Predicting multiple sclerosis disease progression and outcomes with machine learning and MRI-based biomarkers: a review.

Multiple sclerosis (MS) is a demyelinating neurological disorder with a highly heterogeneous clinical presentation and course of progression. Disease-modifying therapies are the only available treatment, as there is no known cure for the disease. Careful selection of suitable therapies is necessary, as they can be accompanied by serious risks and adverse effects such as infection. Magnetic resonance imaging (MRI) plays a central role in the diagnosis and management of MS, though MRI lesions have displayed only moderate associations with MS clinical outcomes, known as the clinico-radiological paradox. With the advent of machine learning (ML) in healthcare, the predictive power of MRI can be improved by leveraging both traditional and advanced ML algorithms capable of analyzing increasingly complex patterns within neuroimaging data. The purpose of this review was to examine the application of MRI-based ML for prediction of MS disease progression. Studies were divided into five main categories: predicting the conversion of clinically isolated syndrome to MS, cognitive outcome, EDSS-related disability, motor disability and disease activity. The performance of ML models is discussed along with highlighting the influential MRI-derived biomarkers. Overall, MRI-based ML presents a promising avenue for MS prognosis. However, integration of imaging biomarkers with other multimodal patient data shows great potential for advancing personalized healthcare approaches in MS.

VISH-Pred: an ensemble of fine-tuned ESM models for protein toxicity prediction.

Peptide- and protein-based therapeutics are becoming a promising treatment regimen for myriad diseases. Toxicity of proteins is the primary hurdle for protein-based therapies. Thus, there is an urgent need for accurate in silico methods for determining toxic proteins to filter the pool of potential candidates. At the same time, it is imperative to precisely identify non-toxic proteins to expand the possibilities for protein-based biologics. To address this challenge, we proposed an ensemble framework, called VISH-Pred, comprising models built by fine-tuning ESM2 transformer models on a large, experimentally validated, curated dataset of protein and peptide toxicities. The primary steps in the VISH-Pred framework are to efficiently estimate protein toxicities taking just the protein sequence as input, employing an under sampling technique to handle the humongous class-imbalance in the data and learning representations from fine-tuned ESM2 protein language models which are then fed to machine learning techniques such as Lightgbm and XGBoost. The VISH-Pred framework is able to correctly identify both peptides/proteins with potential toxicity and non-toxic proteins, achieving a Matthews correlation coefficient of 0.737, 0.716 and 0.322 and F1-score of 0.759, 0.696 and 0.713 on three non-redundant blind tests, respectively, outperforming other methods by over $10\%$ on these quality metrics. Moreover, VISH-Pred achieved the best accuracy and area under receiver operating curve scores on these independent test sets, highlighting the robustness and generalization capability of the framework. By making VISH-Pred available as an easy-to-use web server, we expect it to serve as a valuable asset for future endeavors aimed at discerning the toxicity of peptides and enabling efficient protein-based therapeutics.

Mathematical modeling of the synergistic interplay of radiotherapy and immunotherapy in anti-cancer treatments.

Introduction: While radiotherapy has long been recognized for its ability to directly ablate cancer cells through necrosis or apoptosis, radiotherapy-induced abscopal effect suggests that its impact extends beyond local tumor destruction thanks to immune response. Cellular proliferation and necrosis have been extensively studied using mathematical models that simulate tumor growth, such as Gompertz law, and the radiation effects, such as the linear-quadratic model. However, the effectiveness of radiotherapy-induced immune responses may vary among patients due to individual differences in radiation sensitivity and other factors. Methods: We present a novel macroscopic approach designed to quantitatively analyze the intricate dynamics governing the interactions among the immune system, radiotherapy, and tumor progression. Building upon previous research demonstrating the synergistic effects of radiotherapy and immunotherapy in cancer treatment, we provide a comprehensive mathematical framework for understanding the underlying mechanisms driving these interactions. Results: Our method leverages macroscopic observations and mathematical modeling to capture the overarching dynamics of this interplay, offering valuable insights for optimizing cancer treatment strategies. One shows that Gompertz law can describe therapy effects with two effective parameters. This result permits quantitative data analyses, which give useful indications for the disease progression and clinical decisions. Discussion: Through validation against diverse data sets from the literature, we demonstrate the reliability and versatility of our approach in predicting the time evolution of the disease and assessing the potential efficacy of radiotherapy-immunotherapy combinations. This further supports the promising potential of the abscopal effect, suggesting that in select cases, depending on tumor size, it may confer full efficacy to radiotherapy.

