Article

Pan-cancer tumour classification and risk stratification from whole-genome somatic variants via dual-task representation learning

2026-03-04

Abstract excerpt

Tumour typing from whole-genome sequencing is increasingly accurate, yet molecular subtyping from somatic variants remains challenging because of tumour heterogeneity and inconsistent clinical annotations. Here, we present Mutation-Attention Dual-Task (MuAt2), a Transformer model that jointly classifies histological tumour types and subtypes directly from somatic single-nucleotide variants, indels and structural v...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: b32c8863-b406-5670-ac6f-9baf7f6b2c24
DOI: 10.64898/2026.03.02.26347318

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

Pan-cancer tumour classification and risk stratification from whole-genome somatic variants via dual-task representation learningDOI 10.64898/2026.03.02.26347318Read

Mutation-Attention (MuAt): deep representation learning of somatic mutations for tumour typing and subtyping.Semantic proximity Read

Mutation-Attention (MuAt): deep representation learning of somatic mutations for tumour typing and subtypingSemantic proximity Read

Improved tumor-only variant calling and mutation burden estimation with VarNet-T.Semantic proximity Read

<i>muat</i> : portable transformer-based method for tumour classification and representation learning from somatic variantsSemantic proximity Read

Generalist large language models complement tailor-made predictors for tumor genomics interpretationSemantic proximity Read

Translating clinical gene sequencing into a foundational representation of tumor subtypeSemantic proximity Read

Deep Learning Model for Tumor Type Prediction using Targeted Clinical Genomic Sequencing DataSemantic proximity Read

MS-ConTab: multi-scale contrastive learning of mutation signatures for Pan-Cancer representation and stratification.Semantic proximity Read

Transformer models of mutation risk at base-pair resolution identify non-coding hotspot cancer driver mutationsSemantic proximity Read

A Foundation Model for the Cancer GenomeSemantic proximity Read

A deep learning system accurately classifies primary and metastatic cancers using passenger mutation patterns.Semantic proximity Read

VariantMedium: sensitive and generalizable somatic point mutation calling with 3D DenseNets trained and evaluated on experimental data.Semantic proximity Read