ResBiGAAT: Residual Bi-GRU with attention for protein-ligand binding affinity prediction
This study presents ResBiGAAT, a novel deep learning model that combines a deep Residual Bidirectional Gated Recurrent Unit with two-sided self-attention mechanisms. ResBiGAAT leverages protein and ligand sequence-level features and their physicochemical properties to efficiently predict protein-ligand binding affinity. Through rigorous evaluation using 5-fold cross-validation, we demonstrate the performance of our proposed approach. The model exhibits competitive performance on an external dataset, highlighting its generalizability. Our publicly available web interface, located at resbigaat.streamlit.app, allows users to ...
Source: Computational Biology and Chemistry - October 22, 2023 Category: Bioinformatics Authors: Gelany Aly Abdelkader Soualihou Ngnamsie Njimbouom Tae-Jin Oh Jeong-Dong Kim Source Type: research

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design
In this study, the limitations of affinity prediction in terms of interpretability are tackled by proposing the concept of a protein-ligand interaction feature map. This increases the diversity and quantity of protein-ligand binding data by designing an adaptive autoencoder of target chemical properties to generate new ligands similar to known ligands and adding them to the original training set. AffinityVAE is then retrained using this extended training set to further validate the protein-ligand binding affinity prediction. Comparisons were conducted between the AffinityVAE and recent methods to demonstrate the high effic...
Source: Computational Biology and Chemistry - October 18, 2023 Category: Bioinformatics Authors: Mengying Wang Weimin Li Xiao Yu Yin Luo Ke Han Can Wang Qun Jin Source Type: research

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design
In this study, the limitations of affinity prediction in terms of interpretability are tackled by proposing the concept of a protein-ligand interaction feature map. This increases the diversity and quantity of protein-ligand binding data by designing an adaptive autoencoder of target chemical properties to generate new ligands similar to known ligands and adding them to the original training set. AffinityVAE is then retrained using this extended training set to further validate the protein-ligand binding affinity prediction. Comparisons were conducted between the AffinityVAE and recent methods to demonstrate the high effic...
Source: Computational Biology and Chemistry - October 18, 2023 Category: Bioinformatics Authors: Mengying Wang Weimin Li Xiao Yu Yin Luo Ke Han Can Wang Qun Jin Source Type: research

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design
In this study, the limitations of affinity prediction in terms of interpretability are tackled by proposing the concept of a protein-ligand interaction feature map. This increases the diversity and quantity of protein-ligand binding data by designing an adaptive autoencoder of target chemical properties to generate new ligands similar to known ligands and adding them to the original training set. AffinityVAE is then retrained using this extended training set to further validate the protein-ligand binding affinity prediction. Comparisons were conducted between the AffinityVAE and recent methods to demonstrate the high effic...
Source: Computational Biology and Chemistry - October 18, 2023 Category: Bioinformatics Authors: Mengying Wang Weimin Li Xiao Yu Yin Luo Ke Han Can Wang Qun Jin Source Type: research

AffinityVAE: A multi-objective model for protein-ligand affinity prediction and drug design
In this study, the limitations of affinity prediction in terms of interpretability are tackled by proposing the concept of a protein-ligand interaction feature map. This increases the diversity and quantity of protein-ligand binding data by designing an adaptive autoencoder of target chemical properties to generate new ligands similar to known ligands and adding them to the original training set. AffinityVAE is then retrained using this extended training set to further validate the protein-ligand binding affinity prediction. Comparisons were conducted between the AffinityVAE and recent methods to demonstrate the high effic...
Source: Computational Biology and Chemistry - October 18, 2023 Category: Bioinformatics Authors: Mengying Wang Weimin Li Xiao Yu Yin Luo Ke Han Can Wang Qun Jin Source Type: research

Impact of GSK199 and GSK106 binding on protein arginine deiminase IV stability and flexibility: A computational approach
Comput Biol Chem. 2023 Sep 26;107:107962. doi: 10.1016/j.compbiolchem.2023.107962. Online ahead of print.ABSTRACTProtein arginine deiminase IV (PAD4) is a potential target for diseases including rheumatoid arthritis and cancers. Currently, GSK199 is a potent, selective yet reversible PAD4 inhibitor. Its derivative, GSK106, on the other hand, was reported as an inactive compound when tested against PAD4 assay. Although they had similar skeleton, their impact towards PAD4 structural and flexibility is unknown. In order to fill the research gap, the impact of GSK199 and GSK106 binding towards PAD4 stability and flexibility is...
Source: Computational Biology and Chemistry - October 17, 2023 Category: Bioinformatics Authors: Helmi Husaini Zainal Fithri Zalikha Ibrahim Ernie Zuraida Ali Source Type: research