Computational Approach for Spatially Fractionated Radiation Therapy (SFRT) and Immunological Response in Precision Radiation Therapy.

The field of precision radiation therapy has seen remarkable advancements in both experimental and computational methods. Recent literature has introduced various approaches such as Spatially Fractionated Radiation Therapy (SFRT). This unconventional treatment, demanding high-precision radiotherapy, has shown promising clinical outcomes. A comprehensive computational scheme for SFRT, extrapolated from a case report, is proposed. This framework exhibits exceptional flexibility, accommodating diverse initial conditions (shape, inhomogeneity, etc.) and enabling specific choices for sub-volume selection with administrated higher radiation doses. The approach integrates the standard linear quadratic model and, significantly, considers the activation of the immune system due to radiotherapy. This activation enhances the immune response in comparison to the untreated case. We delve into the distinct roles of the native immune system, immune activation by radiation, and post-radiotherapy immunotherapy, discussing their implications for either complete recovery or disease regrowth.

Toward mechanistic medical digital twins: some use cases in immunology.

A fundamental challenge for personalized medicine is to capture enough of the complexity of an individual patient to determine an optimal way to keep them healthy or restore their health. This will require personalized computational models of sufficient resolution and with enough mechanistic information to provide actionable information to the clinician. Such personalized models are increasingly referred to as medical digital twins. Digital twin technology for health applications is still in its infancy, and extensive research and development is required. This article focuses on several projects in different stages of development that can lead to specific-and practical-medical digital twins or digital twin modeling platforms. It emerged from a two-day forum on problems related to medical digital twins, particularly those involving an immune system component. Open access video recordings of the forum discussions are available.

Forum on immune digital twins: a meeting report.

Medical digital twins are computational models of human biology relevant to a given medical condition, which are tailored to an individual patient, thereby predicting the course of disease and individualized treatments, an important goal of personalized medicine. The immune system, which has a central role in many diseases, is highly heterogeneous between individuals, and thus poses a major challenge for this technology. In February 2023, an international group of experts convened for two days to discuss these challenges related to immune digital twins. The group consisted of clinicians, immunologists, biologists, and mathematical modelers, representative of the interdisciplinary nature of medical digital twin development. A video recording of the entire event is available. This paper presents a synopsis of the discussions, brief descriptions of ongoing digital twin projects at different stages of progress. It also proposes a 5-year action plan for further developing this technology. The main recommendations are to identify and pursue a small number of promising use cases, to develop stimulation-specific assays of immune function in a clinical setting, and to develop a database of existing computational immune models, as well as advanced modeling technology and infrastructure.

A computational model of the effects of macronutrients absorption and physical exercise on hormonal regulation and metabolic homeostasis.

Regular physical exercise and appropriate nutrition affect metabolic and hormonal responses and may reduce the risk of developing chronic non-communicable diseases such as high blood pressure, ischemic stroke, coronary heart disease, some types of cancer, and type 2 diabetes mellitus. Computational models describing the metabolic and hormonal changes due to the synergistic action of exercise and meal intake are, to date, scarce and mostly focussed on glucose absorption, ignoring the contribution of the other macronutrients. We here describe a model of nutrient intake, stomach emptying, and absorption of macronutrients in the gastrointestinal tract during and after the ingestion of a mixed meal, including the contribution of proteins and fats. We integrated this effort to our previous work in which we modeled the effects of a bout of physical exercise on metabolic homeostasis. We validated the computational model with reliable data from the literature. The simulations are overall physiologically consistent and helpful in describing the metabolic changes due to everyday life stimuli such as multiple mixed meals and variable periods of physical exercise over prolonged periods of time. This computational model may be used to design virtual cohorts of subjects differing in sex, age, height, weight, and fitness status, for specialized in silico challenge studies aimed at designing exercise and nutrition schemes to support health.

