Search

The inhibitory activity of peptides on angiotensin-converting enzyme (ACE) is a measure of their antihypertensive potential. Quantitative structure–activity relationship (QSAR) models obtained based on the analysis of sequences of amino acids are suggested. The average determination coefficient for the active training sets is 0.36 ± 0.07. The average determination coefficient for validation sets is 0.79 ± 0.02. The paradoxical situation is caused by applying the vector of ideality of correlation, which improves the statistical quality of a model for the calibration and validation sets but is detrimental to the statistical quality of models for the training sets.

Endocrine-disrupting chemicals (EDCs) are chemicals that can interfere with homeostatic processes. They are a major concern for public health, and they can cause adverse long-term effects such as cancer, intellectual impairment, obesity, diabetes, and male infertility. The endocrine system is a complex machinery, with the estrogen (E), androgen (A), and thyroid hormone (T) modes of action being of major importance. In this context, the availability of in silico models for the rapid detection of hazardous chemicals is an effective contribution to toxicological assessments. We developed Qualitative Gene expression Activity Relationship (QGexAR) models to predict the propensities of chemically induced disruption of EAT modalities. We gathered gene expression profiles from the LINCS database tested on two cell lines, i.e., MCF7 (breast cancer) and A549 (adenocarcinomic human alveolar basal epithelial). We optimized our prediction protocol by testing different feature selection methods and classification algorithms, including CATBoost, XGBoost, Random Forest, SVM, Logistic regression, AutoKeras, TPOT, and deep learning models. For each EAT endpoint, the final prediction was made according to a consensus prediction as a function of the best model obtained for each cell line. With the available data, we were able to develop a predictive model for estrogen receptor and androgen receptor binding and thyroid hormone receptor antagonistic effects with a consensus balanced accuracy on a validation set ranging from 0.725 to 0.840. The importance of each predictive feature was further assessed to identify known genes and suggest new genes potentially involved in the mechanisms of action of EAT perturbation.

Abstract Background Bioconcentration factor (BCF) describes the behaviour of a chemical in terms of its likelihood of concentrating in organisms in the environment. It is a fundamental property in recent regulations, such as the European Community Regulation on chemicals and their safe use or the Globally Harmonized System for classification, labelling and packaging. These new regulations consider the possibility of reducing or waiving animal tests using alternative methods, such as in silico methods. This study assessed and validated the CAESAR predictive model for BCF in fish. Results To validate the model, new experimental data were collected and used to create an external set, as a second validation set (a first validation exercise had been done just after model development). The performance of the model was compared with BCFBAF v3.00. For continuous values and for classification purposes the CAESAR BCF model gave better results than BCFBAF v3.00 for the chemicals in the applicability domain of the model. R2 and Q2 were good and accuracy in classification higher than 90%. Applying an offset of 0.5 to the compounds predicted with BCF close to the thresholds, the number of false negatives (the most dangerous errors) dropped considerably (less than 0.6% of chemicals). Conclusions The CAESAR model for BCF is useful for regulatory purposes because it is robust, reliable and predictive. It is also fully transparent and documented and has a well-defined applicability domain, as required by REACH. The model is freely available on the CAESAR web site and easy to use. The reliability of the model reporting the six most similar compounds found in the CAESAR dataset, and their experimental and predicted values, can be evaluated.

Abstract Background The new European Regulation on chemical safety, REACH, (Registration, Evaluation, Authorisation and Restriction of CHemical substances), is in the process of being implemented. Many chemicals used in industry require additional testing to comply with the REACH regulations. At the same time EU member states are attempting to reduce the number of animals used in experiments under the 3 Rs policy, (refining, reducing, and replacing the use of animals in laboratory procedures). Computational techniques such as QSAR have the potential to offer an alternative for generating REACH data. The FP6 project CAESAR was aimed at developing QSAR models for 5 key toxicological endpoints of which skin sensitisation was one. Results This paper reports the development of two global QSAR models using two different computational approaches, which contribute to the hybrid model freely available online. Conclusions The QSAR models for assessing skin sensitisation have been developed and tested under stringent quality criteria to fulfil the principles laid down by the OECD. The final models, accessible from CAESAR website, offer a robust and reliable method of assessing skin sensitisation for regulatory use.

