Amir Asiaee

The paper shows that pooled correlations in transcriptomic data often reverse sign when analyzed within specific contexts, highlighting the need for context-aware reporting of correlations.

The paper introduces DSEN, a tissue-aware regression method that improves drug response prediction by decomposing models into shared and lineage-specific components, achieving better performance and interpretability.

The paper shows that data leakage in drug response prediction models inflates accuracy and corrupts biomarker discovery, and provides a solution to avoid this issue.

SIR improves drug synergy testing by using shape-constrained regression and bootstrap methods to provide reliable statistical inference and error control.

The paper identifies keystone organisms by analyzing immunological traits and clinical emergence patterns, finding herpesviruses and Mycobacterium tuberculosis as key pathogens with broad niche and immune breadth.

This study identifies a small set of transcription factors and microRNAs that can predict genome-wide gene expression across multiple cancer types with high accuracy.

This study introduces AUC-PR as a better metric for evaluating in silico perturbation models' ability to predict differentially expressed genes, showing it outperforms R2 in capturing biologically relevant outcomes.

This paper improves drug sensitivity prediction using multitask learning, showing better accuracy for sensitive cell lines and identifying tissue-specific predictors.

The paper extends LimoRhyde2 to analyze differential rhythmicity by estimating effect sizes between conditions, improving biological interpretation in circadian systems biology.

This paper introduces a Bayesian network model for oncogenetic network estimation, showing its ability to infer progression networks from synthetic and real data.

SITH is an R package that models tumor growth and mutation spatially, generates synthetic sequencing data, and provides 3D visualizations of intratumor heterogeneity.

The paper identifies genes differentially regulated by transcription factors and miRNAs using TCGA data and linear models to compare their regulatory effects.