Machine learning technology in the application of genome analysis: A systematic review

Artificial Intelligence in Medical Affairs: A New Paradigm with Novel Opportunities

The advent of artificial intelligence (AI) revolutionizes the ways of working in many areas of business and life science. In Medical Affairs (MA) departments of the pharmaceutical industry AI holds great potential for positively influencing the medical mission of identifying and addressing unmet medical needs and care gaps, and fostering solutions that improve the egalitarian and unbiased access of patients to treatments worldwide. Given the essential position of MA in corporate interactions with various healthcare stakeholders, AI offers broad possibilities to support strategic decision-making and to pioneer novel approaches in medical stakeholder interactions. By analyzing data derived from the healthcare environment and by streamlining operations in medical content generation, AI advances data-based prioritization and strategy execution. In this review, we discuss promising AI-based solutions in MA that support the effective use of heterogenous information from observations of the healthcare environment, the enhancement of medical education, and the analysis of real-world data. For a successful implementation of such solutions, specific considerations partly unique to healthcare must be taken care of, for example, transparency, data privacy, healthcare regulations, and in predictive applications, explainability.

Machine learning approaches to the human metabolome in sepsis identify metabolic links with survival

Background

Metabolic predictors and potential mediators of survival in sepsis have been incompletely characterized. We examined whether machine learning (ML) tools applied to the human plasma metabolome could consistently identify and prioritize metabolites implicated in sepsis survivorship, and whether these methods improved upon conventional statistical approaches.

Methods

Plasma gas chromatography–liquid chromatography mass spectrometry quantified 411 metabolites measured ≤ 72 h of ICU admission in 60 patients with sepsis at a single center (Brigham and Women’s Hospital, Boston, USA). Seven ML approaches were trained to differentiate survivors from non-survivors. Model performance predicting 28 day mortality was assessed through internal cross-validation, and innate top-feature (metabolite) selection and rankings were compared across the 7 ML approaches and with conventional statistical methods (logistic regression). Metabolites were consensus ranked by a summary, ensemble ML ranking procedure weighing their contribution to mortality risk prediction across multiple ML models.

Results

Median (IQR) patient age was 58 (47, 62) years, 45% were women, and median (IQR) SOFA score was 9 (6, 12). Mortality at 28 days was 42%. The models’ specificity ranged from 0.619 to 0.821. Partial least squares regression-discriminant analysis and nearest shrunken centroids prioritized the greatest number of metabolites identified by at least one other method. Penalized logistic regression demonstrated top-feature results that were consistent with many ML methods. Across the plasma metabolome, the 13 metabolites with the strongest linkage to mortality defined through an ensemble ML importance score included lactate, bilirubin, kynurenine, glycochenodeoxycholate, phenylalanine, and others. Four of these top 13 metabolites (3-hydroxyisobutyrate, indoleacetate, fucose, and glycolithocholate sulfate) have not been previously associated with sepsis survival. Many of the prioritized metabolites are constituents of the tryptophan, pyruvate, phenylalanine, pentose phosphate, and bile acid pathways.

Conclusions

We identified metabolites linked with sepsis survival, some confirming prior observations, and others representing new associations. The application of ensemble ML feature-ranking tools to metabolomic data may represent a promising statistical platform to support biologic target discovery.

Supplementary Information

The online version contains supplementary material available at 10.1186/s40635-022-00445-8.

Natural products for infectious microbes and diseases: an overview of sources, compounds, and chemical diversities

As coronavirus disease 2019 (COVID-19) threatens human health globally, infectious disorders have become one of the most challenging problem for the medical community. Natural products (NP) have been a prolific source of antimicrobial agents with widely divergent structures and a range vast biological activities. A dataset comprising 618 articles, including 646 NP-based compounds from 672 species of natural sources with biological activities against 21 infectious pathogens from five categories, was assembled through manual selection of published articles. These data were used to identify 268 NP-based compounds classified into ten groups, which were used for network pharmacology analysis to capture the most promising lead-compounds such as agelasine D, dicumarol, dihydroartemisinin and pyridomycin. The distribution of maximum Tanimoto scores indicated that compounds which inhibited parasites exhibited low diversity, whereas the chemistries inhibiting bacteria, fungi, and viruses showed more structural diversity. A total of 331 species of medicinal plants with compounds exhibiting antimicrobial activities were selected to classify the family sources. The family Asteraceae possesses various compounds against C. neoformans, the family Anacardiaceae has compounds against Salmonella typhi, the family Cucurbitacea against the human immunodeficiency virus (HIV), and the family Ancistrocladaceae against Plasmodium. This review summarizes currently available data on NP-based antimicrobials against refractory infections to provide information for further discovery of drugs and synthetic strategies for anti-infectious agents.

