AoP-LSE: Antioxidant Proteins Classification Using Deep Latent Space Encoding of Sequence Features

Usman, Muhammad; Khan, Shujaat; Park, Seongyong; Lee, Jeong-A

doi:10.3390/cimb43030105

Cited by 12 publications

(4 citation statements)

References 31 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Thus, the SVM-based CKSAAP model was selected as the final prediction model in this study. The CKSAAP feature has also been successfully used in various studies to address several prediction problems [18, 19, 24, 81, 82].…”

Section: Discussionmentioning

confidence: 99%

PMTPred: Machine Learning Based Prediction of Protein Methyltransferases using the Composition of k-spaced Amino Acid Pairs

Yadav,

Gupta,

Singh

2023

Preprint

View full text Add to dashboard Cite

Protein methyltransferases (PMTs) are a group of enzymes that help to catalyze the transfer of a methyl group to its substrates. These enzymes play an important role in epigenetic regulation and are able to methylate various substrates with DNA, RNA, protein, and small-molecule secondary metabolites. Dysregulation of methyltransferases is involved in different types of human cancers. However, in light of the well-recognized significance of PMTs, it becomes crucial to have reliable and fast methods for identifying these proteins. In the present work, we propose a machine-learning-based method for the identification of PMTs. Various sequence-based features were calculated and prediction models were developed using different machine-learning methods. A ten-fold cross-validation technique was used for model training. The SVM-based CKSAAP model gave the best prediction and achieved the highest accuracy of 87.94% with balance sensitivity (88.8%) and specificity (87.11%) with MCC of 0.759 and AUROC of 0.945. Also, SVM performed better than the compared deep learning algorithms for the prediction of PMTs. Finally, the best model was implemented in standalone software of PMTPred to facilitate the prediction of PMTs. The PMTPred achieved 86.50% prediction accuracy with 82.33% sensitivity, 90.67% specificity and ROC value 0.939 on the blind dataset. The standalone software of PMTPred is freely available for download at https://github.com/ArvindYadav7/PMTPred for research and academic use.

show abstract

Section: Discussionmentioning

confidence: 99%

PMTPred: Machine Learning Based Prediction of Protein Methyltransferases using the Composition of k-spaced Amino Acid Pairs

Yadav,

Gupta,

Singh

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…VirusImmu adopted Z-descriptor and E-descriptor to describe the physicochemical properties of the residues, but there are also other descriptors such as CKSAAP [30][31][32][33] which may improve the performance. The future aim should be implemented with higher accuracy without throwing away proteins or restricting protein length.…”

Section: Discussionmentioning

confidence: 99%

VirusImmu: a novel ensemble machine learning approach for viral immunogenicity prediction

Li,

Zhao,

Tai

et al. 2023

Preprint

View full text Add to dashboard Cite

BackgroundThe viruses threats provoke concerns regarding their sustained epidemic transmission, making the development of vaccines particularly important. In the prolonged and costly process of vaccine development, the most important initial step is to identify protective immunogens. Machine learning (ML) approaches are productive in analyzing big data such as microbial proteomes, and can remarkably reduce the cost of experimental work in developing novel vaccine candidates.ResultsWe intensively evaluated the immunogenicity prediction power of eight commonly-used ML methods by random sampling cross validation on a large dataset consisting of known viral immunogens and non-immunogens we manually curated from the public domain. XGBoost, kNN and RF showed the strongest predictive power. We then proposed a novel soft-voting based ensemble approach (VirusImmu), which demonstrated a powerful and stable capability for viral immunogenicity prediction across the test set and external test set irrespective of protein sequence length. VirusImmu was successfully applied to facilitate identifying linear B cell epitopes against African Swine Fever Virus as confirmed by indirect ELISA in vitro.ConclusionsVirusImmu exhibited tremendous potentials in predicting immunogenicity of viral protein segments. It is freely accessible athttps://github.com/zhangjbig/VirusImmu.

show abstract

“…Since their inception, deep neural networks (DNNs) have demonstrated remarkable performance and have been recognized as state-of-the-art methods, achieving near-human performance in various applications, e.g., image processing [1], bioinformatics [2], natural language processing [3], etc. The efficacy of DNNs becomes particularly evident in scenarios involving vast amounts of data with complex features that may not be easily discernible by humans.…”

Section: Introductionmentioning

confidence: 99%

ECHO: Energy-Efficient Computation Harnessing Online Arithmetic—An MSDF-Based Accelerator for DNN Inference

Ibrahim,

Usman,

Lee

2024

Electronics

Self Cite

View full text Add to dashboard Cite

Deep neural network (DNN) inference demands substantial computing power, resulting in significant energy consumption. A large number of negative output activations in convolution layers are rendered zero due to the invocation of the ReLU activation function. This results in a substantial number of unnecessary computations that consume significant amounts of energy. This paper presents ECHO, an accelerator for DNN inference designed for computation pruning, utilizing an unconventional arithmetic paradigm known as online/most significant digit first (MSDF) arithmetic, which performs computations in a digit-serial manner. The MSDF digit-serial computation of online arithmetic enables overlapped computation of successive operations, leading to substantial performance improvements. The online arithmetic, coupled with a negative output detection scheme, facilitates early and precise recognition of negative outputs. This, in turn, allows for the timely termination of unnecessary computations, resulting in a reduction in energy consumption. The implemented design has been realized on the Xilinx Virtex-7 VU3P FPGA and subjected to a comprehensive evaluation through a rigorous comparative analysis involving widely used performance metrics. The experimental results demonstrate promising power and performance improvements compared to contemporary methods. In particular, the proposed design achieved average improvements in power consumption of up to 81%, 82.9%, and 40.6% for VGG-16, ResNet-18, and ResNet-50 workloads compared to the conventional bit-serial design, respectively. Furthermore, significant average speedups of 2.39×, 2.6×, and 2.42× were observed when comparing the proposed design to conventional bit-serial designs for the VGG-16, ResNet-18, and ResNet-50 models, respectively.

show abstract

AoP-LSE: Antioxidant Proteins Classification Using Deep Latent Space Encoding of Sequence Features

Cited by 12 publications

References 31 publications

PMTPred: Machine Learning Based Prediction of Protein Methyltransferases using the Composition of k-spaced Amino Acid Pairs

PMTPred: Machine Learning Based Prediction of Protein Methyltransferases using the Composition of k-spaced Amino Acid Pairs

VirusImmu: a novel ensemble machine learning approach for viral immunogenicity prediction

ECHO: Energy-Efficient Computation Harnessing Online Arithmetic—An MSDF-Based Accelerator for DNN Inference

Contact Info

Product

Resources

About