AtLASS: A Scheme for End-to-End Prediction of Splice Sites Using Attention-based Bi-LSTM DOI Open Access
Ryo Harada, Keitaro Kume, Kazumasa Horie

et al.

IPSJ Transactions on Bioinformatics, Journal Year: 2023, Volume and Issue: 16(0), P. 20 - 27

Published: Jan. 1, 2023

Eukaryotic genomes contain exons and introns, it is necessary to accurately identify exon-intron boundaries, i.e., splice sites, annotate genomes. To address this problem, many previous works have proposed annotation methods/tools based on RNA-seq evidence. Many recent exploit neural networks (NNs) as their prediction models, but only a few can be used generate new genome in practice. In study, we propose AtLASS, fully automated method for predicting sites from genomic data using attention-based Bi-LSTM (Bidirectional Long Short-Term Memory). We two-stage training the problem of biased label thereby reducing false positives. The experiments three species show that performance itself comparable existing methods, achieve better by combining outputs method. first program specialized end-to-end site NNs.

Language: Английский

Gene regulatory network inference in the era of single-cell multi-omics DOI
Pau Badia-i-Mompel, Lorna Wessels, Sophia Müller‐Dott

et al.

Nature Reviews Genetics, Journal Year: 2023, Volume and Issue: 24(11), P. 739 - 754

Published: June 26, 2023

Language: Английский

Citations

187
Artificial Intelligence and Forensic Genetics: Current Applications and Future Perspectives DOI Creative Commons
Francesco Sessa, Massimiliano Esposito, Giuseppe Cocimano

et al.

Applied Sciences, Journal Year: 2024, Volume and Issue: 14(5), P. 2113 - 2113

Published: March 4, 2024

The term artificial intelligence (AI) was coined in the 1950s and it has successfully made its way into different fields of medicine. Forensic sciences AI are increasingly intersecting that hold tremendous potential for solving complex criminal investigations. Considering great evolution technologies applied to forensic genetics, this literature review aims explore existing body research investigates application field genetics. Scopus Web Science were searched: after an accurate evaluation, 12 articles included present systematic review. genetics predominantly focused on two aspects. Firstly, several studies have investigated use haplogroup analysis enhance expedite classification process DNA samples. Secondly, other groups utilized analyze short tandem repeat (STR) profiles, thereby minimizing risk misinterpretation. While proven be highly useful further improvements needed before using these applications real cases. main challenge lies communication gap between experts: as continues advance, collaboration presents immense transforming investigative practices, enabling quicker more precise case resolutions.

Language: Английский

Citations

13
Artificial intelligence for skin permeability prediction: deep learning DOI
Kevin Ita,

Sahba Roshanaei

Journal of drug targeting, Journal Year: 2024, Volume and Issue: 32(3), P. 334 - 346

Published: Jan. 23, 2024

Background and objective Researchers have put in significant laboratory time effort measuring the permeability coefficient (Kp) of xenobiotics. To develop alternative approaches to this labour-intensive procedure, predictive models been employed by scientists describe transport xenobiotics across skin. Most quantitative structure-permeability relationship (QSPR) are derived statistically from experimental data. Recently, artificial intelligence-based computational drug delivery has attracted tremendous interest. Deep learning is an umbrella term for machine-learning algorithms consisting deep neural networks (DNNs). Distinct network architectures, like convolutional (CNNs), feedforward (FNNs), recurrent (RNNs), can be prediction.

Language: Английский

Citations

5
Unlocking gene regulation with sequence-to-function models DOI
Alexander Sasse, Maria Chikina, Sara Mostafavi

et al.

Nature Methods, Journal Year: 2024, Volume and Issue: 21(8), P. 1374 - 1377

Published: Aug. 1, 2024

Language: Английский

Citations

5
Revolutionizing Biological Science: The Synergy of Genomics in Health, Bioinformatics, Agriculture, and Artificial Intelligence DOI

Aakanksha Biswas,

Aditi Kumari,

D. S. Gaikwad

et al.

OMICS A Journal of Integrative Biology, Journal Year: 2023, Volume and Issue: 27(12), P. 550 - 569

Published: Dec. 1, 2023

With climate emergency, COVID-19, and the rise of planetary health scholarship, binary human ecosystem has been deeply challenged. The interdependence nonhuman animal is increasingly acknowledged paving way for new frontiers in integrative biology. convergence genomics health, bioinformatics, agriculture, artificial intelligence (AI) ushered a era possibilities applications. However, sheer volume genomic/multiomics big data generated also presents formidable sociotechnical challenges extracting meaningful biological, ecological insights. Over past few years, AI-guided bioinformatics emerged as powerful tool managing, analyzing, interpreting complex biological datasets. advances AI, particularly machine learning deep learning, have transforming fields genomics, agriculture. This article aims to unpack explore range that result from such transdisciplinary integration, emphasizes its radically transformative potential health. integration these disciplines driving significant advancements precision medicine personalized care. an unprecedented opportunity deepen our understanding systems advance well-being all life ecosystems. Notwithstanding mind sociotechnical, ethical, critical policy challenges, multiomics, agriculture with opens up vast opportunities transnational collaborative efforts, sharing, analysis, valorization, interdisciplinary innovations sciences

Language: Английский

Citations

11
teemi: An open-source literate programming approach for iterative design-build-test-learn cycles in bioengineering DOI Creative Commons
Søren D. Petersen, Lucas Levassor,

Christine M. Pedersen

et al.

