Machine Learning Methods for Analysis of Metabolic Data and Metabolic Pathway Modeling

Machine learning in biofluid mechanics: A review of recent developments

This review paper comprehensively examines recent advancements in machine learning (ML) applications within biofluid mechanics, with a targeted focus on enabling clinically actionable diagnostics and simulations. It demonstrates how ML, and in particular physics-informed ML methods, are used to enhance the analysis and understanding of intricate biofluid dynamics. The review systematically analyzes various ML techniques, detailing their strengths and limitations in modeling biofluid behaviors. By integrating physics-informed ML methods, such as Physics-Informed Neural Networks (PINNs), this work addresses critical challenges in translating complex biofluid dynamics into practical clinical tools. Differentiating itself from previous literature, this review not only summarizes current methods but also proposes potential solutions-including data augmentation, transfer learning, and hybrid modeling approaches (e.g., PINNs)-to overcome challenges related to limited datasets and the integration of complex physics. The review emphasizes ML's ability to enhance diagnostic accuracy, enable personalized treatment strategies, and accelerate computational simulations for applications like cardiovascular disease detection and respiratory disorder diagnosis, with findings showing that ML-driven approaches can reduce diagnostic errors by up to 30 % in cardiovascular applications and improve early detection rates in metabolomics-based diagnostics. Findings indicate that while ML techniques have significantly improved predictive capabilities in biofluid dynamics, challenges such as data scarcity and multi-scale physical integration remain critical. By outlining strategies to bridge the gap between ML advancements and clinical implementation, this review provides a robust framework for future research aimed at integrating ML with biofluid mechanics to revolutionize healthcare delivery. The paper concludes by identifying future research directions aimed at further integrating ML with domain-specific physical insights to achieve more reliable and accurate biofluid models.

Binary classification of gynecological cancers based on ATR-FTIR spectroscopy and machine learning using urine samples

Making an early diagnosis of cancer still in the early stages, when completely asymptomatic, is the challenge modern medicine has been setting for several decades. In gynecology, no effective screening has yet been found and approved for endometrial and ovarian cancer. Mammography is an effective screening method for Breast Cancer, as well as Pap Test for Cervical Cancer, but they are underused in third world countries because of their expensive and specific instrumentation. Previous studies showed how "machine learning analysis methods" of the spectral information obtained from dried urine samples could provide good accuracy in differentiation between healthy and ovarian or endometrial cancer. In this study, we also apply ATR-FTIR spectrometry's practical, fast, and relatively inexpensive principles to liquid urine analysis from 309 patients undergoing surgical treatment for benign or malignant diseases (endometrium, breast, cervix, vulvar and ovarian cancer). The data obtained from those liquid samples were then analyzed to train a machine learning model to classify healthy VS cancer patients. We obtained an accuracy of > 91%, and we also identified discriminant wavelengths (2093, 1774 cm-1). These frequencies are close to already reported ones in other studies, indicating a possible association with tumor presence and/or progression.

Recent Developments in Single-Cell Metabolomics by Mass Spectrometry─A Perspective

Recent advancements in single-cell (sc) resolution analyses, particularly in sc transcriptomics and sc proteomics, have revolutionized our ability to probe and understand cellular heterogeneity. The study of metabolism through small molecules, metabolomics, provides an additional level of information otherwise unattainable by transcriptomics or proteomics by shedding light on the metabolic pathways that translate gene expression into functional outcomes. Metabolic heterogeneity, critical in health and disease, impacts developmental outcomes, disease progression, and treatment responses. However, dedicated approaches probing the sc metabolome have not reached the maturity of other sc omics technologies. Over the past decade, innovations in sc metabolomics have addressed some of the practical limitations, including cell isolation, signal sensitivity, and throughput. To fully exploit their potential in biological research, however, remaining challenges must be thoroughly addressed. Additionally, integrating sc metabolomics with orthogonal sc techniques will be required to validate relevant results and gain systems-level understanding. This perspective offers a broad-stroke overview of recent mass spectrometry (MS)-based sc metabolomics advancements, focusing on ongoing challenges from a biologist's viewpoint, aimed at addressing pertinent and innovative biological questions. Additionally, we emphasize the use of orthogonal approaches and showcase biological systems that these sophisticated methodologies are apt to explore.

De novo biosynthesis of 4,6-dihydroxycoumarin in Escherichia coli

Coumarins and their derivatives possess crucial biochemical and pharmaceutical properties. However, the exploration of the coumarin biosynthesis pathways remains limited, restricting their microbial biosynthesis, especially for hydroxycoumarins. In this work, we designed and verified novel artificial pathways to produce a valuable compound 4,6-dihydroxycoumarin (4,6-DHC) in Escherichia coli. Based on the retrosynthesis analysis, multiple routes were designed and verified by extending the shikimate pathway, screening the potential enzymes, and characterizing the enzymes involved. Rare codon optimization and protein engineering strategies were applied to optimize the rate-limiting steps. De novo biosynthesis of 4,6-DHC was achieved using the cheap carbon source glycerol, and the titer can reach 18.3 ± 0.7 mg L-1. Ultimately, inducible regulation of critical pathway genes with a tetracycline-inducible controller yielded a significant boost in 4,6-DHC production, achieving a titer of 56.7 ± 2.1 mg L-1. This research successfully created a microbial platform for 4,6-dihydroxycoumarin production and demonstrated a generalizable strategy for synthesizing valuable compounds.

Artificial intelligence driven innovations in biochemistry: A review of emerging research frontiers

Artificial intelligence (AI) has become a powerful tool in biochemistry, greatly enhancing research capabilities by enabling the analysis of complex datasets, predicting molecular interactions, and accelerating drug discovery. As AI continues to evolve, its applications in biochemistry are poised to expand, revolutionizing both theoretical and applied research. This review explores current and potential AI applications in biochemistry, with a focus on data analysis, molecular modeling, enzyme engineering, and metabolic pathway studies. Key AI techniques-such as machine learning algorithms, natural language processing, and AI-based molecular modeling-are discussed. The review also highlights emerging research areas benefiting from AI, including personalized medicine and synthetic biology. The methodology involves an extensive analysis of existing literature, particularly peer-reviewed studies on AI applications in biochemistry. AI-driven tools like AlphaFold, which have significantly advanced protein structure prediction, are evaluated alongside AI's role in expediting drug discovery. The review also addresses challenges such as data quality, model interpretability, and ethical considerations. Results indicate that AI has expanded the scope of biochemical research by facilitating large-scale data analysis, enhancing molecular simulations, and opening new avenues of inquiry. However, challenges remain, particularly in data handling and ethical concerns. In conclusion, AI is transforming biochemistry by driving innovation and expanding research possibilities. Future advancements in AI algorithms, interdisciplinary collaboration, and integration with automated techniques will be crucial to fully unlocking AI's potential in advancing biochemical research.

Recent advances in culture medium design for enhanced production of monoclonal antibodies in CHO cells: A comparative study of machine learning and systems biology approaches

The production of monoclonal antibodies (mAbs) using Chinese Hamster Ovary (CHO) cells has revolutionized the treatment of numerous diseases, solidifying their position as a cornerstone of the biopharmaceutical industry. However, achieving maximum mAb production while upholding strict product quality standards remains a significant hurdle. Optimizing cell culture media emerges as a critical factor in this endeavor, requiring a nuanced understanding of the complex interplay of nutrients, growth factors, and other components that profoundly influence cellular growth, productivity, and product quality. Significant strides have been made in media optimization, including techniques such as media blending, one factor at a time, and statistical design of experiments approaches. The present review provides a comprehensive analysis of the recent advancements in culture media design strategies, focusing on the comparative application of systems biology (SB) and machine learning (ML) approaches. The applications of SB and ML in optimizing CHO cell culture medium and successful examples of their use are summarized. Finally, we highlight the immense potential of integrating SB and ML, emphasizing the development of hybrid models that leverage the strengths of both approaches for robust, efficient, and scalable optimization of mAb production in CHO cells. This review provides a roadmap for researchers and industry professionals to navigate the complex landscape of mAb production optimization, paving the way for developing next-generation CHO cell culture media that drive significant improvements in yield and productivity.

