Machine Learning-Based QSPR Modeling of log CMC Values of Per- and Polyfluoroalkyl Substances (PFASs) and the Identification of Property Cliffs Per- and polyfluoroalkyl substances (PFASs) possess sufficient water solubility and chemical durability, enabling them to affect both terrestrial and aquatic environments. Their wide chemical diversity makes it difficult to assess property end points experimentally. In this study, experimental critical micelle concentration (log CMC) data for representative PFASs and non-PFASs were used to develop computational predictive models. We developed a quantitative structure-property relationship (QSPR) model and a quantitative read-across structure-property relationship (q-RASPR) model for PFASs and defluorinated/non-PFASs separately and explored the importance of similarity and error-based features along with molecular descriptors. Subsequently, a combined data set of PFASs and non-PFASs was used to develop a read-across structure property relationship coupled with the multiclass arithmetic residuals in the K-groups analysis framework (ARKA-RASPR) for capturing response range-specific contribution. We explored the physicochemical insights of our developed models for PFASs and non-PFASs separately to understand the underlying reasons for the positive or negative correlations between the modeled descriptors and response variables. Furthermore, we developed a Python-based expert system, PFAS_(CMC)_Predictor v1.0 (available from https://sites.google.com/jadavpuruniversity.in/dtc-lab-software/home/pfas-cmc-predictor), to predict the CMC value of a true external set comprising PFAS surfactants exclusively and any organic surfactants separately and to provide applicability domain status with graphical representation, thus emphasizing overall practicality and accessibility of this study. Additionally, we identified the property cliffs and investigated the reason for their cliff behavior. The developed models will further help in mapping sustainable mitigation strategies and control measures to reduce PFAS persistence.

A new study in Industrial & Engineering Chemistry Research shows how QSPR and RASPR modeling can support the prediction of log CMC values for PFASs.
alvaDesc was used to calculate 0D–2D molecular descriptors.

📖 Paper: doi.org/10.1021/acs....
🔗 alvaDesc: alvascience.com/alvadesc/

#alvaDesc #chemsky

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Pogliani index has been proposed in "Modeling with special descriptors derived from a medium-sized set of connectivity indices" doi.org/10.1021/jp96...

Check #alvaDesc at: alvascience.com/alvadesc/

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Total structure connectivity index has been proposed in "Molecular Modeling of the Physical Properties of the..." via
@ACSPublications
doi.org/10.1021/ja00...

Check #alvaDesc at: alvascience.com/alvadesc/

Comparative machine learning and deep learning frameworks for robust carcinogenicity prediction and activity cliff analysis Many industrial chemicals are recognized as carcinogenic to humans. In this study, we developed predictive models for binary carcinogenicity data in rats that are closely associated with human carcino...

The study identified key structural factors linked to carcinogenicity, including nitrogen-containing groups, branching, and molecular size

📖 Paper: doi.org/10.1039/D5EM...
🔗 alvaDesc: alvascience.com/alvadesc/

#QSAR #Toxicology #Carcinogenicity #MachineLearning #Cheminformatics #chemsky

Comparative machine learning and deep learning frameworks for robust carcinogenicity prediction and activity cliff analysis Many industrial chemicals are recognized as carcinogenic to humans. In this study, we developed predictive models for binary carcinogenicity data in rats that are closely associated with human carcino...

A new study in Environmental Science: Processes & Impacts shows how ML and DL can support carcinogenicity prediction.

In the work by Banerjee, Kumar, and Kunal Roy, alvaDesc was used to calculate 2D molecular descriptors and MACCS-166 fingerprints, supporting QSAR workflow.

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Narumi geometric topological index has been proposed in "New topological indices for finite and infinite systems" match.pmf.kg.ac.rs/electronic_v...

Check #alvaDesc at: alvascience.com/alvadesc/

alvaModel - Applicability Domain YouTube video by Alvascience

How to define the applicability domain (AD) in your models?

This video shows how to add and evaluate #AD in #alvaModel, helping ensure reliable predictions.

🎥 Video: youtube.com/watch?v=jnQl...
🔗 More on alvaModel: alvascience.com/alvamodel/

#Alvascience #alvaModel #QSAR #QSPR #chemsky

Blood Coagulation in COVID-19: Systems-Biology Evidence, Clinical Implications, and Therapeutic Opportunities in an Evolving Pandemic Background: SARS-CoV-2 continues to cause substantial morbidity, with COVID-19-associated coagulopathy driving complications across acute and postacute stages. Host-targeted therapies that address thi...

#COVID-19 coagulopathy study (ACS Omega) integrates bioinformatics + #cheminformatics.

🔬 #alvaDesc used to compute 5,290 descriptors for chemical space analysis and candidate prioritization.
🧬 VWF identified as key target.

🔗 alvaDesc: alvascience.com/alvadesc/
🔗 Paper: pubs.acs.org/doi/10.1021/...

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Narumi harmonic topological index has been proposed in "New topological indices for finite and infinite systems" match.pmf.kg.ac.rs/electronic_v...

Check #alvaDesc at: alvascience.com/alvadesc/

Prediction of gas chromatographic retention times of narcotic and hazardous drugs in blood using QSRR and machine learning models The reliable identification of narcotic and hazardous drugs in blood is of critical importance in forensic, clinical, and public health investigations. In this work, gas chromatography (GC) combined w...

New study in RSC Advances: #QSRR and #machinelearning were used to predict GC retention times of narcotic and hazardous drugs in blood.

Read the paper: doi.org/10.1039/D5RA...
Check alvaDesc: alvascience.com/alvadesc/

#QSAR #machinelearning #cheminformatics #moleculardescriptors #chemsky

Streamlit is a computational tool that into their three structural components: (target-binding ligand), ,...

📄 Read the paper: doi.org/10.1021/acsm...
🌐 Check the app: bellerophon-protac-decomposing-tool.streamlit.app
💻 Check the code: github.com/giulia-appra...

#PROTAC #DrugDiscovery #Cheminformatics #ComputationalChemistry

Bellerophon: An Automated Tool for PROTAC Decomposition Proteolysis-targeting chimeras (PROTACs) represent a promising modality for targeted protein degradation, yet their structural complexity complicates systematic design and analysis. Bellerophon is a new computational tool that automatically decomposes PROTACs into their warhead, linker, and E3 ligase ligand directly from molecular structure. By enabling automated and standardized decomposition of degraders, the tool facilitates drug design at different levels: Bellerophon demonstrated versatility for moiety replacement (ARV-110), large-scale annotation (PROTAC-DB) and linker analysis (IRAK4 data set). The tool is freely available through a user-friendly web interface, with open-source code to encourage transparency and collaborative development in chemical biology and medicinal chemistry.

Glad to have contributed to Bellerophon: an automated tool for PROTAC decomposition (warhead, linker, E3 ligand)

✔️ Rule-based, deterministic approach
✔️ Full atom conservation, no ML hallucinations
✔️ Useful for design, annotation & linker analysis

#PROTAC #bellerophon #chemsky

New study highlights how QSAR can support ecotoxicological assessment of pesticides against Ephemera vulgata.

Paper: doi.org/10.1016/j.sc...
Check AlvaDesc at: alvascience.com/alvadesc/

#QSAR #Ecotoxicology #Cheminformatics #SustainableChemistry #alvaDesc #compchem #chemsky

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Narumi simple topological index has been proposed in "New topological indices for finite and infinite systems". MATCH match.pmf.kg.ac.rs/electronic_v...

Check #alvaDesc at: alvascience.com/alvadesc/

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Bertz branching index has been proposed in Bertz, S. H. (1988). Branching in graphs and molecules. Discrete Applied Mathematics. doi.org/10.1016/0166...

Check #alvaDesc at: alvascience.com/alvadesc/

Alvascience company presentation YouTube video by Alvascience

Discover what we do at Alvascience and how our solutions support the full cheminformatics workflow, from molecular data to predictive modeling and #drugdesign.

A short overview of our approach to #QSAR, #QSPR, and #cheminformatics.

▶️ youtube.com/watch?v=1MKD...

#CompChem #machinelearning

🔗 Learn more about alvaDesc and explore its molecular descriptor platform for QSAR, QSPR, and cheminformatics modeling:
alvascience.com/alvadesc/

#moleculardescriptors #cheminformatics #OECD #toxycology #machinelearning

Machine Learning-Based Quantitative Structure Activity Relationship Modeling of Repeated Dose Toxicity: A Data-Driven Approach Following Organisation for Economic Co-operation and Development Test Gui... In recent years, the rapid increase in the production and environmental release of synthetic organic chemicals has raised serious concerns about their potential adverse effects on human health and the...

New in Chemical Research in Toxicology: alvaDesc descriptors supported ML-based QSAR models for repeated-dose toxicity using OECD TG 407, 408, and 422 data, helping predict NOAEL/LOAEL classes and identify key toxicological substructures. doi.org/10.1021/acs....

#alvaDesc #QSAR #chemsky

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Quadratic index has been proposed in Balaban, A. T. (1979). Chemical graphs. Theoretica Chimica Acta, 53(4), 355–375. doi.org/10.1007/BF00...

Check #alvaDesc at: alvascience.com/alvadesc/

A recent study highlights how in silico workflows can accelerate the search for new Ebola virus glycoprotein inhibitors. In this work, #alvaDesc supported the #QSAR stage through molecular descriptor calculation.

Paper: doi.org/10.3390/ijms...
AlvaDesc: alvascience.com/alvadesc/

#chemsky

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Kupchik vertex degree has been proposed in "Molar Refraction Relationships of Alkylgermanes Using Molecular Connectivity" doi.org/10.1002/qsar...

Check #alvaDesc at: alvascience.com/alvadesc/

Second Zagreb Index

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Second Zagreb Index has been proposed in "Graph theory and molecular orbitals. XII. Acyclic polyenes" The Journal of Chemical Physics doi.org/10.1063/1.43...

Check #alvaDesc at: alvascience.com/alvadesc/

alvaDesc is featured in a new study on quinazolin-4-one derivatives as potential SARS-CoV-2 3CLpro inhibitors. Using 2D-QSAR, docking, ADMET and MD, the authors identified promising hits.

Paper: doi.org/10.25259/AJC...
alvaDesc: alvascience.com/alvadesc/

#cheminformatics #sarscov2 #chemsky

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Valence vertex degree has been proposed in "Derivation and Significance of Valence Molecular Connectivity" doi.org/10.1002/jps....

Check #alvaDesc at: alvascience.com/alvadesc/

Advances in the applications of machine learning for cosmetic formulation development - Chemical Papers Chemical Papers - Machine learning (ML), a core branch of AI, enhances efficiency, accuracy, and systematization in cosmetic formulation development through advanced data processing and analytical...

Machine learning is reshaping cosmetic formulation development, from ingredient screening and QSAR/QSPR modeling to quality control and personalization. This review highlights the opportunities and the challenges

Paper: doi.org/10.1007/s116...
alvaDesc: alvascience.com/alvadesc/

#chemsky #alvaDesc

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

First Zagreb Index has been proposed in "Graph theory and molecular orbitals. Total φ-electron energy of alternant hydrocarbons" doi.org/10.1016/0009...

Check #alvaDesc at: alvascience.com/alvadesc/

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Wiener Index has been proposed by Harry Wiener in (1947). Structural Determination of Paraffin Boiling Points. via
@pubs.acs.org doi.org/10.1021/ja01...

Check #alvaDesc at: alvascience.com/alvadesc/

New paper: Chandra, Banerjee & Roy (2026) used #alvaDesc descriptors to build ML/QSPR models for predicting log CMC of PFASs and surfactants, identifying key structural drivers and property cliffs.

Paper: pubs.acs.org/doi/full/10....
alvaDesc: alvascience.com/alvadesc/

#QSPR #QSAR #chemsky

#descriptoroftheday #moleculardescriptors #qsar #cheminformatics #alvatips #chemsky

Distance/detour ring indices have been described in Randić, M. (1997). On Characterization of Cyclic Structures. via @pubs.acs.org
doi.org/10.1021/ci97...

Check #alvaDesc at: alvascience.com/alvadesc/

🔗 Explore alvaDesc and see how it can support your cheminformatics and QSAR workflows: alvascience.com/alvadesc/

#Cheminformatics #QSPR #RASPR #Antioxidants #FoodChemistry #Nutraceuticals #alvaDesc #Alvascience