A resting state EEG study on depressed persons with suicidal ideation.

Background: Major Depressive Disorder (MDD) is a psychiatric illness that is often associated with potentially life-threatening physiological changes and increased risk for suicidal behavior. Electroencephalography (EEG) research suggests an association between depression and specific frequency imbalances in the frontal brain region. Further, while recently developed technology has been proposed to simplify EEG data acquisition, more research is still needed to support its use in patients with MDD. Methods: Using the 14-channel EMOTIV EPOC cap, we recorded resting state EEG from 15 MDD patients with and MDD persons with suicidal ideation (SI) vs. 12 healthy controls (HC) to investigate putative power spectral density (PSD) between-group differences at the F3 and F4 electrode sites. Specifically, we explored 1) between-group alpha power asymmetries (AA), 2) between-group differences in delta, theta, alpha and beta power, 3) between PSD data and the scores in the Beck's Depression Inventory-II (BDI-II), Beck's Anxiety Inventory (BAI), Reasons for Living Inventory (RFL), and Self-Disgust Questionnaire (SDS). Results: When compared to HC, patients had higher scores on the BAI (p = 0.0018), BDI-II (p = 0.0001) or SDS (p = 0.0142) scale and lower scores in the RFL (p = 0.0006) scale. The PSD analysis revealed no between-group difference or correlation with questionnaire scores for any of the measures considered. Conclusions: The present study could not confirm previous research suggesting frequency-specific anomalies in depressed persons with SI but might suggest that frontal EEG imbalances reflect greater anxiety and negative self-referencing. Future studies should confirm these findings in a larger population sample.

A multiscale hybrid model for exploring the effect of Resolvin D1 on macrophage polarization during acute inflammation.

Dysregulated inflammation underlies various diseases. Specialized pro-resolving mediators (SPMs) like Resolvin D1 (RvD1) have been shown to resolve inflammation and halt disease progression. Macrophages, key immune cells that drive inflammation, respond to the presence of RvD1 by polarizing to an anti-inflammatory type (M2). However, RvD1's mechanisms, roles, and utility are not fully understood. This paper introduces a gene-regulatory network (GRN) model that contains pathways for RvD1 and other SPMs and proinflammatory molecules like lipopolysaccharides. We couple this GRN model to a partial differential equation-agent-based hybrid model using a multiscale framework to simulate an acute inflammatory response with and without the presence of RvD1. We calibrate and validate the model using experimental data from two animal models. The model reproduces the dynamics of key immune components and the effects of RvD1 during acute inflammation. Our results suggest RvD1 can drive macrophage polarization through the G protein-coupled receptor 32 (GRP32) pathway. The presence of RvD1 leads to an earlier and increased M2 polarization, reduced neutrophil recruitment, and faster apoptotic neutrophil clearance. These results support a body of literature that suggests that RvD1 is a promising candidate for promoting the resolution of acute inflammation. We conclude that once calibrated and validated on human data, the model can identify critical sources of uncertainty, which could be further elucidated in biological experiments and assessed for clinical use.

Explainable Drug Repurposing Approach From Biased Random Walks.