Metabolomic profiling of dengue infection: unraveling molecular signatures by LC-MS/MS and machine learning models

BACKGROUND & OBJECTIVE

The progression of dengue fever to severe dengue (SD) is a major public health concern that impairs the capacity of the medical system to predict and treat dengue patients. Hence, the present study used a metabolomic approach integrated with machine models to identify differentially expressed metabolites in patients with SD compared to nonsevere patients and healthy controls.

METHODS

Comprehensively, the plasma was collected at different clinical phases during dengue without warning signs (DWOW, N = 10), dengue with warning signs (DWW, N = 10), and SD (N = 10) at different stages [i.e., day of admission (DOA), day of defervescence (DOD), and day of convalescent (DOC)] in comparison to healthy control (HC). The samples were subjected to LC‒ESI‒MS/MS to identify metabolites. Statistical and machine learning analyses were performed using R and Python language. Further, biomarker, pathway and correlation analysis was performed to identify potential predictors of dengue.

RESULTS & CONCLUSION

A total of 423 metabolites were identified in all the study groups. Paired and unpaired t-tests revealed 14 highly differentially expressed metabolites between and across the dengue groups, with four metabolites (shikimic acid, ureidosuccinic acid, propionyl carnitine, and alpha-tocopherol) showing significant differences compared to HC. Furthermore, biomarker (ROC) analysis revealed 11 potential molecules with a significant AUC value of 1 that could serve as potential biomarkers for identifying different dengue clinical stages that are beneficial for predicting dengue disease outcomes. The logistic regression model revealed that S-adenosylhomocysteine, hypotaurine, and shikimic acid metabolites could be beneficial indicators for predicting severe dengue, with an accuracy and AUC of 0.75. The data showed that dengue infection is related to lipid metabolism, oxidative stress, inflammation, metabolomic adaptation, and virus manipulation. Moreover, the biomarkers had a significant correlation with biochemical parameters like platelet count, and hematocrit. These results shed some light on host-derived small-molecule biomarkers that are associated with dengue severity and novel insights into metabolomics mechanisms interlinked with disease severity.

Artificial Intelligence in Metabolomics: A Current Review

Metabolomics and artificial intelligence (AI) form a synergistic partnership. Metabolomics generates large datasets comprising hundreds to thousands of metabolites with complex relationships. AI, aiming to mimic human intelligence through computational modeling, possesses extraordinary capabilities for big data analysis. In this review, we provide a recent overview of the methodologies and applications of AI in metabolomics studies in the context of systems biology and human health. We first introduce the AI concept, history, and key algorithms for machine learning and deep learning, summarizing their strengths and weaknesses. We then discuss studies that have successfully used AI across different aspects of metabolomic analysis, including analytical detection, data preprocessing, biomarker discovery, predictive modeling, and multi-omics data integration. Lastly, we discuss the existing challenges and future perspectives in this rapidly evolving field. Despite limitations and challenges, the combination of metabolomics and AI holds great promises for revolutionary advancements in enhancing human health.

Enhancing Withanolide Production in the Withania Species: Advances in In Vitro Culture and Synthetic Biology Approaches

Withanolides are naturally occurring steroidal lactones found in certain species of the Withania genus, especially Withania somnifera (commonly known as Ashwagandha). These compounds have gained considerable attention due to their wide range of therapeutic properties and potential applications in modern medicine. To meet the rapidly growing demand for withanolides, innovative approaches such as in vitro culture techniques and synthetic biology offer promising solutions. In recent years, synthetic biology has enabled the production of engineered withanolides using heterologous systems, such as yeast and bacteria. Additionally, in vitro methods like cell suspension culture and hairy root culture have been employed to enhance withanolide production. Nevertheless, one of the primary obstacles to increasing the production of withanolides using these techniques has been the intricacy of the biosynthetic pathways for withanolides. The present article examines new developments in withanolide production through in vitro culture. A comprehensive summary of viable traditional methods for producing withanolide is also provided. The development of withanolide production in heterologous systems is examined and emphasized. The use of machine learning as a potent tool to model and improve the bioprocesses involved in the generation of withanolide is then discussed. In addition, the control and modification of the withanolide biosynthesis pathway by metabolic engineering mediated by CRISPR are discussed.

Can digital twin efforts shape microorganism-based alternative food?

With the continuous increment in global population growth, compounded by post-pandemic food security challenges due to labor shortages, effects of climate change, political conflicts, limited land for agriculture, and carbon emissions control, addressing food production in a sustainable manner for future generations is critical. Microorganisms are potential alternative food sources that can help close the gap in food production. For the development of more efficient and yield-enhancing products, it is necessary to have a better understanding on the underlying regulatory molecular pathways of microbial growth. Nevertheless, as microbes are regulated at multiomics scales, current research focusing on single omics (genomics, proteomics, or metabolomics) independently is inadequate for optimizing growth and product output. Here, we discuss digital twin (DT) approaches that integrate systems biology and artificial intelligence in analyzing multiomics datasets to yield a microbial replica model for in silico testing before production. DT models can thus provide a holistic understanding of microbial growth, metabolite biosynthesis mechanisms, as well as identifying crucial production bottlenecks. Our argument, therefore, is to support the development of novel DT models that can potentially revolutionize microorganism-based alternative food production efficiency.

Predicting pathways for old and new metabolites through clustering

The diverse metabolic pathways are fundamental to all living organisms, as they harvest energy, synthesize biomass components, produce molecules to interact with the microenvironment, and neutralize toxins. While the discovery of new metabolites and pathways continues, the prediction of pathways for new metabolites can be challenging. It can take vast amounts of time to elucidate pathways for new metabolites; thus, according to HMDB (Human Metabolome Database), only 60% of metabolites get assigned to pathways. Here, we present an approach to identify pathways based on metabolite structure. We extracted 201 features from SMILES annotations and identified new metabolites from PubMed abstracts and HMDB. After applying clustering algorithms to both groups of features, we quantified correlations between metabolites, and found the clusters accurately linked 92% of known metabolites to their respective pathways. Thus, this approach could be valuable for predicting metabolic pathways for new metabolites.

Prospective Detection of Early Lung Cancer in Patients With COPD in Regular Care by Electronic Nose Analysis of Exhaled Breath

BACKGROUND

Patients with COPD are at high risk of lung cancer developing, but no validated predictive biomarkers have been reported to identify these patients. Molecular profiling of exhaled breath by electronic nose (eNose) technology may qualify for early detection of lung cancer in patients with COPD.

RESEARCH QUESTION

Can eNose technology be used for prospective detection of early lung cancer in patients with COPD?

STUDY DESIGN AND METHODS

BreathCloud is a real-world multicenter prospective follow-up study using diagnostic and monitoring visits in day-to-day clinical care of patients with a standardized diagnosis of asthma, COPD, or lung cancer. Breath profiles were collected at inclusion in duplicate by a metal-oxide semiconductor eNose positioned at the rear end of a pneumotachograph (SpiroNose; Breathomix). All patients with COPD were managed according to standard clinical care, and the incidence of clinically diagnosed lung cancer was prospectively monitored for 2 years. Data analysis involved advanced signal processing, ambient air correction, and statistics based on principal component (PC) analysis, linear discriminant analysis, and receiver operating characteristic analysis.

