AlvaBuilder: A Software for De Novo Molecular Design.

AlvaBuilder is a software tool for de novo molecular design and can be used to generate novel molecules having desirable characteristics. Such characteristics can be defined using a simple step by step graphical interface, and they can be based on molecular descriptors, on predictions of QSAR/QSPR models, and on matching molecular fragments or used to design compounds similar to a given one. The molecules generated are always syntactically valid since they are composed by combining fragments of molecules taken from a training data set chosen by the user. In this paper, we demonstrate how the software can be used to design new compounds for a defined case study. AlvaBuilder is available at https://www.alvascience.com/alvabuilder/.

GNN for Deep Full Event Interpretation and Hierarchical Reconstruction of Heavy-Hadron Decays in Proton-Proton Collisions.

The LHCb experiment at the Large Hadron Collider (LHC) is designed to perform high-precision measurements of heavy-hadron decays, which requires the collection of large data samples and a good understanding and suppression of multiple background sources. Both factors are challenged by a fivefold increase in the average number of proton-proton collisions per bunch crossing, corresponding to a change in the detector operation conditions for the LHCb Upgrade I phase, recently started. A further tenfold increase is expected in the Upgrade II phase, planned for the next decade. The limits in the storage capacity of the trigger will bring an inverse relationship between the number of particles selected to be stored per event and the number of events that can be recorded. In addition the background levels will rise due to the enlarged combinatorics. To tackle both challenges, we propose a novel approach, never attempted before in a hadronic collider: a Deep-learning based Full Event Interpretation (DFEI), to perform the simultaneous identification, isolation and hierarchical reconstruction of all the heavy-hadron decay chains per event. This strategy radically contrasts with the standard selection procedure used in LHCb to identify heavy-hadron decays, that looks individually at subsets of particles compatible with being products of specific decay types, disregarding the contextual information from the rest of the event. Following the DFEI approach, once the relevant particles in each event are identified, the rest can be safely removed to optimise the storage space and maximise the trigger efficiency. We present the first prototype for the DFEI algorithm, that leverages the power of Graph Neural Networks (GNN). This paper describes the design and development of the algorithm, and its performance in Upgrade I simulated conditions.

Alvascience: A New Software Suite for the QSAR Workflow Applied to the Blood-Brain Barrier Permeability.

Quantitative structure-activity relationship (QSAR) and quantitative structure-property relationship (QSPR) are established techniques to relate endpoints to molecular features. We present the Alvascience software suite that takes care of the whole QSAR/QSPR workflow necessary to use models to predict endpoints for untested molecules. The first step, data curation, is covered by alvaMolecule. Features such as molecular descriptors and fingerprints are generated by using alvaDesc. Models are built and validated with alvaModel. The models can then be deployed and used on new molecules by using alvaRunner. We use these software tools on a real case scenario to predict the blood-brain barrier (BBB) permeability. The resulting predictive models have accuracy equal or greater than 0.8. The models are bundled in an alvaRunner project available on the Alvascience website.

Empowering local communities using artificial intelligence.

Artificial intelligence (AI) applications can profoundly affect society. Recently, there has been extensive interest in studying how scientists design AI systems for general tasks. However, it remains an open question as to whether the AI systems developed in this way can work as expected in different regional contexts while simultaneously empowering local people. How can scientists co-create AI systems with local communities to address regional concerns? This article contributes new perspectives in this underexplored direction at the intersection of data science, AI, citizen science, and human-computer interaction. Through case studies, we discuss challenges in co-designing AI systems with local people, collecting and explaining community data using AI, and adapting AI systems to long-term social change. We also consolidate insights into bridging AI research and citizen needs, including evaluating the social impact of AI, curating community datasets for AI development, and building AI pipelines to explain data patterns to laypeople.

CATMoS: Collaborative Acute Toxicity Modeling Suite.