Phenotype analysis of cultivation processes via unsupervised machine learning: Demonstration for Clostridium pasteurianum

A novel approach of phenotype analysis of fermentation-based bioprocesses based on unsupervised learning (clustering) is presented. As a prior identification of phenotypes and conditional interrelations is desired to control fermentation performance, an automated learning method to output reference phenotypes (defined as vector of biomass-specific rates) was developed and the necessary computing process and parameters were assessed. For its demonstration, time series data of 90 Clostridium pasteurianum cultivations were used which feature a broad spectrum of solventogenic and acidogenic phenotypes, while 14 clusters of phenotypic manifestations were identified. The analysis of reference phenotypes showed distinct differences, where potential conditionalities were exemplary isolated. Further, cluster-based balancing of carbon and ATP or the use of reference phenotypes as indicator for bioprocess monitoring were demonstrated to highlight the perks of this approach. Overall, such analysis depends strongly on the quality of the data and experimental validations will be required before conclusions. However, the automated, streamlined and abstracted approach diminishes the need of individual evaluation of all noisy dataset and showed promising results, which could be transferred to strains with comparably wide-ranging phenotypic manifestations or as indicators for repeated bioprocesses with clearly defined target.

Placental DNA methylation changes and the early prediction of autism in full-term newborns

Autism spectrum disorder (ASD) is associated with abnormal brain development during fetal life. Overall, increasing evidence indicates an important role of epigenetic dysfunction in ASD. The placenta is critical to and produces neurotransmitters that regulate fetal brain development. We hypothesized that placental DNA methylation changes are a feature of the fetal development of the autistic brain and importantly could help to elucidate the early pathogenesis and prediction of these disorders. Genome-wide methylation using placental tissue from the full-term autistic disorder subtype was performed using the Illumina 450K array. The study consisted of 14 cases and 10 control subjects. Significantly epigenetically altered CpG loci (FDR p-value <0.05) in autism were identified. Ingenuity Pathway Analysis (IPA) was further used to identify molecular pathways that were over-represented (epigenetically dysregulated) in autism. Six Artificial Intelligence (AI) algorithms including Deep Learning (DL) to determine the predictive accuracy of CpG markers for autism detection. We identified 9655 CpGs differentially methylated in autism. Among them, 2802 CpGs were inter- or non-genic and 6853 intragenic. The latter involved 4129 genes. AI analysis of differentially methylated loci appeared highly accurate for autism detection. DL yielded an AUC (95% CI) of 1.00 (1.00-1.00) for autism detection using intra- or intergenic markers by themselves or combined. The biological functional enrichment showed, four significant functions that were affected in autism: quantity of synapse, microtubule dynamics, neuritogenesis, and abnormal morphology of neurons. In this preliminary study, significant placental DNA methylation changes. AI had high accuracy for the prediction of subsequent autism development in newborns. Finally, biologically functional relevant gene pathways were identified that may play a significant role in early fetal neurodevelopmental influences on later cognition and social behavior.

Systematic Review on Local Ancestor Inference From a Mathematical and Algorithmic Perspective

Genotypic data provide deep insights into the population history and medical genetics. The local ancestry inference (LAI) (also termed local ancestry deconvolution) method uses the hidden Markov model (HMM) to solve the mathematical problem of ancestry reconstruction based on genomic data. HMM is combined with other statistical models and machine learning techniques for particular genetic tasks in a series of computer tools. In this article, we surveyed the mathematical structure, application characteristics, historical development, and benchmark analysis of the LAI method in detail, which will help researchers better understand and further develop LAI methods. Firstly, we extensively explore the mathematical structure of each model and its characteristic applications. Next, we use bibliometrics to show detailed model application fields and list articles to elaborate on the historical development. LAI publications had experienced a peak period during 2006-2016 and had kept on moving in the following years. The efficiency, accuracy, and stability of the existing models were evaluated by the benchmark. We find that phased data had higher accuracy in comparison with unphased data. We summarize these models with their distinct advantages and disadvantages. The Loter model uses dynamic programming to obtain a globally optimal solution with its parameter-free advantage. Aligned bases can be used directly in the Seqmix model if the genotype is hard to call. This research may help model developers to realize current challenges, develop more advanced models, and enable scholars to select appropriate models according to given populations and datasets.

