HUBioDataSciLab

Research

Our lab focuses on the application of machine learning and deep learning to complex challenges in bioinformatics and cheminformatics. We specialize in developing novel computational methods for protein function prediction, drug-target interaction analysis, and de novo molecular design, aiming to accelerate the pace of scientific discovery.

Highlighted

Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks
Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks
Atabey Ünlü, Elif Çevrim, Melih Gökay Yiğit, Ahmet Sarıgün, Hayriye Çelikbilek, …, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Sureyya Rifaioglu, Erden Banoğlu, Tunca Doğan
Nature Machine Intelligence  ·  15 Sep 2025  ·  doi:10.1038/s42256-025-01082-y

All

2025

Molecular Contrastive Learning with Graph Attention Network MoCL-GAT for Enhanced Molecular Representation
Molecular Contrastive Learning with Graph Attention Network (MoCL-GAT) for Enhanced Molecular Representation
Alperen Dalkıran, Ahmet S. Rifaioğlu, Rengul Cetin-Atalay, Aybar C. Acar, Tunca Doğan, M. Volkan Atalay
Cold Spring Harbor Laboratory  ·  19 Sep 2025  ·  doi:10.1101/2025.09.17.676724
Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks
Target-specific de novo design of drug candidate molecules with graph-transformer-based generative adversarial networks
Atabey Ünlü, Elif Çevrim, Melih Gökay Yiğit, Ahmet Sarıgün, Hayriye Çelikbilek, …, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Sureyya Rifaioglu, Erden Banoğlu, Tunca Doğan
Nature Machine Intelligence  ·  15 Sep 2025  ·  doi:10.1038/s42256-025-01082-y
Mpox: disease manifestations and therapeutic development
Mpox: disease manifestations and therapeutic development
Yining Wang, Xin Wang, Tunca Doğan, Nadia A. Sam-Agudu, Jaffar A. Al-Tawfiq, Qiuwei Pan
Journal of Virology  ·  11 Aug 2025  ·  doi:10.1128/jvi.00152-25
ProtHGT: Heterogeneous Graph Transformers for Automated Protein Function Prediction Using Biological Knowledge Graphs and Language Models
ProtHGT: Heterogeneous Graph Transformers for Automated Protein Function Prediction Using Biological Knowledge Graphs and Language Models
Erva Ulusoy, Tunca Doğan
Cold Spring Harbor Laboratory  ·  24 Apr 2025  ·  doi:10.1101/2025.04.19.649272
A Benchmarking Platform for Assessing Protein Language Models on Function-related Prediction Tasks
A Benchmarking Platform for Assessing Protein Language Models on Function-related Prediction Tasks
Elif Çevrim, Melih Gökay Yiğit, Erva Ulusoy, Ardan Yılmaz, Tunca Doğan
Cold Spring Harbor Laboratory  ·  16 Apr 2025  ·  doi:10.1101/2025.04.10.648084
Protein language models for predicting drug target interactions: Novel approaches, emerging methods, and future directions
Protein language models for predicting drug–target interactions: Novel approaches, emerging methods, and future directions
Atabey Ünlü, Erva Ulusoy, Melih Gökay Yiğit, Melih Darcan, Tunca Doğan
Current Opinion in Structural Biology  ·  01 Apr 2025  ·  doi:10.1016/j.sbi.2025.103017
A Benchmarking Platform for Assessing Protein Language Models on Function-Related Prediction Tasks
A Benchmarking Platform for Assessing Protein Language Models on Function-Related Prediction Tasks
Elif Çevrim, Melih Gökay Yiğit, Erva Ulusoy, Ardan Yılmaz, Tunca Doğan
Methods in Molecular Biology  ·  01 Jan 2025  ·  doi:10.1007/978-1-0716-4662-5_14

2024

Design, synthesis, and evaluation of novel Indole Based small molecules as sirtuin inhibitors with anticancer activities
Design, synthesis, and evaluation of novel Indole‐Based small molecules as sirtuin inhibitors with anticancer activities
Busra Binarci, Ensar Korkut Kilic, Tunca Dogan, Rengul Cetin Atalay, Deniz Cansen Kahraman, Sultan Nacak Baytas
Drug Development Research  ·  21 Oct 2024  ·  doi:10.1002/ddr.70008
Mutual annotation based prediction of protein domain functions with scp Domain2GO scp
Mutual annotation‐based prediction of protein domain functions with Domain2GO
Erva Ulusoy, Tunca Doğan
Protein Science  ·  16 May 2024  ·  doi:10.1002/pro.4988