Impact of GSK199 and GSK106 binding on protein arginine deiminase IV stability and flexibility: A computational approach
Comput Biol Chem. 2023 Sep 26;107:107962. doi: 10.1016/j.compbiolchem.2023.107962. Online ahead of print.ABSTRACTProtein arginine deiminase IV (PAD4) is a potential target for diseases including rheumatoid arthritis and cancers. Currently, GSK199 is a potent, selective yet reversible PAD4 inhibitor. Its derivative, GSK106, on the other hand, was reported as an inactive compound when tested against PAD4 assay. Although they had similar skeleton, their impact towards PAD4 structural and flexibility is unknown. In order to fill the research gap, the impact of GSK199 and GSK106 binding towards PAD4 stability and flexibility is...
Source: Computational Biology and Chemistry - October 17, 2023 Category: Bioinformatics Authors: Helmi Husaini Zainal Fithri Zalikha Ibrahim Ernie Zuraida Ali Source Type: research

Multi-dimensional search for drug-target interaction prediction by preserving the consistency of attention distribution
Comput Biol Chem. 2023 Oct 7;107:107968. doi: 10.1016/j.compbiolchem.2023.107968. Online ahead of print.ABSTRACTPredicting drug-target interaction (DTI) is a crucial step in the process of drug repurposing and new drug development. Although the attention mechanism has been widely used to capture the interactions between drugs and targets, it mainly uses the Simplified Molecular Input Line Entry System (SMILES) and two-dimensional (2D) molecular graph features of drugs. In this paper, we propose a neural network model called MdDTI for DTI prediction. The model searches for binding sites that may interact with the target fro...
Source: Computational Biology and Chemistry - October 16, 2023 Category: Bioinformatics Authors: Huaihu Li Shunfang Wang Weihua Zheng Li Yu Source Type: research

Polyphenolic flavonoid compounds act as the inhibitory potential of aggregation process: Implications for the prevention and therapeutics against FALS-associated D101G SOD1 mutant
In this study, using computational parameters such as protein-ligand interaction and molecular dynamics (MD) simulation analyses, we are trying to identify a pharmacodynamically promising flavonoid compound that can effectively inhibit the pathogenic behavior of the D101G mutant. Epigallocatechin-gallate (EGCG), Hesperidin, Isorhamnetin, and Diosmetin were identified as potential leads in a preliminary screening of flavonoids to anti-amyloid action. The results of MD showed that the binding of flavonoids to D101G mutant caused changes in stability, hydrophobicity of protein, and flexibility, as well as significantly led to...
Source: Computational Biology and Chemistry - October 16, 2023 Category: Bioinformatics Authors: Hussein Maitham Qassim Bagher Seyedalipour Payam Baziyar Salman Ahamady-Asbchin Source Type: research

Harnessing the druggability at orthosteric and allosteric sites of PD-1 for small molecule discovery by an integrated in silico pipeline
This study emphasizes the need for an integrated pipeline that uses molecular dynamics simulations and binding energetics to identify potential binders for the dynamic PD-1/PD-L1 interface, due to the lack of small molecule co-crystals. Only a few potential binders were discovered from a large pool of molecules targeting both the allosteric and orthosteric zones. Our results suggest that the allosteric site has more potential than the orthosteric site for inhibitor design. The identified "computational hits" hold potential as starting points for in vitro evaluations followed by hit-to-lead optimization. Overall, this study...
Source: Computational Biology and Chemistry - October 12, 2023 Category: Bioinformatics Authors: Lovika Mittal Rajiv K Tonk Amit Awasthi Shailendra Asthana Source Type: research

