Package: MMINP 0.1.1

Wenli Tang

MMINP: Microbe-Metabolite Interactions-Based Metabolic Profiles Predictor

Implements a computational framework to predict microbial community-based metabolic profiles with 'O2PLS' model. It provides procedures of model training and prediction. Paired microbiome and metabolome data are needed for modeling, and the trained model can be applied to predict metabolites of analogous environments using new microbial feature abundances.

Authors:Wenli Tang [aut, cre], Guangchuang Yu [aut, ths]

MMINP_0.1.1.tar.gz
MMINP_0.1.1.zip(r-4.5)MMINP_0.1.1.zip(r-4.4)MMINP_0.1.1.zip(r-4.3)
MMINP_0.1.1.tgz(r-4.5-any)MMINP_0.1.1.tgz(r-4.4-any)MMINP_0.1.1.tgz(r-4.3-any)
MMINP_0.1.1.tar.gz(r-4.5-noble)MMINP_0.1.1.tar.gz(r-4.4-noble)
MMINP_0.1.1.tgz(r-4.4-emscripten)MMINP_0.1.1.tgz(r-4.3-emscripten)
MMINP.pdf |MMINP.html✨
MMINP/json (API)

# Install 'MMINP' in R:

install.packages('MMINP', repos = c('https://yulab-smu.r-universe.dev', 'https://cloud.r-project.org'))

Bug tracker:https://github.com/yulab-smu/mminp/issues

Datasets:

MMINP_trained_model - (Data) A MMINP model
test_metab - (Data) Normalized metabolite abundances for MMINP prediction
test_metag - (Data) Normalized gene family abundances for MMINP prediction
train_metab - (Data) Normalized metabolite abundances for MMINP training
train_metag - (Data) Normalized gene family abundances for MMINP training

On CRAN:

metabolite-prediction metabolites microbes

4.81 score 13 stars 9 scripts 141 downloads 8 exports 49 dependencies

Last updated 2 years agofrom:77359aeb9a. Checks:9 OK. Indexed: yes.

Target	Result	Latest binary
Doc / Vignettes	OK	Mar 06 2025
R-4.5-win	OK	Mar 06 2025
R-4.5-mac	OK	Mar 06 2025
R-4.5-linux	OK	Mar 06 2025
R-4.4-win	OK	Mar 06 2025
R-4.4-mac	OK	Mar 06 2025
R-4.4-linux	OK	Mar 06 2025
R-4.3-win	OK	Mar 06 2025
R-4.3-mac	OK	Mar 06 2025

Exports:checkInputdata compareFeatures filterFeatures get_Components MMINP.predict MMINP.preprocess MMINP.train O2PLSvip

Dependencies:cli colorspace curl dplyr fansi farver forecast fracdiff generics ggplot2 glue gtable isoband jsonlite labeling lattice lifecycle lmtest magrittr MASS Matrix mgcv munsell nlme nnet OmicsPLS pillar pkgconfig quadprog quantmod R6 RColorBrewer Rcpp RcppArmadillo rlang scales softImpute tibble tidyselect timeDate tseries TTR urca utf8 vctrs viridisLite withr xts zoo

Introduction to MMINP

| Wenli Tang and GuangChuang Yu | School of Basic Medical Sciences, Southern Medical University

Rendered fromMMINP.Rmdusingknitr::rmarkdownon Mar 06 2025.

Last update: 2022-07-04
Started: 2022-03-28

Citation

Development and contributors

Readme and manuals

Help Manual

Help page	Topics
Calculation of the orthogonal variable influence on projection	calOrthVIP
Calculation of the predictive variable influence on projection	calPredVIP
Check if input data satisfies input conditions	checkInputdata
Compare features' abundance obtained by prediction and measurement.	compareFeatures
Filter features of input table according to prevalence and/or abundance	filterFeatures
Estimate components for O2-PLS method	get_Components
get components number from Cross-validate procedure of O2PLS	get_cvo2mComponent
(Data) A MMINP model	MMINP_trained_model
Predict metabolites from new microbiome samples using MMINP model.	MMINP.predict
Data Preprocessing function for MMINP	MMINP.preprocess
Train MMINP model using paired microbial features and metabolites data	MMINP.train
Evaluate the importance of variables in O2PLS models	O2PLSvip
Print function for MMINP.train	print.mminp
estimation of the sum of squares of deviations	ssd
(Data) Normalized metabolite abundances for MMINP prediction	test_metab
(Data) Normalized gene family abundances for MMINP prediction	test_metag
(Data) Normalized metabolite abundances for MMINP training	train_metab
(Data) Normalized gene family abundances for MMINP training	train_metag