Framework and resource for more than 11,000 gene-transcript-protein-reaction associations in human metabolism

Genome-scale metabolic models in translational medicine: the current status and potential of machine learning in improving the effectiveness of the models

The genome-scale metabolic model (GEM) has emerged as one of the leading modeling approaches for systems-level metabolic studies and has been widely explored for a broad range of organisms and applications. Owing to the development of genome sequencing technologies and available biochemical data, it is possible to reconstruct GEMs for model and non-model microorganisms as well as for multicellular organisms such as humans and animal models. GEMs will evolve in parallel with the availability of biological data, new mathematical modeling techniques and the development of automated GEM reconstruction tools. The use of high-quality, context-specific GEMs, a subset of the original GEM in which inactive reactions are removed while maintaining metabolic functions in the extracted model, for model organisms along with machine learning (ML) techniques could increase their applications and effectiveness in translational research in the near future. Here, we briefly review the current state of GEMs, discuss the potential contributions of ML approaches for more efficient and frequent application of these models in translational research, and explore the extension of GEMs to integrative cellular models.

Prediction of metabolites associated with somatic mutations in cancers by using genome-scale metabolic models and mutation data

BACKGROUND

Oncometabolites, often generated as a result of a gene mutation, show pro-oncogenic function when abnormally accumulated in cancer cells. Identification of such mutation-associated metabolites will facilitate developing treatment strategies for cancers, but is challenging due to the large number of metabolites in a cell and the presence of multiple genes associated with cancer development.

RESULTS

Here we report the development of a computational workflow that predicts metabolite-gene-pathway sets. Metabolite-gene-pathway sets present metabolites and metabolic pathways significantly associated with specific somatic mutations in cancers. The computational workflow uses both cancer patient-specific genome-scale metabolic models (GEMs) and mutation data to generate metabolite-gene-pathway sets. A GEM is a computational model that predicts reaction fluxes at a genome scale and can be constructed in a cell-specific manner by using omics data. The computational workflow is first validated by comparing the resulting metabolite-gene pairs with multi-omics data (i.e., mutation data, RNA-seq data, and metabolome data) from acute myeloid leukemia and renal cell carcinoma samples collected in this study. The computational workflow is further validated by evaluating the metabolite-gene-pathway sets predicted for 18 cancer types, by using RNA-seq data publicly available, in comparison with the reported studies. Therapeutic potential of the resulting metabolite-gene-pathway sets is also discussed.

CONCLUSIONS

Validation of the metabolite-gene-pathway set-predicting computational workflow indicates that a decent number of metabolites and metabolic pathways appear to be significantly associated with specific somatic mutations. The computational workflow and the resulting metabolite-gene-pathway sets will help identify novel oncometabolites and also suggest cancer treatment strategies.

Systematic analysis of Mendelian disease-associated gene variants reveals new classes of cancer-predisposing genes

BACKGROUND

Despite the acceleration of somatic driver gene discovery facilitated by recent large-scale tumor sequencing data, the contribution of inherited variants remains largely unexplored, primarily focusing on previously known cancer predisposition genes (CPGs) due to the low statistical power associated with detecting rare pathogenic variant-phenotype associations.

METHODS

Here, we introduce a generalized log-regression model to measure the excess of pathogenic variants within genes in cancer patients compared to control samples. It aims to measure gene-level cancer risk enrichment by collapsing rare pathogenic variants after controlling the population differences across samples.

RESULTS

In this study, we investigate whether pathogenic variants in Mendelian disease-associated genes (OMIM genes) are enriched in cancer patients compared to controls. Utilizing data from PCAWG and the 1,000 Genomes Project, we identify 103 OMIM genes demonstrating significant enrichment of pathogenic variants in cancer samples (FDR 20%). Through an integrative approach considering three distinct properties, we classify these CPG-like OMIM genes into four clusters, indicating potential diverse mechanisms underlying tumor progression. Further, we explore the function of PAH (a key metabolic enzyme associated with Phenylketonuria), the gene exhibiting the highest prevalence of pathogenic variants in a pan-cancer (1.8%) compared to controls (0.6%).

