CancerVar: an Artificial Intelligence empowered platform for clinical interpretation of somatic mutations in cancer
Bibliographic record
Abstract
ABSTRACT Several knowledgebases, such as CIViC and OncoKB, have been manually curated to support clinical interpretations of a limited number of “hotspot” somatic mutations in cancer, yet discrepancies or even conflicting interpretations have been observed among these knowledgebases. Additionally, while these knowledgebases have been extremely useful, they typically cannot interpret novel mutations, which may also have functional and clinical impacts in cancer. To address these challenges, we developed an automated interpretation tool called CancerVar (Cancer Variants interpretation) to score more than 12.9 million somatic mutations and classify them into four tiers: strong clinical significance, potential clinical significance, uncertain clinical significance, and benign/likely benign, based on the AMP/ASCO/CAP 2017 guideline. Considering that the AMP/ASCO/CAP rule-based scoring system may have inherent limitations, such as lack of a clear guidance on weighing different pieces of functional evidence or unclear definition for certain clinical evidence, it may cause misinterpretation for certain variants that have functional impacts but no proven clinical significance. To address this issue, we further introduced a deep learning-based scoring system to predict oncogenicity of mutations by semi-supervised generative adversarial network (SGAN) method using both functional and clinical evidence. We trained and validated the SGAN model on 5,234 somatic mutations from an in-house database of clinical reports on cancer patients, and achieved a good performance when testing on 6,226 variants that were curated by us through literature search. We also compared the prediction with several independent datasets and showed great utility in classifying variants with previously unknown interpretations. CancerVar is also incorporated into a web server that can generate automated texts with summarized descriptive interpretations, such as diagnostic, prognostic, targeted drug responses and clinical trial information for many hotspot mutations. In summary, CancerVar can facilitate clinical interpretation and hypothesis generation for somatic mutations, and greatly reduce manual workload for retrieving relevant evidence and implementing existing guidelines.
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 | 0.003 | 0.013 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.005 | 0.002 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.003 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.006 | 0.003 |
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".