolve uniquely from sporadic cancers, implying that the somatic genomes of LFS patients exhibit distinct characteristics that can infer the predisposition syndrome. To investigate this, we interrogated mutational signatures, TP53 copy number, TP53 loss of heterozygosity, ploidy, and the incidence of chromothripsis in tumor compared to normal samples (blood or fibroblast) of individuals with germline TP53 mutations (n=27), somatic TP53 mutations (n=17) and WT for TP53 (n=158). We created a random forest model with 10-fold cross validation to determine if somatic features could diagnose LFS. Results: No signatures were significantly associated with LFS (Wilcoxon rank-sum test, Benjamin-Hochberg FDR correction). As previously reported in the literature, LFS compared to non-LFS cancers in our cohort were more likely to: be hyperdiploid (odds ratio (OR) = 11.83, FDR < 0.0001, Fisher exact test), have undergone TP53 loss of heterozygosity (OR = 23.15, FDR < 0.0001, Fisher exact test) and experience chromothripsis (OR = 7.76, FDR < 0.001, Fisher exact test). The area under the receiver operating curve (AUROC) for our random forest model with 10-fold cross validation was 0.90, the area under the precision recall curve (AUPRC) was 0.59, the positive predictive value (PPV) was 0.70, the negative predictive value (NPV) was 0.93 and the F1-score was 0.52. This implies that the somatic genomic features are reliable indicators of this germline syndrome. We have obtained access to a future 50 LFS samples from the Pediatric Cancer Genome Project dataset, which we hope will improve our model’s performance. Conclusion: We have developed a machine learning tool that uses somatic features to identify LFS, a germline cancer predisposition syndrome. As the importance of precision oncology becomes apparent, a tool to identify LFS patients from the somatic genome will facilitate early diagnosis. This will allow individuals to enter a surveillance program for early detection of secondary tumors, leading to improved outcomes. Citation Format: Brianne Laverty, Vallijah Subasri, Nicholas Light, David Malkin. Diagnosing Li-Fraumeni syndrome from the somatic genome [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 3364.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".