Skip to main content

Artificial Intelligence for Computational Chemistry and Computational Drug Design


Welcome to our website!

We are an independent research group focusing on applying message-passing neural networks to model potential energy surfaces and point cloud–based deep learning methods for drug discovery.


Amir Mahdi Zardoshti

> B.Sc. Applied Chemistry — University of Tehran

> M.Sc. Physical Chemistry — Sharif University of Technology


Supervisor:

Prof. Zahra Jamshidi (Link)(Link)

Professor of Physical Chemistry Department of Chemistry Sharif University of Technology


E-mail: mahdi.zardoshti02@sharif.edu

CV: [Download Link]

LinkedIn: [Link]

X: [Link]

GitHub: [Link]







 

Amir Reza Zardoshti


> M.Sc. Biochemistry —  University of Tehran


Supervisor:

Reza Yousefi (Link)

Professor of Biochemistry at University of Tehran


E-mail: Reza.zardoshti@at.uc.ir

CV: [Download Link]

LinkedIn: [Link]








 

Highlighted Research Projects

Quantum Chemistry:

>>> Hartree-Fock Study of Two-Electron Systems.


AI for Computational Drug Design:


>>> Point cloud–based deep learning for predicting drug efficacy on the VEGFR2 protein.


>>> Generative point-cloud models combined with transformer-based SMILES captioning for de novo drug design.



 AI for Computational Chemistry:


>>> Machine-learning–enhanced molecular dynamics for infrared (IR) spectral simulation.


>>> Learning the Potential Energy Surface of Ag Clusters with Active Learning–Enhanced Interatomic Potentials.





Point Cloud-based Deep Learning to Predict Drug Efficacy on the VEGFR2 Protein

Hartree-Fock Study of Two-Electron Systems

Generative Point Cloud Model with Transformer-Based SMILES Captioning for De Novo Drug Design

AFFAL: Automated Fast-Flow Active Learning for Constructing Potential Energy Surfaces of Metal Clusters

Machine Learning–enhanced Molecular Dynamics for Infrared spectral Simulation

pioneering professors in machine learning and computational chemistry

Alexandre Tkatchenko

(link)

Markus Meuwly

(link)

‪Jeremy Richardson

(link)

Sandra Luber

(link)

O. Anatole von Lilienfeld

(link)

Rafael Gómez-Bombarelli

(link)

Andrew D. White

(link)

Leticia González

(link)

Pavlo O. Dral

(link)

Olexandr Isayev

(link)

leonardo medrano sandonas

(link)

Alán Aspuru-Guzik

(link)

Sereina Riniker

(link)

Jörg Behler

(link)


Research Interests                                              

> Geometric Deep Learning
> Point Clouds-based Deep Learning
> Message Passing Neural Network (MPNN)


Our GPUs: NVIDIA RTX 3090 & NVIDIA Tesla K80


Headline

NVIDIA GeForce RTX 3090

  • VRAM: 24 GB GDDR6X

  • CUDA Cores: 10,496

  • Release Year: 2020


  • Headline

    NVIDIA Tesla K80

  • VRAM: 24 GB GDDR5 (12 GB per GPU, dual-GPU card)

  • CUDA Cores: 4,992 (2,496 per GPU)

  • Release Year: 2014