Integrating Mechanistic and Toxicokinetic Information in Predictive Models of Cholestasis.

Drug development involves the thorough assessment of the candidate's safety and efficacy. In silico toxicology (IST) methods can contribute to the assessment, complementing in vitro and in vivo experimental methods, since they have many advantages in terms of cost and time. Also, they are less demanding concerning the requirements of product and experimental animals. One of these methods, Quantitative Structure-Activity Relationships (QSAR), has been proven successful in predicting simple toxicity end points but has more difficulties in predicting end points involving more complex phenomena. We hypothesize that QSAR models can produce better predictions of these end points by combining multiple QSAR models describing simpler biological phenomena and incorporating pharmacokinetic (PK) information, using quantitative in vitro to in vivo extrapolation (QIVIVE) models. In this study, we applied our methodology to the prediction of cholestasis and compared it with direct QSAR models. Our results show a clear increase in sensitivity. The predictive quality of the models was further assessed to mimic realistic conditions where the query compounds show low similarity with the training series. Again, our methodology shows clear advantages over direct QSAR models in these situations. We conclude that the proposed methodology could improve existing methodologies and could be suitable for being applied to other toxicity end points.

Uncertainty assessment of proarrhythmia predictions derived from multi-level in silico models.

In silico methods can be used for an early assessment of arrhythmogenic properties of drug candidates. However, their use for decision-making is conditioned by the possibility to estimate the predictions' uncertainty. This work describes our efforts to develop uncertainty quantification methods for the predictions produced by multi-level proarrhythmia models. In silico models used in this field usually start with experimental or predicted IC50 values that describe drug-induced ion channel blockade. Using such inputs, an electrophysiological model computes how the ion channel inhibition, exerted by a drug in a certain concentration, translates to an altered shape and duration of the action potential in cardiac cells, which can be represented as arrhythmogenic risk biomarkers such as the APD90. Using this framework, we identify the main sources of aleatory and epistemic uncertainties and propose a method based on probabilistic simulations that replaces single-point estimates predicted using multiple input values, including the IC50s and the electrophysiological parameters, by distributions of values. Two selected variability types associated with these inputs are then propagated through the multi-level model to estimate their impact on the uncertainty levels in the output, expressed by means of intervals. The proposed approach yields single predictions of arrhythmogenic risk biomarkers together with value intervals, providing a more comprehensive and realistic description of drug effects on a human population. The methodology was tested by predicting arrhythmogenic biomarkers on a series of twelve well-characterised marketed drugs, belonging to different arrhythmogenic risk classes.

Applicability of probabilistic graphical models for early detection of SARS-CoV-2 reactive antibodies after SARS-CoV-2 vaccination in hematological patients.

Prior studies of antibody response after full SARS-CoV-2 vaccination in hematological patients have confirmed lower antibody levels compared to the general population. Serological response in hematological patients varies widely according to the disease type and its status, and the treatment given and its timing with respect to vaccination. Through probabilistic machine learning graphical models, we estimated the conditional probabilities of having detectable anti-SARS-CoV-2 antibodies at 3-6 weeks after SARS-CoV-2 vaccination in a large cohort of patients with several hematological diseases (n= 1166). Most patients received mRNA-based vaccines (97%), mainly Moderna® mRNA-1273 (74%) followed by Pfizer-BioNTech® BNT162b2 (23%). The overall antibody detection rate at 3 to 6 weeks after full vaccination for the entire cohort was 79%. Variables such as type of disease, timing of anti-CD20 monoclonal antibody therapy, age, corticosteroids therapy, vaccine type, disease status, or prior infection with SARS-CoV-2 are among the most relevant conditions influencing SARS-CoV-2-IgG-reactive antibody detection. A lower probability of having detectable antibodies was observed in patients with B-cell non-Hodgkin's lymphoma treated with anti-CD20 monoclonal antibodies within 6 months before vaccination (29.32%), whereas the highest probability was observed in younger patients with chronic myeloproliferative neoplasms (99.53%). The Moderna® mRNA-1273 compound provided higher probabilities of antibody detection in all scenarios. This study depicts conditional probabilities of having detectable antibodies in the whole cohort and in specific scenarios such as B cell NHL, CLL, MM, and cMPN that may impact humoral responses. These results could be useful to focus on additional preventive and/or monitoring interventions in these highly immunosuppressed hematological patients.

