Despite recent advances in algorithmic fairness, methodologies for achieving fairness with generalized linear models (GLMs) have yet to be explored in general, despite GLMs being widely used in practice. In this paper we introduce two fairness criteria for GLMs based on equalizing expected outcomes or log-likelihoods. We prove that for GLMs both criteria can be achieved via a convex penalty term based solely on the linear components of the GLM, thus permitting efficient optimization. We also derive theoretical properties for the resulting fair GLM estimator. To empirically demonstrate the efficacy of the proposed fair GLM, we compare it with other well-known fair prediction methods on an extensive set of benchmark datasets for binary classification and regression. In addition, we demonstrate that the fair GLM can generate fair predictions for a range of response variables, other than binary and continuous outcomes.

By using sequencing results from a cohort of 1,054 patients with advanced lung adenocarcinomas, we developed OncoCast, a machine learning tool for survival risk stratification and biomarker identification. We found that comutations of both STK11 and KEAP1 are strong determinants of unfavorable prognosis with currently available therapies.

This novel study suggests that polymorphisms in genes involved in aging and inflammation, dopamine, myelin and cell cycle regulation, and DNA repair and response to oxidative stress may be associated with cognitive outcome in patients with brain tumors.

Utilizing a recently published dog Y-chromosome reference, we analyzed Y-chromosome sequence across a diverse collection of canids and determined the Y haplogroup of three ancient European dogs. We estimate that the time to the most recent comment ancestor of dog Y haplogroups is 68–151 thousand years ago and confirm long-standing population structure among European dogs.

OncoCast R package Please find all the package’s resources on it’s github repository. An Ensemble Learning Approach for Outcome Prediction in Precision Oncology Setting Ensemble learner framework for survival outcome prediction and stratification for high dimension data.

gnomeR R package Please find all the package’s resources on it’s github repository. Introduction The gnomeR package provides a consistent framework for genetic data processing, visualization and analysis. This is primarily targeted to IMPACT datasets but can also be applied to any genomic data provided by CbioPortal.

genomeVerse: Framework for Genomic data Processing and Analysis genomeVerse is an umbrella package for genomic data processing and analysis with the genomeVerse ecosystem of R packages developed in the department of Epidemiology & Biostatistics at Memorial Sloan Kettering Cancer Center.