RESULTS

Exhaled breath data from 682 patients with COPD and 211 patients with lung cancer were available. Thirty-seven patients with COPD (5.4%) demonstrated clinically manifest lung cancer within 2 years after inclusion. Principal components 1, 2, and 3 were significantly different between patients with COPD and those with lung cancer in both training and validation sets with areas under the receiver operating characteristic curve of 0.89 (95% CI, 0.83-0.95) and 0.86 (95% CI, 0.81-0.89). The same three PCs showed significant differences (P < .01) at baseline between patients with COPD who did and did not subsequently demonstrate lung cancer within 2 years, with a cross-validation value of 87% and an area under the receiver operating characteristic curve of 0.90 (95% CI, 0.84-0.95).

INTERPRETATION

Exhaled breath analysis by eNose identified patients with COPD in whom lung cancer became clinically manifest within 2 years after inclusion. These results show that eNose assessment may detect early stages of lung cancer in patients with COPD.

Integrated data-driven cross-disciplinary framework to prevent chemical water pollution

Access to a clean and healthy environment is a human right and a prerequisite for maintaining a sustainable ecosystem. Experts across domains along the chemical life cycle have traditionally operated in isolation, leading to limited connectivity between upstream chemical innovation to downstream development of water-treatment technologies. This fragmented and historically reactive approach to managing emerging contaminants has resulted in significant externalized societal costs. Herein, we propose an integrated data-driven framework to foster proactive action across domains to effectively address chemical water pollution. By implementing this integrated framework, it will not only enhance the capabilities of experts in their respective fields but also create opportunities for novel approaches that yield co-benefits across multiple domains. To successfully operationalize the integrated framework, several concerted efforts are warranted, including adopting open and FAIR (findable, accessible, interoperable, and reusable) data practices, developing common knowledge bases/platforms, and staying vigilant against new substance "properties" of concern.

DeepRT: Predicting compounds presence in pathway modules and classifying into module classes using deep neural networks based on molecular properties

Metabolic pathways play a crucial role in understanding the biochemistry of organisms. In metabolic pathways, modules refer to clusters of interconnected reactions or sub-networks representing specific functional units or biological processes within the overall pathway. In pathway modules, compounds are major elements and refer to the various molecules that participate in the biochemical reactions within the pathway modules. These molecules can include substrates, intermediates and final products. Determining the presence relation of compounds and pathway modules is essential for synthesizing new molecules and predicting hidden reactions. To date, several computational methods have been proposed to address this problem. However, all methods only predict the metabolic pathways and their types, not the pathway modules. To address this issue, we proposed a novel deep learning model, DeepRT that integrates message passing neural networks (MPNNs) and transformer encoder. This combination allows DeepRT to effectively extract global and local structure information from the molecular graph. The model is designed to perform two tasks: first, determining the present relation of the compound with the pathway module, and second, predicting the relation of query compound and module classes. The proposed DeepRT model evaluated on a dataset comprising compounds and pathway modules, and it outperforms existing approaches.

Integrating Omics Data in Genome-Scale Metabolic Modeling: A Methodological Perspective for Precision Medicine

Recent advancements in omics technologies have generated a wealth of biological data. Integrating these data within mathematical models is essential to fully leverage their potential. Genome-scale metabolic models (GEMs) provide a robust framework for studying complex biological systems. GEMs have significantly contributed to our understanding of human metabolism, including the intrinsic relationship between the gut microbiome and the host metabolism. In this review, we highlight the contributions of GEMs and discuss the critical challenges that must be overcome to ensure their reproducibility and enhance their prediction accuracy, particularly in the context of precision medicine. We also explore the role of machine learning in addressing these challenges within GEMs. The integration of omics data with GEMs has the potential to lead to new insights, and to advance our understanding of molecular mechanisms in human health and disease.

Deciphering the recent trends in pesticide bioremediation using genome editing and multi-omics approaches: a review

Pesticide pollution in recent times has emerged as a grave environmental problem contaminating both aquatic and terrestrial ecosystems owing to their widespread use. Bioremediation using gene editing and system biology could be developed as an eco-friendly and proficient tool to remediate pesticide-contaminated sites due to its advantages and greater public acceptance over the physical and chemical methods. However, it is indispensable to understand the different aspects associated with microbial metabolism and their physiology for efficient pesticide remediation. Therefore, this review paper analyses the different gene editing tools and multi-omics methods in microbes to produce relevant evidence regarding genes, proteins and metabolites associated with pesticide remediation and the approaches to contend against pesticide-induced stress. We systematically discussed and analyzed the recent reports (2015-2022) on multi-omics methods for pesticide degradation to elucidate the mechanisms and the recent advances associated with the behaviour of microbes under diverse environmental conditions. This study envisages that CRISPR-Cas, ZFN and TALEN as gene editing tools utilizing Pseudomonas, Escherichia coli and Achromobacter sp. can be employed for remediation of chlorpyrifos, parathion-methyl, carbaryl, triphenyltin and triazophos by creating gRNA for expressing specific genes for the bioremediation. Similarly, systems biology accompanying multi-omics tactics revealed that microbial strains from Paenibacillus, Pseudomonas putida, Burkholderia cenocepacia, Rhodococcus sp. and Pencillium oxalicum are capable of degrading deltamethrin, p-nitrophenol, chlorimuron-ethyl and nicosulfuron. This review lends notable insights into the research gaps and provides potential solutions for pesticide remediation by using different microbe-assisted technologies. The inferences drawn from the current study will help researchers, ecologists, and decision-makers gain comprehensive knowledge of value and application of systems biology and gene editing in bioremediation assessments.

Association of Metabolomic Biomarkers with Sleeve Gastrectomy Weight Loss Outcomes

This prospective observational study aimed to evaluate the association of metabolomic alterations with weight loss outcomes following sleeve gastrectomy (SG). We evaluated the metabolomic profile of serum and feces prior to SG and three months post-SG, along with weight loss outcomes in 45 adults with obesity. The percent total weight loss for the highest versus the lowest weight loss tertiles (T3 vs. T1) was 17.0 ± 1.3% and 11.1 ± 0.8%, p < 0.001. Serum metabolite alterations specific to T3 at three months included a decrease in methionine sulfoxide concentration as well as alterations to tryptophan and methionine metabolism (p < 0.03). Fecal metabolite changes specific to T3 included a decrease in taurine concentration and perturbations to arachidonic acid metabolism, and taurine and hypotaurine metabolism (p < 0.002). Preoperative metabolites were found to be highly predictive of weight loss outcomes in machine learning algorithms, with an average area under the curve of 94.6% for serum and 93.4% for feces. This comprehensive metabolomics analysis of weight loss outcome differences post-SG highlights specific metabolic alterations as well as machine learning algorithms predictive of weight loss. These findings could contribute to the development of novel therapeutic targets to enhance weight loss outcomes after SG.

Bayesian kinetic modeling for tracer-based metabolomic data

BACKGROUND

Stable Isotope Resolved Metabolomics (SIRM) is a new biological approach that uses stable isotope tracers such as uniformly [Formula: see text]-enriched glucose ([Formula: see text]-Glc) to trace metabolic pathways or networks at the atomic level in complex biological systems. Non-steady-state kinetic modeling based on SIRM data uses sets of simultaneous ordinary differential equations (ODEs) to quantitatively characterize the dynamic behavior of metabolic networks. It has been increasingly used to understand the regulation of normal metabolism and dysregulation in the development of diseases. However, fitting a kinetic model is challenging because there are usually multiple sets of parameter values that fit the data equally well, especially for large-scale kinetic models. In addition, there is a lack of statistically rigorous methods to compare kinetic model parameters between different experimental groups.

