alvaQSAR 1.2 is here — a FREE web-based QSAR platform for rapid in silico prediction of environmental and toxicological endpoints.
✔ 9 OECD-aligned models
✔ Applicability Domain & QMRF
✔ Prediction reports & charts
✔ Designed to support alternatives to animal testing
New paper using #alvaDesc:
D’Anna et al. introduce AGAPE, an ML workflow for predicting G-quadruplex stabilization.
alvaDesc descriptors were combined with quantum chemical features to support interpretable prediction of G4 stabilizers.
🔗 https://t.co/gGW2Ot0TGA
New paper citing Alvascience tools:
Garibay-Manríquez et al. (2026) used alvaMolecule for structure checking and data curation in a chemoinformatic study of 1,5-disubstituted tetrazoles as potential anticancer resistance agents.
📄 https://t.co/dEbam4p1lI
#alvaMolecule
New research highlights a machine learning-guided workflow to identify potential anti-ovarian cancer leads from fungal secondary metabolites.
https://t.co/Y46zYtMM7Q
Using alvaDesc molecular descriptors, the study combined ML, docking, ADMET, MD simulations, and MM-GBSA analysis
New study by Li et al. applies an integrated in silico workflow to identify potential inhibitors of the Nipah virus matrix protein.
#AlvaDesc was used to calculate molecular descriptors for QSAR modeling and candidate prioritization.
📄 https://t.co/7eXDE0xGpv
#DrugDiscovery
Join the webinar with @ZastraIndia on integrated QSAR and cheminformatics workflows using Alvascience tools.
From molecular curation and 5,000+ descriptors with alvaDesc to QSAR modelling, deployment, and de novo design.
📅 May 29, 2026 | 3 PM IST
🔗 https://t.co/bH4keBlP3B
📢 Free Webinar — Introduction to the Alvascience Software Suite Join our Japanese reseller @AffinityScience on Tuesday, June 2 for a webinar introducing the Alvascience software suite, including live demonstrations of our tools.
Casanola-Martin et al. (2026) developed explainable ML-QSPR models to predict water permeability coefficients of polymers for packaging applications.
AlvaDesc was used to calculate molecular descriptors supporting model development and interpretation.
📄 https://t.co/199Y6Lv7lw
Recent studies published in Journal of Hazardous Materials showed the potential of machine learning and QSAR modeling to predict honey bee toxicity.
Supporting safer chemicals through computational science.
#WorldBeeDay#QSAR#Cheminformatics#InSilico#MachineLearning
🐝 Happy World Bee Day
In silico models and QSAR approaches can help assess pesticide toxicity and support safer environmental decisions for pollinators.
alvaQSAR 1.2 is here — a FREE web-based QSAR platform for rapid in silico prediction of environmental and toxicological endpoints.
✔ 9 OECD-aligned models
✔ Applicability Domain & QMRF
✔ Prediction reports & charts
✔ Designed to support alternatives to animal testing