Attila Gürsoy

Network-Based Analysis of Human Astrocytes Links Aging to Neurodegenerative and Cardiovascular Diseases

The paper identifies a 127-gene core network in human astrocytes linking aging to neurodegenerative and cardiovascular diseases through proteostasis and stress signaling.

DeepAllo: Allosteric Site Prediction using Protein Language Model (pLM) with Multitask Learning

DeepAllo uses a fine-tuned protein language model with multitask learning to predict allosteric sites, achieving higher accuracy than previous methods.

An Inflammation Centered Perspective to the Mechanisms and Interactions Related to Vascular Cognitive Impairment

This study identifies key protein interactions and pathways involved in vascular cognitive impairment by analyzing protein-protein interaction networks and conformational changes.

DiPPI: A curated dataset for drug-like molecules in protein-protein interfaces

The paper introduces DiPPI, a curated dataset of drug-like molecules in protein-protein interfaces, along with a website for drug repurposing studies, containing 55,135 interface-drug interactions.

Comparative Analysis of Structural Alignment Algorithms for Protein-Protein Interfaces in Template-Based Docking Studies

This study compares four structural alignment algorithms for protein-protein interfaces in template-based docking, finding that TM-align performs well despite not being designed for sequence-order independent alignment.

ProInterVal: Validation of Protein-Protein Interfaces through Learned Interface Representations

This paper introduces a method to validate protein-protein interfaces using learned representations, achieving 0.91 accuracy on a benchmark dataset.

Understanding Molecular Links of Vascular Cognitive Impairment: Selective Interaction between Mutant APP, TP53, and MAPKs

The paper identifies novel protein interactions involving mutant APP, TP53, and MAPKs in vascular cognitive impairment using network analysis and molecular modeling.

Structural Coverage of the Human Interactome

The paper assesses the structural coverage of the human interactome by analyzing experimental and modeled protein structures and their alignment to known interactions.

Revealing Shared Proteins and Pathways in Cardiovascular and Cognitive Diseases Using Protein Interaction Network Analysis

The paper identifies shared proteins and pathways between cardiovascular and cognitive diseases using protein interaction network analysis, highlighting oxidative and glycative stress mechanisms in vascular cognitive impairment.

Conformational diversity and protein-protein interfaces in drug repurposing in Ras signaling pathway

The paper identifies FDA-approved drugs that may bind to structurally similar protein-protein interfaces in the Ras/Raf/MEK/ERK pathway, increasing structural coverage from 21% to 92% using PRISM.

3D spatial organization and network-guided comparison of mutation profiles in Glioblastoma reveals similarities across patients

This study analyzes mutation distribution in GBM tumors using 3D spatial organization and network-guided methods, revealing four patient clusters with distinct mutation patterns and pathways.

DeepInterface: Protein-protein interface validation using 3D Convolutional Neural Networks

DeepInterface predicts whether a protein complex interface is true using 3D CNNs, achieving 88% accuracy on validation data.