Machine learning application for development of a data-driven predictive model able to investigate quality of life scores in a rare disease

Prediction of inherited metabolic disorders using tandem mass spectrometry data with the help of artificial neural networks

Background/aim

Tandem mass spectrometry is helpful in diagnosing amino acid metabolism disorders, organic acidemias, and fatty acid oxidation disorders and can provide rapid and accurate diagnosis for inborn errors of metabolism. The aim of this study was to predict inborn errors of metabolism in children with the help of artificial neural networks using tandem mass spectrometry data.

Materials and methods

Forty-seven and 13 parameters of tandem mass spectrometry datasets obtained from 2938 different patients were respectively taken into account to train and test the artificial neural networks. Different artificial neural network models were established to obtain better prediction performances. The obtained results were compared with each other for fair comparisons.

Results

The best results were obtained by using the rectified linear unit activation function. One, two, and three hidden layers were considered for artificial neural network models established with both 47 and 13 parameters. The sensitivity of model B2 for definitive inherited metabolic disorders was found to be 80%. The accuracy rates of model A3 and model B2 are 99.3% and 99.2%, respectively. The area under the curve value of model A3 was 0.87, while that of model B2 was 0.90.

Conclusion

The results showed that the proposed artificial neural networks are capable of predicting inborn errors of metabolism very accurately. Therefore, developing new technologies to identify and predict inborn errors of metabolism will be very useful.

Alkaptonuria: From Molecular Insights to a Dedicated Digital Platform

Alkaptonuria (AKU) is a genetic disorder that affects connective tissues of several body compartments causing cartilage degeneration, tendon calcification, heart problems, and an invalidating, early-onset form of osteoarthritis. The molecular mechanisms underlying AKU involve homogentisic acid (HGA) accumulation in cells and tissues. HGA is highly reactive, able to modify several macromolecules, and activates different pathways, mostly involved in the onset and propagation of oxidative stress and inflammation, with consequences spreading from the microscopic to the macroscopic level leading to irreversible damage. Gaining a deeper understanding of AKU molecular mechanisms may provide novel possible therapeutical approaches to counteract disease progression. In this review, we first describe inflammation and oxidative stress in AKU and discuss similarities with other more common disorders. Then, we focus on HGA reactivity and AKU molecular mechanisms. We finally describe a multi-purpose digital platform, named ApreciseKUre, created to facilitate data collection, integration, and analysis of AKU-related data.

Identification of Smith-Magenis syndrome cases through an experimental evaluation of machine learning methods

This research work introduces a novel, nonintrusive method for the automatic identification of Smith-Magenis syndrome, traditionally studied through genetic markers. The method utilizes cepstral peak prominence and various machine learning techniques, relying on a single metric computed by the research group. The performance of these techniques is evaluated across two case studies, each employing a unique data preprocessing approach. A proprietary data "windowing" technique is also developed to derive a more representative dataset. To address class imbalance in the dataset, the synthetic minority oversampling technique (SMOTE) is applied for data augmentation. The application of these preprocessing techniques has yielded promising results from a limited initial dataset. The study concludes that the k-nearest neighbors and linear discriminant analysis perform best, and that cepstral peak prominence is a promising measure for identifying Smith-Magenis syndrome.

Alkaptonuria

Alkaptonuria is a rare inborn error of metabolism caused by the deficiency of homogentisate 1,2-dioxygenase activity. The consequent homogentisic acid (HGA) accumulation in body fluids and tissues leads to a multisystemic and highly debilitating disease whose main features are dark urine, ochronosis (HGA-derived pigment in collagen-rich connective tissues), and a painful and severe form of osteoarthropathy. Other clinical manifestations are extremely variable and include kidney and prostate stones, aortic stenosis, bone fractures, and tendon, ligament and/or muscle ruptures. As an autosomal recessive disorder, alkaptonuria affects men and women equally. Debilitating symptoms appear around the third decade of life, but a proper and timely diagnosis is often delayed due to their non-specific nature and a lack of knowledge among physicians. In later stages, patients' quality of life might be seriously compromised and further complicated by comorbidities. Thus, appropriate management of alkaptonuria requires a multidisciplinary approach, and periodic clinical evaluation is advised to monitor disease progression, complications and/or comorbidities, and to enable prompt intervention. Treatment options are patient-tailored and include a combination of medications, physical therapy and surgery. Current basic and clinical research focuses on improving patient management and developing innovative therapies and implementing precision medicine strategies.