Abstract Background One of the main goals of the new chemical regulation REACH (Registration, Evaluation and Authorization of Chemicals) is to fulfill the gaps in data concerned with properties of chemicals affecting the human health. (Q)SAR models are accepted as a suitable source of information. The EU funded CAESAR project aimed to develop models for prediction of 5 endpoints for regulatory purposes. Carcinogenicity is one of the endpoints under consideration. Results Models for prediction of carcinogenic potency according to specific requirements of Chemical regulation were developed. The dataset of 805 non-congeneric chemicals extracted from Carcinogenic Potency Database (CPDBAS) was used. Counter Propagation Artificial Neural Network (CP ANN) algorithm was implemented. In the article two alternative models for prediction carcinogenicity are described. The first model employed eight MDL descriptors (model A) and the second one twelve Dragon descriptors (model B). CAESAR's models have been assessed according to the OECD principles for the validation of QSAR. For the model validity we used a wide series of statistical checks. Models A and B yielded accuracy of training set (644 compounds) equal to 91% and 89% correspondingly; the accuracy of the test set (161 compounds) was 73% and 69%, while the specificity was 69% and 61%, respectively. Sensitivity in both cases was equal to 75%. The accuracy of the leave 20% out cross validation for the training set of models A and B was equal to 66% and 62% respectively. To verify if the models perform correctly on new compounds the external validation was carried out. The external test set was composed of 738 compounds. We obtained accuracy of external validation equal to 61.4% and 60.0%, sensitivity 64.0% and 61.8% and specificity equal to 58.9% and 58.4% respectively for models A and B. Conclusion Carcinogenicity is a particularly important endpoint and it is expected that QSAR models will not replace the human experts opinions and conventional methods. However, we believe that combination of several methods will provide useful support to the overall evaluation of carcinogenicity. In present paper models for classification of carcinogenic compounds using MDL and Dragon descriptors were developed. Models could be used to set priorities among chemicals for further testing. The models at the CAESAR site were implemented in java and are publicly accessible.

Background: Despite all the progress in the management of acute COVID-19, it is still not clear why some people continue to experience symptoms after recovery. Using data from a self-administered online survey, we assessed the prevalence and predictors of post-acute COVID-19 in an unselected population followed by GPs. Methods: Patients ≥18 years with a confirmed COVID-19 diagnosis were included. The survey collected information on demographics, risk factors, COVID-19 course and symptomatology. Fatigue and Quality of Life questionnaires were also administered. Descriptive statistics were used to describe patients’ characteristics, stratified as acute and post-acute COVID-19. Logistic regression models were used to assess the association between clinical characteristics and post-acute COVID-19. Results: A total of 1108 surveys were analyzed. Nearly 29% of patients reported post-acute COVID-19. The more persistent symptoms were fatigue, memory and concentration impairment. Adjusted Odds Ratio (OR) showed a significantly higher probability of post-acute COVID-19 for women compared to men (OR 1.9, 95% CI 1.4-2.5), for age >50 years than ≤50 years (OR 1.6, 95% CI 1.2-2.2), for BMI > 25 compared to BMI ≤ 25 (OR 1.6, 95% CI 1.1-2.1) and those with autoimmune diseases, compared to those without (OR 1.8 95% CI 1.1-2.9). In addition, a significant association was found with COVID-19 hospitalization, anxiety and allergies. We found that post-acute COVID-19 patients showed a higher fatigue and a worst quality of life. Conclusions: These findings suggest the need for tailored personalized strategies to improve the management of patients with post-acute COVID-19.