RESULTS

We propose a new Bayesian statistical framework to enhance parameter estimation and hypothesis testing for non-steady-state kinetic modeling of SIRM data. For estimating kinetic model parameters, we leverage the prior distribution not only to allow incorporation of experts' knowledge but also to provide robust parameter estimation. We also introduce a shrinkage approach for borrowing information across the ensemble of metabolites to stably estimate the variance of an individual isotopomer. In addition, we use a component-wise adaptive Metropolis algorithm with delayed rejection to perform efficient Monte Carlo sampling of the posterior distribution over high-dimensional parameter space. For comparing kinetic model parameters between experimental groups, we propose a new reparameterization method that converts the complex hypothesis testing problem into a more tractable parameter estimation problem. We also propose an inference procedure based on credible interval and credible value. Our method is freely available for academic use at https://github.com/xuzhang0131/MCMCFlux .

CONCLUSIONS

Our new Bayesian framework provides robust estimation of kinetic model parameters and enables rigorous comparison of model parameters between experimental groups. Simulation studies and application to a lung cancer study demonstrate that our framework performs well for non-steady-state kinetic modeling of SIRM data.

Accurate Classification and Prediction of Acute Myocardial Infarction through an ARMD Procedure

The risk stratification of acute myocardial infarction (AMI) patients is of prime importance for clinical management and prognosis assessment. Thus, we propose an ensemble machine learning analysis procedure named ADASYN-RFECV-MDA-DNN (ARMD) to address sample-unbalanced problems and enable stratification and prediction of AMI outcomes. The ARMD analysis procedure was applied to the NMR data of sera from 534 AMI-related subjects in four categories with an extremely imbalanced sample proportion. Firstly, the adaptive synthetic sampling (ADASYN) algorithm was used to address the issue of the original sample imbalance. Secondly, the recursive feature elimination with cross-validation (RFECV) processing and random forest mean decrease accuracy (RF-MDA) algorithm was performed to identify the differential metabolites corresponding to each AMI outcome. Finally, the deep neural network (DNN) was employed to classify and predict AMI events, and its performance was evaluated by comparing the four traditional machine learning methods. Compared with the other four machine learning models, DNN presented consistent superiority in almost all of the model parameters including precision, f1-score, sensitivity, specificity, area under the receiver operating characteristic curve (AUC), and classification accuracy, highlighting the potential of deep learning in classification and stratification of clinical diseases. The ARMD analysis procedure was a practical analysis tool for supervised classification and regression modeling of clinical diseases.

Environmental phenol exposure associates with urine metabolome alteration in young Northeast Indian females

Urinary biomonitoring delivers the most accurate environmental phenols exposure assessment. However, environmental phenol exposure-related biomarkers are required to improve risk assessment to understand the internal processes perturbed, which may link exposure to specific health outcomes. This study aimed to investigate the association between environmental phenols exposure and the metabolome of young adult females from India. Urinary metabolomics was performed using liquid chromatography-mass spectrometry. Environmental phenols-related metabolic biomarkers were investigated by comparing the low and high exposure of environmental phenols. Seven potential biomarkers, namely histidine, cysteine-s-sulfate, 12-KETE, malonic acid, p-hydroxybenzoic acid, PE (36:2), and PS (36:0), were identified, revealing that environmental phenol exposure altered the metabolic pathways such as histidine metabolism, beta-Alanine metabolism, glycerophospholipid metabolism, and other pathways. This study also conceived an innovative strategy for the early prediction of diseases by combining urinary metabolomics with machine learning (ML) algorithms. The differential metabolites predictive accuracy by ML models was >80%. This is the first mass spectrometry-based metabolomics study on young adult females from India with environmental phenols exposure. The study is valuable in demonstrating multiple urine metabolic changes linked to environmental phenol exposure and a better understanding of the mechanisms behind environmental phenol-induced effects in young female adults.

Diagnostic performance of electronic nose technology in chronic lung allograft dysfunction

BACKGROUND

There is a need for reliable biomarkers for the diagnosis of chronic lung allograft dysfunction (CLAD). In this light, we investigated the diagnostic value of exhaled breath analysis using an electronic nose (eNose) for CLAD, CLAD phenotype, and CLAD stage in lung transplant recipients (LTR).

METHODS

We performed eNose measurements in LTR with and without CLAD, visiting the outpatient clinic. Through supervised machine learning, the diagnostic value of eNose for CLAD was assessed in a random training and validation set. Next, we investigated the diagnostic value of the eNose measurements combined with known risk factors for CLAD. Model performance was evaluated using ROC-analysis.

RESULTS

We included 152 LTR (median age 60 years, 49% females), of whom 38 with CLAD. eNose-based classification of patients with and without CLAD provided an AUC of 0.86 in the training set, and 0.82 in the validation set. After adding established risk factors for CLAD (age, gender, type of transplantation, time after transplantation and prior occurrence of acute cellular rejection) to a model with the eNose data, the discriminative ability of the model improved to an AUC of 0.94 (p = 0.02) in the training set and 0.94 (p = 0.04) in the validation set. Discrimination between BOS and RAS was good (AUC 0.95). Discriminative ability for other phenotypes (AUCs ranging 0.50-0.92) or CLAD stages (AUC 0.56) was limited.

CONCLUSION

Exhaled breath analysis using eNose is a promising novel biomarker for enabling diagnosis and phenotyping CLAD. eNose technology could be a valuable addition to the diagnostic armamentarium for suspected graft failure in LTR.

Machine learning-assisted medium optimization revealed the discriminated strategies for improved production of the foreign and native metabolites

The composition of medium components is crucial for achieving the best performance of synthetic construction in genetically engineered cells. Which and how medium components determine the performance, e.g., productivity, remain poorly investigated. To address the questions, a comparative survey with two genetically engineered Escherichia coli strains was performed. As a case study, the strains carried the synthetic pathways for producing the aromatic compounds of 4-aminophenylalanine (4APhe) or tyrosine (Tyr), common in the upstream but differentiated in the downstream metabolism. Bacterial growth and compound production were examined in hundreds of medium combinations that comprised 48 pure chemicals. The resultant data sets linking the medium composition to bacterial growth and production were subjected to machine learning for improved production. Intriguingly, the primary medium components determining the production of 4PheA and Tyr were differentiated, which were the initial resource (glucose) of the synthetic pathway and the inducer (IPTG) of the synthetic construction, respectively. Fine-tuning of the primary component significantly increased the yields of 4APhe and Tyr, indicating that a single component could be crucial for the performance of synthetic construction. Transcriptome analysis observed the local and global changes in gene expression for improved production of 4APhe and Tyr, respectively, revealing divergent metabolic strategies for producing the foreign and native metabolites. The study demonstrated that ML-assisted medium optimization could provide a novel point of view on how to make the synthetic construction meet the designed working principle and achieve the expected biological function.

