Hamid Alinejad-Rokny

This study identifies backdoor vulnerabilities in genomic foundation models through data poisoning during fine-tuning and proposes an auditing framework to detect such threats.

The paper introduces GenSyntax, a large language model for prokaryotic genomes that captures functional context, achieving competitive performance in genome-scale tasks.

LabscriptAI translates natural language into robot scripts for synthetic biology, achieving high simulation accuracy and enabling secure, standardized, and traceable lab automation.

DeepGenePrior uses deep learning to prioritize genes affected by copy number variants in neurodevelopmental disorders, identifying common genes across autism, schizophrenia, and developmental delay.