Milad Rayka
Tehran, Iran. Email: milad.rayka@yahoo.com
EDUCATION
Chemistry and Chemical Engineering Research Center of Iran, Tehran, Iran
- Ph.D., Physical Chemistry (18.93/20) 2018-2022
Shahid Beheshti University, Tehran, Iran
- M.Sc., Physical Chemistry (18.99/20) 2015-2017
- B.Sc., Applied Chemistry (18.42/20) 2011-2015
Work Experience
Shahid Beheshti University 2024-?
Computational Chemistry Postdoctoral Fellow
RESEARCH EXPERIENCE
Chemistry and Chemical Engineering Research Center of Iran, Tehran, Iran 2018-2022
Ph.D. Research
Supervisior: Dr. Rohoullah Firouzi
Advisor: Dr. M. H. Karimi-Jafari
Project: Ligand and Protein Interaction Prediction Using Machine Learning
- Results: A new method for generating features based on distance-weighted interatomic contacts is presented, which is coupled with machine learning algorithms such as Random Forest, Extremely Randomized Trees, and Gradient Boosting Trees for predicting binding affinity in protein-ligand complexes. Additionally, a user-friendly software called 3S Application is introduced to facilitate the design of scoring functions for users without programming experience.
- Articles have been published by Molecular Informatics.
Shahid Beheshti University, Tehran, Iran 2015-2017
M.Sc. Research
Supervisior: Dr. Shant Shahbazian
Project: Development of effective electronic structure theory for Muonic moleculer systems: Hartree-Fock and Kohn-Shams equations
- Results: In the Born-Oppenheimer approximation, where nuclei are stationary, quantum behavior in nuclei or particles like muons cannot be studied. To study these effects, we utilize the nuclear-electronic orbital method in both Hartree-Fock and density functional theory frameworks. We derive non-Coulombic potentials that can be incorporated into Hartree-Fock and density functional theory equations to describe the quantum effects of these particles.
- Articles have been published by Physical Chemistry Chemical Physics.
Shahid Beheshti University, Tehran, Iran 2011-2015
B.Sc. Project
Supervisior: Dr. Shant Shahbazian
Project: Study Atom in Molecule (AIM) theory
- Results: Study the theory of Atom in Molecule and its’ extension under the guidance of Dr. Shahbazian.
TEACHING EXPERIENCE
- Teaching Assistant, Quantum chemistry 1 and 2 for graduate students, Shahid Beheshti University 2016-2017
- Teaching Assistant, Quantum chemistry for undergradue students, Shahid Beheshti University 2014-2015
- Teaching Mathematica software, Chemistry and Chemical Engineering Research Center of Iran 2019-2020
- Teaching Python programming language, Chemistry and Chemical Engineering Research Center of Iran 2020-2021
PUBLICATION
- Milad Rayka. REINDEER: A Protein-Ligand Feature Generator Software for Machine Learning Algorithms. ChemRxiv, 2024 (DOI).
- Milad Rayka, Morteza Mirzaei, Gholamreza Farnoosh, Ali Mohammad Latifi. Investigating Enzyme Biochemistry by Deep Learning: A Computational Tool for a New Era. Journal of Computational Biophysics and Chemistry, 2024, 23, 741 (DOI).
- Milad Rayka, Ali Mohammad Latifi, Morteza Mirzaei, Gholamreza Farnoosh, Zeinab Khosravi, ADDZYME: A Software to Predict Effect of Additives on Enzyme Activity. J Chem Sci, 2024, 136, 47 (DOI).
- Milad Rayka, Morteza Mirzaei, Ali Mohammad Latifi. An Ensemble-Based Approach to Estimate Confidence of Predicted Protein-Ligand Binding Affinity Values. Mol. inf. 2024, 43, e202300292 (DOI).
- Milad Rayka, Ali Mohammad Latifi, Morteza Mirzaei. Assisting In-Silico Drug Discovery Through Protein-Ligand Binding Affinity Prediction By Convolutional Neural Networks. 2024, Accepted by Journal of Applied Biotechnology Reports.
- Milad Rayka, Rohoullah Firouzi. GB-Score: Minimally Designed MachineLearning Scoring Function Based on Distance-weighted Interatomic ContactFeatures. Mol. Inf. 2023 , 42, 2200135 (DOI).
- Milad Rayka, Mohammad Hossein Karimi-Jafari, Rohoullah Firouzi. ET-score:Improving Protein-ligand Binding Affinity Prediction Based on Distance-weighted Interatomic Contact Features Using Extremely Randomized Trees Algorithm. Mol. Inf. 2021 , 40, 2060084 (DOI).
- Milad Rayka, Mohammad Goli, and Shant Shahbazian. Toward a muon-specificelectronic structure theory: effective electronic Hartree–Fock equations formuonic molecules. Phys. Chem. Chem. Phys, 2018, 20, 4466 (DOI).
- Milad Rayka, Mohammad Goli, and Shant Shahbazian. Effective electronic-onlyKohn–Sham equations for the muonic molecules. Phys. Chem. Chem. Phys, 2018, 20, 8802 (DOI).
HONORS AND AWARDS
- Selected by the National Elite Foundation as Elite Student, 2018 and 2022.
- Achieving the second rank of national entrance exam for Ph.D. in Physical Chemistry, 2018.
- Ranked 1st among students as a top student in M.Sc. Physical Chemistry, Shahid Beheshti University, 2017.
- Ranked 1st among students as a top student in B.Sc. Applied Chemistry, Shahid Beheshti University, 2015.
- Member of Special Talent in Shahid Beheshti University, 2015.
Skills
- The experience of machine and deep learning algorithms (theoretical and practical).
- The experience of Python programming language and its’ relevant libraries, e.g., Tensorflow, PyTorch, Scikit-Learn, BioPython, etc.
- Experience in computational chemistry and bioinformatics software: Gaussian, GAMESS, Autodock, PyMol.
Websites