Drug repurposing is a highly active research area, aiming at finding novel uses for drugs that have been previously developed for other therapeutic purposes. Despite the flourishing of methodologies, success is still partial, and different approaches offer, each, peculiar advantages. In this composite landscape, we present a novel methodology focusing on an efficient mathematical procedure based on gene similarity scores and biased random walks which rely on robust drug-gene-disease association data sets. The recommendation mechanism is further unveiled by means of the Markov chain underlying the random walk process, hence providing explainability about how findings are suggested. Performances evaluation and the analysis of a case study on rheumatoid arthritis show that our approach is accurate in providing useful recommendations and is computationally efficient, compared to the state of the art of drug repurposing approaches.

In-silico evaluation of adenoviral COVID-19 vaccination protocols: Assessment of immunological memory up to 6 months after the third dose.

Background: The immune response to adenoviral COVID-19 vaccines is affected by the interval between doses. The optimal interval is unknown. Aim: We aim to explore in-silico the effect of the interval between vaccine administrations on immunogenicity and to analyze the contribution of pre-existing levels of antibodies, plasma cells, and memory B and T lymphocytes. Methods: We used a stochastic agent-based immune simulation platform to simulate two-dose and three-dose vaccination protocols with an adenoviral vaccine. We identified the model's parameters fitting anti-Spike antibody levels from individuals immunized with the COVID-19 vaccine AstraZeneca (ChAdOx1-S, Vaxzevria). We used several statistical methods, such as principal component analysis and binary classification, to analyze the correlation between pre-existing levels of antibodies, plasma cells, and memory B and T cells to the magnitude of the antibody response following a booster dose. Results and conclusions: We find that the magnitude of the antibody response to a booster depends on the number of pre-existing memory B cells, which, in turn, is highly correlated to the number of T helper cells and plasma cells, and the antibody titers. Pre-existing memory T cytotoxic cells and antibodies directly influence antigen availability hence limiting the magnitude of the immune response. The optimal immunogenicity of the third dose is achieved over a large time window, spanning from 6 to 16 months after the second dose. Interestingly, after any vaccine dose, individuals can be classified into two groups, sustainers and decayers, that differ in the kinetics of decline of their antibody titers due to differences in long-lived plasma cells. This suggests that the decayers may benefit from a tailored boosting schedule with a shorter interval to avoid the temporary loss of serological immunity.

Immunoinformatics based designing a multi-epitope vaccine against pathogenic Chandipura vesiculovirus.

Chandipura vesiculovirus (CHPV) is a rapidly emerging pathogen responsible for causing acute encephalitis. Due to its widespread occurrence in Asian and African countries, this has become a global threat, and there is an urgent need to design an effective and nonallergenic vaccine against this pathogen. The present study aimed to develop a multi-epitope vaccine using an immunoinformatics approach. The conventional method of vaccine design involves large proteins or whole organism which leads to unnecessary antigenic load with increased chances of allergenic reactions. In addition, the process is also very time-consuming and labor-intensive. These limitations can be overcome by peptide-based vaccines comprising short immunogenic peptide fragments that can elicit highly targeted immune responses, avoiding the chances of allergenic reactions, in a relatively shorter time span. The multi-epitope vaccine constructed using CTL, HTL, and IFN-γ epitopes was able to elicit specific immune responses when exposed to the pathogen, in silico. Not only that, molecular docking and molecular dynamics simulation studies confirmed a stable interaction of the vaccine with the immune receptors. Several physicochemical analyses of the designed vaccine candidate confirmed it to be highly immunogenic and nonallergic. The computer-aided analysis performed in this study suggests that the designed multi-epitope vaccine can elicit specific immune responses and can be a potential candidate against CHPV.

Emulating complex simulations by machine learning methods.