CONCLUSIONS

Our findings suggest a possible cancer progression mechanism through metabolic profile alterations. Overall, our data indicates that pathogenic OMIM gene variants contribute to cancer progression and introduces new CPG classifications potentially underpinning diverse tumorigenesis mechanisms.

A contribution of metabolic engineering to addressing medical problems: Metabolic flux analysis

Metabolic engineering has served as a systematic discipline for industrial biotechnology as it has offered systematic tools and methods for strain development and bioprocess optimization. Because these metabolic engineering tools and methods are concerned with the biological network of a cell with emphasis on metabolic network, they have also been applied to a range of medical problems where better understanding of metabolism has also been perceived to be important. Metabolic flux analysis (MFA) is a unique systematic approach initially developed in the metabolic engineering community, and has proved its usefulness and potential when addressing a range of medical problems. In this regard, this review discusses the contribution of MFA to addressing medical problems. For this, we i) provide overview of the milestones of MFA, ii) define two main branches of MFA, namely constraint-based reconstruction and analysis (COBRA) and isotope-based MFA (iMFA), and iii) present successful examples of their medical applications, including characterizing the metabolism of diseased cells and pathogens, and identifying effective drug targets. Finally, synergistic interactions between metabolic engineering and biomedical sciences are discussed with respect to MFA.

Network medicine: an approach to complex kidney disease phenotypes

Scientific reductionism has been the basis of disease classification and understanding for more than a century. However, the reductionist approach of characterizing diseases from a limited set of clinical observations and laboratory evaluations has proven insufficient in the face of an exponential growth in data generated from transcriptomics, proteomics, metabolomics and deep phenotyping. A new systematic method is necessary to organize these datasets and build new definitions of what constitutes a disease that incorporates both biological and environmental factors to more precisely describe the ever-growing complexity of phenotypes and their underlying molecular determinants. Network medicine provides such a conceptual framework to bridge these vast quantities of data while providing an individualized understanding of disease. The modern application of network medicine principles is yielding new insights into the pathobiology of chronic kidney diseases and renovascular disorders by expanding the understanding of pathogenic mediators, novel biomarkers and new options for renal therapeutics. These efforts affirm network medicine as a robust paradigm for elucidating new advances in the diagnosis and treatment of kidney disorders.

Proteomic analysis for the effects of non-saponin fraction with rich polysaccharide from Korean Red Ginseng on Alzheimer's disease in a mouse model

Background

The most common type of dementia, Alzheimer's disease (AD), is marked by the formation of extracellular amyloid beta (Aβ) plaques. The impairments of axons and synapses appear in the process of Aβ plaques formation, and this damage could cause neurodegeneration. We previously reported that non-saponin fraction with rich polysaccharide (NFP) from Korean Red Ginseng (KRG) showed neuroprotective effects in AD. However, precise molecular mechanism of the therapeutic effects of NFP from KRG in AD still remains elusive.

Methods

To investigate the therapeutic mechanisms of NFP from KRG on AD, we conducted proteomic analysis for frontal cortex from vehicle-treated wild-type, vehicle-treated 5XFAD mice, and NFP-treated 5XFAD mice by using nano-LC-ESI-MS/MS. Metabolic network analysis was additionally performed as the effects of NFP appeared to be associated with metabolism according to the proteome analysis.

Results

Starting from 5,470 proteins, 2,636 proteins were selected for hierarchical clustering analysis, and finally 111 proteins were further selected for protein-protein interaction network analysis. A series of these analyses revealed that proteins associated with synapse and mitochondria might be linked to the therapeutic mechanism of NFP. Subsequent metabolic network analysis via genome-scale metabolic models that represent the three mouse groups showed that there were significant changes in metabolic fluxes of mitochondrial carnitine shuttle pathway and mitochondrial beta-oxidation of polyunsaturated fatty acids.

