Recep Adiyaman

Curriculum Vitae

Recep Adiyaman, PhD

Computational Structural Biologist | Protein Structure Prediction & Drug Design

Coventry, UK

Computational structural biologist with 9+ years of research experience in protein structure prediction, molecular dynamics simulation, and AI/ML-driven drug design. Developer of multiple internationally benchmarked tools (IntFOLD, ReFOLD, FunFOLD, MultiFOLD, ModFOLDdock2Q) that consistently rank among the top methods at CASP blind prediction experiments. Published 14 peer-reviewed papers (H-index 9, 470+ citations) in journals including Nucleic Acids Research, Blood, and Bioinformatics Advances. Currently combining deep learning structure predictors (AlphaFold2/3, Boltz-2, Chai-1) with physics-based methods for cancer vaccine design in collaboration with InstaDeep/BioNTech. Experienced in Python, PyTorch, HPC/SLURM environments, and end-to-end bioinformatics pipeline development.

ReFOLD3: top-5 CASP13; best server at CASP14 (NAR Web Server 2021) ReFOLD4: lifted models beyond AlphaFold2 with QA-guided MD recycling FunFOLD5: 2nd place CASP16 ligand-pose ranking; surpasses AlphaFold3 server MultiFOLD3: outperformed AlphaFold3 in quaternary structure prediction (CAMEO) ModFOLDdock2Q: 16,000+ engineered features for protein binder quality assessment IntFOLD server: 30,000+ users & 400,000+ jobs/year serving the research community OpenStructure contributor: --min-pep-length parameter for peptide QA accuracy InstaDeep/BioNTech: TCR-pMHC pipeline for personalised cancer vaccine programme

Experience

Collaborative Researcher (Part-Time)

InstaDeep (BioNTech Group) — London, UK

2023 – Present
  • Designed and developed a protein structure prediction pipeline for structural immunology, integrating TCR-pMHC modelling using AlphaFold2, Boltz-2, and Chai-1 to support BioNTech's personalised cancer vaccine programme.
  • Contributed the --min-pep-length parameter to the OpenStructure framework, improving peptide quality assessment accuracy.
  • Engineered a hybrid scoring system combining physics-based energy terms (FoldX, Rosetta) with ML-based features (DockQ, QS, PatchDockQ, PatchQS, ilDDT, aa-local-lddt, ics scores) for candidate ranking and selection.
  • Collaborated with cross-functional teams spanning computational biology, experimental immunology, and vaccine development.

Research Fellow

McGuffin Lab, University of Reading — Reading, UK

Sep 2020 – Present
  • Co-led the development and maintenance of IntFOLD integrated server for 3D protein model prediction, serving 30,000+ users and 400,000+ jobs every year.
  • Built ModFOLDdock2Q, a model quality assessment method utilising over 16,000 engineered features, achieving significant performance for identification of better protein binders.
  • Led ReFOLD4 development — MD-based refinement protocol that improves 3D predictions beyond AlphaFold2 accuracy by integrating local quality estimation with MD simulations (Bioinformatics Advances, 2023).
  • Led FunFOLD5 development for CASP16, achieving 2nd place in protein-ligand pose ranking and surpassing AlphaFold3 server method in protein-ligand interaction prediction.
  • Contributed to MultiFOLD3, which outperformed AlphaFold3 in quaternary structure prediction by integrating Boltz-2, Chai-1, Protenix and geometric-based rescoring in CAMEO.
  • ReFOLD3 ranked top-5 in CASP13 for difficult refinement targets; became top-performing refinement server at CASP14 (NAR Web Server Issue, 2021).
  • Published 10+ papers across Nucleic Acids Research, Bioinformatics Advances, Proteins, and Haematologica.

Teaching Assistant

University of Reading — Reading, UK

2017 – 2020
  • Delivered practical demonstrations for undergraduate bioinformatics and programming modules.
  • Supported student learning in Python scripting, sequence analysis (BLAST, HHpred), and structural biology concepts (PyMOL, ChimeraX).

