Furkan Özden

Probabilistic Modelling of Base Editing Efficiency and Bystander Outcome Composition

The paper introduces crispAIBE, a probabilistic framework for predicting base editing efficiency and bystander allele composition, achieving high correlation and coverage on benchmark datasets.

crispAIPE: Probabilistic Modelling of Prime Editing Variant Correction Efficiency

crispAIPE quantifies uncertainty in prime editing pegRNA efficiency predictions using a transformer-based probabilistic model, achieving high correlation with experimental data and providing coverage guarantees.

RNAGEN: A generative adversarial network-based model to generate synthetic RNA sequences to target proteins

The paper introduces RNAGEN, a GAN-based model to generate synthetic RNA sequences that bind to target proteins, validated with in vitro experiments for SOX2.

Deep Agentic Variant Prioritisation for Expert Level Genetic Diagnosis

DAVP uses an agentic-LLM pipeline to prioritize genetic variants for diagnosis, achieving high recall in identifying causal variants across multiple datasets.

CoNVict: An Agentic AI System for Copy Number Variation Prioritization in Rare Disease Diagnosis

CoNVict is an agentic AI system that prioritizes copy number variants in rare disease diagnosis by ranking candidates through structured reasoning, outperforming existing methods in identifying causal variants.

UTRGAN: Learning to Generate 5' UTR Sequences for Optimized Translation Efficiency and Gene Expression

UTRGAN generates 5' UTR sequences optimized for higher translation efficiency and gene expression, outperforming existing UTRs in multiple metrics.

Learning to quantify uncertainty in off-target activity for CRISPR guide RNAs

This paper introduces crispAI, a neural network for predicting uncertainty in CRISPR off-target activity, and presents crispAI-aggregate for improved sgRNA prioritization.

ECOLE: Learning to call copy number variants on whole exome sequencing data

ECOLE is a deep learning model for detecting copy number variants in whole exome sequencing data, achieving improved precision and recall over existing methods.

Polishing Copy Number Variant Calls on Exome Sequencing Data via Deep Learning

DECoNT improves CNV detection accuracy on WES data by learning from matched WES and WGS data, tripling duplication precision and doubling deletion precision.