Conclusion

Our results suggested that the therapeutic effects of NFP on AD were associated with synaptic- and mitochondrial-related pathways, and they provided targets for further rigorous studies on precise understanding of the molecular mechanism of NFP.

Context-Specific Genome-Scale Metabolic Modelling and Its Application to the Analysis of COVID-19 Metabolic Signatures

Genome-scale metabolic models (GEMs) have found numerous applications in different domains, ranging from biotechnology to systems medicine. Herein, we overview the most popular algorithms for the automated reconstruction of context-specific GEMs using high-throughput experimental data. Moreover, we describe different datasets applied in the process, and protocols that can be used to further automate the model reconstruction and validation. Finally, we describe recent COVID-19 applications of context-specific GEMs, focusing on the analysis of metabolic implications, identification of biomarkers and potential drug targets.

Identifying essential genes in genome-scale metabolic models of consensus molecular subtypes of colorectal cancer

Identifying essential targets in the genome-scale metabolic networks of cancer cells is a time-consuming process. The present study proposed a fuzzy hierarchical optimization framework for identifying essential genes, metabolites and reactions. On the basis of four objectives, the present study developed a framework for identifying essential targets that lead to cancer cell death and evaluating metabolic flux perturbations in normal cells that have been caused by cancer treatment. Through fuzzy set theory, a multiobjective optimization problem was converted into a trilevel maximizing decision-making (MDM) problem. We applied nested hybrid differential evolution to solve the trilevel MDM problem to identify essential targets in genome-scale metabolic models for five consensus molecular subtypes (CMSs) of colorectal cancer. We used various media to identify essential targets for each CMS and discovered that most targets affected all five CMSs and that some genes were CMS-specific. We obtained experimental data on the lethality of cancer cell lines from the DepMap database to validate the identified essential genes. The results reveal that most of the identified essential genes were compatible with the colorectal cancer cell lines obtained from DepMap and that these genes, with the exception of EBP, LSS, and SLC7A6, could generate a high level of cell death when knocked out. The identified essential genes were mostly involved in cholesterol biosynthesis, nucleotide metabolisms, and the glycerophospholipid biosynthetic pathway. The genes involved in the cholesterol biosynthetic pathway were also revealed to be determinable, if a cholesterol uptake reaction was not induced when the cells were in the culture medium. However, the genes involved in the cholesterol biosynthetic pathway became non-essential if such a reaction was induced. Furthermore, the essential gene CRLS1 was revealed as a medium-independent target for all CMSs.

Review of Current Human Genome-Scale Metabolic Models for Brain Cancer and Neurodegenerative Diseases

Brain disorders represent 32% of the global disease burden, with 169 million Europeans affected. Constraint-based metabolic modelling and other approaches have been applied to predict new treatments for these and other diseases. Many recent studies focused on enhancing, among others, drug predictions by generating generic metabolic models of brain cells and on the contextualisation of the genome-scale metabolic models with expression data. Experimental flux rates were primarily used to constrain or validate the model inputs. Bi-cellular models were reconstructed to study the interaction between different cell types. This review highlights the evolution of genome-scale models for neurodegenerative diseases and glioma. We discuss the advantages and drawbacks of each approach and propose improvements, such as building bi-cellular models, tailoring the biomass formulations for glioma and refinement of the cerebrospinal fluid composition.

