TY - JOUR
T1 - A multimodal analysis of genomic and RNA splicing features in myeloid malignancies
AU - Durmaz, Arda
AU - Gurnari, Carmelo
AU - Hershberger, Courtney E.
AU - Pagliuca, Simona
AU - Daniels, Noah
AU - Awada, Hassan
AU - Awada, Hussein
AU - Adema, Vera
AU - Mori, Minako
AU - Ponvilawan, Ben
AU - Kubota, Yasuo
AU - Kewan, Tariq
AU - Bahaj, Waled S.
AU - Barnard, John
AU - Scott, Jacob
AU - Padgett, Richard A.
AU - Haferlach, Torsten
AU - Maciejewski, Jaroslaw P.
AU - Visconte, Valeria
N1 - Publisher Copyright:
© 2023 The Author(s)
PY - 2023/3/17
Y1 - 2023/3/17
N2 - RNA splicing dysfunctions are more widespread than what is believed by only estimating the effects resulting by splicing factor mutations (SFMT) in myeloid neoplasia (MN). The genetic complexity of MN is amenable to machine learning (ML) strategies. We applied an integrative ML approach to identify co-varying features by combining genomic lesions (mutations, deletions, and copy number), exon-inclusion ratio as measure of RNA splicing (percent spliced in, PSI), and gene expression (GE) of 1,258 MN and 63 normal controls. We identified 15 clusters based on mutations, GE, and PSI. Different PSI levels were present at various extents regardless of SFMT suggesting that changes in RNA splicing were not strictly related to SFMT. Combination of PSI and GE further distinguished the features and identified PSI similarities and differences, common pathways, and expression signatures across clusters. Thus, multimodal features can resolve the complex architecture of MN and help identifying convergent molecular and transcriptomic pathways amenable to therapies.
AB - RNA splicing dysfunctions are more widespread than what is believed by only estimating the effects resulting by splicing factor mutations (SFMT) in myeloid neoplasia (MN). The genetic complexity of MN is amenable to machine learning (ML) strategies. We applied an integrative ML approach to identify co-varying features by combining genomic lesions (mutations, deletions, and copy number), exon-inclusion ratio as measure of RNA splicing (percent spliced in, PSI), and gene expression (GE) of 1,258 MN and 63 normal controls. We identified 15 clusters based on mutations, GE, and PSI. Different PSI levels were present at various extents regardless of SFMT suggesting that changes in RNA splicing were not strictly related to SFMT. Combination of PSI and GE further distinguished the features and identified PSI similarities and differences, common pathways, and expression signatures across clusters. Thus, multimodal features can resolve the complex architecture of MN and help identifying convergent molecular and transcriptomic pathways amenable to therapies.
KW - Bioinformatics
KW - Cancer
KW - Omics
UR - http://www.scopus.com/inward/record.url?scp=85149787352&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85149787352&partnerID=8YFLogxK
U2 - 10.1016/j.isci.2023.106238
DO - 10.1016/j.isci.2023.106238
M3 - Article
C2 - 36926651
AN - SCOPUS:85149787352
SN - 2589-0042
VL - 26
JO - iScience
JF - iScience
IS - 3
M1 - 106238
ER -