MD-SVM: a novel SVM-based algorithm for the motif discovery of transcription factor binding sites

Hu, Jialu; Wang, Jingru; Lin, Jianan; Liu, Tianwei; Zhong, Yuanke; Liu, Jie; Zheng, Yanyan; Gao, Yiqun; He, Junhao; Shang, Xuequn

doi:10.1186/s12859-019-2735-3

Cited by 12 publications

(6 citation statements)

References 34 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For custom PWM-based predictions, the MEME software suite (Bailey et al 2015 ) includes multiple tools relating to motif analysis. Alternatively, sequences can be queried for TF binding sites at the PePPER webserver (de Jong et al 2012 ), or, with more recent approaches for TF binding site prediction based on Bayesian Markov models (Ge et al 2021 ), support vector machines (Hu et al 2019 ), random forest models (Ardakani et al 2019 ), and deep learning methods (Oliveira Monteiro et al 2022 ).…”

Section: Knowledge-driven Approachesmentioning

confidence: 99%

From genotype to phenotype: computational approaches for inferring microbial traits relevant to the food industry

Karlsen

Rau

Sánchez

et al. 2023

FEMS Microbiology Reviews

View full text Add to dashboard Cite

When selecting microbial strains for the production of fermented foods, various microbial phenotypes need to be taken into account to achieve target product characteristics, such as biosafety, flavor, texture, and health-promoting effects. Through continuous advances in sequencing technologies, microbial whole-genome sequences of increasing quality can now be obtained both cheaper and faster, which increases the relevance of genome-based characterization of microbial phenotypes. Prediction of microbial phenotypes from genome sequences makes it possible to quickly screen large strain collections in silico to identify candidates with desirable traits. Several microbial phenotypes relevant to the production of fermented foods can be predicted using knowledge-based approaches, leveraging our existing understanding of the genetic and molecular mechanisms underlying those phenotypes. In the absence of this knowledge, data-driven approaches can be applied to estimate genotype-phenotype relationships based on large experimental datasets. Here, we review computational methods that implement knowledge- and data-driven approaches for phenotype prediction, as well as methods that combine elements from both approaches. Furthermore, we provide examples of how these methods have been applied in industrial biotechnology, with special focus on the fermented food industry.

show abstract

Section: Knowledge-driven Approachesmentioning

confidence: 99%

From genotype to phenotype: computational approaches for inferring microbial traits relevant to the food industry

Karlsen

Rau

Sánchez

et al. 2023

FEMS Microbiology Reviews

View full text Add to dashboard Cite

show abstract

“…The twofold classification strategy of SVM was initially recommended as it can manage precisely with complex nonlinear limit models. Yet, this way of computing parameters is computationally expensive (Wang, et al, 2019). Hence, an enhanced multi-instance algorithm dependent on the SVM algorithm, which is similar to instance feature selection by Wang, et al (2019), is proposed to be applied when working with small sample instances, nonlinear and high dimensional design perception.…”

Section: Instance Learningmentioning

confidence: 99%

Diabetes Prediction Using Enhanced SVM and Deep Neural Network Learning Techniques

Nagaraj

Deepalakshmi

2021

International Journal of Healthcare Information Systems and Informatics

View full text Add to dashboard Cite

Diabetes, caused by the rise in level of glucose in blood, has many latest devices to identify from blood samples. Diabetes, when unnoticed, may bring many serious diseases like heart attack, kidney disease. In this way, there is a requirement for solid research and learning model’s enhancement in the field of gestational diabetes identification and analysis. SVM is one of the powerful classification models in machine learning, and similarly, Deep Neural Network is powerful under deep learning models. In this work, we applied Enhanced Support Vector Machine and Deep Learning model Deep Neural Network for diabetes prediction and screening. The proposed method uses Deep Neural Network obtaining its input from the output of Enhanced Support Vector Machine, thus having a combined efficacy. The dataset we considered includes 768 patients’ data with eight major features and a target column with result “Positive” or “Negative”. Experiment is done with Python and the outcome of our demonstration shows that the deep Learning model gives more efficiency for diabetes prediction.

show abstract

“…It involves the social, economic, water quality status, pollution load, pollution source parameters, water quality parameters, and hydrological conditions of the entire water area. The water environment management system is of non-linearity, non-uniformity, network type, and controllability [8].…”

Section: Introductionmentioning

confidence: 99%

Analysis of Water Pollution Causes and Control Countermeasures in Liaohe Estuary via Support Vector Machine Particle Swarm Optimization under Deep Learning

Liu¹,

Ye²,

Chen³

et al. 2022

Computer Modeling in Engineering &Amp; Sciences

View full text Add to dashboard Cite

This study explores the loss or degradation of the ecosystem and its service function in the Liaohe estuary coastal zone due to the deterioration of water quality. A prediction system based on support vector machine (SVM)-particle swarm optimization (PSO) (SVM-PSO) algorithm is proposed under the background of deep learning. SVM-PSO algorithm is employed to analyze the pollution status of the Liaohe estuary, so is the difference in water pollution of different sea consuming types. Based on the analysis results for causes of pollution, the control countermeasures of water pollution in Liaohe estuary are put forward. The results suggest that the water pollution index prediction model based on SVM-PSO algorithm shows the maximum error of 2.41%, the average error of 1.24% in predicting the samples, the root mean square error (RMSE) of 5.36 × 10 −4 , and the square of correlation coefficient of 0.91. Therefore, the prediction system in this study is feasible. At present, the water pollution status of Liaohe estuary is of moderate and severe levels of eutrophication, and the water pollution status basically remains at the level of mild pollution. The general trend is from phosphorus moderate restricted eutrophication to phosphorus restricted potential eutrophication. To sum up, the SVM-PSO algorithm shows good sewage prediction ability, which can be applied and promoted in water pollution control and has reliable reference significance.

show abstract

MD-SVM: a novel SVM-based algorithm for the motif discovery of transcription factor binding sites

Cited by 12 publications

References 34 publications

From genotype to phenotype: computational approaches for inferring microbial traits relevant to the food industry

From genotype to phenotype: computational approaches for inferring microbial traits relevant to the food industry

Diabetes Prediction Using Enhanced SVM and Deep Neural Network Learning Techniques

Analysis of Water Pollution Causes and Control Countermeasures in Liaohe Estuary via Support Vector Machine Particle Swarm Optimization under Deep Learning

Contact Info

Product

Resources

About