Typical in silico models for ecotoxicology focus on a few endpoints, but there is a need to increase the diversity of these models. This study proposes models using the NOEC for the harlequin fly (Chironomus riparius) and EC50 for swollen duckweed (Lemna gibba) for the first time. The data were derived from the EFSA OpenFoodTox database. The models were based on the correlation weights of molecular features used to calculate the 2D descriptor in CORAL software. The Monte Carlo method was used to calculate the correlation weights of the algorithms. The determination coefficients of the best models for the external validation set were 0.74 (NOAEC) and 0.85 (EC50).

Abstract Background Glucagon-like peptide-1 receptor agonists (GLP-1 RA) and sodium glucose cotransporter-2 inhibitors (SGLT-2i) demonstrated cardiovascular and renal protection. Whether their benefits occur also during hospitalization for acute myocardial infarction (AMI) in patients with diabetes mellitus (DM) is not known. We evaluated in-hospital outcomes of patients hospitalized with AMI according to their chronic use of GLP-1 RA and/or SGLT-2i. Methods Using the health administrative databases of Lombardy, patients hospitalized with AMI from 2010 to 2019 were included. They were stratified according to DM status, then grouped into three cohorts using a propensity score matching: non-DM patients; DM patients treated with GLP-1 RA and/or SGLT-2i; DM patients not treated with GLP-1 RA/SGLT-2i. The primary endpoint of the study was the composite of in-hospital mortality, acute heart failure, and acute kidney injury requiring renal replacement therapy. Results We identified 146,798 patients hospitalized with AMI (mean age 71 ± 13 years, 34% females, 47% STEMI; 26% with DM). After matching, 3,090 AMI patients (1030 in each group) were included in the analysis. Overall, the primary endpoint rate was 16% (n = 502) and progressively increased from non-DM patients to DM patients treated with and without GLP-1 RA/SGLT-2i (13%, 16%, and 20%, respectively; P

Cardiovascular disease is a leading global cause of mortality. The potential cardiotoxic effects of chemicals from different classes, such as environmental contaminants, pesticides, and drugs can significantly contribute to effects on health. The same chemical can induce cardiotoxicity in different ways, following various Adverse Outcome Pathways (AOPs). In addition, the potential synergistic effects between chemicals further complicate the issue. In silico methods have become essential for tackling the problem from different perspectives, reducing the need for traditional in vivo testing, and saving valuable resources in terms of time and money. Artificial intelligence (AI) and machine learning (ML) are among today’s advanced approaches for evaluating chemical hazards. They can serve, for instance, as a first-tier component of Integrated Approaches to Testing and Assessment (IATA). This study employed ML and AI to assess interactions between chemicals and specific biological targets within the AOP networks for cardiotoxicity, starting with molecular initiating events (MIEs) and progressing through key events (KEs). We explored methods to encode chemical information in a suitable way for ML and AI. We started with commonly used approaches in Quantitative Structure–Activity Relationship (QSAR) methods, such as molecular descriptors and different types of fingerprint. We then increased the complexity of encoders, incorporating graph-based methods, auto-encoders, and character embeddings employed in neural language processing. We also developed a multimodal neural network architecture, capable of considering the complementary nature of different chemical representations simultaneously. The potential of this approach, compared to more conventional architectures designed to handle a single encoder, becomes apparent when the amount of data increases.

