Shin‐Han Shiu

This study integrates multi-omic data with interpretable machine learning to identify genetic mechanisms underlying trait variation and phenotypic plasticity in switchgrass across environments.

The paper uses machine learning to predict yeast fitness across 35 environments using genetic variants, finding that copy number variants explain most fitness variation and that gene contributions depend on isolate and environment.

This study uses machine learning to identify gene families associated with oxidative stress resistance in yeasts and validates their roles experimentally.

This study evaluates factors affecting genomic prediction accuracy in switchgrass, finding that exome capture and multi-allelic variants improve predictions for complex traits.

This study identifies HvFCP1 and HvCLV1 as key regulators of barley inflorescence architecture by coordinating meristem activity and determinacy.

The paper reports on a competition to predict maize yield using genetic and environmental data, showing that diverse modeling approaches can achieve good results.

This study integrates multi-omics data to predict complex traits in Arabidopsis, showing that transcriptome- and methylome-based models perform comparably to genome-based models and reveal novel gene interactions.

This study uses deep learning to accurately measure Arabidopsis fitness traits, revealing gene function effects previously undetected by traditional methods.

The paper models transcriptional responses to heat and drought stress in Arabidopsis thaliana using machine learning and deep learning, identifying cis-regulatory elements that predict gene response patterns.

The paper shows that TF-TF interactions improve co-expression signals for predicting regulatory complexes in Arabidopsis, highlighting the role of combinatorial gene regulation.

The paper identifies misassembled regions in short-read genome assemblies using coverage variation and machine learning, finding that 27.8% of high coverage regions are potentially misassembled.

This study predicts complex traits in maize using transcriptome and genetic marker data, finding similar performance between both approaches and highlighting transcriptome's role in capturing trait variation not captured by sequence data.

The paper evaluates intergenic transcribed regions (ITRs) in Poaceae species to determine if they represent functional genes or noisy transcription, finding most ITRs lack conservation and are likely nonfunctional.

This study benchmarks linear and non-linear algorithms for genomic prediction of complex traits across multiple plant species, finding that ensemble methods and feature selection improve performance.

The paper predicts cell-cycle expressed genes in S. cerevisiae using regulatory data, identifying both canonical and non-canonical regulators of time-specific expression.

The paper identifies intergenic transcribed regions (ITRs) in 15 flowering plant species and uses machine learning to classify them as functional or non-functional based on sequence and evolutionary features.