High‐throughput molecular assays for inclusion in personalised oncology trials–State‐of‐the‐art and beyond
A Edsjö, HG Russnes, J Lehtiö… - Journal of internal …, 2024 - Wiley Online Library
In the last decades, the development of high‐throughput molecular assays has
revolutionised cancer diagnostics, paving the way for the concept of personalised cancer …
revolutionised cancer diagnostics, paving the way for the concept of personalised cancer …
A phenocopy signature of TP53 loss predicts response to chemotherapy
H Bakhtiar, MN Sharifi, KT Helzer, Y Shi… - NPJ Precision …, 2024 - nature.com
In preclinical studies, p53 loss of function impacts chemotherapy response, but this has not
been consistently validated clinically. We trained a TP53-loss phenocopy gene expression …
been consistently validated clinically. We trained a TP53-loss phenocopy gene expression …
Best holdout assessment is sufficient for cancer transcriptomic model selection
Guidelines in statistical modeling for genomics hold that simpler models have advantages
over more complex ones. Potential advantages include cost, interpretability, and improved …
over more complex ones. Potential advantages include cost, interpretability, and improved …
Machine learning enabled prediction of digital biomarkers from whole slide histopathology images
Current predictive biomarkers generally leverage technologies such as immunohis-
tochemistry or genetic analysis, which may require specialized equipment, be time-intensive …
tochemistry or genetic analysis, which may require specialized equipment, be time-intensive …
Bayesian inference for multivariate probit model with latent envelope
K Lee, Y Park - Biometrics, 2024 - academic.oup.com
The response envelope model proposed by Cook et al. is an efficient method to estimate the
regression coefficient under the context of the multivariate linear regression model. It …
regression coefficient under the context of the multivariate linear regression model. It …
Optimizer's dilemma: optimization strongly influences model selection in transcriptomic prediction
Motivation Most models can be fit to data using various optimization approaches. While
model choice is frequently reported in machine-learning-based research, optimizers are not …
model choice is frequently reported in machine-learning-based research, optimizers are not …
Methods of generating phenocopy signatures and uses thereof
S Zhao, H Bakhtiar - US Patent App. 18/522,977, 2024 - Google Patents
Methods of generating phenocopy signatures and uses thereof. The methods of generating
phenocopy signatures can include determining gene expression signatures that predict the …
phenocopy signatures can include determining gene expression signatures that predict the …