Hello, visitor!

I am Rıza! I am a lively Ph.D. candidate happy to be supervised by Francesca Grisoni 👩‍🔬 at the Molecular Machine Learning Group in Eindhoven University of Technology. I also hold high honor BSc. and MSc. degrees from the Dept. of Computer Engineering in Boğaziçi University, where I was lucky to work with Arzucan Özgür and Elif Özkırımlı👩‍🔬👩‍🔬.

Want to meet? Or just say something? Find me here!

Interests

  • Computational Drug Discovery
  • Generative Deep Learning
  • Natural Language Processing

Education

  • Ph.D. in Biomedical Engineering

    Thesis: Advancing Chemical Language Models for De Novo Drug Design. Eindhoven University of Technology.

  • MSc. in Computer Engineering, 2022

    GPA: 3.94/4.00. Thesis: Biomolecular Language Processing for Drug - Target Affinity Prediction.

  • BSc. in Computer Engineering, 2018

    GPA: 3.57/4.00. Thesis: Disease Classification based on Genomic Data with Machine Learning.

Employment 👨‍🔬

 
 
 
 
 

Great Minds Research Intern

IBM Research

June 2021 – November 2021 Zurich, Switzerland
Discovering new research fields and environments is a joy for me. For 6 months, I worked on IBM’s AppConnect platform, to map natural text inputs to application flows. My research empowered a type-ahead component to hint users while typing, which was backed by a knowledge graph 🧠
 
 
 
 
 

Research Assistant

Dept. of Computer Engineering, Boğaziçi University

July 2019 – February 2022 İstanbul, Turkey
I make my living by processing the language; let it be natural, scientific, or biomolecular. During my time as a research assistant, I led and participated in research studies on computational drug discovery 💊, Turkish natural language processing 🇹🇷, and biological text mining 🧬. Our research resulted in novel machine learning approaches for binding affinity-prediction, first large-scale Turkish Natural Language Inference data sets and representations, and an online search engine for Coronavirus researchers. The linked publications are available below.
 
 
 
 
 

Teaching Assistant

Dept. of Computer Engineering, Boğaziçi University

July 2019 – October 2021 İstanbul, Turkey
I love sharing! And what is better your scientific knowledge to share? So I became a teaching assistant for an incredible audience: curious bachelor students. I instructed problem sessions, created assignments, and guided senior projects as a teaching assistant 👨‍🏫. I always made learning fun and interactive and devised themed projects (such as helping Katniss Everdeen 🔥) and scheduled additional sessions to interact with students as much as I can. I am happy that students appreciated my efforts with their feedback: ‘It is clear that you love and devote yourself to teaching’, ‘You are unexpectedly supportive, helpful and caring’, and ‘‘You are the best TA I have ever known! 😎😎

Publications

peptidy: A light-weight Python library for peptide representation in machine learning

We present a python library to encode peptides for machine learning applications. Non-canonical amino acids and post-translational modifications are supported.
peptidy: A light-weight Python library for peptide representation in machine learning

The Jungle of Generative Drug Discovery: Traps, Treasures, and Ways Out

Surprising pitfalls in common evaluation approaches for molecule libraries generated by deep learning models. Simple solutions are proposed.
The Jungle of Generative Drug Discovery: Traps, Treasures, and Ways Out

A Hitchhiker's Guide to Deep Chemical Language Processing for Bioactivity Prediction

Practical guidelines for training deep learning models on molecular string representations for bioactivity prediction.
A Hitchhiker's Guide to Deep Chemical Language Processing for Bioactivity Prediction

Deep Supramolecular Language Processing for Co-crystal Prediction

DeepCocrystal is a convolutional neural network to predict co-crystal formation. SMILES augmentation is key to its development.
Deep Supramolecular Language Processing for Co-crystal Prediction

Chemical Language Modeling with Structured State Space Sequence Models

A novel approach to chemical language modeling. First application of structured state space sequence models (S4) to de novo design.
Chemical Language Modeling with Structured State Space Sequence Models

Contact 💭

  • r.ozcelik@tue.nl
  • De Zaale, Eindhoven, Noord-Brabant. 5612 AZ
  • Institute of Complex Molecular Systems, Ceres. Office: 1.44a
  • DM Me