Artur Yakimovich

The paper refines a genome-wide poxvirus-host interaction screen using a protein language model to improve hit prioritisation and provides the results as a community resource.

DeepDiffusion detects heterogeneous diffusion in single-molecule trajectories using a physics-informed neural network, accurately identifying subtle changes despite large errors.

The paper uses an image-based screening approach to identify VACV genes that affect LC3 lipidation, revealing candidate viral membrane proteins involved in this process.

DeBCR improves microscopy image quality through physics-informed deep learning, outperforming existing models in denoising, deblurring, and optical deconvolution across light microscopy and cryo-ET.

The paper introduces a benchmark and datasets for virus infection reporter virtual staining in microscopy, using U-Net and pix2pix models to address the challenge of continuous signal generation.

PyPlaque is an open-source Python package for analyzing virus plaque assays, offering flexibility and modularity to improve measurement consistency and adaptability to different experimental setups.

The paper develops a tandem segmentation-classification approach to identify morphological predictors of C. elegans lifespan and motility using convolutional neural networks.

This paper introduces a mimicry embedding strategy to enable efficient deep learning for 3D biomedical micrographs by mimicking verified datasets.