BACKGROUND: Humans are exposed to tens of thousands of chemical substances that need to be assessed for their potential toxicity. Acute systemic toxicity testing serves as the basis for regulatory hazard classification, labeling, and risk management. However, it is cost- and time-prohibitive to evaluate all new and existing chemicals using traditional rodent acute toxicity tests. In silico models built using existing data facilitate rapid acute toxicity predictions without using animals. OBJECTIVES: The U.S. Interagency Coordinating Committee on the Validation of Alternative Methods (ICCVAM) Acute Toxicity Workgroup organized an international collaboration to develop in silico models for predicting acute oral toxicity based on five different end points: Lethal Dose 50 (LD50 value, U.S. Environmental Protection Agency hazard (four) categories, Globally Harmonized System for Classification and Labeling hazard (five) categories, very toxic chemicals [LD50 (LD50≤50mg/kg)], and nontoxic chemicals (LD50>2,000mg/kg). METHODS: An acute oral toxicity data inventory for 11,992 chemicals was compiled, split into training and evaluation sets, and made available to 35 participating international research groups that submitted a total of 139 predictive models. Predictions that fell within the applicability domains of the submitted models were evaluated using external validation sets. These were then combined into consensus models to leverage strengths of individual approaches. RESULTS: The resulting consensus predictions, which leverage the collective strengths of each individual model, form the Collaborative Acute Toxicity Modeling Suite (CATMoS). CATMoS demonstrated high performance in terms of accuracy and robustness when compared with in vivo results. DISCUSSION: CATMoS is being evaluated by regulatory agencies for its utility and applicability as a potential replacement for in vivo rat acute oral toxicity studies. CATMoS predictions for more than 800,000 chemicals have been made available via the National Toxicology Program's Integrated Chemical Environment tools and data sets (ice.ntp.niehs.nih.gov). The models are also implemented in a free, standalone, open-source tool, OPERA, which allows predictions of new and untested chemicals to be made. https://doi.org/10.1289/EHP8495.

A QSTR-Based Expert System to Predict Sweetness of Molecules.

This work describes a novel approach based on advanced molecular similarity to predict the sweetness of chemicals. The proposed Quantitative Structure-Taste Relationship (QSTR) model is an expert system developed keeping in mind the five principles defined by the Organization for Economic Co-operation and Development (OECD) for the validation of (Q)SARs. The 649 sweet and non-sweet molecules were described by both conformation-independent extended-connectivity fingerprints (ECFPs) and molecular descriptors. In particular, the molecular similarity in the ECFPs space showed a clear association with molecular taste and it was exploited for model development. Molecules laying in the subspaces where the taste assignation was more difficult were modeled trough a consensus between linear and local approaches (Partial Least Squares-Discriminant Analysis and N-nearest-neighbor classifier). The expert system, which was thoroughly validated through a Monte Carlo procedure and an external set, gave satisfactory results in comparison with the state-of-the-art models. Moreover, the QSTR model can be leveraged into a greater understanding of the relationship between molecular structure and sweetness, and into the design of novel sweeteners.

Mixtures, metabolites, ionic liquids: a new measure to evaluate similarity between complex chemical systems.

This communication deals with the scientific problem of evaluating the similarity between two chemical systems, each described by a finite discrete set of elements/members, which are in turn p-dimensional vectors of chemical/biological descriptors. A variant of the Hausdorff measure, called Hausdorff-like similarity (Hs), is proposed aimed at taking into account information on all the elements present in the compared sets, information that is usually lost by the other measures.

Prediction of acute aquatic toxicity toward Daphnia magna by using the GA-kNN method.

In this study, a QSAR model was developed from a data set consisting of 546 organic molecules, to predict acute aquatic toxicity toward Daphnia magna. A modified k-Nearest Neighbour (kNN) strategy was used as the regression method, which provided prediction only for those molecules with an average distance from the k nearest neighbours lower than a selected threshold. The final model showed good performance (R(2) and Q(2) cv equal to 0.78, Q(2) ext equal to 0.72). It comprised eight molecular descriptors that encoded information about lipophilicity, the formation of H-bonds, polar surface area, polarisability, nucleophilicity and electrophilicity.

Comparison of different approaches to define the applicability domain of QSAR models.

