iPro-GAN: A novel model based on generative adversarial learning for identifying promoters and their strength

Qiao, Huijuan; Zhang, Shengli; Xue, Tian; Wang, Jinyue; Wang, Bowei

doi:10.1016/j.cmpb.2022.106625

Cited by 13 publications

(6 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(i) Encoding a DNA sequence as in Section "Vector representations of DNA sequence". (ii) Constructing a neural network to predict the presence of enhancers or promoters, such as CNN [69,73,76,78,81,85,88,[98][99][100]102,104,111], transfer learning [110], or LSTM [82,88,108]. To establish the right characteristics and increase the accuracy of Sedb [117] PReMod [119] Human Transcribed Enhancer Atlas [120] VISTA [121] dbSUPER [122] ENdb [123] (human enhancer)…”

Section: Methods For Identifying Enhancer/promoter Based On Deep-lear...mentioning

confidence: 99%

“…Methods based on deep-learning primarily focus on training a neural network with DNA sequences or DNA sequences with epigenomic characteristics (such as histone modifications, chromatin accessibility, DNA methylation, or CpG islands) as inputs. Though some scholars have trained their networks with epigenome features [67,68,71,74,75,82], most have done so with only DNA sequences as inputs [69,70,72,73,[77][78][79][80][81]85,[88][89][90][98][99][100]102,[104][105][106][107][108][109][110][111]142]. Predicting enhancers and promoters directly from DNA sequences is believed to be more applicable than identifying them from multiple epigenomic features because the epigenomic characteristics data carries with it substantial sequencing costs, and a high rate of false positives.…”

Section: Methods For Identifying Enhancer/promoter Based On Deep-lear...mentioning

confidence: 99%

See 1 more Smart Citation

Computational methods for identifying enhancer‐promoter interactions

Gong,

Chen,

Tang

et al. 2023

Quant. Biol.

View full text Add to dashboard Cite

BackgroundAs parts of the cis‐regulatory mechanism of the human genome, interactions between distal enhancers and proximal promoters play a crucial role. Enhancers, promoters, and enhancer‐promoter interactions (EPIs) can be detected using many sequencing technologies and computation models. However, a systematic review that summarizes these EPI identification methods and that can help researchers apply and optimize them is still needed.ResultsIn this review, we first emphasize the role of EPIs in regulating gene expression and describe a generic framework for predicting enhancer‐promoter interaction. Next, we review prediction methods for enhancers, promoters, loops, and enhancer‐promoter interactions using different data features that have emerged since 2010, and we summarize the websites available for obtaining enhancers, promoters, and enhancer‐promoter interaction datasets. Finally, we review the application of the methods for identifying EPIs in diseases such as cancer.ConclusionsThe advance of computer technology has allowed traditional machine learning, and deep learning methods to be used to predict enhancer, promoter, and EPIs from genetic, genomic, and epigenomic features. In the past decade, models based on deep learning, especially transfer learning, have been proposed for directly predicting enhancer‐promoter interactions from DNA sequences, and these models can reduce the parameter training time required of bioinformatics researchers. We believe this review can provide detailed research frameworks for researchers who are beginning to study enhancers, promoters, and their interactions.

show abstract

Section: Methods For Identifying Enhancer/promoter Based On Deep-lear...mentioning

confidence: 99%

Section: Methods For Identifying Enhancer/promoter Based On Deep-lear...mentioning

confidence: 99%

Computational methods for identifying enhancer‐promoter interactions

Gong,

Chen,

Tang

et al. 2023

Quant. Biol.

View full text Add to dashboard Cite

show abstract

“…Our model finally obtains the probability values of the sample to be positive and negative respectively, and then compares the two, and selects the category corresponding to the larger probability value as the final prediction result of the sample. In order to fairly evaluate our model, we use the following five evaluation metrics as in previous studies: accuracy (ACC), sensitivity (Sn), specificity (Sp), Matthew's correlation coefficient (MCC), and area under ROC curve (AUC) [41][42][43]. Among them, we use ACC as the main metric to train and evaluate the model.…”

Section: Model Evaluationmentioning

confidence: 99%

AMP-EF: An Ensemble Framework of Extreme Gradient Boosting and Bidirectional Long Short-Term Memory Network for Identifying Antimicrobial Peptides