A machine learning approach to identify groups of patients with hematological malignant disorders.

BACKGROUND AND OBJECTIVE: Vaccination against SARS-CoV-2 in immunocompromised patients with hematologic malignancies (HM) is crucial to reduce the severity of COVID-19. Despite vaccination efforts, over a third of HM patients remain unresponsive, increasing their risk of severe breakthrough infections. This study aims to leverage machine learning's adaptability to COVID-19 dynamics, efficiently selecting patient-specific features to enhance predictions and improve healthcare strategies. Highlighting the complex COVID-hematology connection, the focus is on interpretable machine learning to provide valuable insights to clinicians and biologists. METHODS: The study evaluated a dataset with 1166 patients with hematological diseases. The output was the achievement or non-achievement of a serological response after full COVID-19 vaccination. Various machine learning methods were applied, with the best model selected based on metrics such as the Area Under the Curve (AUC), Sensitivity, Specificity, and Matthew Correlation Coefficient (MCC). Individual SHAP values were obtained for the best model, and Principal Component Analysis (PCA) was applied to these values. The patient profiles were then analyzed within identified clusters. RESULTS: Support vector machine (SVM) emerged as the best-performing model. PCA applied to SVM-derived SHAP values resulted in four perfectly separated clusters. These clusters are characterized by the proportion of patients that generate antibodies (PPGA). Cluster 1, with the second-highest PPGA (69.91%), included patients with aggressive diseases and factors contributing to increased immunodeficiency. Cluster 2 had the lowest PPGA (33.3%), but the small sample size limited conclusive findings. Cluster 3, representing the majority of the population, exhibited a high rate of antibody generation (84.39%) and a better prognosis compared to cluster 1. Cluster 4, with a PPGA of 66.33%, included patients with B-cell non-Hodgkin's lymphoma on corticosteroid therapy. CONCLUSIONS: The methodology successfully identified four separate patient clusters using Machine Learning and Explainable AI (XAI). We then analyzed each cluster based on the percentage of HM patients who generated antibodies after COVID-19 vaccination. The study suggests the methodology's potential applicability to other diseases, highlighting the importance of interpretable ML in healthcare research and decision-making.

Application of machine learning to improve the efficiency of electrophysiological simulations used for the prediction of drug-induced ventricular arrhythmia.

BACKGROUND AND OBJECTIVE: In silico prediction of drug-induced ventricular arrhythmia often requires computationally intensive simulations, making its application tedious and non-interactive. This inconvenience can be mitigated using matrices of precomputed simulation results, allowing instantaneous computation of biomarkers such as action potential duration at 90% of the repolarisation (APD90). However, preparing such matrices can be computationally intensive for the method developers, limiting the range of simulated conditions. In this work, we aim to optimise the generation of these matrices so that they can be obtained with less effort and for a broader range of input values. METHODS: Machine learning methods were applied, building models trained with only a small fraction of the originally simulated results. The predictive performances of the models were assessed by comparing their predicted values with the actual simulation results, using percentual mean absolute error and mean relative error, as well as the percentage of data with a relative error below 5%. RESULTS: Our method obtained highly accurate estimations of the original values, leading to a nearly one hundred-fold decrease in computation time. This method also allows precomputing more complex matrices, describing the effect of more ion channels on the APD90. The best results were obtained by applying Support Vector Machine models, which yielded errors below 1% in most cases. This approach was further validated by predicting the APD90 of a set of 12 CiPA compounds and exporting the optimal settings for predicting APD90 using a different set of ion channels, always with satisfactory results. CONCLUSIONS: The proposed method effectively reduces the computational effort required to generate matrices of precomputed electrophysiological simulation values. The same approach can be applied in other fields where computationally costly simulations are applied repeatedly using slightly different input values.

Usage of model combination in computational toxicology.