BACKGROUND: The aim of the present paper is to construct an emulator of a complex biological system simulator using a machine learning approach. More specifically, the simulator is a patient-specific model that integrates metabolic, nutritional, and lifestyle data to predict the metabolic and inflammatory processes underlying the development of type-2 diabetes in absence of familiarity. Given the very high incidence of type-2 diabetes, the implementation of this predictive model on mobile devices could provide a useful instrument to assess the risk of the disease for aware individuals. The high computational cost of the developed model, being a mixture of agent-based and ordinary differential equations and providing a dynamic multivariate output, makes the simulator executable only on powerful workstations but not on mobile devices. Hence the need to implement an emulator with a reduced computational cost that can be executed on mobile devices to provide real-time self-monitoring. RESULTS: Similarly to our previous work, we propose an emulator based on a machine learning algorithm but here we consider a different approach which turn out to have better performances, indeed in terms of root mean square error we have an improvement of two order magnitude. We tested the proposed emulator on samples containing different number of simulated trajectories, and it turned out that the fitted trajectories are able to predict with high accuracy the entire dynamics of the simulator output variables. We apply the emulator to control the level of inflammation while leveraging on the nutritional input. CONCLUSION: The proposed emulator can be implemented and executed on mobile health devices to perform quick-and-easy self-monitoring assessments.

From Infection to Immunity: Understanding the Response to SARS-CoV2 Through In-Silico Modeling.

Background: Immune system conditions of the patient is a key factor in COVID-19 infection survival. A growing number of studies have focused on immunological determinants to develop better biomarkers for therapies. Aim: Studies of the insurgence of immunity is at the core of both SARS-CoV-2 vaccine development and therapies. This paper attempts to describe the insurgence (and the span) of immunity in COVID-19 at the population level by developing an in-silico model. We simulate the immune response to SARS-CoV-2 and analyze the impact of infecting viral load, affinity to the ACE2 receptor, and age in an artificially infected population on the course of the disease. Methods: We use a stochastic agent-based immune simulation platform to construct a virtual cohort of infected individuals with age-dependent varying degrees of immune competence. We use a parameter set to reproduce known inter-patient variability and general epidemiological statistics. Results: By assuming the viremia at day 30 of the infection to be the proxy for lethality, we reproduce in-silico several clinical observations and identify critical factors in the statistical evolution of the infection. In particular, we evidence the importance of the humoral response over the cytotoxic response and find that the antibody titers measured after day 25 from the infection are a prognostic factor for determining the clinical outcome of the infection. Our modeling framework uses COVID-19 infection to demonstrate the actionable effectiveness of modeling the immune response at individual and population levels. The model developed can explain and interpret observed patterns of infection and makes verifiable temporal predictions. Within the limitations imposed by the simulated environment, this work proposes quantitatively that the great variability observed in the patient outcomes in real life can be the mere result of subtle variability in the infecting viral load and immune competence in the population. In this work, we exemplify how computational modeling of immune response provides an important view to discuss hypothesis and design new experiments, in particular paving the way to further investigations about the duration of vaccine-elicited immunity especially in the view of the blundering effect of immunosenescence.

In silico designing of vaccine candidate against Clostridium difficile.

Clostridium difficile is a spore-forming gram-positive bacterium, recognized as the primary cause of antibiotic-associated nosocomial diarrhoea. Clostridium difficile infection (CDI) has emerged as a major health-associated infection with increased incidence and hospitalization over the years with high mortality rates. Contamination and infection occur after ingestion of vegetative spores, which germinate in the gastro-intestinal tract. The surface layer protein and flagellar proteins are responsible for the bacterial colonization while the spore coat protein, is associated with spore colonization. Both these factors are the main concern of the recurrence of CDI in hospitalized patients. In this study, the CotE, SlpA and FliC proteins are chosen to form a multivalent, multi-epitopic, chimeric vaccine candidate using the immunoinformatics approach. The overall reliability of the candidate vaccine was validated in silico and the molecular dynamics simulation verified the stability of the vaccine designed. Docking studies showed stable vaccine interactions with Toll-Like Receptors of innate immune cells and MHC receptors. In silico codon optimization of the vaccine and its insertion in the cloning vector indicates a competent expression of the modelled vaccine in E. coli expression system. An in silico immune simulation system evaluated the effectiveness of the candidate vaccine to trigger a protective immune response.