Machine learning-guided evaluation of extraction and simulation methods for cancer patient-specific metabolic models

Genome-scale metabolic model (GEM) has been established as an important tool to study cellular metabolism at a systems level by predicting intracellular fluxes. With the advent of generic human GEMs, they have been increasingly applied to a range of diseases, often for the objective of predicting effective metabolic drug targets. Cancer is a representative disease where the use of GEMs has proved to be effective, partly due to the massive availability of patient-specific RNA-seq data. When using a human GEM, so-called context-specific GEM needs to be developed first by using cell-specific RNA-seq data. Biological validity of a context-specific GEM highly depends on both model extraction method (MEM) and model simulation method (MSM). However, while MEMs have been thoroughly examined, MSMs have not been systematically examined, especially, when studying cancer metabolism. In this study, the effects of pairwise combinations of three MEMs and five MSMs were evaluated by examining biological features of the resulting cancer patient-specific GEMs. For this, a total of 1,562 patient-specific GEMs were reconstructed, and subjected to machine learning-guided and biological evaluations to draw robust conclusions. Noteworthy observations were made from the evaluation, including the high performance of two MEMs, namely rank-based ‘task-driven Integrative Network Inference for Tissues’ (tINIT) or ‘Gene Inactivity Moderated by Metabolism and Expression’ (GIMME), paired with least absolute deviation (LAD) as a MSM, and relatively poorer performance of flux balance analysis (FBA) and parsimonious FBA (pFBA). Insights from this study can be considered as a reference when studying cancer metabolism using patient-specific GEMs.

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 .

Development of computational models using omics data for the identification of effective cancer metabolic biomarkers

Identification of novel biomarkers has been an active area of study for the effective diagnosis, prognosis and treatment of cancers. Among various types of cancer biomarkers, metabolic biomarkers, including enzymes, metabolites and metabolic genes, deserve attention as they can serve as a reliable source for diagnosis, prognosis and treatment of cancers. In particular, efforts to identify novel biomarkers have been greatly facilitated by a rapid increase in the volume of multiple omics data generated for a range of cancer cells. These omics data in turn serve as ingredients for developing computational models that can help derive deeper insights into the biology of cancer cells, and identify metabolic biomarkers. In this review, we provide an overview of omics data generated for cancer cells, and discuss recent studies on computational models that were developed using omics data in order to identify effective cancer metabolic biomarkers.

Omics and Computational Modeling Approaches for the Effective Treatment of Drug-Resistant Cancer Cells

Chemotherapy is a mainstream cancer treatment, but has a constant challenge of drug resistance, which consequently leads to poor prognosis in cancer treatment. For better understanding and effective treatment of drug-resistant cancer cells, omics approaches have been widely conducted in various forms. A notable use of omics data beyond routine data mining is to use them for computational modeling that allows generating useful predictions, such as drug responses and prognostic biomarkers. In particular, an increasing volume of omics data has facilitated the development of machine learning models. In this mini review, we highlight recent studies on the use of multi-omics data for studying drug-resistant cancer cells. We put a particular focus on studies that use computational models to characterize drug-resistant cancer cells, and to predict biomarkers and/or drug responses. Computational models covered in this mini review include network-based models, machine learning models and genome-scale metabolic models. We also provide perspectives on future research opportunities for combating drug-resistant cancer cells.

Optimization of a modeling platform to predict oncogenes from genome-scale metabolic networks of non-small-cell lung cancers

Cancer cell dysregulations result in the abnormal regulation of cellular metabolic pathways. By simulating this metabolic reprogramming using constraint-based modeling approaches, oncogenes can be predicted, and this knowledge can be used in prognosis and treatment. We introduced a trilevel optimization problem describing metabolic reprogramming for inferring oncogenes. First, this study used RNA-Seq expression data of lung adenocarcinoma (LUAD) and lung squamous cell carcinoma (LUSC) samples and their healthy counterparts to reconstruct tissue-specific genome-scale metabolic models and subsequently build the flux distribution pattern that provided a measure for the oncogene inference optimization problem for determining tumorigenesis. The platform detected 45 genes for LUAD and 84 genes for LUSC that lead to tumorigenesis. A high level of differentially expressed genes was not an essential factor for determining tumorigenesis. The platform indicated that pyruvate kinase (PKM), a well-known oncogene with a low level of differential gene expression in LUAD and LUSC, had the highest fitness among the predicted oncogenes based on computation. By contrast, pyruvate kinase L/R (PKLR), an isozyme of PKM, had a high level of differential gene expression in both cancers. Phosphatidylserine synthase 1 (PTDSS1), an oncogene in LUAD, was inferred to have a low level of differential gene expression, and overexpression could significantly reduce survival probability. According to the factor analysis, PTDSS1 characteristics were close to those of the template, but they were unobvious in LUSC. Angiotensin-converting enzyme 2 (ACE2) has recently garnered widespread interest as the SARS-CoV-2 virus receptor. Moreover, we determined that ACE2 is an oncogene of LUSC but not of LUAD. The platform developed in this study can identify oncogenes with low levels of differential expression and be used to identify potential therapeutic targets for cancer treatment.

