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

2022/10/25 by Andrea Mauri, Matteo Bertola · 1 voice · 22 citations
Biochemistry, Genetics and Molecular Biology · Computer Science · Materials Science · #Computational Drug Discovery Methods #Machine Learning in Materials Science #Metabolomics and Mass Spectrometry Studies

paper · pdf · doi:10.3390/ijms232112882

openalex publication_date 2022/10/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

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.

Citations

• Search for all self-avoiding paths for molecular graphs
• SHED: Shannon Entropy Descriptors from Topological Feature Distributions
• PubChem in 2021: new data content and improved web interfaces
• Comparison of Reliability of log P Values for Drugs Calculated by Several Methods.
• Handbook of Molecular Descriptors
• Simple Method of Calculating Octanol/Water Partition Coefficient.

Cited by

• QSPR modeling to predict the Partition Coefficient (logP) of psychoanaleptic drugs using ARKA descriptors
• Structure‐Guided De Novo Design of Carbapenem Analogs Targeting Penicillin‐Binding Protein 1B Using Pharmacophore‐Based Strategies
• A Fullerene‐Based Selenosugar Ball
• Machine learning-guided optimization of flame retardancy in rigid polyurethane foams
• Quantitative structure retention relationship applied to capillary scale liquid chromatography for the identification of phenolic compounds
• Retention behavior analysis and lipophilicity assessment of COX-2/5-LOX inhibitors using RP-HPLC
• QSAR-Guided and Fragment-Based Drug Design of Monoterpenoid Inhibitors Targeting Ebola Virus Glycoprotein
• Comparative evaluation of machine Learning-based QSPR techniques for predicting polymer glass transition temperature
• N-Benzyl-6-Chloro-4-Hydroxy-2-Quinolone-3-Carboxamides: Synthesis, Computational Studies, and Biological Investigation as Anticancer Agents
• Predictive Modeling of Yield Sooting Index Using Machine Learning with Uncertainty Estimation
• In-Silico discovery of novel cephalosporin antibiotic conformers via ligand-based pharmacophore modelling and de novo molecular design
• Pharmacokinetic Equations Applied to Obtain New Topological Models in the Search of Antibacterial Compounds
• Integrating surface chemistry properties and machine learning to map the toxicity landscape of superparamagnetic iron oxide nanoparticles
• Selective protease inhibitors from secondary metabolites of Philippine medicinal plants against porcine epidemic diarrhea virus: A computational veterinary drug discovery approach
• Machine learning-driven molecular generation for accelerated screening of high-performance flame retardants in epoxy resin composites
• Development of Quantitative Structure–Anti-Inflammatory Relationships of Alkaloids
• Unveiling first report on in silico modeling of aquatic toxicity of organic chemicals to Labeo rohita (Rohu) employing QSAR and q-RASAR
• QSAR Regression Models for Predicting HMG-CoA Reductase Inhibition
• On the Development of Descriptor-Based Machine Learning Models for Thermodynamic Properties: Part 2—Applicability Domain and Outliers
• QSPR modeling to predict surface tension of psychoanaleptic drugs using the hybrid DA-SVR algorithm
• In silico identification of Nipah virus protein inhibitors from secondary metabolites of medicinal plants using a high-throughput virtual screening approach
• Machine learning-guided computational discovery of anti-ovarian cancer leads from fungal secondary metabolites

Discussions

• Our paper "Alvascience: A New Software Suite for the QSAR Workflow Applied to BBB Permeability" doi.org/10.3390/ijms... via Molecules @mdpiopenaccess.bsky.social has surpassed 100 citations on Google [bsky, 0 points, 0 comments]