One of the OECD principles for model validation requires defining the Applicability Domain (AD) for the QSAR models. This is important since the reliable predictions are generally limited to query chemicals structurally similar to the training compounds used to build the model. Therefore, characterization of interpolation space is significant in defining the AD and in this study some existing descriptor-based approaches performing this task are discussed and compared by implementing them on existing validated datasets from the literature. Algorithms adopted by different approaches allow defining the interpolation space in several ways, while defined thresholds contribute significantly to the extrapolations. For each dataset and approach implemented for this study, the comparison analysis was carried out by considering the model statistics and relative position of test set with respect to the training space.

Gauge fields, membranes, and subdeterminant vector models.

We present a class of classically marginal N-vector models in d=4 and d=3 whose scalar potentials can be written as subdeterminants of symmetric matrices. The d=3 case can be thought of as a generalization of the scalar sector of the Bagger-Lambert-Gustavsson model. Using the Hubbard-Stratonovich transformation we calculate their effective potentials which exhibit intriguing large-N scaling behaviors. We comment on the possible relevance of our models to strings, membranes, and also to a class of novel spin systems that are based on ternary commutation relations.

Canonical Measure of Correlation (CMC) and Canonical Measure of Distance (CMD) between sets of data. Part 3. Variable selection in classification.

In multivariate regression and classification issues variable selection is an important procedure used to select an optimal subset of variables with the aim of producing more parsimonious and eventually more predictive models. Variable selection is often necessary when dealing with methodologies that produce thousands of variables, such as Quantitative Structure-Activity Relationships (QSARs) and highly dimensional analytical procedures. In this paper a novel method for variable selection for classification purposes is introduced. This method exploits the recently proposed Canonical Measure of Correlation between two sets of variables (CMC index). The CMC index is in this case calculated for two specific sets of variables, the former being comprised of the independent variables and the latter of the unfolded class matrix. The CMC values, calculated by considering one variable at a time, can be sorted and a ranking of the variables on the basis of their class discrimination capabilities results. Alternatively, CMC index can be calculated for all the possible combinations of variables and the variable subset with the maximal CMC can be selected, but this procedure is computationally more demanding and classification performance of the selected subset is not always the best one. The effectiveness of the CMC index in selecting variables with discriminative ability was compared with that of other well-known strategies for variable selection, such as the Wilks' Lambda, the VIP index based on the Partial Least Squares-Discriminant Analysis, and the selection provided by classification trees. A variable Forward Selection based on the CMC index was finally used in conjunction of Linear Discriminant Analysis. This approach was tested on several chemical data sets. Obtained results were encouraging.

Mini Nutritional Assessment in patients with Parkinson's disease: correlation between worsening of the malnutrition and increasing number of disease-years.

OBJECTIVE: To monitor the nutritional status of patients with Parkinson's disease using the Mini Nutritional Assessment (MNA) questionnaire. PATIENTS AND METHODS: This was a 3-year longitudinal study conducted in a national referral centre for Parkinson's disease and other movement disorders. The cohort included 61 Parkinson's disease patients, 37 men and 24 women, mean age of 70.5 +/- 5.5 years, mean duration of disease 9 +/- 6.3 years; 35 patients were followed-up after 3 years. RESULTS: MNA score diminished from 24.9 +/- 1.6 to 24 +/- 2.5 (P = 0.02); the proportion of patients at risk of malnutrition increased from 22.9% to 34.3%. A linear correlation was observed between MNA score and the duration of disease (P = 0.0096). The dietary assessment subscore significantly diminished (8.6 versus 8.1; P = 0.0009) as did body mass index (25.9 +/- 3.5 kg/m(2) versus 27.1 +/- 3.1 kg/m(2); P = 0.001). CONCLUSIONS: The evaluation of nutritional status should be part of the routine work-up of a Parkinson's disease patient. Dietary education should be included amongst the therapeutic measures designed to improve the general conditions in Parkinson's disease.

Diet with LPP for renal patients increases daily energy expenditure and improves motor function in parkinsonian patients with motor fluctuations.

