Obtaining genetics insights from deep learning via explainable artificial intelligence

G Novakovsky, N Dexter, MW Libbrecht… - Nature Reviews …, 2023 - nature.com
Artificial intelligence (AI) models based on deep learning now represent the state of the art
for making functional predictions in genomics research. However, the underlying basis on …

A review of deep learning applications in human genomics using next-generation sequencing data

WS Alharbi, M Rashid - Human Genomics, 2022 - Springer
Genomics is advancing towards data-driven science. Through the advent of high-throughput
data generating technologies in human genomics, we are overwhelmed with the heap of …

Scaffolding protein functional sites using deep learning

J Wang, S Lisanza, D Juergens, D Tischer, JL Watson… - Science, 2022 - science.org
The binding and catalytic functions of proteins are generally mediated by a small number of
functional residues held in place by the overall protein structure. Here, we describe deep …

Predicting RNA-seq coverage from DNA sequence as a unifying model of gene regulation

J Linder, D Srivastava, H Yuan, V Agarwal, DR Kelley - Nature Genetics, 2025 - nature.com
Sequence-based machine-learning models trained on genomics data improve genetic
variant interpretation by providing functional predictions describing their impact on the cis …

CADD v1. 7: using protein language models, regulatory CNNs and other nucleotide-level scores to improve genome-wide variant predictions

M Schubach, T Maass, L Nazaretyan… - Nucleic acids …, 2024 - academic.oup.com
Abstract Machine Learning-based scoring and classification of genetic variants aids the
assessment of clinical findings and is employed to prioritize variants in diverse genetic …

Base-resolution models of transcription-factor binding reveal soft motif syntax

Ž Avsec, M Weilert, A Shrikumar, S Krueger… - Nature …, 2021 - nature.com
The arrangement (syntax) of transcription factor (TF) binding motifs is an important part of the
cis-regulatory code, yet remains elusive. We introduce a deep learning model, BPNet, that …

Current sequence-based models capture gene expression determinants in promoters but mostly ignore distal enhancers

A Karollus, T Mauermeier, J Gagneur - Genome biology, 2023 - Springer
Background The largest sequence-based models of transcription control to date are
obtained by predicting genome-wide gene regulatory assays across the human genome …

Controlling gene expression with deep generative design of regulatory DNA

J Zrimec, X Fu, AS Muhammad, C Skrekas… - Nature …, 2022 - nature.com
Abstract Design of de novo synthetic regulatory DNA is a promising avenue to control gene
expression in biotechnology and medicine. Using mutagenesis typically requires screening …

An atlas of alternative polyadenylation quantitative trait loci contributing to complex trait and disease heritability

L Li, KL Huang, Y Gao, Y Cui, G Wang, ND Elrod, Y Li… - Nature …, 2021 - nature.com
Genome-wide association studies have identified thousands of noncoding variants
associated with human traits and diseases. However, the functional interpretation of these …

Context-aware poly (a) signal prediction model via deep spatial–temporal neural networks

Y Guo, D Zhou, P Li, C Li, J Cao - IEEE Transactions on Neural …, 2022 - ieeexplore.ieee.org
Polyadenylation [Poly (A)] is an essential process during messenger RNA (mRNA)
maturation in biological eukaryote systems. Identifying Poly (A) signals (PASs) from the …