BackgroundCOVID-19 has been associated with a higher risk of post-acute complications. Our aim was to analyze and compare post-acute cardiovascular complications of COVID-19 survivors of the first and second/third pandemic waves in Lombardy, in both hospitalized and non-hospitalized COVID-19 patients.Methods and resultsWe included adults aged ≥40 years infected during the first and second/third waves of COVID-19 pandemic. The follow-up initiated 30 days after COVID-19 diagnosis and continued up to 9 months. Hazard ratios (HRs) and 95% confidence intervals (CIs) of the post-acute cardiovascular outcomes were calculated against an inverse probability treatment weighted control group. Subgroup analysis were performed by age classes, sex, previous cardiovascular disease and stratified by COVID-19 hospitalization status to explore the impact of COVID-19 severity on outcomes. Compared to the control group, COVID-19 patients had an increased risk of hospitalization for any cardiovascular complications (HR 1st wave 1.53 95% CI: 1.38–1.69; HR 2nd/3rd wave 1.25 95% CI: 1.19–1.31) and for individual cardiovascular outcomes, although HRs were higher in COVID-19 group from the 1st pandemic wave. The results were confirmed in the subgroup analyses. Of note, the risk for any cardiovascular disease was also evident even among individuals who were not hospitalized during the acute phase of the infection.ConclusionOur results provide evidence that COVID-19 is a risk factor for post-acute cardiovascular complications among different pandemic waves regardless of COVID-19 severity, age, sex and a history of cardiovascular diseases. Care strategies of people with COVID-19 should include cardiac monitoring.

Introduction Prevention of cardiovascular disease (CVD) is of key importance in reducing morbidity, disability and mortality worldwide. Observational studies suggest that digital health interventions can be an effective strategy to reduce cardiovascular (CV) risk. However, evidence from large randomised clinical trials is lacking.Methods and analysis The CV-PREVITAL study is a multicentre, prospective, randomised, controlled, open-label interventional trial designed to compare the effectiveness of an educational and motivational mobile health (mHealth) intervention versus usual care in reducing CV risk. The intervention aims at improving diet, physical activity, sleep quality, psycho-behavioural aspects, as well as promoting smoking cessation and adherence to pharmacological treatment for CV risk factors. The trial aims to enrol approximately 80 000 subjects without overt CVDs referring to general practitioners’ offices, community pharmacies or clinics of Scientific Institute for Research, Hospitalization and Health Care (Italian acronym IRCCS) affiliated with the Italian Cardiology Network. All participants are evaluated at baseline and after 12 months to assess the effectiveness of the intervention on short-term endpoints, namely improvement in CV risk score and reduction of major CV risk factors. Beyond the funded life of the study, a long-term (7 years) follow-up is also planned to assess the effectiveness of the intervention on the incidence of major adverse CV events. A series of ancillary studies designed to evaluate the effect of the mHealth intervention on additional risk biomarkers are also performed.Ethics and dissemination This study received ethics approval from the ethics committee of the coordinating centre (Monzino Cardiology Center; R1256/20-CCM 1319) and from all other relevant IRBs and ethics committees. Findings are disseminated through scientific meetings and peer-reviewed journals and via social media. Partners are informed about the study’s course and findings through regular meetings.Trial registration number NCT05339841.

Abstract Background Diabetes mellitus (DM) is associated with an increased mortality risk in patients hospitalized with acute myocardial infarction (AMI); however, no studies have investigated the impact of the duration of DM on in-hospital mortality. In this study, we evaluated in-hospital mortality in AMI patients according to DM status and its duration. Methods Using health administrative databases of Lombardy, DM patients≥50 years hospitalized with AMI from 2010 to 2019 were included in the analysis and were stratified according to the duration of DM: 10 years. The primary endpoint was mortality during AMI hospitalization and the secondary endpoint was 1-year mortality in comparison with No-DM patients. Logistic and Cox regressions analyses were used to estimate odds ratios (ORs, CI 95%) and hazard ratios (HRs, CI 95%) for the outcomes, according to DM status and duration and AMI type (STEMI and NSTEMI). Results Our study cohort comprised 29,566 and 109,247 DM and No-DM patients, respectively. Adjusted ORs and HRs showed a significantly higher risk of in-hospital mortality (OR 1.50, 95% CI 1.43–1.58) and 1-year mortality (HR 1.51, 95% CI 1.46–1.55) in DM patients in comparison with those without. These risks increased progressively with the duration of DM, with the highest risk observed in patients with DM duration ≥ 10 years (OR 1.59, 95% CI 1.50–1.69 for in-hospital mortality and HR 1.59, 95% CI 1.53–1.64 for 1-year mortality). These findings were similar in STEMI and in NSTEMI patients. Conclusions Our study demonstrates that the duration of DM parallels mortality risk in patients hospitalized with AMI, highlighting that DM duration should be considered as an important early prognostic risk factor in patients with AMI.