PLoS Computational Biology, Journal Year: 2024, Volume and Issue: 20(3), P. e1011929 - e1011929

Published: March 8, 2024

Synthetic biology dictates the data-driven engineering of biocatalysis, cellular functions, and organism behavior. Integral to synthetic is aspiration efficiently find, access, interoperate, reuse high-quality data on genotype-phenotype relationships native engineered biosystems under FAIR principles, from this facilitate forward-engineering strategies. However, complex at regulatory level, noisy operational thus necessitating systematic diligent handling all levels design, build, test phases in order maximize learning iterative design-build-test-learn cycle. To enable user-friendly simulation, organization, guidance for biosystems, we have developed an open-source python-based computer-aided design analysis platform operating a literate programming user-interface hosted Github. The called teemi fully compliant with principles. In study apply i) designing simulating bioengineering, ii) integrating analyzing multivariate datasets, iii) machine-learning predictive metabolic pathway designs production key precursor medicinal alkaloids yeast. publicly available PyPi GitHub .

Language: Английский

Citations

4
Transformers and genome language models DOI

Micaela E. Consens,

C Dufault,

Michael Wainberg

et al.

Nature Machine Intelligence, Journal Year: 2025, Volume and Issue: unknown

Published: March 13, 2025

Citations

0
DNA sequence analysis landscape: a comprehensive review of DNA sequence analysis task types, databases, datasets, word embedding methods, and language models DOI Creative Commons
Muhammad Nabeel Asim, Muhammad Ali Ibrahim, Alam Zaib

et al.

Frontiers in Medicine, Journal Year: 2025, Volume and Issue: 12

Published: April 8, 2025

Deoxyribonucleic acid (DNA) serves as fundamental genetic blueprint that governs development, functioning, growth, and reproduction of all living organisms. DNA can be altered through germline somatic mutations. Germline mutations underlie hereditary conditions, while induced by various factors including environmental influences, chemicals, lifestyle choices, errors in replication repair mechanisms which lead to cancer. sequence analysis plays a pivotal role uncovering the intricate information embedded within an organism's understanding modify it. This helps early detection diseases design targeted therapies. Traditional wet-lab experimental traditional methods is costly, time-consuming, prone errors. To accelerate large-scale analysis, researchers are developing AI applications complement methods. These approaches help generate hypotheses, prioritize experiments, interpret results identifying patterns large genomic datasets. Effective integration with validation requires scientists understand both fields. Considering need comprehensive literature bridges gap between fields, contributions this paper manifold: It presents diverse range tasks methodologies. equips essential biological knowledge 44 distinct aligns these 3 AI-paradigms, namely, classification, regression, clustering. streamlines into consolidating 36 databases used develop benchmark datasets for different tasks. ensure performance comparisons new existing predictors, it provides insights 140 related word embeddings language models across development predictors providing survey 39 67 based predictive pipeline values well top performing encoding-based their performances

Language: Английский

Citations

0
The power of microRNA regulation—insights into immunity and metabolism DOI Creative Commons
Stefania Oliveto, Nicola Manfrini, Stefano Biffo

et al.

FEBS Letters, Journal Year: 2025, Volume and Issue: unknown

Published: April 11, 2025

MicroRNAs (miRNAs) are a prominent class of small non‐coding RNAs that control gene expression. This comprehensive review explores the intricate roles miRNAs in metabolism and immunity, as well emerging field immunometabolism. The core this work delves into functional regulatory capabilities miRNAs, examining their complex influence on glucose lipid metabolism, pivotal shaping T‐cell development function. Specifically, addresses how orchestrate interaction between cellular metabolic processes immune responses, underscoring essential nature these molecules maintaining homeostasis. Finally, we examine role Artificial Intelligence (AI) miRNA research, focusing machine learning techniques revolutionizing identification validation potential biomarkers. By integrating diverse aspects, underscores multifaceted biological significant advancing biomedical research clinical applications.

Language: Английский

Citations

0
Transfer learning using generative pretrained genomic DNA models for predicting perturbation-induced changes in gene expression DOI

Takuya Shihashi,

Itoshi Nikaido

Published: May 5, 2025

Abstract Background Transfer learning applied to genomic DNA models has the potential improve predictive capabilities, especially when target-domain datasets and computational resources are limited. Despite its promise, practical effectiveness of transfer in models, particularly for predicting gene expression changes due perturbations, not been thoroughly investigated. This study aimed systematically evaluate performance utility approaches using accurately predict perturbation-induced expression. Results We benchmarked three across 12 distinct containing data identify optimal conditions effective learning. Notably, were included pre-training these models. Among these, Enformer model consistently generated accurate embeddings, demonstrating superior clustering signature scoring aligned closely with observed experimental data. Additionally, we identified a phenomenon termed "genomic neighbouring interference," wherein partially overlapping sequences adjacent genes cause correlated predictions, resulting both beneficial detrimental effects on accuracy. Conclusions Our findings highlight efficacy expression, emphasizing model's robust performance. Understanding interference offers critical insights refining accuracy applications. provides guidance researchers developing strategies paving way more resource-efficient predictions.

Language: Английский

Citations

0