GGAS2SN: Gated Graph and SmilesToSeq Network for Solubility Prediction DOI
Waqar Ahmad, Kil To Chong, Hilal Tayara

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(20), P. 7833 - 7843

Published: Oct. 10, 2024

Aqueous solubility is a critical physicochemical property of drug discovery. Solubility key issue in pharmaceutical development because it can limit drug's absorption capacity. Accurate prediction crucial for pharmacological, environmental, and studies. This research introduces novel method by combining gated graph neural networks (GGNNs) attention (GATs) with Smiles2Seq encoding. Our methodology involves converting chemical compounds into structures nodes representing atoms edges indicating bonds. These graphs are then processed using specialized network (GNN) architecture. Incorporating mechanisms GNN allows capturing subtle structural dependencies, fostering improved predictions. Furthermore, we utilized the encoding technique to bridge semantic gap between molecular their textual representations. seamlessly converts notations numeric sequences, facilitating efficient transfer information our model. We demonstrate efficacy approach through comprehensive experiments on benchmark data sets, showcasing superior predictive performance compared traditional methods. model outperforms existing models provides interpretable insights features driving behavior. signifies an important advancement prediction, offering potent tools discovery, formulation development, environmental assessments. The fusion GGNN establishes robust framework accurately forecasting across various compounds, innovation domains reliant data.

Language: Английский

Harnessing machine learning to predict cytochrome P450 inhibition through molecular properties DOI

Hamza Zahid,

Hilal Tayara, Kil To Chong

et al.

Archives of Toxicology, Journal Year: 2024, Volume and Issue: 98(8), P. 2647 - 2658

Published: April 15, 2024

Language: Английский

Citations

8
Stack-AAgP: Computational prediction and interpretation of anti-angiogenic peptides using a meta-learning framework DOI

Saima Gaffar,

Hilal Tayara, Kil To Chong

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 174, P. 108438 - 108438

Published: April 9, 2024

Language: Английский

Citations

7
A comprehensive review and evaluation of machine learning-based approaches for identifying tumor T cell antigens DOI
Watshara Shoombuatong,

Saeed Ahmed,

Sakib Mahmud

et al.

Computational Biology and Chemistry, Journal Year: 2025, Volume and Issue: unknown, P. 108440 - 108440

Published: April 1, 2025

Language: Английский

Citations

0
GAN-ML: Advancing anticancer peptide prediction through innovative Deep Convolution Generative Adversarial Network data augmentation technique DOI
Sadik Bhattarai, Kil To Chong, Hilal Tayara

et al.

Chemometrics and Intelligent Laboratory Systems, Journal Year: 2025, Volume and Issue: unknown, P. 105390 - 105390

Published: April 1, 2025

Language: Английский

Citations

0
Ensemble insights: Unlocking the recombination losses in perovskite solar cells using stacked classifier DOI
Basir Akbar, Kil To Chong, Hilal Tayara

et al.

Engineering Applications of Artificial Intelligence, Journal Year: 2025, Volume and Issue: 153, P. 110909 - 110909

Published: April 18, 2025

Language: Английский

Citations

0
TFProtBert: Detection of Transcription Factors Binding to Methylated DNA Using ProtBert Latent Space Representation DOI Open Access

Saima Gaffar,

Kil To Chong, Hilal Tayara

et al.

International Journal of Molecular Sciences, Journal Year: 2025, Volume and Issue: 26(9), P. 4234 - 4234

Published: April 29, 2025

Transcription factors (TFs) are fundamental regulators of gene expression and perform diverse functions in cellular processes. The management 3-dimensional (3D) genome conformation relies primarily on TFs. TFs crucial expression, performing various roles biological They attract transcriptional machinery to the enhancers or promoters specific genes, thereby activating inhibiting transcription. Identifying these is a significant step towards understanding mechanisms. Due time-consuming labor-intensive nature experimental methods, development computational models essential. In this work, we introduced two-layer prediction framework based support vector machine (SVM) using latent space representation protein language model, ProtBert. first layer method reliably predicts identifies transcription (TFs), second layer, proposed that prefer binding methylated deoxyribonucleic acid (TFPMs). addition, also tested an imbalanced database. detecting TFPMs, model consistently outperformed state-of-the-art approaches, as demonstrated by performance comparisons via empirical cross-validation analysis independent tests.

Language: Английский

Citations

0
NaII-Pred: An ensemble-learning framework for the identification and interpretation of sodium ion inhibitors by fusing multiple feature representation DOI
Mir Tanveerul Hassan, Hilal Tayara, Kil To Chong

et al.

Computers in Biology and Medicine, Journal Year: 2024, Volume and Issue: 178, P. 108737 - 108737

Published: June 15, 2024

Language: Английский

Citations

2
SB-Net: Synergizing CNN and LSTM networks for uncovering retrosynthetic pathways in organic synthesis DOI
Bilal Ahmad Mir, Hilal Tayara, Kil To Chong

et al.

Computational Biology and Chemistry, Journal Year: 2024, Volume and Issue: 112, P. 108130 - 108130

Published: June 15, 2024

Language: Английский

Citations

1
Possum: identification and interpretation of potassium ion inhibitors using probabilistic feature vectors DOI
Mir Tanveerul Hassan, Hilal Tayara, Kil To Chong

et al.

Archives of Toxicology, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 22, 2024

Language: Английский

Citations

1
GGAS2SN: Gated Graph and SmilesToSeq Network for Solubility Prediction DOI
Waqar Ahmad, Kil To Chong, Hilal Tayara

et al.

Journal of Chemical Information and Modeling, Journal Year: 2024, Volume and Issue: 64(20), P. 7833 - 7843

Published: Oct. 10, 2024

Aqueous solubility is a critical physicochemical property of drug discovery. Solubility key issue in pharmaceutical development because it can limit drug's absorption capacity. Accurate prediction crucial for pharmacological, environmental, and studies. This research introduces novel method by combining gated graph neural networks (GGNNs) attention (GATs) with Smiles2Seq encoding. Our methodology involves converting chemical compounds into structures nodes representing atoms edges indicating bonds. These graphs are then processed using specialized network (GNN) architecture. Incorporating mechanisms GNN allows capturing subtle structural dependencies, fostering improved predictions. Furthermore, we utilized the encoding technique to bridge semantic gap between molecular their textual representations. seamlessly converts notations numeric sequences, facilitating efficient transfer information our model. We demonstrate efficacy approach through comprehensive experiments on benchmark data sets, showcasing superior predictive performance compared traditional methods. model outperforms existing models provides interpretable insights features driving behavior. signifies an important advancement prediction, offering potent tools discovery, formulation development, environmental assessments. The fusion GGNN establishes robust framework accurately forecasting across various compounds, innovation domains reliant data.

Language: Английский

Citations

0