Machine Learning and Hybrid Methods for Metabolic Pathway Modeling

Computational cell metabolism models seek to provide metabolic explanations of cell behavior under different conditions or following genetic alterations, help in the optimization of in vitro cell growth environments, or predict cellular behavior in vivo and in vitro. In the extremes, mechanistic models can include highly detailed descriptions of a small number of metabolic reactions or an approximate representation of an entire metabolic network. To date, all mechanistic models have required details of individual metabolic reactions, either kinetic parameters or metabolic flux, as well as information about extracellular and intracellular metabolite concentrations. Despite the extensive efforts and the increasing availability of high-quality data, required in vivo data are not available for the majority of known metabolic reactions; thus, mechanistic models are based primarily on ex vivo kinetic measurements and limited flux information. Machine learning approaches provide an alternative for derivation of functional dependencies from existing data. The increasing availability of metabolomic and lipidomic data, with growing feature coverage as well as sample set size, is expected to provide new data options needed for derivation of machine learning models of cell metabolic processes. Moreover, machine learning analysis of longitudinal data can lead to predictive models of cell behaviors over time. Conversely, machine learning models trained on steady-state data can provide descriptive models for the comparison of metabolic states in different environments or disease conditions. Additionally, inclusion of metabolic network knowledge in these analyses can further help in the development of models with limited data.This chapter will explore the application of machine learning to the modeling of cell metabolism. We first provide a theoretical explanation of several machine learning and hybrid mechanistic machine learning methods currently being explored to model metabolism. Next, we introduce several avenues for improving these models with machine learning. Finally, we provide protocols for specific examples of the utilization of machine learning in the development of predictive cell metabolism models using metabolomic data. We describe data preprocessing, approaches for training of machine learning models for both descriptive and predictive models, and the utilization of these models in synthetic and systems biology. Detailed protocols provide a list of software tools and libraries used for these applications, step-by-step modeling protocols, troubleshooting, as well as an overview of existing limitations to these approaches.

Data Processing and Analysis in Mass Spectrometry-Based Metabolomics

Metabolomics is the latest of the omics sciences. It attempts to measure and characterize metabolites-small chemical compounds <1500 Da-on cells, tissue, or biofluids, which are usually products of biological reactions. As metabolic reactions are closer to the phenotype, metabolomics has emerged as an attractive science for various areas of research, including personalized medicine. However, due to the complexity of data obtained and the absence of curated databases for metabolite identification, data processing is the major bottleneck in this area since most technicians lack the required bioinformatics expertise to process datasets in a reliable and fast manner. The aim of this chapter is to describe the available tools for data processing that makes an inexperienced researcher capable of obtaining reliable results without having to undergo through huge parametrization steps.

Metabolomics and modelling approaches for systems metabolic engineering

Metabolic engineering involves the manipulation of microbes to produce desirable compounds through genetic engineering or synthetic biology approaches. Metabolomics involves the quantitation of intracellular and extracellular metabolites, where mass spectrometry and nuclear magnetic resonance based analytical instrumentation are often used. Here, the experimental designs, sample preparations, metabolite quenching and extraction are essential to the quantitative metabolomics workflow. The resultant metabolomics data can then be used with computational modelling approaches, such as kinetic and constraint-based modelling, to better understand underlying mechanisms and bottlenecks in the synthesis of desired compounds, thereby accelerating research through systems metabolic engineering. Constraint-based models, such as genome scale models, have been used successfully to enhance the yield of desired compounds from engineered microbes, however, unlike kinetic or dynamic models, constraint-based models do not incorporate regulatory effects. Nevertheless, the lack of time-series metabolomic data generation has hindered the usefulness of dynamic models till today. In this review, we show that improvements in automation, dynamic real-time analysis and high throughput workflows can drive the generation of more quality data for dynamic models through time-series metabolomics data generation. Spatial metabolomics also has the potential to be used as a complementary approach to conventional metabolomics, as it provides information on the localization of metabolites. However, more effort must be undertaken to identify metabolites from spatial metabolomics data derived through imaging mass spectrometry, where machine learning approaches could prove useful. On the other hand, single-cell metabolomics has also seen rapid growth, where understanding cell-cell heterogeneity can provide more insights into efficient metabolic engineering of microbes. Moving forward, with potential improvements in automation, dynamic real-time analysis, high throughput workflows, and spatial metabolomics, more data can be produced and studied using machine learning algorithms, in conjunction with dynamic models, to generate qualitative and quantitative predictions to advance metabolic engineering efforts.

Bioremediation of Endocrine Disrupting Chemicals- Advancements and Challenges

Endocrine Disrupting Chemicals (EDCs), major group of recalcitrant compounds, poses a serious threat to the health and future of millions of human beings, and other flora and fauna for years to come. A close analysis of various xenobiotics undermines the fact that EDC is structurally diverse chemical compounds generated as a part of anthropogenic advancements as well as part of their degradation. Regardless of such structural diversity, EDC is common in their ultimate drastic effect of impeding the proper functioning of the endocrinal system, basic physiologic systems, resulting in deregulated growth, malformations, and cancerous outcomes in animals as well as humans. The current review outlines an overview of various EDCs, their toxic effects on the ecosystem and its inhabitants. Conventional remediation methods such as physico-chemical methods and enzymatic approaches have been put into action as some form of mitigation measures. However, the last decade has seen the hunt for newer technologies and methodologies at an accelerated pace. Genetically engineered microbial degradation, gene editing strategies, metabolic and protein engineering, and in-silico predictive approaches - modern day's additions to our armamentarium in combating the EDCs are addressed. These additions have greater acceptance socially with lesser dissonance owing to reduced toxic by-products, lower health trepidations, better degradation, and ultimately the prevention of bioaccumulation. The positive impact of such new approaches on controlling the menace of EDCs has been outlaid. This review will shed light on sources of EDCs, their impact, significance, and the different remediation and bioremediation approaches, with a special emphasis on the recent trends and perspectives in using sustainable approaches for bioremediation of EDCs. Strict regulations to prevent the release of estrogenic chemicals to the ecosystem, adoption of combinatorial methods to remove EDC and prevalent use of bioremediation techniques should be followed in all future endeavors to combat EDC pollution. Moreover, the proper development, growth and functioning of future living forms relies on their non-exposure to EDCs, thus remediation of such chemicals present even in nano-concentrations should be addressed gravely.

Global coordination of the mutation and growth rates across the genetic and nutritional variety in Escherichia coli

Fitness and mutability are the primary traits of living organisms for adaptation and evolution. However, their quantitative linkage remained largely deficient. Whether there is any general relationship between the two features and how genetic and environmental variables influence them remained unclear and were addressed here. The mutation and growth rates of an assortment of Escherichia coli strain collections, including the wild-type strains and the genetically disturbed strains of either reduced genomes or deletion of the genes involved in the DNA replication fidelity, were evaluated in various media. The contribution of media to the mutation and growth rates was differentiated depending on the types of genetic disturbance. Nevertheless, the negative correlation between the mutation and growth rates was observed across the genotypes and was common in all media. It indicated the comprehensive association of the correlated mutation and growth rates with the genetic and medium variation. Multiple linear regression and support vector machine successfully predicted the mutation and growth rates and the categories of genotypes and media, respectively. Taken together, the study provided a quantitative dataset linking the mutation and growth rates, genotype, and medium and presented a simple and successful example of predicting bacterial growth and mutability by data-driven approaches.

Behavior Data Analysis of English Learners Based on Discrete Dynamic System Modeling Method

With the rapid development of computer science, there are more and more kinds of discrete dynamic systems. Computer integrated system CIMS, network communication database administrator system, and human behavior analysis system are all discrete dynamic systems. At present, many researchers have studied by adding human behavior data to discrete dynamic systems. This paper aims to study the behavior data of English learners by using the discrete dynamic modeling technology of complex systems and the discrete dynamic system modeling method of Petri nets. By adding the behavior data of learners to the discrete dynamic system of fuzzy Petri nets, the system is diagnosed and optimized. The experimental results show that the complex discrete dynamic system in this paper has achieved good experimental results according to the performance indicators selected in theory. Based on the combination of the above technologies and systems, the fuzzy Petri net discrete dynamic system studied in this paper improves the processing speed of English learners' behavior data.