A Drug Discovery Approach to a Reveal Novel Antioxidant Natural Source: The Case of Chestnut Burr Biomass

Currently, many environmental and energy-related problems are threatening the future of our planet. In October 2022, the Worldmeter recorded the world population as 7.9 billion people, estimating that there will be an increase of 2 billion by 2057. The rapid growth of the population and the continuous increase in needs are causing worrying conditions, such as pollution, climate change, global warming, waste disposal, and natural resource reduction. Looking for novel and innovative methods to overcome these global troubles is a must for our common welfare. The circular bioeconomy represents a promising strategy to alleviate the current conditions using biomass-like natural wastes to replace commercial products that have a negative effect on our ecological footprint. Applying the circular bioeconomy concept, we propose an integrated in silico and in vitro approach to identify antioxidant bioactive compounds extracted from chestnut burrs (an agroforest waste) and their potential biological targets. Our study provides a novel and robust strategy developed within the circular bioeconomy concept aimed at target and drug discovery for a wide range of diseases. Our study could open new frontiers in the circular bioeconomy related to target and drug discovery, offering new ideas for sustainable scientific research aimed at identifying novel therapeutical strategies.

The Impact of Artificial Intelligence in the Odyssey of Rare Diseases

Emerging machine learning (ML) technologies have the potential to significantly improve the research and treatment of rare diseases, which constitute a vast set of diseases that affect a small proportion of the total population. Artificial Intelligence (AI) algorithms can help to quickly identify patterns and associations that would be difficult or impossible for human analysts to detect. Predictive modeling techniques, such as deep learning, have been used to forecast the progression of rare diseases, enabling the development of more targeted treatments. Moreover, AI has also shown promise in the field of drug development for rare diseases with the identification of subpopulations of patients who may be most likely to respond to a particular drug. This review aims to highlight the achievements of AI algorithms in the study of rare diseases in the past decade and advise researchers on which methods have proven to be most effective. The review will focus on specific rare diseases, as defined by a prevalence rate that does not exceed 1-9/100,000 on Orphanet, and will examine which AI methods have been most successful in their study. We believe this review can guide clinicians and researchers in the successful application of ML in rare diseases.

Structure-Function Relationship of Homogentisate 1,2-dioxygenase: Understanding the Genotype-Phenotype Correlations in the Rare Genetic Disease Alkaptonuria

Alkaptonuria (AKU), a rare genetic disorder, is characterized by the accumulation of homogentisic acid (HGA) in organs, which occurs because the homogentisate 1,2-dioxygenase (HGD) enzyme is not functional due to gene variants. Over time, HGA oxidation and accumulation cause the formation of the ochronotic pigment, a deposit that provokes tissue degeneration and organ malfunction. Here, we report a comprehensive review of the variants so far reported, the structural studies on the molecular consequences of protein stability and interaction, and molecular simulations for pharmacological chaperones as protein rescuers. Moreover, evidence accumulated so far in alkaptonuria research will be re-proposed as the bases for a precision medicine approach in a rare disease.

Effects of Nitisinone on Oxidative and Inflammatory Markers in Alkaptonuria: Results from SONIA1 and SONIA2 Studies

Nitisinone (NTBC) was recently approved to treat alkaptonuria (AKU), but there is no information on its impact on oxidative stress and inflammation, which are observed in AKU. Therefore, serum samples collected during the clinical studies SONIA1 (40 AKU patients) and SONIA2 (138 AKU patients) were tested for Serum Amyloid A (SAA), CRP and IL-8 by ELISA; Advanced Oxidation Protein Products (AOPP) by spectrophotometry; and protein carbonyls by Western blot. Our results show that NTBC had no significant effects on the tested markers except for a slight but statistically significant effect for NTBC, but not for the combination of time and NTBC, on SAA levels in SONIA2 patients. Notably, the majority of SONIA2 patients presented with SAA > 10 mg/L, and 30 patients in the control group (43.5%) and 40 patients (58.0%) in the NTBC-treated group showed persistently elevated SAA > 10 mg/L at each visit during SONIA2. Higher serum SAA correlated with lower quality of life and higher morbidity. Despite no quantitative differences in AOPP, the preliminary analysis of protein carbonyls highlighted patterns that deserve further investigation. Overall, our results suggest that NTBC cannot control the sub-clinical inflammation due to increased SAA observed in AKU, which is also a risk factor for developing secondary amyloidosis.