2023

Democratizing knowledge representation with BioCypher
Democratizing knowledge representation with BioCypher
Sebastian Lobentanzer, Patrick Aloy, Jan Baumbach, Balazs Bohar, Vincent J. Carey, …, Denes Turei, Erva Ulusoy, Dagmar Waltemath, Judith A. H. Wodke, Julio Saez-Rodriguez
Nature Biotechnology  ·  19 Jun 2023  ·  doi:10.1038/s41587-023-01848-y
Transfer learning for drug target interaction prediction
Transfer learning for drug–target interaction prediction
Alperen Dalkıran, Ahmet Atakan, Ahmet S Rifaioğlu, Maria J Martin, Rengül Çetin Atalay, Aybar C Acar, Tunca Doğan, Volkan Atalay
Bioinformatics  ·  01 Jun 2023  ·  doi:10.1093/bioinformatics/btad234
SELFormer: molecular representation learning via SELFIES language models
SELFormer: molecular representation learning via SELFIES language models
Atakan Yüksel, Erva Ulusoy, Atabey Ünlü, Tunca Doğan
Machine Learning: Science and Technology  ·  01 Jun 2023  ·  doi:10.1088/2632-2153/acdb30
How to approach machine learning-based prediction of drug compound target interactions
How to approach machine learning-based prediction of drug/compound–target interactions
Heval Atas Guvenilir, Tunca Doğan
Journal of Cheminformatics  ·  06 Feb 2023  ·  doi:10.1186/s13321-023-00689-w
ProFAB open protein functional annotation benchmark
ProFAB—open protein functional annotation benchmark
A Samet Özdilek, Ahmet Atakan, Gökhan Özsarı, Aybar Acar, M Volkan Atalay, Tunca Doğan, Ahmet S Rifaioğlu
Briefings in Bioinformatics  ·  03 Feb 2023  ·  doi:10.1093/bib/bbac627
Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks
Target Specific De Novo Design of Drug Candidate Molecules with Graph Transformer-based Generative Adversarial Networks
Atabey Ünlü, Elif Çevrim, Melih Gökay Yiğit, Ahmet Sarıgün, Hayriye Çelikbilek, …, Deniz Cansen Kahraman, Abdurrahman Olğaç, Ahmet Sureyya Rifaioğlu, Erden Banoğlu, Tunca Doğan
arXiv  ·  01 Jan 2023  ·  doi:10.48550/ARXIV.2302.07868
ASCARIS: Positional feature annotation and protein structure-based representation of single amino acid variations
ASCARIS: Positional feature annotation and protein structure-based representation of single amino acid variations
Fatma Cankara, Tunca Doğan
Computational and Structural Biotechnology Journal  ·  01 Jan 2023  ·  doi:10.1016/j.csbj.2023.09.017

2022

Machine learning-based prediction of drug approvals using molecular, physicochemical, clinical trial, and patent-related features
Machine learning-based prediction of drug approvals using molecular, physicochemical, clinical trial, and patent-related features
Fulya Ciray, Tunca Doğan
Expert Opinion on Drug Discovery  ·  02 Dec 2022  ·  doi:10.1080/17460441.2023.2153830
Mutual Annotation-Based Prediction of Protein Domain Functions with Domain2GO
Mutual Annotation-Based Prediction of Protein Domain Functions with Domain2GO
Erva Ulusoy, Tunca Doğan
Cold Spring Harbor Laboratory  ·  04 Nov 2022  ·  doi:10.1101/2022.11.03.514980
SLPred: a multi-view subcellular localization prediction tool for multi-location human proteins
SLPred: a multi-view subcellular localization prediction tool for multi-location human proteins
Gökhan Özsarı, Ahmet Sureyya Rifaioglu, Ahmet Atakan, Tunca Doğan, Maria Jesus Martin, Rengül Çetin Atalay, Volkan Atalay
Bioinformatics  ·  08 Jul 2022  ·  doi:10.1093/bioinformatics/btac458
How to Best Represent Proteins in Machine Learning-based Prediction of Drug Compound-Target Interactions
How to Best Represent Proteins in Machine Learning-based Prediction of Drug/Compound-Target Interactions
Heval Atas, Tunca Doğan
Cold Spring Harbor Laboratory  ·  01 May 2022  ·  doi:10.1101/2022.05.01.490207
Learning functional properties of proteins with language models
Learning functional properties of proteins with language models
Serbulent Unsal, Heval Atas, Muammer Albayrak, Kemal Turhan, Aybar C. Acar, Tunca Doğan
Nature Machine Intelligence  ·  21 Mar 2022  ·  doi:10.1038/s42256-022-00457-9

