Cell type–specific interpretation of noncoding variants using deep learning–based methods

Abstract

Interpretation of noncoding genomic variants is one of the most important challenges in human genetics. Machine learning methods have emerged recently as a powerful tool to solve this problem. State-of-the-art approaches allow prediction of transcriptional and epigenetic effects caused by noncoding mutations. However, these approaches require specific experimental data for training and cannot generalize across cell types where required features were not experimentally measured. We show here that available epigenetic characteristics of human cell types are extremely sparse, limiting those approaches that rely on specific epigenetic input. We propose a new neural network architecture, DeepCT, which can learn complex interconnections of epigenetic features and infer unmeasured data from any available input. Furthermore, we show that DeepCT can learn cell type–specific properties, build biologically meaningful vector representations of cell types, and utilize these representations to generate cell type–specific predictions of the effects of noncoding variations in the human genome.

GENA-LM: A Family of Open-Source Foundational DNA Language Models for Long Sequences

“…2, G). These observations reinforce our prior observation [5] that broad histone marks necessitate an expansive context for precise prediction. This highlights the pivotal role of models capable of handling extended input lengths for such tasks.…”

“…We found that the optimal balance between these two factors varies depending on the specific task. For instance, an extended context is vital for predicting promoter activity or deciphering widespread histone mark distributions, as previously indicated by [5]. However, for certain tasks, a more concise context is adequate, making it more advantageous to augment the model’s parameter count.…”

“…The advent of next-generation sequencing and additional high-throughput technologies has catalyzed the accumulation and public deposition of extensive databases, rich with functional genomic elements, enabling the broad application of computational methods to large-scale genomic data analysis [2]. We, along with others [3], have successfully employed machine-learning methods, including ensemble learning [4] and convolutional neural networks [5, 6], for this purpose. However, while potent, these approaches encounter constraints in identifying long-range dependencies within DNA sequences, a common phenomenon in human and other eukaryotic genomes [7].…”