Vladimir Gligorijević

MIMOSA improves de novo antibody design by constraining generative models to known binder interfaces, achieving validated binders on targets where unconstrained methods fail.

DyAb predicts antibody properties and designs new sequences with high binding affinity using a low-data approach.

This paper reports on the fourth CAFA challenge, showing improvements in Gene Ontology term prediction but highlighting challenges in new evaluation settings.

ConformAb designs antibody sequences that maintain CDR canonical conformations, improving binding affinity without target-specific data.

Property Enhancer optimizes antibody properties using a data-efficient framework, achieving significant affinity gains in both in silico and in vitro tests.

deepNGS Navigator uses deep contrastive learning to visualize and analyze antibody sequence datasets, revealing clonal relationships and evolutionary patterns.

The paper compresses protein sequence and structure representations, showing that compressed embeddings retain structural accuracy and enable downstream applications.

This paper introduces a machine learning framework for therapeutic antibody design that integrates computational methods with experimental validation, resulting in significantly improved binding affinity for multiple targets.

PLAID generates controllable all-atom protein structures from sequences using a diffusion model trained on sequence data, enabling functional control through Gene Ontology and organism keywords.

This paper trains a protein language model in 24 GPU hours, achieving performance comparable to a much larger model trained for 15,000x more GPU hours.

The paper develops a metagenome analysis workflow combining de novo genome reconstruction, taxonomic profiling, and deep learning-based functional annotation, showing improved coverage over existing methods.

This paper introduces a neural machine translation model to generate natural language descriptions of protein functions, enabling the discovery of novel functions beyond existing label spaces.

EquiFold predicts all-atom protein structures using an SE(3)-equivariant coarse-grained geometric representation without sequence alignments or language model embeddings, matching AlphaFold accuracy orders of magnitude faster in preliminary tests.

TM-Vec predicts structural similarity from sequence pairs to detect remote homologs, outperforming sequence alignment methods and matching structure-based alignment performance.

TCRconv predicts T-cell receptor-epitope recognition using a deep learning model and provides insights into T-cell dynamics in COVID-19 patients.

The paper predicts structures and annotates functions for diverse microbial protein sequences, identifying novel folds and highlighting the saturation of structural space.

This paper introduces a deep learning method for protein design that uses a sequence denoising autoencoder and function predictor to guide sampling towards functional sequences.

This paper introduces a Graph Convolutional Network for predicting protein function and identifying important residues, showing improved accuracy over sequence-based methods.

NetQuilt improves protein function prediction across species by integrating sequence and network data from multiple organisms.

The paper introduces DeepBLAST, a method using protein language model embeddings to generate explicit sequence alignments, improving speed and accuracy for structurally similar proteins.

The paper reports results from the CAFA3 challenge, showing improved computational protein function prediction and new annotations for over 1000 genes through experimental screens in C. albicans, P. aureginosa, and Drosophila.

deepNF improves protein function prediction by integrating heterogeneous networks using deep learning, outperforming existing methods on human and yeast datasets.