arXiv subjects

Rosa Aghdam

Publications and source records attributed to Rosa Aghdam.

4 recordsLinked to original sources

arXiv2025

MiNAA-WebApp: A Web-Based Tool for the Visualization and Analysis of Microbiome Networks

Microbial networks, representing microbes as nodes and their interactions as edges, are crucial for understanding community dynamics in various environments. Analyzing microbiome networks is crucial for identifying keystone taxa that play central roles in maintaining microbial community structure and function, assessing how environmental changes such as pollution, climate shifts, or land use affect microbial dynamics, tracking disease progression by revealing alterations in microbial interactions over time, and predicting microbial community responses to interventions such as antibiotics, probiotics, or changes in diet and habitat. The complexity of microbial interactions necessitates the use of computational tools such as the MiNAA-WebApp, available at https://minaa.wid.wisc.edu, which enhances the accessibility of the Microbiome Network Alignment Algorithm MiNAA. This tool allows researchers to align microbial networks and explore ecological relationships and community dynamics without extensive computational skills. Originally, MiNAA's command-line interface limited its usability for those without programming backgrounds. The web-based MiNAA-WebApp addresses this shortcoming by offering an intuitive interface with visualization tools, allowing easy exploration and analysis of microbial networks. The web app is designed for microbiome networks but also applicable to other biological networks, broadening its use in computational biology and making network-based research accessible to a wider audience.

q-bio.MN↗

arXiv2024

CMiNet: R package for learning the Consensus Microbiome Network

Understanding complex interactions within microbiomes is essential for exploring their roles in health and disease. However, constructing reliable microbiome networks often poses a challenge due to variations in the output of different network inference algorithms. To address this issue, we present CMiNet, an R package designed to generate a consensus microbiome network by integrating results from multiple established network construction methods. CMiNet incorporates nine widely used algorithms, including Pearson, Spearman, Biweight Midcorrelation (Bicor), SparCC, SpiecEasi, SPRING, GCoDA, and CCLasso, along with a novel algorithm based on conditional mutual information (CMIMN). By combining the strengths of these algorithms, CMiNet generates a single, weighted consensus network that provides a more stable and comprehensive representation of microbial interactions. The package includes customizable functions for network construction, visualization, and analysis, allowing users to explore network structures at different threshold levels and assess connectivity and reliability. CMiNet is designed to handle both quantitative and compositional data, ensuring broad applicability for researchers aiming to understand the intricate relationships within microbiome communities. Availability: Source code is freely available at https://github.com/solislemuslab/CMiNet.

stat.AP↗

arXiv2024

Human Limits in Machine Learning: Prediction of Plant Phenotypes Using Soil Microbiome Data

The preservation of soil health is a critical challenge in the 21st century due to its significant impact on agriculture, human health, and biodiversity. We provide the first deep investigation of the predictive potential of machine learning models to understand the connections between soil and biological phenotypes. We investigate an integrative framework performing accurate machine learning-based prediction of plant phenotypes from biological, chemical, and physical properties of the soil via two models: random forest and Bayesian neural network. We show that prediction is improved when incorporating environmental features like soil physicochemical properties and microbial population density into the models, in addition to the microbiome information. Exploring various data preprocessing strategies confirms the significant impact of human decisions on predictive performance. We show that the naive total sum scaling normalization that is commonly used in microbiome research is not the optimal strategy to maximize predictive power. Also, we find that accurately defined labels are more important than normalization, taxonomic level or model characteristics. In cases where humans are unable to classify samples accurately, machine learning model performance is limited. Lastly, we provide domain scientists via a full model selection decision tree to identify the human choices that optimize model prediction power. Our work is accompanied by open source reproducible scripts (https://github.com/solislemuslab/soil-microbiome-nn) for maximum outreach among the microbiome research community.

stat.ML↗

arXiv2022

MiNAA: Microbiome Network Alignment Algorithm

Our Microbiome Network Alignment Algorithm (MiNAA) aligns two microbial networks using a combination of the GRAph ALigner (GRAAL) algorithm and the Hungarian algorithm. Network alignment algorithms find pairs of nodes (one node from the first network and the other node from the second network) that have the highest similarity. Traditionally, similarity has been defined as topological similarity such that the neighborhoods around the two nodes are similar. Recent implementations of network alignment methods such as NETAL and L-GRAAL also include measures of biological similarity, yet these methods are restricted to one specific type of biological similarity (e.g. sequence similarity in L-GRAAL). Our work extends existing network alignment implementations by allowing any type of biological similarity to be input by the user. This flexibility allows the user to choose whatever measure of biological similarity is suitable for the study at hand. In addition, unlike most existing network alignment methods that are tailored for protein or gene interaction networks, our work is the first one suited for microbiome networks.

q-bio.MN↗