Non-linearity of Metabolic Pathways Critically Influences the Choice of Machine Learning Model

The use of machine learning (ML) in life sciences has gained wide interest over the past years, as it speeds up the development of high performing models. Important modeling tools in biology have proven their worth for pathway design, such as mechanistic models and metabolic networks, as they allow better understanding of mechanisms involved in the functioning of organisms. However, little has been done on the use of ML to model metabolic pathways, and the degree of non-linearity associated with them is not clear. Here, we report the construction of different metabolic pathways with several linear and non-linear ML models. Different types of data are used; they lead to the prediction of important biological data, such as pathway flux and final product concentration. A comparison reveals that the data features impact model performance and highlight the effectiveness of non-linear models (e.g., QRF: RMSE = 0.021 nmol·min-1 and R2 = 1 vs. Bayesian GLM: RMSE = 1.379 nmol·min-1 R2 = 0.823). It turns out that the greater the degree of non-linearity of the pathway, the better suited a non-linear model will be. Therefore, a decision-making support for pathway modeling is established. These findings generally support the hypothesis that non-linear aspects predominate within the metabolic pathways. This must be taken into account when devising possible applications of these pathways for the identification of biomarkers of diseases (e.g., infections, cancer, neurodegenerative diseases) or the optimization of industrial production processes.

Unraveling the Rewired Metabolism in Lung Cancer Using Quantitative NMR Metabolomics

Lung cancer cells are well documented to rewire their metabolism and energy production networks to enable proliferation and survival in a nutrient-poor and hypoxic environment. Although metabolite profiling of blood plasma and tissue is still emerging in omics approaches, several techniques have shown potential in cancer diagnosis. In this paper, the authors describe the alterations in the metabolic phenotype of lung cancer patients. In addition, we focus on the metabolic cooperation between tumor cells and healthy tissue. Furthermore, the authors discuss how metabolomics could improve the management of lung cancer patients.

EPIMUTESTR: a nearest neighbor machine learning approach to predict cancer driver genes from the evolutionary action of coding variants

Discovering rare cancer driver genes is difficult because their mutational frequency is too low for statistical detection by computational methods. EPIMUTESTR is an integrative nearest-neighbor machine learning algorithm that identifies such marginal genes by modeling the fitness of their mutations with the phylogenetic Evolutionary Action (EA) score. Over cohorts of sequenced patients from The Cancer Genome Atlas representing 33 tumor types, EPIMUTESTR detected 214 previously inferred cancer driver genes and 137 new candidates never identified computationally before of which seven genes are supported in the COSMIC Cancer Gene Census. EPIMUTESTR achieved better robustness and specificity than existing methods in a number of benchmark methods and datasets.

Soft Hydrogel Actuator for Fast Machine-Learning-Assisted Bacteria Detection

We demonstrate that our bio-electrochemical platform facilitates the reduction of detection time from the 3-day period of the existing tests to 15 min. Machine learning and robotized bioanalytical platforms require the principles such as hydrogel-based actuators for fast and easy analysis of bioactive analytes. Bacteria are fragile and environmentally sensitive microorganisms that require a special environment to support their lifecycles during analytical tests. Here, we develop a bio-electrochemical platform based on the soft hydrogel/eutectic gallium-indium alloy interface for the detection of Streptococcus thermophilus and Bacillus coagulans bacteria in various mediums. The soft hydrogel-based device is capable to support bacteria' viability during detection time. Current-voltage data are used for multilayer perceptron algorithm training. The multilayer perceptron model is capable of detecting bacterial concentrations in the 10⁴ to 10⁸ cfu/mL range of the culture medium or in the dairy products with high accuracy (94%). Such a fast and easy biodetection is extremely important for food and agriculture industries and biomedical and environmental science.

Estimated Renal Metabolomics at Reperfusion Predicts One-Year Kidney Graft Function

Renal transplantation is the gold-standard procedure for end-stage renal disease patients, improving quality of life and life expectancy. Despite continuous advancement in the management of post-transplant complications, progress is still needed to increase the graft lifespan. Early identification of patients at risk of rapid graft failure is critical to optimize their management and slow the progression of the disease. In 42 kidney grafts undergoing protocol biopsies at reperfusion, we estimated the renal metabolome from RNAseq data. The estimated metabolites' abundance was further used to predict the renal function within the first year of transplantation through a random forest machine learning algorithm. Using repeated K-fold cross-validation we first built and then tuned our model on a training dataset. The optimal model accurately predicted the one-year eGFR, with an out-of-bag root mean square root error (RMSE) that was 11.8 ± 7.2 mL/min/1.73 m2. The performance was similar in the test dataset, with a RMSE of 12.2 ± 3.2 mL/min/1.73 m2. This model outperformed classic statistical models. Reperfusion renal metabolome may be used to predict renal function one year after allograft kidney recipients.

A Practical Guide to Integrating Multimodal Machine Learning and Metabolic Modeling

Complex, distributed, and dynamic sets of clinical biomedical data are collectively referred to as multimodal clinical data. In order to accommodate the volume and heterogeneity of such diverse data types and aid in their interpretation when they are combined with a multi-scale predictive model, machine learning is a useful tool that can be wielded to deconstruct biological complexity and extract relevant outputs. Additionally, genome-scale metabolic models (GSMMs) are one of the main frameworks striving to bridge the gap between genotype and phenotype by incorporating prior biological knowledge into mechanistic models. Consequently, the utilization of GSMMs as a foundation for the integration of multi-omic data originating from different domains is a valuable pursuit towards refining predictions. In this chapter, we show how cancer multi-omic data can be analyzed via multimodal machine learning and metabolic modeling. Firstly, we focus on the merits of adopting an integrative systems biology led approach to biomedical data mining. Following this, we propose how constraint-based metabolic models can provide a stable yet adaptable foundation for the integration of multimodal data with machine learning. Finally, we provide a step-by-step tutorial for the combination of machine learning and GSMMs, which includes: (i) tissue-specific constraint-based modeling; (ii) survival analysis using time-to-event prediction for cancer; and (iii) classification and regression approaches for multimodal machine learning. The code associated with the tutorial can be found at https://github.com/Angione-Lab/Tutorials_Combining_ML_and_GSMM .

Protocol for hybrid flux balance, statistical, and machine learning analysis of multi-omic data from the cyanobacterium Synechococcus sp. PCC 7002

Combining a computational framework for flux balance analysis with machine learning improves the accuracy of predicting metabolic activity across conditions, while enabling mechanistic interpretation. This protocol presents a guide to condition-specific metabolic modeling that integrates regularized flux balance analysis with machine learning approaches to extract key features from transcriptomic and fluxomic data. We demonstrate the protocol as applied to Synechococcus sp. PCC 7002; we also outline how it can be adapted to any species or community with available multi-omic data. For complete details on the use and execution of this protocol, please refer to Vijayakumar et al. (2020).

