Learning Robust Multilabel Sample Specific Distances for Identifying HIV-1 Drug Resistance

Brand, Lodewijk; Yang, Xue; Li, Kai; Elbeleidy, Saad; Wang, Hua; Zhang, Hao; Nie, Feiping

doi:10.1089/cmb.2019.0329

Cited by 5 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, weighted categorical kernel functions were introduced to evaluate the contribution of different positions on the resistance prediction [ 15 ]. Recently, Brand expanded the application of the prediction model and proposed a multi-label classification model to predict the cross-resistance between RT sequences and five nucleoside analogs [ 16 ].…”

Section: Introductionmentioning

confidence: 99%

Revealing the Mutation Patterns of Drug-Resistant Reverse Transcriptase Variants of Human Immunodeficiency Virus through Proteochemometric Modeling

et al. 2021

View full text Add to dashboard Cite

Drug-resistant cases of human immunodeficiency virus (HIV) nucleoside reverse transcriptase inhibitors (NRTI) are constantly accumulating due to the frequent mutations of the reverse transcriptase (RT). Predicting the potential drug resistance of HIV-1 NRTIs could provide instructions for the proper clinical use of available drugs. In this study, a novel proteochemometric (PCM) model was constructed to predict the drug resistance between six NRTIs against different variants of RT. Forty-seven dominant mutation sites were screened using the whole protein of HIV-1 RT. Thereafter, the physicochemical properties of the dominant mutation sites can be derived to generate the protein descriptors of RT. Furthermore, by combining the molecular descriptors of NRTIs, PCM modeling can be constructed to predict the inhibition ability between RT variants and NRTIs. The results indicated that our PCM model could achieve a mean AUC value of 0.946 and a mean accuracy of 0.873 on the external validation set. Finally, based on PCM modeling, the importance of features was calculated to reveal the dominant amino acid distribution and mutation patterns on RT, to reflect the characteristics of drug-resistant sequences.

show abstract

Section: Introductionmentioning

confidence: 99%

Revealing the Mutation Patterns of Drug-Resistant Reverse Transcriptase Variants of Human Immunodeficiency Virus through Proteochemometric Modeling

et al. 2021

View full text Add to dashboard Cite

show abstract

“…1 demonstrates, when noise exists in data, which is widely existed in real world, the learned projection matrix may deviate from expected significantly. Considering that outliers and noises are difficult to be identified and eliminated in most cases, many researchers focus on improving the robustness of PCA by utilizing 2,p (0 < p < 2) or 1 -norm loss functions to alleviate this problem due to their robustness to noise [13,14,15,16,17,18]. 1 -PCA is proposed to obtain the projection matrix by minimizing the 1 norm reconstruction error [19], which is to decompose an image matrix with a weighted combination of the nuclear norm and of the 1 -norm [20,21].…”

Section: Introductionmentioning

confidence: 99%

Robust Principal Component Analysis: A Construction Error Minimization Perspective

Liu¹,

Cao²

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Principal Component Analysis (PCA) has been widely used in data mining and analysis as it can significantly reduce data dimensionality while maintaining the most useful information carried in data. However, from the perspective of minimizing reconstruction error, each data sample's error is squared, and therefore sensitive to widely existed outliers and noises which increases dramatically as data dimensionality grows. To alleviate the problem, many researchers focus on improving the robustness of PCA by using more robust norm such as 2,p (p < 2) or 1 -norm loss formulation. In this paper we propose a novel optimization framework to systematically solve 2,p and 1 -norm-based PCA problem with rigorous theoretical guarantee, based on which we investigate a very computationally economic updating version. The proposed methods are not only robust to outliers but also easy to implement.

show abstract

“…( 1) by relaxing the nonconvex 0 -norm to a convex one (e.g. 1 -norm) Liu andWang [2015, 2018], Liu et al [2019a], Yang et al [2019], Brand et al [2020] to obtain approximated solutions faster Mairal et al [2009], Wu et al [2018] or by focusing on reducing the computation complexity Rubinstein et al [2008], Gilboa et al [2018].…”

Section: Introductionmentioning

confidence: 99%

Exact Sparse Orthogonal Dictionary Learning

Liu,

Zhao,

Wang

2021

Preprint

Self Cite

View full text Add to dashboard Cite

Over the past decade, learning a dictionary from input images for sparse modeling has been one of the topics which receive most research attention in image processing and compressed sensing. Most existing dictionary learning methods consider an over-complete dictionary, such as the K-SVD method, which may result in high mutual incoherence and therefore has a negative impact in recognition. On the other side, the sparse codes are usually optimized by adding the 0 or 1 -norm penalty, but with no strict sparsity guarantee. In this paper, we propose an orthogonal dictionary learning model which can obtain strictly sparse codes and orthogonal dictionary with global sequence convergence guarantee. We find that our method can result in better denoising results than over-complete dictionary based learning methods, and has the additional advantage of high computation efficiency.

show abstract

Learning Robust Multilabel Sample Specific Distances for Identifying HIV-1 Drug Resistance

Cited by 5 publications

References 17 publications

Revealing the Mutation Patterns of Drug-Resistant Reverse Transcriptase Variants of Human Immunodeficiency Virus through Proteochemometric Modeling

Revealing the Mutation Patterns of Drug-Resistant Reverse Transcriptase Variants of Human Immunodeficiency Virus through Proteochemometric Modeling

Robust Principal Component Analysis: A Construction Error Minimization Perspective

Exact Sparse Orthogonal Dictionary Learning

Contact Info

Product

Resources

About