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

Handling DNA malfunctions by unsupervised machine learning model DOI Creative Commons
Mutaz Khazaaleh, Mohammad A. Alsharaiah,

Wafa Alsharafat

et al.

Journal of Pathology Informatics, Journal Year: 2023, Volume and Issue: 14, P. 100340 - 100340

Published: Jan. 1, 2023

The cell cycle is a rich field for research, especially, the DNA damage. damage, which happened naturally or as result of environmental influences causes change in chemical structure DNA. extent damage has significant impact on fate later stages. In this paper, we introduced an Unsupervised Machine learning Model Damage Diagnosis and Analysis. Mainly, employed K-means clustering unsupervised machine algorithms. algorithms commonly draw conclusions from datasets by solely utilizing input vectors, disregarding any known labeled outcomes. model provided deep insight about exposes protein levels proteins when work together sub-network to deal with occurrence, artificial explained biological activities regard changing their concentrations several clusters, they have been grouped such (0 - no 1 low, 2 medium, 3 high, 4 excess) clusters. results rational persuasive explanation numerous important phenomena, including oscillation p53, clear understandable manner. Which encouraging since it demonstrates that approach can be easily applied many similar systems, aids better understanding key dynamics these systems.

Language: Английский

Citations

3
Navigating the global stock market: correlation, prediction, and the influence of external factors DOI
Mohammad Shariful Islam, Mohammad Abu Tareq Rony

Iran Journal of Computer Science, Journal Year: 2024, Volume and Issue: 7(3), P. 397 - 422

Published: March 23, 2024

Language: Английский

Citations

0
Advances in computational and experimental approaches for deciphering transcriptional regulatory networks DOI Creative Commons
Camille Moeckel,

Ioannis Mouratidis,

Nikol Chantzi

et al.

BioEssays, Journal Year: 2024, Volume and Issue: 46(7)

Published: May 8, 2024

Understanding the influence of cis-regulatory elements on gene regulation poses numerous challenges given complexities stemming from variations in transcription factor (TF) binding, chromatin accessibility, structural constraints, and cell-type differences. This review discusses role regulatory networks enhancing understanding transcriptional covers construction methods ranging expression-based approaches to supervised machine learning. Additionally, key experimental methods, including MPRAs CRISPR-Cas9-based screening, which have significantly contributed TF binding preferences element functions, are explored. Lastly, potential learning artificial intelligence unravel logic is analyzed. These computational advances far-reaching implications for precision medicine, therapeutic target discovery, study genetic health disease.

Language: Английский

Citations

0
Enhancing Gene Expression Classification Through Explainable Machine Learning Models DOI
Thanh‐Nghi Do

SN Computer Science, Journal Year: 2024, Volume and Issue: 5(5)

Published: May 31, 2024

Language: Английский

Citations

0
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

Citations

1