New Approach Methodologies (NAMs) have ushered in a new era in the field of toxicology, aiming to replace animal testing. However, despite these advancements, they are not exempt from the inherent complexities associated with the study's endpoint. In this review, we have identified three major groups of complexities: mechanistic, chemical space, and methodological. The mechanistic complexity arises from interconnected biological processes within a network that are challenging to model in a single step. In the second group, chemical space complexity exhibits significant dissimilarity between compounds in the training and test series. The third group encompasses algorithmic and molecular descriptor limitations and typical class imbalance problems. To address these complexities, this work provides a guide to the usage of a combination of predictive Quantitative Structure-Activity Relationship (QSAR) models, known as metamodels. This combination of low-level models (LLMs) enables a more precise approach to the problem by focusing on different sub-mechanisms or sub-processes. For mechanistic complexity, multiple Molecular Initiating Events (MIEs) or levels of information are combined to form a mechanistic-based metamodel. Regarding the complexity arising from chemical space, two types of approaches were reviewed to construct a fragment-based chemical space metamodel: those with and without structure sharing. Metamodels with structure sharing utilize unsupervised strategies to identify data patterns and build low-level models for each cluster, which are then combined. For situations without structure sharing due to pharmaceutical industry intellectual property, the use of prediction sharing, and federated learning approaches have been reviewed. Lastly, to tackle methodological complexity, various algorithms are combined to overcome their limitations, diverse descriptors are employed to enhance problem definition and balanced dataset combinations are used to address class imbalance issues (methodological-based metamodels). Remarkably, metamodels consistently outperformed classical QSAR models across all cases, highlighting the importance of alternatives to classical QSAR models when faced with such complexities.

SARS-CoV-2 vaccine response and rate of breakthrough infection in patients with hematological disorders.

BACKGROUND: The clinical efficacy of SARS-CoV-2 vaccines according to antibody response in immunosuppressed patients such as hematological patients has not yet been established. PATIENTS AND METHODS: A prospective multicenter registry-based cohort study conducted from December 2020 to December 2021 by the Spanish transplant and cell therapy group was used to analyze the relationship of antibody response at 3-6 weeks after full vaccination (2 doses) with breakthrough SARS-CoV-2 infection in 1394 patients with hematological disorders. RESULTS: At a median follow-up of 165 days after complete immunization, 37 out of 1394 (2.6%) developed breakthrough SARS-CoV-2 infection at median of 77 days (range 7-195) after full vaccination. The incidence rate was 6.39 per 100 persons-year. Most patients were asymptomatic (19/37, 51.4%), whereas only 19% developed pneumonia. The mortality rate was 8%. Lack of detectable antibodies at 3-6 weeks after full vaccination was the only variable associated with breakthrough infection in multivariate logistic regression analysis (Odds Ratio 2.35, 95% confidence interval 1.2-4.6, p = 0.012). Median antibody titers were lower in cases than in non-cases [1.83 binding antibody units (BAU)/mL (range 0-4854.93) vs 730.81 BAU/mL (range 0-56,800), respectively (p = 0.007)]. We identified 250 BAU/mL as a cutoff above which incidence and severity of the infection were significantly lower. CONCLUSIONS: Our study highlights the benefit of developing an antibody response in these highly immunosuppressed patients. Level of antibody titers at 3 to 6 weeks after 2-dose vaccination links with protection against both breakthrough infection and severe disease for non-Omicron SARS-CoV-2 variants.

Machine Learning for Mortality Analysis in Patients with COVID-19.

This paper analyzes a sample of patients hospitalized with COVID-19 in the region of Madrid (Spain). Survival analysis, logistic regression, and machine learning techniques (both supervised and unsupervised) are applied to carry out the analysis where the endpoint variable is the reason for hospital discharge (home or deceased). The different methods applied show the importance of variables such as age, O2 saturation at Emergency Rooms (ER), and whether the patient comes from a nursing home. In addition, biclustering is used to globally analyze the patient-drug dataset, extracting segments of patients. We highlight the validity of the classifiers developed to predict the mortality, reaching an appreciable accuracy. Finally, interpretable decision rules for estimating the risk of mortality of patients can be obtained from the decision tree, which can be crucial in the prioritization of medical care and resources.