The era of big data: Genome-scale modelling meets machine learning

With omics data being generated at an unprecedented rate, genome-scale modelling has become pivotal in its organisation and analysis. However, machine learning methods have been gaining ground in cases where knowledge is insufficient to represent the mechanisms underlying such data or as a means for data curation prior to attempting mechanistic modelling. We discuss the latest advances in genome-scale modelling and the development of optimisation algorithms for network and error reduction, intracellular constraining and applications to strain design. We further review applications of supervised and unsupervised machine learning methods to omics datasets from microbial and mammalian cell systems and present efforts to harness the potential of both modelling approaches through hybrid modelling.

An atlas of human metabolism

Genome-scale metabolic models (GEMs) are valuable tools to study metabolism and provide a scaffold for the integrative analysis of omics data. Researchers have developed increasingly comprehensive human GEMs, but the disconnect among different model sources and versions impedes further progress. We therefore integrated and extensively curated the most recent human metabolic models to construct a consensus GEM, Human1. We demonstrated the versatility of Human1 through the generation and analysis of cell- and tissue-specific models using transcriptomic, proteomic, and kinetic data. We also present an accompanying web portal, Metabolic Atlas (https://www.metabolicatlas.org/), which facilitates further exploration and visualization of Human1 content. Human1 was created using a version-controlled, open-source model development framework to enable community-driven curation and refinement. This framework allows Human1 to be an evolving shared resource for future studies of human health and disease.

Oncogene inference optimization using constraint-based modelling incorporated with protein expression in normal and tumour tissues

Cancer cells are known to exhibit unusual metabolic activity, and yet few metabolic cancer driver genes are known. Genetic alterations and epigenetic modifications of cancer cells result in the abnormal regulation of cellular metabolic pathways that are different when compared with normal cells. Such a metabolic reprogramming can be simulated using constraint-based modelling approaches towards predicting oncogenes. We introduced the tri-level optimization problem to use the metabolic reprogramming towards inferring oncogenes. The algorithm incorporated Recon 2.2 network with the Human Protein Atlas to reconstruct genome-scale metabolic network models of the tissue-specific cells at normal and cancer states, respectively. Such reconstructed models were applied to build the templates of the metabolic reprogramming between normal and cancer cell metabolism. The inference optimization problem was formulated to use the templates as a measure towards predicting oncogenes. The nested hybrid differential evolution algorithm was applied to solve the problem to overcome solving difficulty for transferring the inner optimization problem into the single one. Head and neck squamous cells were applied as a case study to evaluate the algorithm. We detected 13 of the top-ranked one-hit dysregulations and 17 of the top-ranked two-hit oncogenes with high similarity ratios to the templates. According to the literature survey, most inferred oncogenes are consistent with the observation in various tissues. Furthermore, the inferred oncogenes were highly connected with the TP53/AKT/IGF/MTOR signalling pathway through PTEN, which is one of the most frequently detected tumour suppressor genes in human cancer.