Zhang,

Zhao,

Liang

2023

MATCH

View full text Add to dashboard Cite

In recent years, bacterial resistance becomes a serious problem due to the abuse of antibiotics. Antimicrobial peptides (AMPs) have rapidly emerged as the best alternative to antibiotics because of their ability to rapidly target bacteria, fungi, viruses, and cancer cells and counteract the toxins they produce. In this study, a two-branch ensemble framework is proposed to identify AMPs, which integrates extreme gradient boosting (XGBoost) and bidirectional long short-term memory network (Bi-LSTM) with attention mechanism to form a stronger model. First, one-hot coding and -mer are used to represent the sequence features. Then, the feature vectors are input into the two base classifiers respectively to obtain two predicted values. Finally, the prediction results are obtained by compromise. As one of the classical machine learning methods, XGBoost has strong stability and can adapt to datasets of different sizes. Bi-LSTM recurses for each peptide from N-terminal to C-terminal and C-terminal to N-terminal, respectively. As the context information is provided, the model can make more accurate prediction. Our method achieves higher or highly comparable results across the eight independent test datasets. The ACC values of XUAMP, YADAMP, DRAMP, CAMP, LAMP, APD3, dbAMP, and DBAASP are 77.9%, 98.5%, 72.5%, 99.8%, 83.0%, 92.4%, 87.5%, and 84.6%, respectively. This shows that the two-branch ensemble structure is feasible and has strong generalization. The codes and datasets are accessible at https://github.com/z11code/AMP-EF.

show abstract

“…However, alternative approaches that consider structural properties hold promise for this task, as they provide discernible biological signals in the context of transcription initiation mechanisms. Machine learning techniques utilizing DNA duplex stability and base stacking energy of promoter, intergenic and transcribed sequences can be compared to demonstrate the unique features of the core promoter providing a high-scale annotation of these essential genetic regions. , Multiple machine learning and deep learning methods have been developed for bacterial promoter prediction, including iPromoter-2L, G4PromFinder, iPro70-FMWin, MUL-TiPLy, iProEP, SELECTOR, CNNProm, iPromoter-BnCNN, Promotech, iPro-GAN, PromoterLCNN, iPromoter-CLA, iPro-WAEL, and Sigma70Pred . These methods employ various algorithms and feature encoding schemes to identify promoters and their specific types in different bacterial species.…”

Section: Introductionmentioning

confidence: 99%

MLDSPP: Bacterial Promoter Prediction Tool Using DNA Structural Properties with Machine Learning and Explainable AI

Paul,

Olymon,

Martinez

et al. 2024

J. Chem. Inf. Model.

View full text Add to dashboard Cite

Bacterial promoters play a crucial role in gene expression by serving as docking sites for the transcription initiation machinery. However, accurately identifying promoter regions in bacterial genomes remains a challenge due to their diverse architecture and variations. In this study, we propose MLDSPP (Machine Learning and Duplex Stability based Promoter prediction in Prokaryotes), a machine learning-based promoter prediction tool, to comprehensively screen bacterial promoter regions in 12 diverse genomes. We leveraged biologically relevant and informative DNA structural properties, such as DNA duplex stability and base stacking, and state-of-the-art machine learning (ML) strategies to gain insights into promoter characteristics. We evaluated several machine learning models, including Support Vector Machines, Random Forests, and XGBoost, and assessed their performance using accuracy, precision, recall, specificity, F1 score, and MCC metrics. Our findings reveal that XGBoost outperformed other models and current state-of-the-art promoter prediction tools, namely Sigma70pred and iPromoter2L, achieving F1-scores >95% in most systems. Significantly, the use of one-hot encoding for representing nucleotide sequences complements these structural features, enhancing our XGBoost model's predictive capabilities. To address the challenge of model interpretability, we incorporated explainable AI techniques using Shapley values. This enhancement allows for a better understanding and interpretation of the predictions of our model. In conclusion, our study presents MLDSPP as a novel, generic tool for predicting promoter regions in bacteria, utilizing original downstream sequences as nonpromoter controls. This tool has the potential to significantly advance the field of bacterial genomics and contribute to our understanding of gene regulation in diverse bacterial systems.

show abstract

iPro-GAN: A novel model based on generative adversarial learning for identifying promoters and their strength

Cited by 13 publications

References 52 publications

Computational methods for identifying enhancer‐promoter interactions

Computational methods for identifying enhancer‐promoter interactions

AMP-EF: An Ensemble Framework of Extreme Gradient Boosting and Bidirectional Long Short-Term Memory Network for Identifying Antimicrobial Peptides

MLDSPP: Bacterial Promoter Prediction Tool Using DNA Structural Properties with Machine Learning and Explainable AI

Contact Info

Product

Resources

About