Are batch effects still relevant in the age of big data?

Advancing atmospheric solids analysis probe mass spectrometry applications: a multifaceted approach to optimising clinical data set generation

The use of rapid mass spectrometry techniques, such as atmospheric-solids-analysis-probe mass spectrometry (ASAP-MS), in the analysis of metabolite patterns in clinical samples holds significant promise for developing new diagnostic tools and enabling rapid disease screening. The rapid measurement times, ease of use, and relatively low cost of ASAP-MS makes it an appealing option for use in clinical settings. However, despite the potential of such approaches, a number of important experimental considerations are often overlooked. As well as instrument-specific choices and settings, these include the treatment of background noise and/or contaminant peaks in the mass spectra, and the influence of consumables, different users, and batch effects more generally. The present study assesses the impact of these various factors on measurement accuracy and reproducibility, using human brain and cerebrospinal fluid samples as examples. Based on our results, we make a series of recommendations relating to optimisation of measurement and cleaning protocols, consumable selection, and batch effect detection and correction, in order to optimise the reliability and reproducibility of ASAP-MS measurements in clinical settings.

SATINN v2: automated image analysis for mouse testis histology with multi-laboratory data integration†

Analysis of testis histology is fundamental to the study of male fertility, but it is a slow task with a high skill threshold. Here, we describe new neural network models for the automated classification of cell types and tubule stages from whole-slide brightfield images of mouse testis. The cell type classifier recognizes 14 cell types, including multiple steps of meiosis I prophase, with an external validation accuracy of 96%. The tubule stage classifier distinguishes all 12 canonical tubule stages with external validation accuracy of 63%, which increases to 96% when allowing for ±1 stage tolerance. We addressed generalizability of SATINN, through extensive training diversification and testing on external (non-training population) wildtype and mutant datasets. This allowed us to use SATINN to successfully process data generated in multiple laboratories. We used SATINN to analyze testis images from eight different mutant lines, generated from three different labs with a range of tissue processing protocols. Finally, we show that it is possible to use SATINN output to cluster histology images in latent space, which, when applied to the eight mutant lines, reveals known relationships in their pathology. This work represents significant progress towards a tool for robust, automated testis histopathology that can be used by multiple labs.

Balancing ethical data sharing and open science for reproducible research in biomedical data science

Analyses of large-scale health data in biomedical data science can help uncover new treatments and deepen our understanding of disease and fundamental biology. Here we examine the balance between ethical and responsible data sharing and open science practices that are essential for reproducible research in biomedical data science.

Assessing and mitigating batch effects in large-scale omics studies

Batch effects in omics data are notoriously common technical variations unrelated to study objectives, and may result in misleading outcomes if uncorrected, or hinder biomedical discovery if over-corrected. Assessing and mitigating batch effects is crucial for ensuring the reliability and reproducibility of omics data and minimizing the impact of technical variations on biological interpretation. In this review, we highlight the profound negative impact of batch effects and the urgent need to address this challenging problem in large-scale omics studies. We summarize potential sources of batch effects, current progress in evaluating and correcting them, and consortium efforts aiming to tackle them.

Thinking points for effective batch correction on biomedical data

Batch effects introduce significant variability into high-dimensional data, complicating accurate analysis and leading to potentially misleading conclusions if not adequately addressed. Despite technological and algorithmic advancements in biomedical research, effectively managing batch effects remains a complex challenge requiring comprehensive considerations. This paper underscores the necessity of a flexible and holistic approach for selecting batch effect correction algorithms (BECAs), advocating for proper BECA evaluations and consideration of artificial intelligence-based strategies. We also discuss key challenges in batch effect correction, including the importance of uncovering hidden batch factors and understanding the impact of design imbalance, missing values, and aggressive correction. Our aim is to provide researchers with a robust framework for effective batch effects management and enhancing the reliability of high-dimensional data analyses.

Ten quick tips for ensuring machine learning model validity

Artificial Intelligence (AI) and Machine Learning (ML) models are increasingly deployed on biomedical and health data to shed insights on biological mechanism, predict disease outcomes, and support clinical decision-making. However, ensuring model validity is challenging. The 10 quick tips described here discuss useful practices on how to check AI/ML models from 2 perspectives-the user and the developer.