Abstract Background GLP-1 receptor agonists (GLP-1 RA) and SGLT-2 inhibitors (SGLT-2i) have shown to reduce the risk of major adverse cardiovascular events (MACE), death and worsening nephropathy when added to standard of care. However, these two dug classes differ in efficacy and safety. We compared the effectiveness and safety profile of GLP-1 RA and SGLT-2i in a large and unselected cohort of patients with type 2 diabetes resident in Lombardy from 2015 to 2020. Methods Using linkable administrative health databases, we included patients aged 50 years and older initiating GLP-1 RA or SGLT-2i. Clinical events were: death, hospital admission for myocardial infarction (MI), stroke, heart failure (HF), and renal disease as individual and composite outcomes (MACE-3: all cause-death, non-fatal MI, non-fatal stroke; MACE-4: MACE-3 plus unstable angina). Outcomes were evaluated separately in subjects with and without previous cardiovascular (CV) diseases. Treatments were compared using Cox proportional hazards regression model after Propensity Score Matching (PSM) in both intention-to-treat (ITT) and per protocol (PP) analyses. Serious adverse events were also evaluated. Results The analysis comprised 20,762 patients per cohort. The ITT analysis showed a significant risk reduction for non-fatal MI (HR 0.77; CI 95% 0.66–0.90), MACE-3 (HR 0.91; CI 95% 0.84–0.98), and MACE-4 (HR 0.92; CI 95% 0.86–0.99) in GLP-1RA compared with SGLT-2i users, while no difference was reported in the incidence of HF hospitalization and stroke between the two cohorts. Similar benefits were found in the subgroup of patients without previous CV diseases only. PP analysis largely confirmed the main results. The incidence of serious adverse events was low in both cohorts (

The OECD recognizes that data on a compound’s ability to treat eye irritation are essential for the assessment of new compounds on the market. In silico models are frequently used to provide information when experimental data are lacking. Semi-correlations, as they are called, can be useful to build up categorical models for eye irritation. Semi-correlations are latent regressions that can be used when the endpoint is expressed by two values: 1 for an active molecule and 0 for an inactive molecule. The regression line is based on the descriptor values which serve to distribute the data into four classes: true positive, true negative, false positive, and false negative. These values are applied to calculate the corresponding statistical criterion for assessing the predictive potential of the categorical model. In our model, the descriptor is the sum of what are termed correlation weights. These are defined by optimization using the Monte Carlo method. The target function of the optimization is related to the determination coefficient and the mean absolute error for the training set. Our model gives results that are better than those previously reported for the same endpoint.

Data on Henry’s law constants make it possible to systematize geochemical conditions affecting atmosphere status and consequently triggering climate changes. The constants of Henry’s law are desired for assessing the processes related to atmospheric contaminations caused by pollutants. The most important are those that are capable of long-term movements over long distances. This ability is closely related to the values of Henry’s law constants. Chemical changes in gaseous mixtures affect the fate of atmospheric pollutants and ecology, climate, and human health. Since the number of organic compounds present in the atmosphere is extremely large, it is desirable to develop models suitable for predictions for the large pool of organic molecules that may be present in the atmosphere. Here, we report the development of such a model for Henry’s law constants predictions of 29,439 compounds using the CORAL software (2023). The statistical quality of the model is characterized by the value of the coefficient of determination for the training and validation sets of about 0.81 (on average).

