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

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.

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.

The use of artificial intelligence in the treatment of rare diseases: A scoping review

With the increasing application of artificial intelligence (AI) in medicine and healthcare, AI technologies have the potential to improve the diagnosis, treatment, and prognosis of rare diseases. Presently, existing research predominantly focuses on the areas of diagnosis and prognosis, with relatively fewer studies dedicated to the domain of treatment. The purpose of this review is to systematically analyze the existing literature on the application of AI in the treatment of rare diseases. We searched three databases for related studies, and established criteria for the selection of retrieved articles. From the 407 unique articles identified across the three databases, 13 articles from 8 countries were selected, which investigated 10 different rare diseases. The most frequently studied rare disease group was rare neurologic diseases (n = 5/13, 38.46%). Among the four identified therapeutic domains, 7 articles (53.85%) focused on drug research, with 5 specifically focused on drug discovery (drug repurposing, the discovery of drug targets and small-molecule inhibitors), 1 on pre-clinical studies (drug interactions), and 1 on clinical studies (information strength assessment of clinical parameters). Across the selected 13 articles, we identified total 32 different algorithms, with random forest (RF) being the most commonly used (n = 4/32, 12.50%). The predominant purpose of AI in the treatment of rare diseases in these articles was to enhance the performance of analytical tasks (53.33%). The most common data source was database data (35.29%), with 5 of these studies being in the field of drug research, utilizing classic databases such as RCSB, PDB and NCBI. Additionally, 47.37% of the articles highlighted the existing challenge of data scarcity or small sample sizes.

Identification of Potential Inhibitors for the Treatment of Alkaptonuria Using an Integrated In Silico Computational Strategy

Alkaptonuria (AKU) is a rare genetic autosomal recessive disorder characterized by elevated serum levels of homogentisic acid (HGA). In this disease, tyrosine metabolism is interrupted because of the alterations in homogentisate dioxygenase (HGD) gene. The patient suffers from ochronosis, fractures, and tendon ruptures. To date, no medicine has been approved for the treatment of AKU. However, physiotherapy and strong painkillers are administered to help mitigate the condition. Recently, nitisinone, an FDA-approved drug for type 1 tyrosinemia, has been given to AKU patients in some countries and has shown encouraging results in reducing the disease progression. However, this drug is not the targeted treatment for AKU, and causes keratopathy. Therefore, the foremost aim of this study is the identification of potent and druggable inhibitors of AKU with no or minimal side effects by targeting 4-hydroxyphenylpyruvate dioxygenase. To achieve our goal, we have performed computational modelling using BioSolveIT suit. The library of ligands for molecular docking was acquired by fragment replacement of reference molecules by ReCore. Subsequently, the hits were screened on the basis of estimated affinities, and their pharmacokinetic properties were evaluated using SwissADME. Afterward, the interactions between target and ligands were investigated using Discovery Studio. Ultimately, compounds c and f were identified as potent inhibitors of 4-hydroxyphenylpyruvate dioxygenase.

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.

Preventive use of nitisinone in alkaptonuria

Alkaptonuria (AKU, OMIM 203500) is a rare congenital disorder caused by a deficiency of the enzyme homogentisate-1,2,-dioxygenase. The long-term consequences of AKU are joint problems, cardiac valve abnormalities and renal problems. Landmark intervention studies with nitisinone 10 mg daily, suppressing an upstream enzyme activity, demonstrated its beneficial effects in AKU patients with established complications, which usually start to develop in the fourth decade. Lower dose of nitisinone in the range of 0.2–2 mg daily will already reduce urinary homogentisic acid (uHGA) excretion by > 90%, which may prevent AKU-related complications earlier in the course of the disease while limiting the possibility of side-effects related to the increase of plasma tyrosine levels caused by nitisinone. Future preventive studies should establish the lowest possible dose for an individual patient, the best age to start treatment and also collect evidence to which level uHGA excretion should be reduced to prevent complications.

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.