Matches in SemOpenAlex for { <https://semopenalex.org/work/W4383553846> ?p ?o ?g. }
- W4383553846 abstract "Abstract Background Cancer genome sequencing enables accurate classification of tumours and tumour subtypes. However, prediction performance is still limited using exome-only sequencing and for tumour types with low somatic mutation burden such as many paediatric tumours. Moreover, the ability to leverage deep representation learning in discovery of tumour entities remains unknown. Methods We introduce here Mutation-Attention (MuAt), a deep neural network to learn representations of simple and complex somatic alterations for prediction of tumour types and subtypes. In contrast to many previous methods, MuAt utilizes the attention mechanism on individual mutations instead of aggregated mutation counts. Results We trained MuAt models on 2587 whole cancer genomes (24 tumour types) from the Pan-Cancer Analysis of Whole Genomes (PCAWG) and 7352 cancer exomes (20 types) from the Cancer Genome Atlas (TCGA). MuAt achieved prediction accuracy of 89% for whole genomes and 64% for whole exomes, and a top-5 accuracy of 97% and 90%, respectively. MuAt models were found to be well-calibrated and perform well in three independent whole cancer genome cohorts with 10,361 tumours in total. We show MuAt to be able to learn clinically and biologically relevant tumour entities including acral melanoma, SHH-activated medulloblastoma, SPOP -associated prostate cancer, microsatellite instability, POLE proofreading deficiency, and MUTYH -associated pancreatic endocrine tumours without these tumour subtypes and subgroups being provided as training labels. Finally, scrunity of MuAt attention matrices revealed both ubiquitous and tumour-type specific patterns of simple and complex somatic mutations. Conclusions Integrated representations of somatic alterations learnt by MuAt were able to accurately identify histological tumour types and identify tumour entities, with potential to impact precision cancer medicine." @default.
- W4383553846 created "2023-07-08" @default.
- W4383553846 creator A5002667996 @default.
- W4383553846 creator A5002670402 @default.
- W4383553846 creator A5003048867 @default.
- W4383553846 creator A5004439161 @default.
- W4383553846 creator A5005526067 @default.
- W4383553846 creator A5007549481 @default.
- W4383553846 creator A5008723999 @default.
- W4383553846 creator A5008780949 @default.
- W4383553846 creator A5009253078 @default.
- W4383553846 creator A5009530521 @default.
- W4383553846 creator A5010443784 @default.
- W4383553846 creator A5013910686 @default.
- W4383553846 creator A5014458985 @default.
- W4383553846 creator A5017834529 @default.
- W4383553846 creator A5020080514 @default.
- W4383553846 creator A5021709237 @default.
- W4383553846 creator A5022393909 @default.
- W4383553846 creator A5022457689 @default.
- W4383553846 creator A5023430588 @default.
- W4383553846 creator A5025952851 @default.
- W4383553846 creator A5027079581 @default.
- W4383553846 creator A5028725974 @default.
- W4383553846 creator A5033721426 @default.
- W4383553846 creator A5034347591 @default.
- W4383553846 creator A5037665542 @default.
- W4383553846 creator A5039633676 @default.
- W4383553846 creator A5039916547 @default.
- W4383553846 creator A5040035281 @default.
- W4383553846 creator A5040127668 @default.
- W4383553846 creator A5044755722 @default.
- W4383553846 creator A5045553488 @default.
- W4383553846 creator A5046092979 @default.
- W4383553846 creator A5047253474 @default.
- W4383553846 creator A5047435332 @default.
- W4383553846 creator A5048005458 @default.
- W4383553846 creator A5048271276 @default.
- W4383553846 creator A5049126232 @default.
- W4383553846 creator A5051307930 @default.
- W4383553846 creator A5055284086 @default.
- W4383553846 creator A5056156268 @default.
- W4383553846 creator A5056273880 @default.
- W4383553846 creator A5058403686 @default.
- W4383553846 creator A5061349790 @default.
- W4383553846 creator A5061790199 @default.
- W4383553846 creator A5062137975 @default.
- W4383553846 creator A5062194841 @default.
- W4383553846 creator A5062534223 @default.
- W4383553846 creator A5063495458 @default.
- W4383553846 creator A5065495238 @default.
- W4383553846 creator A5066428890 @default.
- W4383553846 creator A5066580354 @default.
- W4383553846 creator A5069454171 @default.
- W4383553846 creator A5069712725 @default.
- W4383553846 creator A5071136927 @default.
- W4383553846 creator A5072894526 @default.
- W4383553846 creator A5072895240 @default.
- W4383553846 creator A5078032321 @default.
- W4383553846 creator A5080857719 @default.
- W4383553846 creator A5081912788 @default.
- W4383553846 creator A5084305193 @default.
- W4383553846 creator A5086631630 @default.
- W4383553846 creator A5088727176 @default.
- W4383553846 creator A5089630665 @default.
- W4383553846 creator A5091002491 @default.
- W4383553846 creator A5091132026 @default.
- W4383553846 creator A5091596735 @default.
- W4383553846 creator A5092424012 @default.
- W4383553846 date "2023-07-07" @default.
- W4383553846 modified "2023-10-10" @default.
- W4383553846 title "Mutation-Attention (MuAt): deep representation learning of somatic mutations for tumour typing and subtyping" @default.
- W4383553846 cites W1562795224 @default.
- W4383553846 cites W1565385417 @default.
- W4383553846 cites W1803857749 @default.
- W4383553846 cites W1898603749 @default.
- W4383553846 cites W1940241680 @default.
- W4383553846 cites W1989456683 @default.
- W4383553846 cites W1994847090 @default.
- W4383553846 cites W2062455051 @default.
- W4383553846 cites W2076774554 @default.
- W4383553846 cites W2086239585 @default.
- W4383553846 cites W2118124054 @default.
- W4383553846 cites W2152061559 @default.
- W4383553846 cites W2160713553 @default.
- W4383553846 cites W2197921176 @default.
- W4383553846 cites W2266041843 @default.
- W4383553846 cites W2515164523 @default.
- W4383553846 cites W2589112207 @default.
- W4383553846 cites W2606616407 @default.
- W4383553846 cites W2612428976 @default.
- W4383553846 cites W2737542366 @default.
- W4383553846 cites W2768211711 @default.
- W4383553846 cites W2772677509 @default.
- W4383553846 cites W2773455549 @default.
- W4383553846 cites W2794804602 @default.
- W4383553846 cites W2796153844 @default.
- W4383553846 cites W2800388620 @default.
- W4383553846 cites W2810664395 @default.
- W4383553846 cites W2889326414 @default.