Mehrsa Mardikoraem

VesicleVoyager: In vivo selection of surface displayed proteins that direct extracellular vesicles to tissue-specific targets

The paper develops a method to select tissue-specific proteins that direct extracellular vesicles in vivo, using EV-display libraries and a Markov chain model to predict selection dynamics.

Predicting Inhibitors of OATP1B1 via Heterogeneous OATP-Ligand Interaction Graph Neural Network (HOLIgraph)

This paper introduces HOLIgraph, a graph neural network model that predicts OATP1B1 inhibitors by integrating ligand features and protein-ligand interactions, achieving over 90% balanced accuracy.

RecombiCraft Library construction: A novel method for DNA Library cloning and expansion using non-enzymatic single-step DNA recombination and liquid culture

This paper introduces RecombiCraft, a method for DNA library construction in E. coli using SLiCE and liquid culture, which minimizes sequence bias and reduces costs.

EvoSeq-ML: Advancing Data-Centric Machine Learning with Evolutionary-Informed Protein Sequence Representation and Generation

This paper evaluates an ancestral sequence reconstruction-informed data augmentation strategy for improving protein sequence generation and representation learning, showing improved thermostability in generated variants.

AP-LASR: Automated Protein Libraries from Ancestral Sequence Reconstruction

AP-LASR automates ancestral sequence reconstruction and generates diverse protein libraries by leveraging ASR uncertainty, improving eLnP scores over existing methods.

Protein Fitness Prediction is Impacted by the Interplay of Language Models, Ensemble Learning, and Sampling Methods

The paper evaluates how language models, ensemble learning, and sampling methods affect protein fitness prediction using binding affinity and thermal stability datasets.