Literature DB >> 35581644

Identifying common transcriptome signatures of cancer by interpreting deep learning models.

Anupama Jha1, Mathieu Quesnel-Vallières2,3, David Wang4, Andrei Thomas-Tikhonenko5,6,7, Kristen W Lynch8, Yoseph Barash9,10.   

Abstract

BACKGROUND: Cancer is a set of diseases characterized by unchecked cell proliferation and invasion of surrounding tissues. The many genes that have been genetically associated with cancer or shown to directly contribute to oncogenesis vary widely between tumor types, but common gene signatures that relate to core cancer pathways have also been identified. It is not clear, however, whether there exist additional sets of genes or transcriptomic features that are less well known in cancer biology but that are also commonly deregulated across several cancer types.
RESULTS: Here, we agnostically identify transcriptomic features that are commonly shared between cancer types using 13,461 RNA-seq samples from 19 normal tissue types and 18 solid tumor types to train three feed-forward neural networks, based either on protein-coding gene expression, lncRNA expression, or splice junction use, to distinguish between normal and tumor samples. All three models recognize transcriptome signatures that are consistent across tumors. Analysis of attribution values extracted from our models reveals that genes that are commonly altered in cancer by expression or splicing variations are under strong evolutionary and selective constraints. Importantly, we find that genes composing our cancer transcriptome signatures are not frequently affected by mutations or genomic alterations and that their functions differ widely from the genes genetically associated with cancer.
CONCLUSIONS: Our results highlighted that deregulation of RNA-processing genes and aberrant splicing are pervasive features on which core cancer pathways might converge across a large array of solid tumor types.
© 2022. The Author(s).

Entities:  

Keywords:  Cancer genomics; Deep learning; Transcriptomics

Mesh:

Year:  2022        PMID: 35581644      PMCID: PMC9112525          DOI: 10.1186/s13059-022-02681-3

Source DB:  PubMed          Journal:  Genome Biol        ISSN: 1474-7596            Impact factor:   17.906


  89 in total

1.  Adjusting batch effects in microarray expression data using empirical Bayes methods.

Authors:  W Evan Johnson; Cheng Li; Ariel Rabinovic
Journal:  Biostatistics       Date:  2006-04-21       Impact factor: 5.899

2.  Hypoxia-Induced WSB1 Promotes the Metastatic Potential of Osteosarcoma Cells.

Authors:  Ji Cao; Yijie Wang; Rong Dong; Guanyu Lin; Ning Zhang; Jing Wang; Nengming Lin; Yongchuan Gu; Ling Ding; Meidan Ying; Qiaojun He; Bo Yang
Journal:  Cancer Res       Date:  2015-09-30       Impact factor: 12.701

3.  A transforming KIF5B and RET gene fusion in lung adenocarcinoma revealed from whole-genome and transcriptome sequencing.

Authors:  Young Seok Ju; Won-Chul Lee; Jong-Yeon Shin; Seungbok Lee; Thomas Bleazard; Jae-Kyung Won; Young Tae Kim; Jong-Il Kim; Jin-Hyoung Kang; Jeong-Sun Seo
Journal:  Genome Res       Date:  2011-12-22       Impact factor: 9.043

4.  Identifying common transcriptome signatures of cancer by interpreting deep learning models.

Authors:  Anupama Jha; Mathieu Quesnel-Vallières; David Wang; Andrei Thomas-Tikhonenko; Kristen W Lynch; Yoseph Barash
Journal:  Genome Biol       Date:  2022-05-17       Impact factor: 17.906

5.  WSB1 overcomes oncogene-induced senescence by targeting ATM for degradation.

Authors:  Jung Jin Kim; Seung Baek Lee; Sang-Yeop Yi; Sang-Ah Han; Sun-Hyun Kim; Jong-Min Lee; Seo-Yun Tong; Ping Yin; Bowen Gao; Jun Zhang; Zhenkun Lou
Journal:  Cell Res       Date:  2016-12-13       Impact factor: 25.617

6.  IUPred2A: context-dependent prediction of protein disorder as a function of redox state and protein binding.

Authors:  Bálint Mészáros; Gábor Erdos; Zsuzsanna Dosztányi
Journal:  Nucleic Acids Res       Date:  2018-07-02       Impact factor: 16.971

Review 7.  Hallmarks of cancer: the next generation.

Authors:  Douglas Hanahan; Robert A Weinberg
Journal:  Cell       Date:  2011-03-04       Impact factor: 41.582

8.  The transcriptional landscape and mutational profile of lung adenocarcinoma.

Authors:  Jeong-Sun Seo; Young Seok Ju; Won-Chul Lee; Jong-Yeon Shin; June Koo Lee; Thomas Bleazard; Junho Lee; Yoo Jin Jung; Jung-Oh Kim; Jung-Young Shin; Saet-Byeol Yu; Jihye Kim; Eung-Ryoung Lee; Chang-Hyun Kang; In-Kyu Park; Hwanseok Rhee; Se-Hoon Lee; Jong-Il Kim; Jin-Hyoung Kang; Young Tae Kim
Journal:  Genome Res       Date:  2012-09-13       Impact factor: 9.043

9.  The long intergenic noncoding RNA landscape of human lymphocytes highlights the regulation of T cell differentiation by linc-MAF-4.

Authors:  Valeria Ranzani; Grazisa Rossetti; Ilaria Panzeri; Alberto Arrigoni; Raoul Jp Bonnal; Serena Curti; Paola Gruarin; Elena Provasi; Elisa Sugliano; Maurizio Marconi; Raffaele De Francesco; Jens Geginat; Beatrice Bodega; Sergio Abrignani; Massimiliano Pagani
Journal:  Nat Immunol       Date:  2015-01-26       Impact factor: 25.606

10.  Human and mouse introns are linked to the same processes and functions through each genome's most frequent non-conserved motifs.

Authors:  Aristotelis Tsirigos; Isidore Rigoutsos
Journal:  Nucleic Acids Res       Date:  2008-05-01       Impact factor: 16.971

View more
  1 in total

1.  Identifying common transcriptome signatures of cancer by interpreting deep learning models.

Authors:  Anupama Jha; Mathieu Quesnel-Vallières; David Wang; Andrei Thomas-Tikhonenko; Kristen W Lynch; Yoseph Barash
Journal:  Genome Biol       Date:  2022-05-17       Impact factor: 17.906

  1 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.