Computational Approaches Integrated in a Digital Ecosystem Platform for a Rare Disease

Alkaptonuria (AKU) is an ultra-rare autosomal recessive disease caused by a mutation in the homogentisate 1,2-dioxygenase gene. One of the main obstacles in studying AKU and other ultra-rare diseases, is the lack of a standardized methodology to assess disease severity or response to treatment. Based on that, a multi-purpose digital platform, called ApreciseKUre, was implemented to facilitate data collection, integration and analysis for patients affected by AKU. It includes genetic, biochemical, histopathological, clinical, therapeutic resources and Quality of Life (QoL) scores that can be shared among registered researchers and clinicians to create a Precision Medicine Ecosystem. The combination of machine learning applications to analyse and re-interpret data available in the ApreciseKUre clearly indicated the potential direct benefits to achieve patients' stratification and the consequent tailoring of care and treatments to a specific subgroup of patients. In order to generate a comprehensive patient profile, computational modeling and database construction support the identification of potential new biomarkers, paving the way for more personalized therapy to maximize the benefit-risk ratio. In this work, different Machine Learning implemented approaches were described.

Machine learning on small size samples: A synthetic knowledge synthesis

Machine Learning is an increasingly important technology dealing with the growing complexity of the digitalised world. Despite the fact, that we live in a 'Big data' world where, almost 'everything' is digitally stored, there are many real-world situations, where researchers are still faced with small data samples. The present bibliometric knowledge synthesis study aims to answer the research question 'What is the small data problem in machine learning and how it is solved?' The analysis a positive trend in the number of research publications and substantial growth of the research community, indicating that the research field is reaching maturity. Most productive countries are China, United States and United Kingdom. Despite notable international cooperation, the regional concentration of research literature production in economically more developed countries was observed. Thematic analysis identified four research themes. The themes are concerned with to dimension reduction in complex big data analysis, data augmentation techniques in deep learning, data mining and statistical learning on small datasets.

HGDiscovery: An online tool providing functional and phenotypic information on novel variants of homogentisate 1,2- dioxigenase

Alkaptonuria (AKU), a rare genetic disorder, is characterized by the accumulation of homogentisic acid (HGA) in the body. Affected individuals lack functional levels of an enzyme required to breakdown HGA. Mutations in the homogentisate 1,2-dioxygenase (HGD) gene cause AKU and they are responsible for deficient levels of functional HGD, which, in turn, leads to excess levels of HGA. Although HGA is rapidly cleared from the body by the kidneys, in the long term it starts accumulating in various tissues, especially cartilage. Over time (rarely before adulthood), it eventually changes the color of affected tissue to slate blue or black. Here we report a comprehensive mutation analysis of 111 pathogenic and 190 non-pathogenic HGD missense mutations using protein structural information. Using our comprehensive suite of graph-based signature methods, mCSM complemented with sequence-based tools, we studied the functional and molecular consequences of each mutation on protein stability, interaction and evolutionary conservation. The scores generated from the structure and sequence-based tools were used to train a supervised machine learning algorithm with 89% accuracy. The empirical classifier was used to generate the variant phenotype for novel HGD missense mutations. All this information is deployed as a user friendly freely available web server called HGDiscovery (https://biosig.lab.uq.edu.au/hgdiscovery/).

•

Functional and phenotypic consequences of HGD non-synonymous variations.

•

Biophysical, structural and evolutionary analysis of novel and known clinical variants.

•

Pathogenic mutations affected protein stability and conformational flexibility.

•

Pathogenic mutations associated with deleterious scores for sequence-based features.

•

HGDiscovery (http://biosig.unimelb.edu.au/hgdiscovery/) – webserver.