Comparative Metabolic Network Flux Analysis to Identify Differences in Cellular Metabolism

Metabolic network flux analysis uses genome-scale metabolic reconstructions to integrate transcriptomics, proteomics, and/or metabolomics data to allow for comprehensive interpretation of genotype to metabolic phenotype relationships. The compilation of many Constraint-based model analysis methods into one MATLAB package, the COBRAtoolbox, has opened the possibility of using these methods to the many biologists with some knowledge of the commonly used statistical program, MATLAB. Here we outline the steps required to take a published genome-scale metabolic reconstruction and interrogate its consistency and biological feasibility. Subsequently, we demonstrate how mRNA expression data and metabolomics data, relating to one or more cell types or biological contexts, can be applied to constrain and generate metabolic models descriptive of metabolic flux phenotypes. Finally, we describe the comparison of the resulting models and model outputs with the aim of identifying metabolic biomarkers and changes in cellular metabolism.

Compartment and hub definitions tune metabolic networks for metabolomic interpretations

BACKGROUND

Metabolic networks represent all chemical reactions that occur between molecular metabolites in an organism's cells. They offer biological context in which to integrate, analyze, and interpret omic measurements, but their large scale and extensive connectivity present unique challenges. While it is practical to simplify these networks by placing constraints on compartments and hubs, it is unclear how these simplifications alter the structure of metabolic networks and the interpretation of metabolomic experiments.

RESULTS

We curated and adapted the latest systemic model of human metabolism and developed customizable tools to define metabolic networks with and without compartmentalization in subcellular organelles and with or without inclusion of prolific metabolite hubs. Compartmentalization made networks larger, less dense, and more modular, whereas hubs made networks larger, more dense, and less modular. When present, these hubs also dominated shortest paths in the network, yet their exclusion exposed the subtler prominence of other metabolites that are typically more relevant to metabolomic experiments. We applied the non-compartmental network without metabolite hubs in a retrospective, exploratory analysis of metabolomic measurements from 5 studies on human tissues. Network clusters identified individual reactions that might experience differential regulation between experimental conditions, several of which were not apparent in the original publications.

CONCLUSIONS

Exclusion of specific metabolite hubs exposes modularity in both compartmental and non-compartmental metabolic networks, improving detection of relevant clusters in omic measurements. Better computational detection of metabolic network clusters in large data sets has potential to identify differential regulation of individual genes, transcripts, and proteins.

Deep learning enables high-quality and high-throughput prediction of enzyme commission numbers

High-quality and high-throughput prediction of enzyme commission (EC) numbers is essential for accurate understanding of enzyme functions, which have many implications in pathologies and industrial biotechnology. Several EC number prediction tools are currently available, but their prediction performance needs to be further improved to precisely and efficiently process an ever-increasing volume of protein sequence data. Here, we report DeepEC, a deep learning-based computational framework that predicts EC numbers for protein sequences with high precision and in a high-throughput manner. DeepEC takes a protein sequence as input and predicts EC numbers as output. DeepEC uses 3 convolutional neural networks (CNNs) as a major engine for the prediction of EC numbers, and also implements homology analysis for EC numbers that cannot be classified by the CNNs. Comparative analyses against 5 representative EC number prediction tools show that DeepEC allows the most precise prediction of EC numbers, and is the fastest and the lightest in terms of the disk space required. Furthermore, DeepEC is the most sensitive in detecting the effects of mutated domains/binding site residues of protein sequences. DeepEC can be used as an independent tool, and also as a third-party software component in combination with other computational platforms that examine metabolic reactions.

Current status and applications of genome-scale metabolic models

Genome-scale metabolic models (GEMs) computationally describe gene-protein-reaction associations for entire metabolic genes in an organism, and can be simulated to predict metabolic fluxes for various systems-level metabolic studies. Since the first GEM for Haemophilus influenzae was reported in 1999, advances have been made to develop and simulate GEMs for an increasing number of organisms across bacteria, archaea, and eukarya. Here, we review current reconstructed GEMs and discuss their applications, including strain development for chemicals and materials production, drug targeting in pathogens, prediction of enzyme functions, pan-reactome analysis, modeling interactions among multiple cells or organisms, and understanding human diseases.

