A New method of LncRNA classification based on ensemble learning

Dai, Zongrui

doi:10.1088/1742-6596/1994/1/012002

Cited by 3 publications

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…One of the possible solutions to that problem is to use Random Forest-based ensembles. These models are widely utilized in different areas because they achieve more robust and stable performance than others [15]. Deep Forest is a multilayer cascade model based on non-differentiable modules (Random Forests) in contrast to deep neural networks.…”

Section: Related Workmentioning

confidence: 99%

Estimation of Vegetation Indices With Random Kernel Forests

Devyatkin¹

2023

IEEE Access

View full text Add to dashboard Cite

Vegetation indexes help perform precision farming because they provide useful information regarding moisture, nutrient content, and crop health. Primary sources of those indexes are satellites and unmanned aerial vehicles equipped with expensive multispectral sensors. Reducing the price of obtaining such information would increase the availability of precision farming. Several studies have proposed deep neural network methods to estimate the indexes from RGB color images. However, these studies report relatively large errors for mature plants, when highly non-linear relationships between image RGB bands and vegetation indexes arise. One could apply multilayer random forest-based models (Deep Forests) to solve this problem, but they have limited discriminative power and ability on catching non-linear relationships between image features. The cornerstone of the Deep Forests is that at each layer they enrich original features with embeddings containing empiric class probabilities from previous layers, although these probabilities deliver limited information. In this paper, we propose methods, which combine ideas of Deep Forests, Random Forests of multivariate trees, and global pruning of Random Forests to tackle these problems. We applied oblique (linear) and kernel (non-linear) trees as basic classifiers of the Deep Forest to improve discriminative power. We also utilized a method to refine Random Forests with a global loss optimization. This method helps to generate more expressive embeddings at each layer of the Deep Forest, which significantly improves results of the data analysis. In the experiments, we compared those methods with AlexNet and ResNet-based neural networks on several image classification datasets as well as on the NDVI prediction task. The experiments on image classification show that the proposed Deep Forest-based methods provide competitive results on datasets with small and medium size of feature-set. The results of the NDVI prediction task indicate that these methods are robust to senescence of plants and outperform neural network-based solutions.

show abstract

Section: Related Workmentioning

confidence: 99%

Estimation of Vegetation Indices With Random Kernel Forests

Devyatkin¹

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It designed multi k-mer frequency and ORF coverage proportion as input of their random forest model [13]. Also, other machine learning such as stacked ensemble models and neural networks were also applied in lncRNA identification [14,15]. The above methods were machine learning-based methods with nucleotide features as their input.…”

Section: Introductionmentioning

confidence: 99%

LncPNdeep: A long non-coding RNA classifier based on Large Language Model with peptide and nucleotide embedding

Dai,

Deng

2023

Preprint

Self Cite

View full text Add to dashboard Cite

Long non-coding RNA plays an important role in various gene transcription and peptide interactions. Classifying lncRNAs from coding RNA is a crucial step in bioinformatics analysis which seriously affects the post-analysis for transcriptome annotation. Although several machine learning-based methods were developed to classify lncRNAs, these methods were mainly focused on nucleotide features without considering the information from the peptide sequence. To integrate both nucleotide and peptide information in lncRNA classification, one efficient deep learning is desired. In this study, we developed one concatenated deep neural network named LncPNdeep to combine this information. LncPNdeep incorporates both peptide and nucleotide embedding from masked language modeling (MLM), being able to discover complex associations between sequence information and lncRNA classification. LncPNdeep achieves state-of-the-art performance in the human transcript database compared with other existing methods (Accuracy=97.1%). It also exhibits superior generalization ability in cross-species comparison, maintaining consistent accuracy and F1 scores compared to other methods. The combination of nucleotide and peptide information makes LncPNdeep able to facilitate the identification of novel lncRNA and gain high accuracy for classification. Our code is available athttps://github.com/yatoka233/LncPNdeep

show abstract