Carcaraqsar: a full-stack computational web application for quantitative structure–activity relationship analysis
DOI:
https://doi.org/10.14571/brajets.v19.n1.185-203Keywords:
computational chemistry, QSAR modeling, machine learning, bio-inspired algorithms, chemistry educationAbstract
CarcaraQSAR is an open-source, full-stack web application designed to simplify the development of Quantitative Structure-Activity Relationship (QSAR) models. By integrating machine learning algorithms and bioinspired feature selection techniques, the tool enables researchers to efficiently identify chemical descriptors correlated with biological activity. Its user-friendly interface eliminates the need for extensive programming knowledge, making QSAR modeling more accessible. CarcaraQSAR supports various validation strategies, including cross-validation and Y-randomization, ensuring robust and reproducible models. Designed for scalability, it allows cloud deployment, overcoming limitations of traditional QSAR tools. This application significantly enhances predictive modeling capabilities, thereby contributing to cost-effective drug discovery and molecular research. The synthesis of important tools in a single flow also makes CarcaraQSAR a teaching tool for University courses in Pharmaceutical and Medicinal Chemistry, providing students with a practical and integrated understanding of the concepts involved in QSAR.
References
Aguirre, G., Boiani, L., Boiani, M., Cerecetto, H., Di Maio, R., González, M., Porcal, W., Denicola, A., Piro, O. E., Castellano, E. E., Sant’Anna, C. M. R., & Barreiro, E. J. (2005). New potent 5-substituted benzofuroxans as inhibitors of Trypanosoma cruzi growth: Quantitative structure–activity relationship studies. Bioorganic & Medicinal Chemistry, 13, 6336–6346.
Ambure, P., Aher, R. B., Gajewicz, A., Puzyn, T., & Roy, K. (2015). NanoBRIDGES software: Open access tools to perform QSAR and nano-QSAR modeling. Chemometrics and Intelligent Laboratory Systems, 147, 1–13. https://doi.org/10.1016/j.chemolab.2015.07.007
Ambure, P., Halder, A. K., González-Díaz, H., & Cordeiro, M. N. D. S. (2019). QSAR-Co: An open source software for developing robust multitasking or multi-target classification-based QSAR models. Journal of Chemical Information and Modeling, 59(6), 2538–2544.
Avila, C. M., Romeiro, N. C., Silva, G. M. S., Sant’Anna, C. M. R., Barreiro, E. J., & Fraga, C. A. M. (2006). Development of new CoMFA and CoMSIA 3D-QSAR models for anti-inflammatory phthalimide-containing TNF-alpha modulators. Bioorganic & Medicinal Chemistry, 14, 6874–6885.
Bahia, M. S., Kaspi, O., Touitou, M., Binayev, I., Dhail, S., Spiegel, J., & Khazanov, N. (2023). A comparison between 2D and 3D descriptors in QSAR modeling based on bioactive conformations. Molecular Informatics, 42(4), e2200196.
Berthold, M. R., Cebron, N., Dill, F., et al. (2009). KNIME – The Konstanz Information Miner: Version 2.0 and beyond. SIGKDD Explorations Newsletter, 11(1), 26–31.
Cherkasov, A., Muratov, E. N., Fourches, D., et al. (2014). QSAR modeling: Where have you been? Where are you going to? Journal of Medicinal Chemistry, 57(12), 4977–5010.
Dassault Systèmes BIOVIA. (2023). Discovery Studio Modeling Environment (Release 2023). San Diego, CA: Dassault Systèmes.
Dos Santos, I. M., Agra, J. P. G., de Carvalho, T. G. C., et al. (2018). Classical and 3D QSAR studies of larvicidal monoterpenes against Aedes aegypti: New molecular insights for the rational design of more active compounds. Structural Chemistry, 29, 1287–1297.
Gramatica, P., Cassani, S., & Roy, P. P. (2014). QSARINS: A new software for the development, analysis, and validation of QSAR MLR models. Journal of Computational Chemistry, 35(13), 1036–1044.
Halder, A. K., & Cordeiro, M. N. D. S. (2021). QSAR-Co-X: An open source toolkit for multitarget QSAR modelling. Journal of Cheminformatics, 13, Article 58.
Mauri, A., & Bertola, M. (2022). Alvascience: A new software suite for the QSAR workflow applied to the blood–brain barrier permeability. International Journal of Molecular Sciences, 23(21), 12882. https://doi.org/10.3390/ijms232112882
Mobley, D. L., & Guthrie, J. P. (2014). FreeSolv: A database of experimental and calculated hydration free energies, with input files. Journal of Computer-Aided Molecular Design, 28, 711–720.
OECD. (2004). Principles for the validation, for regulatory purposes, of (quantitative) structure–activity relationship models. Paris, France: OECD Publishing.
Oliveira Neto, R. F. (2023). ML-SPARD: A dataset for machine learning performance analysis in small-sample regression problems. Harvard Dataverse.
Ramsundar, B., Liu, B., Wu, Z., Verras, A., Tudor, M., Sheridan, R. P., & Pande, V. (2017). Is multitask deep learning practical for pharma? Journal of Chemical Information and Modeling, 57(8), 2068–2076.
Schrödinger LLC. (2023). Schrödinger Release 2023-2: QikProp. New York, NY: Schrödinger LLC.
Supuran, C. T. (2019). Editorial: Teaching medicinal chemistry through computational tools. Journal of Enzyme Inhibition and Medicinal Chemistry, 34(1), 1–2.
Sushko, I., Novotarskyi, S., Körner, R., et al. (2011). Online chemical modeling environment (OCHEM): Web platform for data storage, model development and publishing of chemical information. Journal of Computer-Aided Molecular Design, 25(6), 533–554.
Todeschini, R., Mauri, A., & Consonni, V. (2017). DRAGON software (version 7.0) for the calculation of molecular descriptors. Milano, Italy: Kode Chemometrics srl.
Yap, C. W. (2011). PaDEL-descriptor: An open source software to calculate molecular descriptors and fingerprints. Journal of Computational Chemistry, 32(7), 1466–1474.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Daniel Carvalho, Rosalvo Oliveira Neto, Edilson Alencar Filho
This work is licensed under a Creative Commons Attribution 4.0 International License.
The BRAJETS follows the policy for Open Access Journals, provides immediate and free access to its content, following the principle that making scientific knowledge freely available to the public supports a greater global exchange of knowledge and provides more international democratization of knowledge. Therefore, no fees apply, whether for submission, evaluation, publication, viewing or downloading of articles. In this sense, the authors who publish in this journal agree with the following terms: A) The authors retain the copyright and grant the journal the right to first publication, with the work simultaneously licensed under the Creative Commons Attribution License (CC BY), allowing the sharing of the work with recognition of the authorship of the work and initial publication in this journal. B) Authors are authorized to distribute non-exclusively the version of the work published in this journal (eg, publish in the institutional and non-institutional repository, as well as a book chapter), with acknowledgment of authorship and initial publication in this journal. C) Authors are encouraged to publish and distribute their work online (eg, online repositories or on their personal page), as well as to increase the impact and citation of the published work.