Human Systems Biology and Metabolic Modelling: A Review-From Disease Metabolism to Precision Medicine

In cell and molecular biology, metabolism is the only system that can be fully simulated at genome scale. Metabolic systems biology offers powerful abstraction tools to simulate all known metabolic reactions in a cell, therefore providing a snapshot that is close to its observable phenotype. In this review, we cover the 15 years of human metabolic modelling. We show that, although the past five years have not experienced large improvements in the size of the gene and metabolite sets in human metabolic models, their accuracy is rapidly increasing. We also describe how condition-, tissue-, and patient-specific metabolic models shed light on cell-specific changes occurring in the metabolic network, therefore predicting biomarkers of disease metabolism. We finally discuss current challenges and future promising directions for this research field, including machine/deep learning and precision medicine. In the omics era, profiling patients and biological processes from a multiomic point of view is becoming more common and less expensive. Starting from multiomic data collected from patients and N-of-1 trials where individual patients constitute different case studies, methods for model-building and data integration are being used to generate patient-specific models. Coupled with state-of-the-art machine learning methods, this will allow characterizing each patient's disease phenotype and delivering precision medicine solutions, therefore leading to preventative medicine, reduced treatment, and in silico clinical trials.

The poly-omics of ageing through individual-based metabolic modelling

BACKGROUND

Ageing can be classified in two different ways, chronological ageing and biological ageing. While chronological age is a measure of the time that has passed since birth, biological (also known as transcriptomic) ageing is defined by how time and the environment affect an individual in comparison to other individuals of the same chronological age. Recent research studies have shown that transcriptomic age is associated with certain genes, and that each of those genes has an effect size. Using these effect sizes we can calculate the transcriptomic age of an individual from their age-associated gene expression levels. The limitation of this approach is that it does not consider how these changes in gene expression affect the metabolism of individuals and hence their observable cellular phenotype.

RESULTS

We propose a method based on poly-omic constraint-based models and machine learning in order to further the understanding of transcriptomic ageing. We use normalised CD4 T-cell gene expression data from peripheral blood mononuclear cells in 499 healthy individuals to create individual metabolic models. These models are then combined with a transcriptomic age predictor and chronological age to provide new insights into the differences between transcriptomic and chronological ageing. As a result, we propose a novel metabolic age predictor.

CONCLUSIONS

We show that our poly-omic predictors provide a more detailed analysis of transcriptomic ageing compared to gene-based approaches, and represent a basis for furthering our knowledge of the ageing mechanisms in human cells.

Deep learning improves prediction of drug-drug and drug-food interactions

Drug interactions, including drug-drug interactions (DDIs) and drug-food constituent interactions (DFIs), can trigger unexpected pharmacological effects, including adverse drug events (ADEs), with causal mechanisms often unknown. Several computational methods have been developed to better understand drug interactions, especially for DDIs. However, these methods do not provide sufficient details beyond the chance of DDI occurrence, or require detailed drug information often unavailable for DDI prediction. Here, we report development of a computational framework DeepDDI that uses names of drug-drug or drug-food constituent pairs and their structural information as inputs to accurately generate 86 important DDI types as outputs of human-readable sentences. DeepDDI uses deep neural network with its optimized prediction performance and predicts 86 DDI types with a mean accuracy of 92.4% using the DrugBank gold standard DDI dataset covering 192,284 DDIs contributed by 191,878 drug pairs. DeepDDI is used to suggest potential causal mechanisms for the reported ADEs of 9,284 drug pairs, and also predict alternative drug candidates for 62,707 drug pairs having negative health effects. Furthermore, DeepDDI is applied to 3,288,157 drug-food constituent pairs (2,159 approved drugs and 1,523 well-characterized food constituents) to predict DFIs. The effects of 256 food constituents on pharmacological effects of interacting drugs and bioactivities of 149 food constituents are predicted. These results suggest that DeepDDI can provide important information on drug prescription and even dietary suggestions while taking certain drugs and also guidelines during drug development.