A Graph-based Approach to Variant Extraction
By: Mark A. Santcroos , Walter A. Kosters , Mihai Lefter and more
Potential Business Impact:
Makes genetic descriptions easier and more accurate.
Accurate variant descriptions are of paramount importance in the field of genetics. The domain is confronted with increasingly complex variants, making it more challenging to generate proper variant descriptions. We present a graph based on all minimal alignments that is a complete representation of a variant and we provide three complementary extraction methods to derive variant descriptions from this graph. Our experiments show that our method in comparison with dbSNP results in identical HGVS descriptions for simple variants and more meaningful descriptions for complex variants.
Similar Papers
Incorporating LLM Embeddings for Variation Across the Human Genome
Applications
Helps find genetic causes of diseases faster.
GRAPE: Heterogeneous Graph Representation Learning for Genetic Perturbation with Coding and Non-Coding Biotype
Quantitative Methods
Finds important genes before experiments start.
An Allele-Centric Pan-Graph-Matrix Representation for Scalable Pangenome Analysis
Genomics
Makes understanding DNA easier for everyone.