Precise interpretation and prioritization of sequence variants with Onkopus for supporting molecular tumor boards
Kurz, N. S.; Kornrumpf, K.; Tucholski, T.; Drofenik, K.; König, A.; Beissbarth, T.; Dönitz, J.
Show abstract
One of the major challenges in precision medicine is the identification of pathogenic, actionable variants and the selection of personalized treatments. We present Onkopus, a variant interpretation framework, based on a modular architecture, for interpreting and prioritizing genetic alterations in cancer patients. We show that aggregation and harmonization of clinical databases, coupled with querying of these databases to varying associated biomarkers, can increase the number of identified therapeutic options. We present a protein analysis of mutated sites and show that protein characteristics can provide potential indicators for the functional impairment of variants of unknown significance. Variant interpretation systems like Onkopus have the potential to significantly enhance the performance of personalized treatments, as they reduce the time required for variant interpretation and manual evaluation of personalized treatments, while maintaining reproducibility and traceability. We provide a free public instance of Onkopus at https://mtb.bioinf.med.uni-goettingen.de/onkopus.
Matching journals
The top 9 journals account for 50% of the predicted probability mass.
Similar papers in this journal
- A Platform for Oncogenomic Reporting and Interpretation 95%
- Machine learning-based tissue of origin classification for cancer of unknown primary diagnostics using genome-wide mutation features 94%
- DeMAG predicts the effects of variants in clinically actionable genes by integrating structural and evolutionary epistatic features 94%
Similar papers in this journal
- Scalable and efficient DNA sequencing analysis on different compute infrastructures aiding variant discovery 94%
- Phen2Gene: Rapid Phenotype-Driven Gene Prioritization for Rare Diseases 93%
- Supervised learning with word embeddings derived from PubMed captures latent knowledge about protein kinases and cancer 93%
Similar papers in this journal
- MetaRNN: Differentiating Rare Pathogenic and Rare Benign Missense SNVs and InDels Using Deep Learning 94%
- ClinSV: Clinical grade structural and copy number variant detection from whole genome sequencing data 94%
- OncoGEMINI: Software for Investigating Tumor Variants From Multiple Biopsies With Integrated Cancer Annotations 93%
"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.