Models of toxicity to tadpoles have been developed as single parameters based on special descriptors which are sums of correlation weights, molecular features, and experimental conditions. This information is presented by quasi-SMILES. Fragments of local symmetry (FLS) are involved in the development of the model and the use of FLS correlation weights improves their predictive potential. In addition, the index of ideality correlation (IIC) and correlation intensity index (CII) are compared. These two potential predictive criteria were tested in models built through Monte Carlo optimization. The CII was more effective than IIC for the models considered here. [ABSTRACT FROM AUTHOR]

Endocrine-disrupting chemicals (EDCs) are chemicals that can interfere with homeostatic processes. They are a major concern for public health, and they can cause adverse long-term effects such as cancer, intellectual impairment, obesity, diabetes, and male infertility. The endocrine system is a complex machinery, with the estrogen (E), androgen (A), and thyroid hormone (T) modes of action being of major importance. In this context, the availability of in silico models for the rapid detection of hazardous chemicals is an effective contribution to toxicological assessments. We developed Qualitative Gene expression Activity Relationship (QGexAR) models to predict the propensities of chemically induced disruption of EAT modalities. We gathered gene expression profiles from the LINCS database tested on two cell lines, i.e., MCF7 (breast cancer) and A549 (adenocarcinomic human alveolar basal epithelial). We optimized our prediction protocol by testing different feature selection methods and classification algorithms, including CATBoost, XGBoost, Random Forest, SVM, Logistic regression, AutoKeras, TPOT, and deep learning models. For each EAT endpoint, the final prediction was made according to a consensus prediction as a function of the best model obtained for each cell line. With the available data, we were able to develop a predictive model for estrogen receptor and androgen receptor binding and thyroid hormone receptor antagonistic effects with a consensus balanced accuracy on a validation set ranging from 0.725 to 0.840. The importance of each predictive feature was further assessed to identify known genes and suggest new genes potentially involved in the mechanisms of action of EAT perturbation. [ABSTRACT FROM AUTHOR]

The assessment of cardiotoxicity is a persistent problem in medicinal chemistry. Quantitative structure–activity relationships (QSAR) are one possible way to build up models for cardiotoxicity. Here, we describe the results obtained with the Monte Carlo technique to develop hybrid optimal descriptors correlated with cardiotoxicity. The predictive potential of the cardiotoxicity models (pIC50, Ki in nM) of piperidine derivatives obtained using this approach provided quite good determination coefficients for the external validation set, in the range of 0.90–0.94. The results were best when applying the so-called correlation intensity index, which improves the predictive potential of a model.

Drug-induced cardiotoxicity is a common side effect of drugs in clinical use or under postmarket surveillance and is commonly due to off-target interactions with the cardiac human-ether-a-go-go-related (hERG) potassium channel. Therefore, prioritizing drug candidates based on their hERG blocking potential is a mandatory step in the early preclinical stage of a drug discovery program. Herein, we trained and properly validated 30 ligand-based classifiers of hERG-related cardiotoxicity based on 7,963 curated compounds extracted by the freely accessible repository ChEMBL (version 25). Different machine learning algorithms were tested, namely, random forest, K-nearest neighbors, gradient boosting, extreme gradient boosting, multilayer perceptron, and support vector machine. The application of 1) the best practices for data curation, 2) the feature selection method VSURF, and 3) the synthetic minority oversampling technique (SMOTE) to properly handle the unbalanced data, allowed for the development of highly predictive models (BAMAX = 0.91, AUCMAX = 0.95). Remarkably, the undertaken temporal validation approach not only supported the predictivity of the herein presented classifiers but also suggested their ability to outperform those models commonly used in the literature. From a more methodological point of view, the study put forward a new computational workflow, freely available in the GitHub repository (https://github.com/PDelre93/hERG-QSAR), as valuable for building highly predictive models of hERG-mediated cardiotoxicity.