AÖAtakan Özsan

Atakan Özsan

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Atakan Özsan has a total of 15 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • DynaPIN: A tool for characterizing dynamic protein interfaces

    by Ayşe Berçin Barlas, Atakan Özsan, Chantal Prévost, Sophie Sacquin-Mora, Ezgi Karaca

  • Open Access

    Towards a greener AlphaFold2 protocol for antibody-antigen modeling: Insights from CAPRI Round 55

    by Büşra Savaş, İrem Yılmazbilek, Atakan Özsan, Ezgi Karaca

    In the 55 th round of CAPRI, we used enhanced AlphaFold2 (AF2) sampling and data-driven docking. Our AF2 protocol relies on Wallner’s massive sampling approach, which combines different AF2 versions and sampling parameters to produce thousands of models per target. For T231 (an antibody peptide complex) and T232 (PP2A:TIPRL complex), we employed a 50-fold reduced MinnieFold sampling and a custom ranking approach, leading to a top-ranking medium prediction in both cases. For T233 and T234 (two antibody bound MHC I complexes), we followed data-driven docking, which did not lead to an acceptable model. Our post-CAPRI55 analysis showed that if we would have used our MinnieFold approach on T233 and T234, we could have submitted a medium-quality model for T233 as well. In the scoring challenge, we utilized the scoring function of FoldX, which was effective in selecting acceptable models for T231 and medium quality models for T232. Our success, especially in predicting and ranking a medium quality model for T231 and potentially for T233 underscores the feasibility of green and accurate enhanced AF2 sampling in antibody complex prediction.


  • Benchmarking the accuracy of structure‐based binding affinity predictors on Spike–ACE2 deep mutational interaction set

    by Burcu Ozden, Eda Şamiloğlu, Atakan Özsan, Mehmet Erguven, Can Yükrük, Mehdi Koşaca, Melis Oktayoğlu, Muratcan Menteş, Nazmiye Arslan, Gökhan Karakülah, et al.

    Since the start of COVID-19 pandemic, a huge effort has been devoted to understanding the Spike (SARS-CoV-2)-ACE2 recognition mechanism. To this end, two deep mutational scanning studies traced the impact of all possible mutations across receptor binding domain (RBD) of Spike and catalytic domain of human ACE2. By concentrating on the interface mutations of these experimental data, we bench marked six commonly used structure-based binding affinity predictors (FoldX, EvoEF1, MutaBind2, SSIPe, HADDOCK, and UEP). These predictors were selected based on their user-friendliness, accessibility, and speed. As a result of our bench marking efforts, we observed that none of the methods could generate a meaningful correlation with the experimental binding data. The best correlation is achieved by FoldX (R =-0.51). When we simplified the prediction problem to a binary classification, that is, whether a mutation is enriching or depleting the binding, we showed that the highest accuracy is achieved by FoldX with a 64% success rate. Surprisingly, on this set, simple energetic scoring functions performed significantly better than the ones using extra evolutionary-based terms, as in Mutabind and SSIPe. Furthermore, we demonstrated that recent AI approaches, mmCSM-PPI and TopNetTree, yielded comparable performances to the force field-based techniques. These observations suggest plenty of room to improve the binding affinity predictors in guessing the variant-induced binding profile changes of a host-pathogen system, such as Spike-ACE2. To aid such improvements we provide our benchmarking data at https://github.com/CSB-KaracaLab/RBD-ACE2-MutBench with the option to visualize our mutant models at https://rbd-ace2-mutbench.github.io/.