Harnessing the druggability at orthosteric and allosteric sites of PD-1 for small molecule discovery by an integrated in silico pipeline
This study emphasizes the need for an integrated pipeline that uses molecular dynamics simulations and binding energetics to identify potential binders for the dynamic PD-1/PD-L1 interface, due to the lack of small molecule co-crystals. Only a few potential binders were discovered from a large pool of molecules targeting both the allosteric and orthosteric zones. Our results suggest that the allosteric site has more potential than the orthosteric site for inhibitor design. The identified "computational hits" hold potential as starting points for in vitro evaluations followed by hit-to-lead optimization. Overall, this study...
Source: Computational Biology and Chemistry - October 12, 2023 Category: Bioinformatics Authors: Lovika Mittal Rajiv K Tonk Amit Awasthi Shailendra Asthana Source Type: research

Harnessing the druggability at orthosteric and allosteric sites of PD-1 for small molecule discovery by an integrated in silico pipeline
This study emphasizes the need for an integrated pipeline that uses molecular dynamics simulations and binding energetics to identify potential binders for the dynamic PD-1/PD-L1 interface, due to the lack of small molecule co-crystals. Only a few potential binders were discovered from a large pool of molecules targeting both the allosteric and orthosteric zones. Our results suggest that the allosteric site has more potential than the orthosteric site for inhibitor design. The identified "computational hits" hold potential as starting points for in vitro evaluations followed by hit-to-lead optimization. Overall, this study...
Source: Computational Biology and Chemistry - October 12, 2023 Category: Bioinformatics Authors: Lovika Mittal Rajiv K Tonk Amit Awasthi Shailendra Asthana Source Type: research

Harnessing the druggability at orthosteric and allosteric sites of PD-1 for small molecule discovery by an integrated in silico pipeline
This study emphasizes the need for an integrated pipeline that uses molecular dynamics simulations and binding energetics to identify potential binders for the dynamic PD-1/PD-L1 interface, due to the lack of small molecule co-crystals. Only a few potential binders were discovered from a large pool of molecules targeting both the allosteric and orthosteric zones. Our results suggest that the allosteric site has more potential than the orthosteric site for inhibitor design. The identified "computational hits" hold potential as starting points for in vitro evaluations followed by hit-to-lead optimization. Overall, this study...
Source: Computational Biology and Chemistry - October 12, 2023 Category: Bioinformatics Authors: Lovika Mittal Rajiv K Tonk Amit Awasthi Shailendra Asthana Source Type: research

Phytochemical profiling, human insulin stability and alpha glucosidase inhibition of Gymnema latifolium leaves aqueous extract: Exploring through experimental and in silico approach
This study aimed to investigate the anti-α-glucosidase, insulin stabilization effect, and non-cytotoxic nature of Gymnema latifolium leaf aqueous extract (GLAE). FTIR analysis revealed the functional groups of compounds present in GLAE. Through LC/ESI-MS/MS analysis, about 12 compounds which belongs to different classes, triterpene glycosides, flavonoids, phenolics, stilbene glycosides and chlorophenolic glycosides were identified. GLAE showed in vitro antioxidant activity. GLAE stabilized insulin by increasing its α-helical content. GLAE inhibited the mammalian α-glucosidase (IC50 = 144 μg/mL) activity through competi...
Source: Computational Biology and Chemistry - October 11, 2023 Category: Bioinformatics Authors: Shahanaj Ismail Tajalli Ilm Chandel Jaganathan Ramakrishnan Rizwan Hasan Khan Kumaradhas Poomani Natarajan Devarajan Source Type: research

Phytochemical profiling, human insulin stability and alpha glucosidase inhibition of Gymnema latifolium leaves aqueous extract: Exploring through experimental and in silico approach
This study aimed to investigate the anti-α-glucosidase, insulin stabilization effect, and non-cytotoxic nature of Gymnema latifolium leaf aqueous extract (GLAE). FTIR analysis revealed the functional groups of compounds present in GLAE. Through LC/ESI-MS/MS analysis, about 12 compounds which belongs to different classes, triterpene glycosides, flavonoids, phenolics, stilbene glycosides and chlorophenolic glycosides were identified. GLAE showed in vitro antioxidant activity. GLAE stabilized insulin by increasing its α-helical content. GLAE inhibited the mammalian α-glucosidase (IC50 = 144 μg/mL) activity through competi...
Source: Computational Biology and Chemistry - October 11, 2023 Category: Bioinformatics Authors: Shahanaj Ismail Tajalli Ilm Chandel Jaganathan Ramakrishnan Rizwan Hasan Khan Kumaradhas Poomani Natarajan Devarajan Source Type: research