Exploring epigenetic biomarkers of universal specificities and commonalities among pan-cancer cohorts in The Cancer Genome Atlas

Aim: To explore the mechanism of cancer by employing a comprehensive analysis of DNA methylation patterns and variations among pan-cancer cohorts. Materials & methods: This research focused on the discovery of universally specific or common biomarkers by mathematical statistics and machine learning methods in The Cancer Genome Atlas. Results: We found 138 differently methylated CpGs (DMCs) with a common methylation trend and eight common differently methylated regions in different cancer cohorts. Additionally, we found 99 DMCs to distinguish 32 different cancer cohorts in random forest analysis because of the specificity mechanism, but each DMC still had high instability. Conclusion: Our results could facilitate the development of biomarkers that are universally specific and common features across pan-cancer cohorts.

The Application of Artificial Intelligence in the Genetic Study of Alzheimer's Disease

Alzheimer's disease (AD) is a neurodegenerative disease in which genetic factors contribute approximately 70% of etiological effects. Studies have found many significant genetic and environmental factors, but the pathogenesis of AD is still unclear. With the application of microarray and next-generation sequencing technologies, research using genetic data has shown explosive growth. In addition to conventional statistical methods for the processing of these data, artificial intelligence (AI) technology shows obvious advantages in analyzing such complex projects. This article first briefly reviews the application of AI technology in medicine and the current status of genetic research in AD. Then, a comprehensive review is focused on the application of AI in the genetic research of AD, including the diagnosis and prognosis of AD based on genetic data, the analysis of genetic variation, gene expression profile, gene-gene interaction in AD, and genetic analysis of AD based on a knowledge base. Although many studies have yielded some meaningful results, they are still in a preliminary stage. The main shortcomings include the limitations of the databases, failing to take advantage of AI to conduct a systematic biology analysis of multilevel databases, and lack of a theoretical framework for the analysis results. Finally, we outlook the direction of future development. It is crucial to develop high quality, comprehensive, large sample size, data sharing resources; a multi-level system biology AI analysis strategy is one of the development directions, and computational creativity may play a role in theory model building, verification, and designing new intervention protocols for AD.

Development and Validation of the Predictive Model for Esophageal Squamous Cell Carcinoma Differentiation Degree

The diagnosis of the degree of differentiation of tumor cells can help physicians to make timely detection and take appropriate treatment for the patient's condition. In this study, the original dataset is clustered into two independent types by the Kohonen clustering algorithm. One type is used as the development sets to find correlation indicators and establish predictive models of differentiation, while the other type is used as the validation sets to test the correlation indicators and models. In the development sets, thirteen indicators significantly associated with the degree of differentiation of esophageal squamous cell carcinoma are found by the Kohonen clustering algorithm. Thirteen relevant indicators are used as input features and the degree of tumor differentiations is used as output. Ten classification algorithms are used to predict the differentiation of esophageal squamous cell carcinoma. Artificial bee colony-support vector machine (ABC-SVM) predicts better than the other nine algorithms, with an average accuracy of 81.5% for the 10-fold cross-validation. Based on logistic regression and ReliefF algorithm, five models with the greater merit for the degree of differentiation are found in the development sets. The AUC values of the five models are 0.672, 0.628, 0.630, 0.628, and 0.608 (P < 0.05). The AUC values of the five models in the validation sets are 0.753, 0.728, 0.744, 0.776, and 0.868 (P < 0.0001). The predicted values of the five models are constructed as the input features of ABC-SVM. The accuracy of the 10-fold cross-validation reached 82.0 and 86.5% in the development sets and the validation sets, respectively.

Machine learning health-related applications in low-income and middle-income countries: a scoping review protocol

INTRODUCTION

Machine learning (ML) has been used in bio-medical research, and recently in clinical and public health research. However, much of the available evidence comes from high-income countries, where different health profiles challenge the application of this research to low/middle-income countries (LMICs). It is largely unknown what ML applications are available for LMICs that can support and advance clinical medicine and public health. We aim to address this gap by conducting a scoping review of health-related ML applications in LMICs.

METHODS AND ANALYSIS

This scoping review will follow the methodology proposed by Levac et al. The search strategy is informed by recent systematic reviews of ML health-related applications. We will search Embase, Medline and Global Health (through Ovid), Cochrane and Google Scholar; we will present the date of our searches in the final review. Titles and abstracts will be screened by two reviewers independently; selected reports will be studied by two reviewers independently. Reports will be included if they are primary research where data have been analysed, ML techniques have been used on data from LMICs and they aimed to improve health-related outcomes. We will synthesise the information following evidence mapping recommendations.

ETHICS AND DISSEMINATION

The review will provide a comprehensive list of health-related ML applications in LMICs. The results will be disseminated through scientific publications. We also plan to launch a website where ML models can be hosted so that researchers, policymakers and the general public can readily access them.