Loading
Variant effect prediction uses computation to guess whether a DNA change damages a protein or matters clinically, before or instead of laboratory evidence.
Variant calling, per Wikipedia, identifies single nucleotide and other variants from sequencing reads; effect prediction is the next step, scoring each variant's likely consequence from conservation, protein structure or, latterly, sequence and protein language models. Predictions feed ACMG-style classification as supporting evidence, and genomic foundation models such as Evo 2 have claimed zero-shot pathogenicity prediction, a claim that has to be tested on held-out variants with clinical labels.
Showing the technology this term belongs to: Evo 2 (Arc Institute, NVIDIA).
Shares HGVS variant nomenclature, Variant calling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Zero-shot prediction, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Variant calling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Variant calling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Genomic and protein language models: Evo 2, Enformer, ESM, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Autoregressive (next-token) modelling, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Zero-shot prediction, Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.
Shares Cancer AI vocabulary (CanSim terms map) and the tag cansim-terms.