Urine-Based Metabolomics and Machine Learning Reveals Metabolites Associated with Renal Cell Carcinoma Stage

Urine metabolomics profiling has potential for non-invasive RCC staging, in addition to providing metabolic insights into disease progression. In this study, we utilized liquid chromatography-mass spectrometry (LC-MS), nuclear magnetic resonance (NMR), and machine learning (ML) for the discovery of urine metabolites associated with RCC progression. Two machine learning questions were posed in the study: Binary classification into early RCC (stage I and II) and advanced RCC stages (stage III and IV), and RCC tumor size estimation through regression analysis. A total of 82 RCC patients with known tumor size and metabolomic measurements were used for the regression task, and 70 RCC patients with complete tumor-nodes-metastasis (TNM) staging information were used for the classification tasks under ten-fold cross-validation conditions. A voting ensemble regression model consisting of elastic net, ridge, and support vector regressor predicted RCC tumor size with a R² value of 0.58. A voting classifier model consisting of random forest, support vector machines, logistic regression, and adaptive boosting yielded an AUC of 0.96 and an accuracy of 87%. Some identified metabolites associated with renal cell carcinoma progression included 4-guanidinobutanoic acid, 7-aminomethyl-7-carbaguanine, 3-hydroxyanthranilic acid, lysyl-glycine, glycine, citrate, and pyruvate. Overall, we identified a urine metabolic phenotype associated with renal cell carcinoma stage, exploring the promise of a urine-based metabolomic assay for staging this disease.

Machine learning meets omics: applications and perspectives

The innovation of biotechnologies has allowed the accumulation of omics data at an alarming rate, thus introducing the era of 'big data'. Extracting inherent valuable knowledge from various omics data remains a daunting problem in bioinformatics. Better solutions often need some kind of more innovative methods for efficient handlings and effective results. Recent advancements in integrated analysis and computational modeling of multi-omics data helped address such needs in an increasingly harmonious manner. The development and application of machine learning have largely advanced our insights into biology and biomedicine and greatly promoted the development of therapeutic strategies, especially for precision medicine. Here, we propose a comprehensive survey and discussion on what happened, is happening and will happen when machine learning meets omics. Specifically, we describe how artificial intelligence can be applied to omics studies and review recent advancements at the interface between machine learning and the ever-widest range of omics including genomics, transcriptomics, proteomics, metabolomics, radiomics, as well as those at the single-cell resolution. We also discuss and provide a synthesis of ideas, new insights, current challenges and perspectives of machine learning in omics.

Improving the performance of machine learning models for biotechnology: The quest for deus ex machina

Machine learning is becoming an integral part of the Design-Build-Test-Learn cycle in biotechnology. Machine learning models learn from collected datasets such as omics data and predict a defined outcome, which has led to both production improvements and predictive tools in the field. Robust prediction of the behavior of microbial cell factories and production processes not only greatly increases our understanding of the function of such systems, but also provides significant savings of development time. However, many pitfalls when modeling biological data - bad fit, noisy data, model instability, low data quantity and imbalances in the data - cause models to suffer in their performance. Here we provide an accessible, in-depth analysis on the problems created by these pitfalls, as well as means of their detection and mediation, with a focus on supervised learning. Assessing the state of the art, we show that, currently, in-depth analyses of model performance are often absent and must be improved. This review provides a toolbox for the analysis of model robustness and performance, and simultaneously proposes a standard for the community to facilitate future work. It is further accompanied by an interactive online tutorial on the discussed issues.

Path to improving the life cycle and quality of genome-scale models of metabolism

Genome-scale models of metabolism (GEMs) are key computational tools for the systems-level study of metabolic networks. Here, we describe the "GEM life cycle," which we subdivide into four stages: inception, maturation, specialization, and amalgamation. We show how different types of GEM reconstruction workflows fit in each stage and proceed to highlight two fundamental bottlenecks for GEM quality improvement: GEM maturation and content removal. We identify common characteristics contributing to increasing quality of maturing GEMs drawing from past independent GEM maturation efforts. We then shed some much-needed light on the latent and unrecognized but pervasive issue of content removal, demonstrating the substantial effects of model pruning on its solution space. Finally, we propose a novel framework for content removal and associated confidence-level assignment which will help guide future GEM development efforts, reduce duplication of effort across groups, potentially aid automated reconstruction platforms, and boost the reproducibility of model development.

Plasma-metabolite-based machine learning is a promising diagnostic approach for esophageal squamous cell carcinoma investigation

The aim of this study was to develop a diagnostic strategy for esophageal squamous cell carcinoma (ESCC) that combines plasma metabolomics with machine learning algorithms. Plasma-based untargeted metabolomics analysis was performed with samples derived from 88 ESCC patients and 52 healthy controls. The dataset was split into a training set and a test set. After identification of differential metabolites in training set, single-metabolite-based receiver operating characteristic (ROC) curves and multiple-metabolite-based machine learning models were used to distinguish between ESCC patients and healthy controls. Kaplan-Meier survival analysis and Cox proportional hazards regression analysis were performed to investigate the prognostic significance of the plasma metabolites. Finally, twelve differential plasma metabolites (six up-regulated and six down-regulated) were annotated. The predictive performance of the six most prevalent diagnostic metabolites through the diagnostic models in the test set were as follows: arachidonic acid (accuracy: 0.887), sebacic acid (accuracy: 0.867), indoxyl sulfate (accuracy: 0.850), phosphatidylcholine (PC) (14:0/0:0) (accuracy: 0.825), deoxycholic acid (accuracy: 0.773), and trimethylamine N-oxide (accuracy: 0.653). The prediction accuracies of the machine learning models in the test set were partial least-square (accuracy: 0.947), random forest (accuracy: 0.947), gradient boosting machine (accuracy: 0.960), and support vector machine (accuracy: 0.980). Additionally, survival analysis demonstrated that acetoacetic acid was an unfavorable prognostic factor (hazard ratio (HR): 1.752), while PC (14:0/0:0) (HR: 0.577) was a favorable prognostic factor for ESCC. This study devised an innovative strategy for ESCC diagnosis by combining plasma metabolomics with machine learning algorithms and revealed its potential to become a novel screening test for ESCC.

•

Six most prevalent diagnostic plasma metabolites were identified in ESCC.

•

Plasma-metabolite-based machine learning models (PLS, RF, GBM, and SVM) for ESCC diagnosis.

•

Acetoacetic acid was an unfavorable prognostic factor, while PC (14:0/0:0) was a favorable prognostic factor for ESCC.

Lipid Metabolite Biomarkers in Cardiovascular Disease: Discovery and Biomechanism Translation from Human Studies

Lipids represent a valuable target for metabolomic studies since altered lipid metabolism is known to drive the pathological changes in cardiovascular disease (CVD). Metabolomic technologies give us the ability to measure thousands of metabolites providing us with a metabolic fingerprint of individual patients. Metabolomic studies in humans have supported previous findings into the pathomechanisms of CVD, namely atherosclerosis, apoptosis, inflammation, oxidative stress, and insulin resistance. The most widely studied classes of lipid metabolite biomarkers in CVD are phospholipids, sphingolipids/ceramides, glycolipids, cholesterol esters, fatty acids, and acylcarnitines. Technological advancements have enabled novel strategies to discover individual biomarkers or panels that may aid in the diagnosis and prognosis of CVD, with sphingolipids/ceramides as the most promising class of biomarkers thus far. In this review, application of metabolomic profiling for biomarker discovery to aid in the diagnosis and prognosis of CVD as well as metabolic abnormalities in CVD will be discussed with particular emphasis on lipid metabolites.

