Kaveh Kavousi

This study maps viral RNA signals across cell types and tissues in colorectal cancer, identifying significant viral associations with specific cell types and tissue conditions.

The paper introduces ANA, an agentic AI framework that improves cross-site generalization in ASD fMRI classification by reducing data leakage and achieving higher accuracy than existing models.

This paper integrates metabolomics data with machine learning techniques to improve cancer detection and biomarker discovery by comparing multiple integration strategies.

The paper constructs a genome-wide regulatory network in Arabidopsis thaliana during flowering transition by analyzing gene expression across genotypes and identifies LHY and TCP16 as key integrators of flowering pathways.

This study identifies biomarkers for drug response in TNBC using scRNA-seq and machine learning, showing high predictive accuracy and highlighting blood-derived biomarkers.

This paper converts protein sequences into music using NMR data, assigning notes based on amino acid frequencies and relaxation periods, and applies set theory to analyze homologous beta-globin sequences.

The paper uses computational modeling to simulate the evolutionary transition from C3 to C4 photosynthesis in Arabidopsis thaliana under high photorespiration conditions and different environmental scenarios.

This paper develops a machine learning method to predict the thermal dependence of xylanases from metagenomic data, identifying three novel xylanases from rumen microbiota.

BNrich improves pathway enrichment analysis by incorporating Bayesian networks and gene expression data to prioritize impacted pathways.

The paper models chemotactic behavior in E. coli using a hierarchical approach, showing the behavior can be reduced to a non-homogeneous Markov process.

The paper investigates the relationship between short tandem repeats (STRs) and translation initiation site (TIS) selection in humans by analyzing STR distribution and comparative genomics across vertebrate species.

The paper compares EBSeq-HMM and multiDE models for differential expression analysis in time course RNA-seq data, finding multiDE identifies more benchmark DEGs and agrees better with them.