COMBAI computational biology and artificial intelligence


ISURVIVAL seeks to improve the accuracy from the current survival analysis model, Cox proportional-hazards regression model (coxph).

Please note: this software also includes principal component analysis result to dramatically improve the universality during gene selections and makes the selection general for all conditions as described in our recent study as listed in applications below. .

Conventionally, the Cox proportional-hazards regression model (coxph) has been widely employed to find gene regulators, but it lacks random sampling during regression, leading to inaccurate estimations. Here, we developed an improved survival analysis software, referred as ISURVIVAL, to insert stability-selection into coxph model to make results accurate. Implementing ISURVIVAL with julia computer language also make it much faster than current software.


Wang, A. & Hai, R. FINET: Fast Inferring NETwork. BMC Research Notes volume 13, Article number: 521 (2020) download ISURVIVAL, please cite "Noncoding RNAs Serve as the Deadliest Universal Regulators of all Cancers".Cancer Genomics Proteomics . Jan-Feb 2021;18(1):43-52. doi: 10.21873/cgp.20240