DNALongBench eQTL data

Modeling long-range DNA dependencies is crucial for understanding genome structure and function for a wide-range of biological contexts in health and disease. However, effectively capturing the extensive long-range dependencies between DNA sequences, spanning millions of base pairs as seen in tasks such as three- dimensional (3D) chromatin folding, remains a significant challenge. Additionally, a comprehensive benchmark suite for evaluating tasks reliant on long-range depen- dencies is notably absent. To address this gap, we introduce DNALONGBENCH, a benchmark dataset spanning five important genomics tasks that consider long- range dependencies up to 1 million base pairs: enhancer-target gene interaction, expression quantitative trait loci, 3D genome organization, regulatory sequence activity, and transcription initiation signal. In order to comprehensively assess DNALONGBENCH, we evaluate the performance of three baseline methods: a task- specific expert model, a convolutional neural network (CNN)-based model, and a fine-tuned DNA foundation model, HyenaDNA. We envision DNALONGBENCH with the potential to become a standardized resource facilitating comprehensive comparisons and rigorous evaluations of the emerging DNA sequence-based deep learning models that consider long-range dependencies.