Precision reimbursement for precision medicine: the need for patient-level decisions between payers, providers and pharmaceutical companies

Healthcare costs have been dramatically rising in developed economies worldwide. A key driver of cost increases has been high-cost drugs. The current model of reimbursement is not configured for drugs with uncertain outcomes. Future reimbursement will require better allocation of available healthcare system funds. Technological advancements have opened the door to a new type of outcomes-based reimbursement, enabling value exchange between payers and pharmaceutical companies, which we term precision reimbursement. Precision reimbursement extends beyond value-based contracts, with decisions at individual rather than aggregate level. For precision reimbursement to be adopted, there are data, computation and infrastructure requirements. All stakeholders benefit in moving to precision reimbursement for optimal resource allocation, risk sharing and, ultimately, improved outcomes. There are implementation challenges including cost, change management, information governance and development of surrogate markers. The overarching trend in medicine is toward personalised interventions, with precision reimbursement as the logical consequence.

Leveraging proteomics in orphan disease research: pitfalls and potential

Introduction: The term 'orphan diseases' includes conditions meeting prevalence-based or commercial viability criteria: they affect a small number of individuals and are considered an unviable market for drug development. Proteomics is an important technology to study them, providing information on mechanisms and evolution, biomarkers, and effects of therapeutic interventions.Areas covered: Herein, we review how proteomics and bioinformatic tools could be applied to the study of rare diseases and discuss pitfalls and potential.Expert opinion: Research in the field of rare diseases has to face many challenges, and implementation plans should foresee highly specialized collaborative consortia to create multidisciplinary frameworks for data sharing, advancing research, supporting clinical studies, and accelerating drug development. The integration of different technologies will allow better knowledge of disease pathophysiology, and the inclusion of proteomics and other omics technologies in this context will be pivotal to this aim.Several aspects of rare diseases, often perceived as limiting factors, might actually be advantages for a precision medicine approach: the limited number of patients, the collaboration with patient societies, and the availability of curated clinical registries could allow the development of homogeneous clinical databases and ultimately a better control over the data to be analyzed.

Machine learning application for patient stratification and phenotype/genotype investigation in a rare disease

Alkaptonuria (AKU, OMIM: 203500) is an autosomal recessive disorder caused by mutations in the Homogentisate 1,2-dioxygenase (HGD) gene. A lack of standardized data, information and methodologies to assess disease severity and progression represents a common complication in ultra-rare disorders like AKU. This is the reason why we developed a comprehensive tool, called ApreciseKUre, able to collect AKU patients deriving data, to analyse the complex network among genotypic and phenotypic information and to get new insight in such multi-systemic disease. By taking advantage of the dataset, containing the highest number of AKU patient ever considered, it is possible to apply more sophisticated computational methods (such as machine learning) to achieve a first AKU patient stratification based on phenotypic and genotypic data in a typical precision medicine perspective. Thanks to our sufficiently populated and organized dataset, it is possible, for the first time, to extensively explore the phenotype-genotype relationships unknown so far. This proof of principle study for rare diseases confirms the importance of a dedicated database, allowing data management and analysis and can be used to tailor treatments for every patient in a more effective way.

Towards a Precision Medicine Approach Based on Machine Learning for Tailoring Medical Treatment in Alkaptonuria

ApreciseKUre is a multi-purpose digital platform facilitating data collection, integration and analysis for patients affected by Alkaptonuria (AKU), an ultra-rare autosomal recessive genetic disease. It includes genetic, biochemical, histopathological, clinical, therapeutic resources and quality of life scores that can be shared among registered researchers and clinicians in order to create a Precision Medicine Ecosystem (PME). The combination of machine learning application to analyse and re-interpret data available in the ApreciseKUre shows the potential direct benefits to achieve patient stratification and the consequent tailoring of care and treatments to a specific subgroup of patients. In this study, we have developed a tool able to investigate the most suitable treatment for AKU patients in accordance with their Quality of Life scores, which indicates changes in health status before/after the assumption of a specific class of drugs. This fact highlights the necessity of development of patient databases for rare diseases, like ApreciseKUre. We believe this is not limited to the study of AKU, but it represents a proof of principle study that could be applied to other rare diseases, allowing data management, analysis, and interpretation.