Back

Integrative Computational Framework, Dyscovr, Links Mutated Driver Genes to Expression Dysregulation Across 19 Cancer Types

Geraghty, S. E.; Boyer, J. A.; Fazel-Zarandi, M.; Arzouni, N.; Ryseck, R.-P.; McBride, M. J.; Parsons, L. R.; Rabinowitz, J. D.; Singh, M.

2024-11-21 systems biology
10.1101/2024.11.20.624509 bioRxiv
Show abstract

Though somatic mutations play a critical role in driving cancer initiation and progression, the systems-level functional impacts of these mutations--particularly, how they alter expression across the genome and give rise to cancer hallmarks--are not yet well-understood, even for well-studied cancer driver genes. To address this, we designed an integrative machine learning model, Dyscovr, that leverages mutation, gene expression, copy number alteration (CNA), methylation, and clinical data to uncover putative relationships between nonsynonymous mutations in key cancer driver genes and transcriptional changes across the genome. We applied Dyscovr pan-cancer and within 19 individual cancer types, finding both broadly relevant and cancer type-specific links between driver genes and putative targets, including a subset we further identify as exhibiting negative genetic relationships. Our work newly implicates-and validates in cell lines-KBTBD2 and mutant PIK3CA as putative synthetic lethals in breast cancer, suggesting a novel combinatorial treatment approach. HIGHLIGHTSO_LIIntegrative framework Dyscovr links mutations within cancer drivers to downstream expression changes C_LIO_LIDyscovr uncovers known and novel targets of cancer-driver genes C_LIO_LIDyscovr reveals clinically important negative genetic interaction pairings C_LIO_LIWeb platform to explore uncovered driver gene-target relationships C_LI eTOC BLURBAn integrative computational framework, Dyscovr, links mutated cancer driver genes to expression changes in putative target genes within and across 19 TCGA cancer types. Dyscovrs results include experimentally verifiable synthetic lethal driver-target pairings. Graphical abstract O_FIG O_LINKSMALLFIG WIDTH=200 HEIGHT=200 SRC="FIGDIR/small/624509v1_ufig1.gif" ALT="Figure 1"> View larger version (78K): org.highwire.dtl.DTLVardef@18ad7d9org.highwire.dtl.DTLVardef@610b3aorg.highwire.dtl.DTLVardef@1281c6aorg.highwire.dtl.DTLVardef@61af3d_HPS_FORMAT_FIGEXP M_FIG C_FIG

Matching journals

The top 5 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.