2021

Editorial: Machine Learning Methodologies to Study Molecular Interactions
Editorial: Machine Learning Methodologies to Study Molecular Interactions
Artur Yakimovich, Arzucan Özgür, Tunca Doğan, Elif Ozkirimli
Frontiers in Molecular Biosciences  ·  03 Dec 2021  ·  doi:10.3389/fmolb.2021.806474
Data Centric Molecular Analysis and Evaluation of Hepatocellular Carcinoma Therapeutics Using Machine Intelligence-Based Tools
Data Centric Molecular Analysis and Evaluation of Hepatocellular Carcinoma Therapeutics Using Machine Intelligence-Based Tools
Rengul Cetin-Atalay, Deniz Cansen Kahraman, Esra Nalbat, Ahmet Sureyya Rifaioglu, Ahmet Atakan, Ataberk Donmez, Heval Atas, M. Volkan Atalay, Aybar C. Acar, Tunca Doğan
Journal of Gastrointestinal Cancer  ·  01 Dec 2021  ·  doi:10.1007/s12029-021-00768-x
Protein domain-based prediction of drug compound target interactions and experimental validation on LIM kinases
Protein domain-based prediction of drug/compound–target interactions and experimental validation on LIM kinases
Tunca Doğan, Ece Akhan Güzelcan, Marcus Baumann, Altay Koyas, Heval Atas, Ian R. Baxendale, Maria Martin, Rengul Cetin-Atalay
PLOS Computational Biology  ·  29 Nov 2021  ·  doi:10.1371/journal.pcbi.1009171
CROssBAR: comprehensive resource of biomedical relations with knowledge graph representations
CROssBAR: comprehensive resource of biomedical relations with knowledge graph representations
Tunca Doğan, Heval Atas, Vishal Joshi, Ahmet Atakan, Ahmet Sureyya Rifaioglu, …, Vladimir Volynkin, Hermann Zellner, Rengul Cetin-Atalay, Maria Martin, Volkan Atalay
Nucleic Acids Research  ·  28 Jun 2021  ·  doi:10.1093/nar/gkab543
Protein Domain-Based Prediction of Compound Target Interactions and Experimental Validation on LIM Kinases
Protein Domain-Based Prediction of Compound–Target Interactions and Experimental Validation on LIM Kinases
Tunca Doğan, Ece Akhan Güzelcan, Marcus Baumann, Altay Koyas, Heval Atas, Ian Baxendale, Maria Martin, Rengul Cetin-Atalay
Cold Spring Harbor Laboratory  ·  14 Jun 2021  ·  doi:10.1101/2021.06.14.448307

2020

MDeePred: novel multi-channel protein featurization for deep learning-based binding affinity prediction in drug discovery
MDeePred: novel multi-channel protein featurization for deep learning-based binding affinity prediction in drug discovery
A S Rifaioglu, R Cetin Atalay, D Cansen Kahraman, T Doğan, M Martin, V Atalay
Bioinformatics  ·  07 Dec 2020  ·  doi:10.1093/bioinformatics/btaa858
Evaluation of Methods for Protein Representation Learning: A Quantitative Analysis
Evaluation of Methods for Protein Representation Learning: A Quantitative Analysis
Serbulent Unsal, Heval Ataş, Muammer Albayrak, Kemal Turhan, Aybar C. Acar, Tunca Doğan
Cold Spring Harbor Laboratory  ·  28 Oct 2020  ·  doi:10.1101/2020.10.28.359828
CROssBAR: Comprehensive Resource of Biomedical Relations with Deep Learning Applications and Knowledge Graph Representations
CROssBAR: Comprehensive Resource of Biomedical Relations with Deep Learning Applications and Knowledge Graph Representations
Tunca Doğan, Heval Atas, Vishal Joshi, Ahmet Atakan, Ahmet Sureyya Rifaioglu, …, Vladimir Volynkin, Hermann Zellner, Rengul Cetin-Atalay, Maria Martin, Volkan Atalay
Cold Spring Harbor Laboratory  ·  15 Sep 2020  ·  doi:10.1101/2020.09.14.296889
iBioProVis: interactive visualization and analysis of compound bioactivity space
iBioProVis: interactive visualization and analysis of compound bioactivity space
Ataberk Donmez, Ahmet Sureyya Rifaioglu, Aybar Acar, Tunca Doğan, Rengul Cetin-Atalay, Volkan Atalay
Bioinformatics  ·  14 May 2020  ·  doi:10.1093/bioinformatics/btaa496
DEEPScreen: high performance drug target interaction prediction with convolutional neural networks using 2-D structural compound representations
DEEPScreen: high performance drug–target interaction prediction with convolutional neural networks using 2-D structural compound representations
Ahmet Sureyya Rifaioglu, Esra Nalbat, Volkan Atalay, Maria Jesus Martin, Rengul Cetin-Atalay, Tunca Doğan
Chemical Science  ·  01 Jan 2020  ·  doi:10.1039/c9sc03414e

