Back

Insomnia score: predictive ability of insomnia, high-diagnostic and prognostic value for cancer.

Dan, X.; Lan, Y.; Zhang, H.; Li, S.; Zhou, C.

2024-10-14 bioinformatics
10.1101/2024.08.13.607749 bioRxiv
Show abstract

ObjectiveThis study utilized bioinformatics methods to investigate the association between insomnia and cancer. MethodsWe identified key insomnia-related genes and constructed an insomnia score (riskScore = {sum} Expressiongene * Coefficient) based on an insomnia dataset using differential analysis, Weighted Gene Co-expression Network Analysis (WGCNA), and Least Absolute Shrinkage and Selection Operator (LASSO) regression. The predictive ability of the insomnia score was validated in the insomnia dataset using Receiver Operating Characteristic (ROC) analysis. Finally, the diagnostic and prognostic value of the insomnia score was assessed in a pan-cancer cohort. ResultsDifferential analysis, WGCNA, and LASSO screening of the insomnia dataset yielded three key insomnia-related genes (PTMA, NLRP8, and CCBE1). An insomnia score was then constructed using the formula: riskScore = -0.8039667 * ExpressionPTMA + - 3.1975230 * ExpressionNLRP8 + -0.4957560 * ExpressionCCBE1. The ROC analysis demonstrated that the insomnia score has excellent predictive ability for insomnia. Furthermore, pan-cancer analysis illustrated the diagnostic and prognostic value of the insomnia score across various cancers. ConclusionWe successfully constructed an insomnia score and demonstrated its diagnostic and prognostic value in multiple cancers.

Matching journals

The top 15 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.