Shihang Wang

Shihang Wang

There is more to life than research.

Brief Introduction

I’m Shihang Wang (王世航), a master student of ShanghaiTech University, supervised by Fang Bai. I received my B.S. degree at college of fisheries and life science of Shanghai Ocean University (SHOU) in 2022. I will start my PhD career at Macau Polytechnic University in 2025.

My research interests center around the application of artificial intelligence algorithms in drug design, with a particular focus on molecular representation, ADMET properties prediction, phenotypic-based drug discovery and molecular generation. Additionally, I am dedicated to advancing computational methods for molecular design in order to find new avenues for breakthroughs in drug development.

My WeChat ID is SLST_Daniel, feel free to talk with me!

Representative Works

  • PhenoScreen: a dual-space contrastive learning framework-based phenotypic screening method by linking chemical perturbations to cellular morphology. [bioRxiv]
  • DeepSA: a deep-learning driven predictor of compound synthesis accessibility. [J Cheminform]
  • DeepmRNALoc: the state-of-the-art mRNA subcellular localization prediction method. [Molecules]
  • Molecular evolutionary characteristics of SARS-CoV-2 emerging in the United States. [JMV]

News

  • 10/2024, we have proposed the PhenoScreen, a dual-space contrastive learning framework-based phenotypic screening method by linking chemical perturbations to cellular morphology, refer to GitHub and BioRxiv.
  • 09/2024, congratulations to our two groups for rewarding the first and second prizes in the 2023 Shanghai International Computational Biology Innovation Competition! Utilizing GeminiMol, we identified a new inhibitor targeting GluN1/GluN3A (IC50 = 0.98 μM), GeminiMol is all you need!
  • 08/2024, GeminiMol was published in Advanced Science, congratulations to Lin Wang!
  • 12/2023, congratulations to Pengxuan Ren for successfully publishing his research paper on the last day of 2023, and it was an honor to be a part of this research!
  • 12/2023, we have introduced the GeminiMol, which incorporates conformational space information into molecular representation learning, refer to GitHub and BioRxiv.
  • 11/2023, we proposed a deep learning based computational model called DeepSA, witch could predict the synthesis accessibility of compounds. DeepSA has a high early enrichment rate for difficult to synthesize compounds and is significantly outperforming other existing methods. DeepSA is currently available online through the Bailab website. This work was done jointly by Lin Wang and me.
  • 03/2023, we proposed DeepmRNALoc, a deep learning-based prediction model, and compared it to other existing models, demonstrating significant improvements in predicting eukaryotic mRNA subcellular localization.
  • 09/2022, Shihang Wang joined the Bailab of ShanghaiTech University.
  • 09/2021, we preliminarily clarified the evolutionary characteristics of SARS-CoV-2 in the United States, providing a scientific basis for future surveillance and prevention of virus variants. This work was published on Journal of Medical Virology.