Gene based message passing for drug repurposing

Wang, Yuxing; Li, Zhiyang; Rao, Jiahua; Yang, Yuedong; Dai, Zhiming

doi:10.1016/j.isci.2023.107663

Cited by 3 publications

(2 citation statements)

References 36 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(2) It introduces the gating mechanism, so it can maintain the continuity of gradients and effectively solve the problem of gradient disappearance or explosion. (3) By relying on multiple structures and parameters to control the flow of information, it can not only reduce the risk of underfitting but also be robust to noise [ 47 , 48 ].…”

Section: Methodology Equationmentioning

confidence: 99%

Do multisource data matter for NGP prediction? Evidence from the G-LSTM model

Hao,

Shang,

Yuan

et al. 2024

Heliyon

View full text Add to dashboard Cite

Section: Methodology Equationmentioning

confidence: 99%

Do multisource data matter for NGP prediction? Evidence from the G-LSTM model

Hao,

Shang,

Yuan

et al. 2024

Heliyon

View full text Add to dashboard Cite

“…To improve molecular generation, Popova and Olivecrona et al introduced memory augmentation, a recurrent neural network (RNN) structure, the architectures of which specialize in natural language processing (NLP) problems [19,20]. RNNs include bidirectional RNN (BRNN) [21], long short-term memory (LSTM) [22,23], Gate Recurrent Unit (GRU) [24], etc. As a special type of RNN, LSTM has not only feedforward neural networks but also feedback connections.…”

Section: Introductionmentioning

confidence: 99%

Generating Potential RET-Specific Inhibitors Using a Novel LSTM Encoder–Decoder Model

Liu,

Zhao,

Huang

2024

IJMS

View full text Add to dashboard Cite

The receptor tyrosine kinase RET (rearranged during transfection) plays a vital role in various cell signaling pathways and is a critical factor in the development of the nervous system. Abnormal activation of the RET kinase can lead to several cancers, including thyroid cancer and non-small-cell lung cancer. However, most RET kinase inhibitors are multi-kinase inhibitors. Therefore, the development of an effective RET-specific inhibitor continues to present a significant challenge. To address this issue, we built a molecular generation model based on fragment-based drug design (FBDD) and a long short-term memory (LSTM) encoder–decoder structure to generate receptor-specific molecules with novel scaffolds. Remarkably, our model was trained with a molecular assembly accuracy of 98.4%. Leveraging the pre-trained model, we rapidly generated a RET-specific-candidate active-molecule library by transfer learning. Virtual screening based on our molecular generation model was performed, combined with molecular dynamics simulation and binding energy calculation, to discover specific RET inhibitors, and five novel molecules were selected. Further analyses indicated that two of these molecules have good binding affinities and synthesizability, exhibiting high selectivity. Overall, this investigation demonstrates the capacity of our model to generate novel receptor-specific molecules and provides a rapid method to discover potential drugs.

show abstract