Journal: FEMS Microbiology Ecology

Article Title: Seemingly trivial secondary factors may determine microbial competition: a cautionary tale on the impact of iron supplementation through corrosion

doi: 10.1093/femsec/fiab002

Figure Lengend Snippet: Feast length of P. acidivorans dominated enrichments, cultivated with continuous dosage of chromium (orange circles), nickel (blue squares) or iron (green triangles). Biomass from a stable enrichment in \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{upgreek} \usepackage{mathrsfs} \setlength{\oddsidemargin}{-69pt} \begin{document} }{}${{{\mathbf{SBR}}}_{{\bm{HCl}}}}$\end{document} (cycles 1–10) was cultivated for ten cycles by replacing HCl with H 2 SO 4 as acid source (cycles 10–20). From cycle 20 on, the bioreactors were supplemented with increasing amounts of chromium, nickel or iron, up to final concentrations of 40, 30 and 35 μM, respectively.

Article Snippet: The reasoning for switching from HCl to H 2 SO 4 during cultivation was to reduce the corrosive effect of HCl on the stainless-steel inlet feed triplet of the bioreactors (SAE 316L stainless steel, Applikon, Delft, The Netherlands) (Kovach ).

Techniques:

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BREAST dataset. Left: latent space of the SAE. Right: Distribution using a Gaussian Kernel

Article Snippet: Fig. 5 BREAST SAE Netbio Matrix: features versus hidden layer:Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint,Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques:

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BREAST dataset: Accuracy using 3 seeds and 4-fold cross validation: comparison with PLS-DA, Random Forest, Logistic Regression, SVM and NN

Article Snippet: Fig. 5 BREAST SAE Netbio Matrix: features versus hidden layer:Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint,Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques: Biomarker Discovery, Comparison

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BREAST SAE Netbio Matrix: features versus hidden layer:Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} ℓ 1 , 1 constraint,Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} ℓ 1 constraint

Article Snippet: Fig. 5 BREAST SAE Netbio Matrix: features versus hidden layer:Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint,Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques:

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: Top 5 features on the BREAST dataset. From left to right: SAE, PLS-DA, Random Forest, SVM and NN

Article Snippet: Fig. 5 BREAST SAE Netbio Matrix: features versus hidden layer:Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint,Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques:

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BRAIN dataset. Left: latent space of the SAE, Red and green squares are “test” patients. Right: Distribution using a Gaussian kernel

Article Snippet: Fig. 8 BRAIN SAE Netbio Matrix: features versus hidden layer: Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint, Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques:

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BRAIN dataset Accuracy using 3 seeds and 4-fold cross validation: comparison with PLS-DA, Random Forest , SVM and NN

Article Snippet: Fig. 8 BRAIN SAE Netbio Matrix: features versus hidden layer: Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint, Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques: Biomarker Discovery, Comparison

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BRAIN SAE Netbio Matrix: features versus hidden layer: Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} ℓ 1 , 1 constraint, Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} ℓ 1 constraint

Article Snippet: Fig. 8 BRAIN SAE Netbio Matrix: features versus hidden layer: Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint, Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques:

Journal: BMC Bioinformatics

Article Title: Learning a confidence score and the latent space of a new supervised autoencoder for diagnosis and prognosis in clinical metabolomic studies

doi: 10.1186/s12859-022-04900-x

Figure Lengend Snippet: BRAIN dataset with 7,022 features : Top 5 features selected by the SAE, PLS-DA, Random Forests, SVM and NN

Article Snippet: Fig. 8 BRAIN SAE Netbio Matrix: features versus hidden layer: Left with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1,1}$$\end{document} l 1 , 1 constraint, Right with \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\ell _{1}$$\end{document} l 1 constraint Figure shows the matrix ( \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d \times n$$\end{document} d × n ) of the network connections between the input layer (d feature-neurons) and the hidden layer (n neurons).

Techniques: