Sabari Kumar
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Sabari Kumar has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
- Seonah Kim
Department of Chemistry, Colorado State University, Fort Collins, CO 80523, USA
5 shared publications - Robert S. Paton
Department of Chemistry, Colorado State University, Fort Collins, Colorado 80523, USA
3 shared publications - Yeonjoon Kim
Department of Chemistry, Pukyong National University, Busan 48513, Republic of Korea
3 shared publications - Charles Stewart Mcenally
Department of Chemical & Environmental Engineering, Yale University, New Haven, CT 06520, USA
2 shared publications - Jaeyoung Cho
The University of Texas at El Paso
2 shared publications - Raúl Pérez-Soto
Department of Chemistry, Colorado State University, Fort Collins, CO 80523, USA
2 shared publications
Latest Publications
- Open Access
- 14 October 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (10) , 4512-4526
TopoFormer : a topological-geometric neural network for accurate protein solubility prediction
Interpretable protein solubility prediction from predicted protein structures is enabled through the fusion of geometric and topological protein representations.
- 14 October 2026
- Published by Royal Society of Chemistry (RSC) in Digital Discovery
- Vol. 5 (10) , 4512-4526
Open AccessTopoFormer : a topological-geometric neural network for accurate protein solubility prediction
Interpretable protein solubility prediction from predicted protein structures is enabled through the fusion of geometric and topological protein representations.
- Open Access
- 30 July 2025
- Published by American Chemical Society (ACS) in ChemRxiv
A Fragment Based Approach Towards Curating, Comparing and Developing Machine Learning Models Applied in Photochemistry
The development of Graph Neural Networks for the task of predicting molecular properties has gained a great deal of attention as it typically allows the correlation of quick to compute atomic and bond descriptors with overall molecular properties. With the raising interest in photochemistry and photocatalysis as sustainable alternatives to thermal reactions, curation of virtual databases of computed photophysical properties for training of machine learning models has become popular. Unfortunately, current efforts fail to consider the exciton localization onto different chromophores of the same molecule, leading to potentially large prediction errors. Here we describe a molecular fragmentation strategy that can be used to overcome this limitation, while also providing a way to compare structural diversity between different libraries. Using a newly generated a database of 46,432 adiabatic S0-T1 energy gaps (ALFAST-DB), we compare its diversity against two datasets from the literature and demonstrate that a fragment-based delta learning approach improves model generalizability while achieving accuracies matching those of traditional message passing graph neural network architectures (MPGNN)
- 30 July 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessA Fragment Based Approach Towards Curating, Comparing and Developing Machine Learning Models Applied in Photochemistry
The development of Graph Neural Networks for the task of predicting molecular properties has gained a great deal of attention as it typically allows the correlation of quick to compute atomic and bond descriptors with overall molecular properties. With the raising interest in photochemistry and photocatalysis as sustainable alternatives to thermal reactions, curation of virtual databases of computed photophysical properties for training of machine learning models has become popular. Unfortunately, current efforts fail to consider the exciton localization onto different chromophores of the same molecule, leading to potentially large prediction errors. Here we describe a molecular fragmentation strategy that can be used to overcome this limitation, while also providing a way to compare structural diversity between different libraries. Using a newly generated a database of 46,432 adiabatic S0-T1 energy gaps (ALFAST-DB), we compare its diversity against two datasets from the literature and demonstrate that a fragment-based delta learning approach improves model generalizability while achieving accuracies matching those of traditional message passing graph neural network architectures (MPGNN)
- Open Access
- 24 July 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Combining Geometry and Topology for Accurate Protein Solubility Prediction
Protein solubility is a key consideration for the production of proteins at industrial scales. Due to the complex and nonlinear nature of the physical processes involved in protein solubility, existing models exhibit poor predictive performance, necessitating costly trial-and-error experiments. We introduce TopoFormer, a novel combined topological-geometric equivariant neural network model capable of predicting binary protein solubility from OpenFold predicted 3D structural data. To train the TopoFormer model, the 3DProtSolDB structural dataset was created from OpenFold predictions of experimental protein solubility measurements in the literature. Concurrently, we assembled the 3DProtSolDB-Expt dataset from corresponding structures in the RCSB PDB. The 3DProtSolDB-Expt dataset was used to train TopoCoder, a topological embedding model that captures secondary structure shape information. The resultant embeddings and corresponding 3DProtSolDB structures were used to train the TopoFormer model. The trained TopoFormer model achieves state-of-the-art accuracies on a held-out test set. Additionally, model interpretability analyses reveal that the TopoFormer model acquires key physical insights into solvation behavior. These techniques are used to analyze the solubility of carbonic anhydrase mutants as reported in the literature. We find that metrics from the TopoFormer model correlate well with water survival probabilities from mo-lecular dynamics simulations, highlighting the utility of the trained model in guiding the rational design of soluble mutants.
- 24 July 2025
- Published by American Chemical Society (ACS) in ChemRxiv
Open AccessCombining Geometry and Topology for Accurate Protein Solubility Prediction
Protein solubility is a key consideration for the production of proteins at industrial scales. Due to the complex and nonlinear nature of the physical processes involved in protein solubility, existing models exhibit poor predictive performance, necessitating costly trial-and-error experiments. We introduce TopoFormer, a novel combined topological-geometric equivariant neural network model capable of predicting binary protein solubility from OpenFold predicted 3D structural data. To train the TopoFormer model, the 3DProtSolDB structural dataset was created from OpenFold predictions of experimental protein solubility measurements in the literature. Concurrently, we assembled the 3DProtSolDB-Expt dataset from corresponding structures in the RCSB PDB. The 3DProtSolDB-Expt dataset was used to train TopoCoder, a topological embedding model that captures secondary structure shape information. The resultant embeddings and corresponding 3DProtSolDB structures were used to train the TopoFormer model. The trained TopoFormer model achieves state-of-the-art accuracies on a held-out test set. Additionally, model interpretability analyses reveal that the TopoFormer model acquires key physical insights into solvation behavior. These techniques are used to analyze the solubility of carbonic anhydrase mutants as reported in the literature. We find that metrics from the TopoFormer model correlate well with water survival probabilities from mo-lecular dynamics simulations, highlighting the utility of the trained model in guiding the rational design of soluble mutants.
- 5 September 2024
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 40 (1-4)
Sooting tendencies: Combustion science for designing sustainable fuels with improved properties
- 5 September 2024
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 40 (1-4)
Sooting tendencies: Combustion science for designing sustainable fuels with improved properties
- 3 August 2024
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 40 (1-4)
Sooting tendency of substituted aromatic oxygenates: The role of functional groups and positional isomerism in vanillin isomers
- 3 August 2024
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 40 (1-4)
Sooting tendency of substituted aromatic oxygenates: The role of functional groups and positional isomerism in vanillin isomers
- 19 November 2022
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 39 (4) , 4969-4978
Physics-informed graph neural networks for predicting cetane number with systematic data quality analysis
- 19 November 2022
- Published by Elsevier in Proceedings of the Combustion Institute
- Vol. 39 (4) , 4969-4978
Physics-informed graph neural networks for predicting cetane number with systematic data quality analysis