Identification and validation of viral antigens sharing sequence and structural homology with tumor-associated antigens (TAAs).

BACKGROUND: The host's immune system develops in equilibrium with both cellular self-antigens and non-self-antigens derived from microorganisms which enter the body during lifetime. In addition, during the years, a tumor may arise presenting to the immune system an additional pool of non-self-antigens, namely tumor antigens (tumor-associated antigens, TAAs; tumor-specific antigens, TSAs). METHODS: In the present study, we looked for homology between published TAAs and non-self-viral-derived epitopes. Bioinformatics analyses and ex vivo immunological validations have been performed. RESULTS: Surprisingly, several of such homologies have been found. Moreover, structural similarities between paired TAAs and viral peptides as well as comparable patterns of contact with HLA and T cell receptor (TCR) α and ß chains have been observed. Therefore, the two classes of non-self-antigens (viral antigens and tumor antigens) may converge, eliciting cross-reacting CD8+ T cell responses which possibly drive the fate of cancer development and progression. CONCLUSIONS: An established antiviral T cell memory may turn out to be an anticancer T cell memory, able to control the growth of a cancer developed during the lifetime if the expressed TAA is similar to the viral epitope. This may ultimately represent a relevant selective advantage for patients with cancer and may lead to a novel preventive anticancer vaccine strategy.

An Early Stage Researcher's Primer on Systems Medicine Terminology.

Background: Systems Medicine is a novel approach to medicine, that is, an interdisciplinary field that considers the human body as a system, composed of multiple parts and of complex relationships at multiple levels, and further integrated into an environment. Exploring Systems Medicine implies understanding and combining concepts coming from diametral different fields, including medicine, biology, statistics, modeling and simulation, and data science. Such heterogeneity leads to semantic issues, which may slow down implementation and fruitful interaction between these highly diverse fields. Methods: In this review, we collect and explain more than100 terms related to Systems Medicine. These include both modeling and data science terms and basic systems medicine terms, along with some synthetic definitions, examples of applications, and lists of relevant references. Results: This glossary aims at being a first aid kit for the Systems Medicine researcher facing an unfamiliar term, where he/she can get a first understanding of them, and, more importantly, examples and references for digging into the topic.

Deep learning in systems medicine.

Systems medicine (SM) has emerged as a powerful tool for studying the human body at the systems level with the aim of improving our understanding, prevention and treatment of complex diseases. Being able to automatically extract relevant features needed for a given task from high-dimensional, heterogeneous data, deep learning (DL) holds great promise in this endeavour. This review paper addresses the main developments of DL algorithms and a set of general topics where DL is decisive, namely, within the SM landscape. It discusses how DL can be applied to SM with an emphasis on the applications to predictive, preventive and precision medicine. Several key challenges have been highlighted including delivering clinical impact and improving interpretability. We used some prototypical examples to highlight the relevance and significance of the adoption of DL in SM, one of them is involving the creation of a model for personalized Parkinson's disease. The review offers valuable insights and informs the research in DL and SM.

Potential predictors of type-2 diabetes risk: machine learning, synthetic data and wearable health devices.

BACKGROUND: The aim of a recent research project was the investigation of the mechanisms involved in the onset of type 2 diabetes in the absence of familiarity. This has led to the development of a computational model that recapitulates the aetiology of the disease and simulates the immunological and metabolic alterations linked to type-2 diabetes subjected to clinical, physiological, and behavioural features of prototypical human individuals. RESULTS: We analysed the time course of 46,170 virtual subjects, experiencing different lifestyle conditions. We then set up a statistical model able to recapitulate the simulated outcomes. CONCLUSIONS: The resulting machine learning model adequately predicts the synthetic dataset and can, therefore, be used as a computationally-cheaper version of the detailed mathematical model, ready to be implemented on mobile devices to allow self-assessment by informed and aware individuals. The computational model used to generate the dataset of this work is available as a web-service at the following address: http://kraken.iac.rm.cnr.it/T2DM .