OBJECTIVE: To establish whether a diet based on the usage of low-protein products for renal patients (LPP) is associated with higher energy expenditure (EE) than a free low-protein diet (NO-LPP) by calculating 24 h EE by indirect calorimetry using an electronic armband monitor. DESIGN: Randomized, cross-over, single-blind, pilot clinical trial performed comparing two different low-protein dietary regimens. SUBJECTS: Forty-two days with LPP and 42 days with NO-LPP regimen in six patients with Parkinson's disease with levodopa. METHODS: Monitoring patient response to two different nutritional schemes through indirect calorimetry (armband), BMI, Patient Global Improvement Scale. RESULTS: Mean total EE was 1731 +/- 265 kcal/day with NO-LPP vs. 1903 +/- 265 kcal/day with LPP (p = 0.02). CONCLUSIONS: The usage of LPP increases EE and improves motor function in PD patients to a greater extent than NO-LPP dietary regimen. Calorie intake should be increased to prevent malnutrition in the long-term.

Special low-protein foods ameliorate postprandial off in patients with advanced Parkinson's disease.

Protein intake interferes with levodopa therapy. Patients with advanced Parkinson's disease (PD) should restrict daily protein intake and shift protein intake to the evening. For further reduction of protein intake in the first part of the day, special low-protein products (LPP) should be used instead of normal food products at breakfast and lunch. We studied the efficacy of LPP on postprandial off periods, in PD patients on levodopa therapy. The methods included a randomized, cross-over, single-blind, pilot clinical trial comparing a 2-month balanced diet with a 2-month LPP diet in 18 PD patients with motor fluctuations. The off phases were significantly shorter after LPP diet than after balanced diet (postprandial off, 49 +/- 73 min vs. 79 +/- 72 min and total off, 164 +/- 148 min vs. 271 +/- 174 min, both P < 0.0001). Moreover, a reduction in total off time during LPP diet (3.3 +/- 2.7 hr vs. 4.7 +/- 3.3 hr, P < 0.0001), occurred also in the 9 patients who did not experience subjective benefit. No significant changes in hematological and biochemical variables or body composition were recorded; a slight reduction in body weight (mean, -1.8%) was observed. Consumption of LPP in the first part of the day ameliorates off periods in PD patients, but additional studies including pharmacokinetics are needed.

Geographical classification of wine and olive oil by means of classification and influence matrix analysis (CAIMAN).

Classification and influence matrix analysis (CAIMAN) is a new classification method, recently proposed and based on the influence matrix (also called leverage matrix). Depending on the purposes of the classification analysis, CAIMAN can be used in three outlines: (1) D-CAIMAN is a discriminant classification method, (2) M-CAIMAN is a class modelling method allowing a sample to be classified, not classified at all, or assigned to more than one class (confused) and (3) A-CAIMAN deals with the asymmetric case, where only a reference class needs to be modelled. In this work, the geographic classification of samples of wine and olive oil has been carried out by means of CAIMAN and its results compared with discriminant analysis, by focusing great attention on the model predictive capabilities. The geographic characterization has been carried out on three different datasets: extra virgin olive oils produced in a small area, with a "protected denomination of origin" label, wines with different denominations of origin, but produced in enclosed geographical areas, and olive oils belonging to different production areas. Final results seem to indicate that the application of CAIMAN to the geographical origin identification offers several advantages: first, it shows--on an average basis--good performances; second, it is able to deal in a simple way classification problems related to tipicity, authenticity, and uniqueness characterization, which are of increasing interest in food quality issues.

Virtual computational chemistry laboratory--design and description.

Internet technology offers an excellent opportunity for the development of tools by the cooperative effort of various groups and institutions. We have developed a multi-platform software system, Virtual Computational Chemistry Laboratory, http://www.vcclab.org, allowing the computational chemist to perform a comprehensive series of molecular indices/properties calculations and data analysis. The implemented software is based on a three-tier architecture that is one of the standard technologies to provide client-server services on the Internet. The developed software includes several popular programs, including the indices generation program, DRAGON, a 3D structure generator, CORINA, a program to predict lipophilicity and aqueous solubility of chemicals, ALOGPS and others. All these programs are running at the host institutes located in five countries over Europe. In this article we review the main features and statistics of the developed system that can be used as a prototype for academic and industry models.