Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Allergic Reactions

Allergic Reactions

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by

Same author

Risk of perinatal psychiatric disorder among women with a history of premenstrual disorder: a nationwide register-based study from Sweden.

BMJ open·2026

Same author

Comparative analysis of gut microbiome alterations in early- and late-onset preeclampsia: A case control study.

PloS one·2026

Same author

Association of early initiation of breastfeeding on postpartum depression-multi-centric longitudinal cohort study in Nepal.

Frontiers in global women's health·2026

Same author

Shotgun metagenomic mapping of saliva reveals insights into diversity and function of the oral microbiome in pregnancy.

Scientific reports·2026

Same author

Patterns of menopausal hormone therapy dispensing over 15 years-A Swedish register-based cohort study.

Acta obstetricia et gynecologica Scandinavica·2026

Same author

Endocrine therapy and COVID-19 outcomes in women with breast cancer: a nationwide register- based matched cohort study.

BMC cancer·2026

Search research articles

Related Experiment Video

Updated: Jan 9, 2026

Noninvasive Sampling of Mucosal Lining Fluid for the Quantification of In Vivo Upper Airway Immune-mediator Levels

Noninvasive Sampling of Mucosal Lining Fluid for the Quantification of In Vivo Upper Airway Immune-mediator Levels

Published on: August 7, 2017

Predicting allergy and postpartum depression from an incomplete compositional microbiome.

Andrey Shternshis^1,2, Bangzhuo Tong^3,4, Alkistis Skalkidou⁵

¹Department of Information Technology, Uppsala University, Box 337, Uppsala, 75105, Sweden. andrey.shternshis@it.uu.se.

|December 6, 2025

Summary

This summary is machine-generated.

This study introduces a new method to handle missing data in biological time series, improving predictions for infant food allergies and postpartum depression using gut microbiome data.

Keywords:

Compositional data Forecasting Gut microbiome Imputation Log-transformation

More Related Videos

Generating a Reproducible Model of Mid-Gestational Maternal Immune Activation using PolyI:C to Study Susceptibility and Resilience in Offspring

Generating a Reproducible Model of Mid-Gestational Maternal Immune Activation using PolyI:C to Study Susceptibility and Resilience in Offspring

Published on: August 17, 2022

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Published on: October 15, 2019

Related Experiment Videos

Last Updated: Jan 9, 2026

Noninvasive Sampling of Mucosal Lining Fluid for the Quantification of In Vivo Upper Airway Immune-mediator Levels

Noninvasive Sampling of Mucosal Lining Fluid for the Quantification of In Vivo Upper Airway Immune-mediator Levels

Published on: August 7, 2017

Generating a Reproducible Model of Mid-Gestational Maternal Immune Activation using PolyI:C to Study Susceptibility and Resilience in Offspring

Generating a Reproducible Model of Mid-Gestational Maternal Immune Activation using PolyI:C to Study Susceptibility and Resilience in Offspring

Published on: August 17, 2022

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Microbiota Analysis Using Two-step PCR and Next-generation 16S rRNA Gene Sequencing

Published on: October 15, 2019

Area of Science:

Microbiology
Bioinformatics
Computational Biology

Background:

High-throughput biological studies often generate time series compositional data.
Missing data points in these time series can significantly reduce dataset completeness and impact analysis.
Accurate prediction of health outcomes from biological data is crucial.

Purpose of the Study:

To develop and evaluate a novel method for binary classification of compositional time series data with missing values.
To improve prediction accuracy for health-related outcomes using longitudinal microbiome data.
To identify key microbial features indicative of specific health conditions.

Main Methods:

Proposed a method combining imputation for missing values, dimensionality reduction, and logarithmic transformation of compositional data.
Utilized artificial data alongside true measurements for imputation to supplement datasets.
Applied the method to two case studies involving gut microbiome time series data.

Main Results:

Successfully predicted infants' food allergies from gut microbiome data with 0.72 balanced accuracy.
Forecasted postpartum depression from pregnancy gut microbiome data with 0.62 balanced accuracy.
Identified ratios of bacterial abundance in microbiome time series as statistically significant indicators of depression.

Conclusions:

The proposed method effectively handles missing data in compositional time series for improved predictive modeling.
Gut microbiome composition over time is a valuable predictor for infant food allergies and postpartum depression.
Microbiome-derived features offer statistically significant insights into depression.