A multimodal analysis of genomic and RNA splicing features in myeloid malignancies

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 ex-tents 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 ar-chitecture of MN and help identifying convergent molecular and transcriptomic pathways amenable to therapies.

Automated summary

RNA splicing dysfunctions are more widespread than believed and can't be solely attributed to splicing factor mutations in myeloid neoplasia. An integrative machine learning approach was applied to identify co-varying features in 1,258 MN cases and 63 normal controls, revealing 15 clusters based on mutations, gene expression, and RNA splicing. The combination of RNA splicing measurements and gene expression further distinguished features, identified similarities and differences in RNA splicing levels, and identified common pathways and expression signatures across the clusters.