Matches in SemOpenAlex for { <https://semopenalex.org/work/W4387233997> ?p ?o ?g. }
- W4387233997 abstract "Cancer is a heterogeneous disease that demands precise molecular profiling for better understanding and management. RNA-sequencing has emerged as a potent tool to unravel the transcriptional heterogeneity. However, large-scale characterization of cancer transcriptomes is hindered by the limitations of costs and tissue accessibility. Here, we develop SEQUOIA , a deep learning model employing a transformer architecture to predict cancer transcriptomes from whole-slide histology images. We pre-train the model using data from 2,242 normal tissues, and the model is fine-tuned and evaluated in 4,218 tumor samples across nine cancer types. The results are further validated across two independent cohorts compromising 1,305 tumors. The highest performance was observed in cancers from breast, kidney and lung, where SEQUOIA accurately predicted 13,798, 10,922 and 9,735 genes, respectively. The well predicted genes are associated with the regulation of inflammatory response, cell cycles and hypoxia-related metabolic pathways. Leveraging the well predicted genes, we develop a digital signature to predict the risk of recurrence in breast cancer. While the model is trained at the tissue-level, we showcase its potential in predicting spatial gene expression patterns using spatial transcriptomics datasets. SEQUOIA deciphers clinically relevant gene expression patterns from histology images, opening avenues for improved cancer management and personalized therapies." @default.
- W4387233997 created "2023-10-02" @default.
- W4387233997 creator A5038622280 @default.
- W4387233997 creator A5044805939 @default.
- W4387233997 creator A5051462279 @default.
- W4387233997 creator A5072236307 @default.
- W4387233997 creator A5078274543 @default.
- W4387233997 creator A5078586485 @default.
- W4387233997 creator A5083042926 @default.
- W4387233997 creator A5085496964 @default.
- W4387233997 creator A5003265350 @default.
- W4387233997 date "2023-09-30" @default.
- W4387233997 modified "2023-10-18" @default.
- W4387233997 title "Digital profiling of cancer transcriptomes from histology images with grouped vision attention" @default.
- W4387233997 cites W1979141644 @default.
- W4387233997 cites W2005895632 @default.
- W4387233997 cites W2018838463 @default.
- W4387233997 cites W2110119381 @default.
- W4387233997 cites W2128215249 @default.
- W4387233997 cites W2133059825 @default.
- W4387233997 cites W2157076315 @default.
- W4387233997 cites W2161109798 @default.
- W4387233997 cites W2504220184 @default.
- W4387233997 cites W2760946358 @default.
- W4387233997 cites W2905071914 @default.
- W4387233997 cites W2940627982 @default.
- W4387233997 cites W2948930564 @default.
- W4387233997 cites W2961217357 @default.
- W4387233997 cites W2982402173 @default.
- W4387233997 cites W3010739860 @default.
- W4387233997 cites W3033721673 @default.
- W4387233997 cites W3035647551 @default.
- W4387233997 cites W3035974941 @default.
- W4387233997 cites W3036882247 @default.
- W4387233997 cites W3039376097 @default.
- W4387233997 cites W3041397352 @default.
- W4387233997 cites W3043835773 @default.
- W4387233997 cites W3044996171 @default.
- W4387233997 cites W3046305306 @default.
- W4387233997 cites W3104755560 @default.
- W4387233997 cites W3113328935 @default.
- W4387233997 cites W3122263858 @default.
- W4387233997 cites W3126609356 @default.
- W4387233997 cites W3128646645 @default.
- W4387233997 cites W3135547872 @default.
- W4387233997 cites W3159302505 @default.
- W4387233997 cites W3161790216 @default.
- W4387233997 cites W3175752499 @default.
- W4387233997 cites W3188077199 @default.
- W4387233997 cites W3194280965 @default.
- W4387233997 cites W3199725740 @default.
- W4387233997 cites W3205605830 @default.
- W4387233997 cites W4200620750 @default.
- W4387233997 cites W4282579661 @default.
- W4387233997 cites W4283395547 @default.
- W4387233997 cites W4291972535 @default.
- W4387233997 cites W4309944312 @default.
- W4387233997 cites W4312890670 @default.
- W4387233997 cites W4313591779 @default.
- W4387233997 cites W4317884302 @default.
- W4387233997 cites W4321614454 @default.
- W4387233997 cites W4353065773 @default.
- W4387233997 cites W4361292362 @default.
- W4387233997 cites W4381681791 @default.
- W4387233997 cites W4381839504 @default.
- W4387233997 cites W4383896402 @default.
- W4387233997 cites W4385987383 @default.
- W4387233997 cites W4387130771 @default.
- W4387233997 doi "https://doi.org/10.1101/2023.09.28.560068" @default.
- W4387233997 hasPubMedId "https://pubmed.ncbi.nlm.nih.gov/37808782" @default.
- W4387233997 hasPublicationYear "2023" @default.
- W4387233997 type Work @default.
- W4387233997 citedByCount "0" @default.
- W4387233997 crossrefType "posted-content" @default.
- W4387233997 hasAuthorship W4387233997A5003265350 @default.
- W4387233997 hasAuthorship W4387233997A5038622280 @default.
- W4387233997 hasAuthorship W4387233997A5044805939 @default.
- W4387233997 hasAuthorship W4387233997A5051462279 @default.
- W4387233997 hasAuthorship W4387233997A5072236307 @default.
- W4387233997 hasAuthorship W4387233997A5078274543 @default.
- W4387233997 hasAuthorship W4387233997A5078586485 @default.
- W4387233997 hasAuthorship W4387233997A5083042926 @default.
- W4387233997 hasAuthorship W4387233997A5085496964 @default.
- W4387233997 hasBestOaLocation W43872339971 @default.
- W4387233997 hasConcept C104317684 @default.
- W4387233997 hasConcept C111919701 @default.
- W4387233997 hasConcept C121608353 @default.
- W4387233997 hasConcept C150194340 @default.
- W4387233997 hasConcept C162317418 @default.
- W4387233997 hasConcept C18431079 @default.
- W4387233997 hasConcept C187191949 @default.
- W4387233997 hasConcept C2778811002 @default.
- W4387233997 hasConcept C2779733811 @default.
- W4387233997 hasConcept C41008148 @default.
- W4387233997 hasConcept C530470458 @default.
- W4387233997 hasConcept C54355233 @default.
- W4387233997 hasConcept C59822182 @default.
- W4387233997 hasConcept C60644358 @default.
- W4387233997 hasConcept C70721500 @default.
- W4387233997 hasConcept C86803240 @default.