Oluwatosin Oluwadare

HiC-LEGO reconstructs high-resolution 3D genomes from Hi-C data, preserving chromatin organization and regulatory interactions at kilobase resolution.

SpliceRead improves canonical and non-canonical splice site prediction using residual blocks and synthetic data augmentation, outperforming existing models across multiple metrics.

HiCP2GAN enhances low-resolution Hi-C data using a pretrained Vision Transformer as a discriminator, improving resolution over existing methods.

HiCInterpolate interpolates Hi-C contact matrices between timestamps to generate high-resolution 3D genome structures, preserving key chromatin features.

ASPECT classifies alternative splicing events using a transformer-based model, achieving strong performance on multiple tasks and showing applicability to cancer-related splicing events.

Robin provides a platform to analyze and compare loop caller results using Large Language Models, offering visualization and metrics like recovery and overlap.

ScHiCAtt improves single-cell Hi-C resolution using attention mechanisms, outperforming existing methods across different organisms and downsampling conditions.

The paper investigates how a constitutive heterochromatic region in Neurospora crassa affects genome organization and gene expression by altering chromatin structure and nuclear positioning.

DiCARN-DNase improves Hi-C resolution using a deep learning model enhanced with DNase-seq data, showing better cross-cell line generalization than previous methods.

This study evaluates 22 chromatin loop calling methods using Hi-C data, identifies their strengths and weaknesses, and introduces a new robustness score for performance assessment.

This paper introduces HiC-GNN, a graph neural network for 3D chromosome reconstruction from Hi-C data, showing superior accuracy and generalization across resolutions and cell lines.

ParticleChromo3D uses particle swarm optimization to reconstruct 3D chromosome and genome structures from Hi-C data, showing higher accuracy than existing methods.

ChromeBat uses a bio-inspired algorithm to reconstruct 3D genome structures from Hi-C data, achieving state-of-the-art performance.

GSDB provides a comprehensive repository of 3D genome structures reconstructed from Hi-C data, containing over 50,000 structures from 12 methods.

This paper develops deep learning methods to denoise Hi-C contact matrices and improve chromosome structure predictions, showing consistent improvement in multiple metrics on synthetic yeast data.

The paper introduces Hierarchical3DGenome, an algorithm that reconstructs high-resolution 3D models of human chromosomes, validated against Hi-C and FISH data.