2019

DEEPred: Automated Protein Function Prediction with Multi-task Feed-forward Deep Neural Networks
DEEPred: Automated Protein Function Prediction with Multi-task Feed-forward Deep Neural Networks
Ahmet Sureyya Rifaioglu, Tunca Doğan, Maria Jesus Martin, Rengul Cetin-Atalay, Volkan Atalay
Scientific Reports  ·  14 May 2019  ·  doi:10.1038/s41598-019-43708-3

2018

ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature
ECPred: a tool for the prediction of the enzymatic functions of protein sequences based on the EC nomenclature
Alperen Dalkiran, Ahmet Sureyya Rifaioglu, Maria Jesus Martin, Rengul Cetin-Atalay, Volkan Atalay, Tunca Doğan
BMC Bioinformatics  ·  21 Sep 2018  ·  doi:10.1186/s12859-018-2368-y
Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases
Recent applications of deep learning and machine intelligence on in silico drug discovery: methods, tools and databases
Ahmet Sureyya Rifaioglu, Heval Atas, Maria Jesus Martin, Rengul Cetin-Atalay, Volkan Atalay, Tunca Doğan
Briefings in Bioinformatics  ·  31 Jul 2018  ·  doi:10.1093/bib/bby061
HPO2GO: prediction of human phenotype ontology term associations using cross ontology annotation co-occurrences
HPO2GO: prediction of human phenotype ontology term associations using cross ontology annotation co-occurrences
Tunca Doğan
PeerJ  ·  29 Jul 2018  ·  doi:10.7287/peerj.preprints.26663v2
A Structural Perspective on the Modulation of Protein-Protein Interactions with Small Molecules
A Structural Perspective on the Modulation of Protein-Protein Interactions with Small Molecules
Habibe Cansu Demirel, Tunca Dogan, Nurcan Tuncbag
Current Topics in Medicinal Chemistry  ·  18 Jul 2018  ·  doi:10.2174/1568026618666180601080824
Phylogenetic and Other Conservation-Based Approaches to Predict Protein Functional Sites
Phylogenetic and Other Conservation-Based Approaches to Predict Protein Functional Sites
Heval Atas, Nurcan Tuncbag, Tunca Doğan
Methods in Molecular Biology  ·  01 Jan 2018  ·  doi:10.1007/978-1-4939-7756-7_4

2017

Large scale automated function prediction of protein sequences and an experimental case study validation on PTEN transcript variants
Large‐scale automated function prediction of protein sequences and an experimental case study validation on PTEN transcript variants
Ahmet Sureyya Rifaioglu, Tunca Doğan, Ömer Sinan Saraç, Tulin Ersahin, Rabie Saidi, Mehmet Volkan Atalay, Maria Jesus Martin, Rengul Cetin‐Atalay
Proteins: Structure, Function, and Bioinformatics  ·  29 Nov 2017  ·  doi:10.1002/prot.25416

2016

UniProt-DAAC: domain architecture alignment and classification, a new method for automatic functional annotation in UniProtKB
UniProt-DAAC: domain architecture alignment and classification, a new method for automatic functional annotation in UniProtKB
Tunca Doğan, Alistair MacDougall, Rabie Saidi, Diego Poggioli, Alex Bateman, Claire O’Donovan, Maria J. Martin
Bioinformatics  ·  07 Mar 2016  ·  doi:10.1093/bioinformatics/btw114