Particle uptake in cancer cells can predict malignancy and drug resistance using machine learning

Tumor heterogeneity is a primary factor that contributes to treatment failure. Predictive tools, capable of classifying cancer cells based on their functions, may substantially enhance therapy and extend patient life span. The connection between cell biomechanics and cancer cell functions is used here to classify cells through mechanical measurements, via particle uptake. Machine learning (ML) was used to classify cells based on single-cell patterns of uptake of particles with diverse sizes. Three pairs of human cancer cell subpopulations, varied in their level of drug resistance or malignancy, were studied. Cells were allowed to interact with fluorescently labeled polystyrene particles ranging in size from 0.04 to 3.36 μm and analyzed for their uptake patterns using flow cytometry. ML algorithms accurately classified cancer cell subtypes with accuracy rates exceeding 95%. The uptake data were especially advantageous for morphologically similar cell subpopulations. Moreover, the uptake data were found to serve as a form of "normalization" that could reduce variation in repeated experiments.

Data pre-processing for analyzing microbiome data - A mini review

The human microbiome is an emerging research frontier due to its profound impacts on health. High-throughput microbiome sequencing enables studying microbial communities but suffers from analytical challenges. In particular, the lack of dedicated preprocessing methods to improve data quality impedes effective minimization of biases prior to downstream analysis. This review aims to address this gap by providing a comprehensive overview of preprocessing techniques relevant to microbiome research. We outline a typical workflow for microbiome data analysis. Preprocessing methods discussed include quality filtering, batch effect correction, imputation of missing values, normalization, and data transformation. We highlight strengths and limitations of each technique to serve as a practical guide for researchers and identify areas needing further methodological development. Establishing robust, standardized preprocessing will be essential for drawing valid biological conclusions from microbiome studies.

Correcting batch effects in large-scale multiomics studies using a reference-material-based ratio method

BACKGROUND

Batch effects are notoriously common technical variations in multiomics data and may result in misleading outcomes if uncorrected or over-corrected. A plethora of batch-effect correction algorithms are proposed to facilitate data integration. However, their respective advantages and limitations are not adequately assessed in terms of omics types, the performance metrics, and the application scenarios.

RESULTS

As part of the Quartet Project for quality control and data integration of multiomics profiling, we comprehensively assess the performance of seven batch effect correction algorithms based on different performance metrics of clinical relevance, i.e., the accuracy of identifying differentially expressed features, the robustness of predictive models, and the ability of accurately clustering cross-batch samples into their own donors. The ratio-based method, i.e., by scaling absolute feature values of study samples relative to those of concurrently profiled reference material(s), is found to be much more effective and broadly applicable than others, especially when batch effects are completely confounded with biological factors of study interests. We further provide practical guidelines for implementing the ratio based approach in increasingly large-scale multiomics studies.

CONCLUSIONS

Multiomics measurements are prone to batch effects, which can be effectively corrected using ratio-based scaling of the multiomics data. Our study lays the foundation for eliminating batch effects at a ratio scale.

How missing value imputation is confounded with batch effects and what you can do about it

In data-processing pipelines, upstream steps can influence downstream processes because of their sequential nature. Among these data-processing steps, batch effect (BE) correction (BEC) and missing value imputation (MVI) are crucial for ensuring data suitability for advanced modeling and reducing the likelihood of false discoveries. Although BEC-MVI interactions are not well studied, they are ultimately interdependent. Batch sensitization can improve the quality of MVI. Conversely, accounting for missingness also improves proper BE estimation in BEC. Here, we discuss how BEC and MVI are interconnected and interdependent. We show how batch sensitization can improve any MVI and bring attention to the idea of BE-associated missing values (BEAMs). Finally, we discuss how batch-class imbalance problems can be mitigated by borrowing ideas from machine learning.

Integrating massive RNA-seq data to elucidate transcriptome dynamics in Drosophila melanogaster

The volume of ribonucleic acid (RNA)-seq data has increased exponentially, providing numerous new insights into various biological processes. However, due to significant practical challenges, such as data heterogeneity, it is still difficult to ensure the quality of these data when integrated. Although some quality control methods have been developed, sample consistency is rarely considered and these methods are susceptible to artificial factors. Here, we developed MassiveQC, an unsupervised machine learning-based approach, to automatically download and filter large-scale high-throughput data. In addition to the read quality used in other tools, MassiveQC also uses the alignment and expression quality as model features. Meanwhile, it is user-friendly since the cutoff is generated from self-reporting and is applicable to multimodal data. To explore its value, we applied MassiveQC to Drosophila RNA-seq data and generated a comprehensive transcriptome atlas across 28 tissues from embryogenesis to adulthood. We systematically characterized fly gene expression dynamics and found that genes with high expression dynamics were likely to be evolutionarily young and expressed at late developmental stages, exhibiting high nonsynonymous substitution rates and low phenotypic severity, and they were involved in simple regulatory programs. We also discovered that human and Drosophila had strong positive correlations in gene expression in orthologous organs, revealing the great potential of the Drosophila system for studying human development and disease.