Synergisms of machine learning and constraint-based modeling of metabolism for analysis and optimization of fermentation parameters

Recent noteworthy advances in the development of high-performing microbial and mammalian strains have enabled the sustainable production of bio-economically valuable substances such as bio-compounds, biofuels, and biopharmaceuticals. However, to obtain an industrially viable mass-production scheme, much time and effort are required. The robust and rational design of fermentation processes requires analysis and optimization of different extracellular conditions and medium components, which have a massive effect on growth and productivity. In this regard, knowledge- and data-driven modeling methods have received much attention. Constraint-based modeling (CBM) is a knowledge-driven mathematical approach that has been widely used in fermentation analysis and optimization due to its capabilities of predicting the cellular phenotype from genotype through high-throughput means. On the other hand, machine learning (ML) is a data-driven statistical method that identifies the data patterns within sophisticated biological systems and processes, where there is inadequate knowledge to represent underlying mechanisms. Furthermore, ML models are becoming a viable complement to constraint-based models in a reciprocal manner when one is used as a pre-step of another. As a result, more predictable model is produced. This review highlights the applications of CBM and ML independently and the combination of these two approaches for analyzing and optimizing fermentation parameters. This article is protected by copyright. All rights reserved.

Metabolomics-Guided Elucidation of Plant Abiotic Stress Responses in the 4IR Era: An Overview

Plants are constantly challenged by changing environmental conditions that include abiotic stresses. These are limiting their development and productivity and are subsequently threatening our food security, especially when considering the pressure of the increasing global population. Thus, there is an urgent need for the next generation of crops with high productivity and resilience to climate change. The dawn of a new era characterized by the emergence of fourth industrial revolution (4IR) technologies has redefined the ideological boundaries of research and applications in plant sciences. Recent technological advances and machine learning (ML)-based computational tools and omics data analysis approaches are allowing scientists to derive comprehensive metabolic descriptions and models for the target plant species under specific conditions. Such accurate metabolic descriptions are imperatively essential for devising a roadmap for the next generation of crops that are resilient to environmental deterioration. By synthesizing the recent literature and collating data on metabolomics studies on plant responses to abiotic stresses, in the context of the 4IR era, we point out the opportunities and challenges offered by omics science, analytical intelligence, computational tools and big data analytics. Specifically, we highlight technological advancements in (plant) metabolomics workflows and the use of machine learning and computational tools to decipher the dynamics in the chemical space that define plant responses to abiotic stress conditions.

Review of Machine Learning Methods for the Prediction and Reconstruction of Metabolic Pathways

Prediction and reconstruction of metabolic pathways play significant roles in many fields such as genetic engineering, metabolic engineering, drug discovery, and are becoming the most active research topics in synthetic biology. With the increase of related data and with the development of machine learning techniques, there have many machine leaning based methods been proposed for prediction or reconstruction of metabolic pathways. Machine learning techniques are showing state-of-the-art performance to handle the rapidly increasing volume of data in synthetic biology. To support researchers in this field, we briefly review the research progress of metabolic pathway reconstruction and prediction based on machine learning. Some challenging issues in the reconstruction of metabolic pathways are also discussed in this paper.

SMILE: systems metabolomics using interpretable learning and evolution

Background

Direct link between metabolism and cell and organism phenotype in health and disease makes metabolomics, a high throughput study of small molecular metabolites, an essential methodology for understanding and diagnosing disease development and progression. Machine learning methods have seen increasing adoptions in metabolomics thanks to their powerful prediction abilities. However, the “black-box” nature of many machine learning models remains a major challenge for wide acceptance and utility as it makes the interpretation of decision process difficult. This challenge is particularly predominant in biomedical research where understanding of the underlying decision making mechanism is essential for insuring safety and gaining new knowledge.

Results

In this article, we proposed a novel computational framework, Systems Metabolomics using Interpretable Learning and Evolution (SMILE), for supervised metabolomics data analysis. Our methodology uses an evolutionary algorithm to learn interpretable predictive models and to identify the most influential metabolites and their interactions in association with disease. Moreover, we have developed a web application with a graphical user interface that can be used for easy analysis, interpretation and visualization of the results. Performance of the method and utilization of the web interface is shown using metabolomics data for Alzheimer’s disease.

Conclusions

SMILE was able to identify several influential metabolites on AD and to provide interpretable predictive models that can be further used for a better understanding of the metabolic background of AD. SMILE addresses the emerging issue of interpretability and explainability in machine learning, and contributes to more transparent and powerful applications of machine learning in bioinformatics.

Supplementary Information

The online version contains supplementary material available at 10.1186/s12859-021-04209-1.

Multiscale modeling meets machine learning: What can we learn?

Machine learning is increasingly recognized as a promising technology in the biological, biomedical, and behavioral sciences. There can be no argument that this technique is incredibly successful in image recognition with immediate applications in diagnostics including electrophysiology, radiology, or pathology, where we have access to massive amounts of annotated data. However, machine learning often performs poorly in prognosis, especially when dealing with sparse data. This is a field where classical physics-based simulation seems to remain irreplaceable. In this review, we identify areas in the biomedical sciences where machine learning and multiscale modeling can mutually benefit from one another: Machine learning can integrate physics-based knowledge in the form of governing equations, boundary conditions, or constraints to manage ill-posted problems and robustly handle sparse and noisy data; multiscale modeling can integrate machine learning to create surrogate models, identify system dynamics and parameters, analyze sensitivities, and quantify uncertainty to bridge the scales and understand the emergence of function. With a view towards applications in the life sciences, we discuss the state of the art of combining machine learning and multiscale modeling, identify applications and opportunities, raise open questions, and address potential challenges and limitations. We anticipate that it will stimulate discussion within the community of computational mechanics and reach out to other disciplines including mathematics, statistics, computer science, artificial intelligence, biomedicine, systems biology, and precision medicine to join forces towards creating robust and efficient models for biological systems.

Personalized Metabolic Analysis of Diseases

The metabolic wiring of patient cells is altered drastically in many diseases, including cancer. Understanding the nature of such changes may pave the way for new therapeutic opportunities as well as the development of personalized treatment strategies for patients. In this paper, we propose an algorithm called Metabolitics, which allows systems-level analysis of changes in the biochemical network of cells in disease states. It enables the study of a disease at both reaction- and pathway-level granularities for a detailed and summarized view of disease etiology. Metabolitics employs flux variability analysis with a dynamically built objective function based on biofluid metabolomics measurements in a personalized manner. Moreover, Metabolitics builds supervised classification models to discriminate between patients and healthy subjects based on the computed metabolic network changes. The use of Metabolitics is demonstrated for three distinct diseases, namely, breast cancer, Crohn's disease, and colorectal cancer. Our results show that the constructed supervised learning models successfully differentiate patients from healthy individuals by an average f1-score of 88 percent. Besides, in addition to the confirmation of previously reported breast cancer-associated pathways, we discovered that Biotin Metabolism along with Arginine and Proline Metabolism is subject to a significant increase in flux capacity, which have not been reported before.

Biological network analysis with deep learning

Recent advancements in experimental high-throughput technologies have expanded the availability and quantity of molecular data in biology. Given the importance of interactions in biological processes, such as the interactions between proteins or the bonds within a chemical compound, this data is often represented in the form of a biological network. The rise of this data has created a need for new computational tools to analyze networks. One major trend in the field is to use deep learning for this goal and, more specifically, to use methods that work with networks, the so-called graph neural networks (GNNs). In this article, we describe biological networks and review the principles and underlying algorithms of GNNs. We then discuss domains in bioinformatics in which graph neural networks are frequently being applied at the moment, such as protein function prediction, protein-protein interaction prediction and in silico drug discovery and development. Finally, we highlight application areas such as gene regulatory networks and disease diagnosis where deep learning is emerging as a new tool to answer classic questions like gene interaction prediction and automatic disease prediction from data.