Artificial intelligence-driven electrochemical immunosensing biochips in multi-component detection

Electrochemical Immunosensing (EI) combines electrochemical analysis and immunology principles and is characterized by its simplicity, rapid detection, high sensitivity, and specificity. EI has become an important approach in various fields, such as clinical diagnosis, disease prevention and treatment, environmental monitoring, and food safety. However, EI multi-component detection still faces two major bottlenecks: first, the lack of cost-effective and portable detection platforms; second, the difficulty in eliminating batch differences and accurately decoupling signals from multiple analytes. With the gradual maturation of biochip technology, high-throughput analysis and portable detection utilizing the advantages of miniaturized chips, high sensitivity, and low cost have become possible. Meanwhile, Artificial Intelligence (AI) enables accurate decoupling of signals and enhances the sensitivity and specificity of multi-component detection. We believe that by evaluating and analyzing the characteristics, benefits, and linkages of EI, biochip, and AI technologies, we may considerably accelerate the development of EI multi-component detection. Therefore, we propose three specific prospects: first, AI can enhance and optimize the performance of the EI biochips, addressing the issue of multi-component detection for portable platforms. Second, the AI-enhanced EI biochips can be widely applied in home care, medical healthcare, and other areas. Third, the cross-fusion and innovation of EI, biochip, and AI technologies will effectively solve key bottlenecks in biochip detection, promoting interdisciplinary development. However, challenges may arise from AI algorithms that are difficult to explain and limited data access. Nevertheless, we believe that with technological advances and further research, there will be more methods and technologies to overcome these challenges.

Dealing with missing values in proteomics data

Proteomics data are often plagued with missingness issues. These missing values (MVs) threaten the integrity of subsequent statistical analyses by reduction of statistical power, introduction of bias, and failure to represent the true sample. Over the years, several categories of missing value imputation (MVI) methods have been developed and adapted for proteomics data. These MVI methods perform their tasks based on different prior assumptions (e.g., data is normally or independently distributed) and operating principles (e.g., the algorithm is built to address random missingness only), resulting in varying levels of performance even when dealing with the same dataset. Thus, to achieve a satisfactory outcome, a suitable MVI method must be selected. To guide decision making on suitable MVI method, we provide a decision chart which facilitates strategic considerations on datasets presenting different characteristics. We also bring attention to other issues that can impact proper MVI such as the presence of confounders (e.g., batch effects) which can influence MVI performance. Thus, these too, should be considered during or before MVI.

Clinical stratification improves the diagnostic accuracy of small omics datasets within machine learning and genome-scale metabolic modelling methods

BACKGROUND

Recently, multi-omic machine learning architectures have been proposed for the early detection of cancer. However, for rare cancers and their associated small datasets, it is still unclear how to use the available multi-omics data to achieve a mechanistic prediction of cancer onset and progression, due to the limited data available. Hepatoblastoma is the most frequent liver cancer in infancy and childhood, and whose incidence has been lately increasing in several developed countries. Even though some studies have been conducted to understand the causes of its onset and discover potential biomarkers, the role of metabolic rewiring has not been investigated in depth so far.

METHODS

Here, we propose and implement an interpretable multi-omics pipeline that combines mechanistic knowledge from genome-scale metabolic models with machine learning algorithms, and we use it to characterise the underlying mechanisms controlling hepatoblastoma.

RESULTS AND CONCLUSIONS

While the obtained machine learning models generally present a high diagnostic classification accuracy, our results show that the type of omics combinations used as input to the machine learning models strongly affects the detection of important genes, reactions and metabolic pathways linked to hepatoblastoma. Our method also suggests that, in the context of computer-aided diagnosis of cancer, optimal diagnostic accuracy can be achieved by adopting a combination of omics that depends on the patient's clinical characteristics.

Perspectives for better batch effect correction in mass-spectrometry-based proteomics

Mass-spectrometry-based proteomics presents some unique challenges for batch effect correction. Batch effects are technical sources of variation, can confound analysis and usually non-biological in nature. As proteomic analysis involves several stages of data transformation from spectra to protein, the decision on when and what to apply batch correction on is often unclear. Here, we explore several relevant issues pertinent to batch effect correct considerations. The first involves applications of batch effect correction requiring prior knowledge on batch factors and exploring data to uncover new/unknown batch factors. The second considers recent literature that suggests there is no single best batch effect correction algorithm---i.e., instead of a best approach, one may instead ask, what is a suitable approach. The third section considers issues of batch effect detection. And finally, we look at potential developments for proteomic-specific batch effect correction methods and how to do better functional evaluations on batch corrected data.