PhD Researcher

University of Reading — Reading, UK

2017 – 2021
  • Developed ReFOLD2 (top-10 CASP13) and ReFOLD3 (top-5 CASP13, best server CASP14) using MD restraint strategies to lift predicted structures toward native.
  • Extended refinement methods to protein-ligand binding site prediction; published 4 first-author papers.

Skills

Protein Structure & MD

AlphaFold2/3, Boltz-2, Chai-1, ESMFold SWISS-MODEL, Modeller, HHpred AMBER, OpenMM, GROMACS MD refinement pipelines (restraints, ensembles) IntFOLD / MultiFOLD / ReFOLD

Docking & Drug Design

AutoDock Vina, gnina, DiffDock SwissDock, Rosetta, FoldX TCR-pMHC modelling Protein-ligand interaction prediction FunFOLD5 (CASP16 2nd place)

ML & AI

PyTorch, TensorFlow, scikit-learn, XGBoost Feature engineering (16,000+ features) Model quality estimation (ModFOLDdock2Q) DockQ, QS, PatchDockQ, ilDDT scoring Reproducible benchmarking & MLOps

Programming & Infrastructure

Python, R, Bash/Shell, Perl Flask, CGI, web server deployment HPC (SLURM, PBS), AWS Linux server administration End-to-end bioinformatics pipelines

Bioinformatics Tools

BLAST, NCBI, EMBOSS, HHpred PyMOL, ChimeraX, OpenStructure Sequence analysis & structural alignment CASP blind prediction benchmarking PDB / CATH / UniProt databases

Collaboration & Impact

14 peer-reviewed papers, H-index 9 470+ citations across leading journals InstaDeep / BioNTech cancer vaccine pipeline Teaching bioinformatics to 150+ students/cohort Code review, documentation, mentoring

Education

PhD, Structural Bioinformatics

University of Reading — Reading, UK

2017 – 2021

Thesis: 'The Molecular Dynamics Based Refinement of Predicted 3D Models Using Different Restraint Strategies'. Developed ReFOLD2 (top-10 CASP13) and ReFOLD3 (top-5 CASP13, best server CASP14). 4 first-author papers. Supervisor: Prof. Liam McGuffin.

MSc, Bioengineering

Yildiz Technical University — Istanbul, Turkey

2012 – 2014

Thesis: 'In Silico Optimisation of Zinc Binding Proteins for Biosensor Applications'. Computational protein engineering using molecular docking and mutagenesis. GPA 3.86/4.00.

MSc, Physics

Trakya University — Edirne, Turkey

2011 – 2013

Dissertation: 'GaAs/GaAlAs Quantum Well'. Research on semiconductor quantum well structures.

BSc, Physics

Trakya University — Edirne, Turkey

2007 – 2011

Coursework in classical mechanics, relativity, and quantum mechanics. Foundation for computational physics and simulation methods.

Selected Publications

Improvement of protein tertiary and quaternary structure predictions using the ReFOLD refinement method and the AlphaFold2 recycling process

Using local protein model quality estimates to guide a molecular dynamics-based refinement strategy

ReFOLD3: Refinement of 3D protein models with gradual restraints based on predicted local quality and residue contacts

Methods for the Refinement of Protein Structure 3D Models

Inter-platelet communication driving thrombus formation is regulated by extracellular calpain-1 cleavage of connexin 62

Prediction and quality assessment of protein quaternary structure models using the MultiFOLD2 and ModFOLDdock2 servers

Highlights of model quality assessment in CASP16

Prediction of protein structures, functions and interactions using the IntFOLD7, MultiFOLD and ModFOLDdock servers

Estimation of model accuracy in CASP15 using the ModFOLDdock server

IntFOLD: An integrated web resource for high-performance protein structure and function prediction

ModFOLD8: Accurate global and local quality estimates for 3D protein models

Structural, functional, and mechanistic insights uncover the fundamental role of orphan connexin-62 in platelets

Modeling SARS-CoV-2 proteins in the CASP-commons experiment

Design and synthesis of small peptide sequences to detect concentrations of free transition metal ions

Talks & Posters

  • ReFOLD4 for the refinement of AlphaFold2 predictions — ISMB 2023, 3D-SIG (Oral)
  • MD-Based Refinement of Protein Models with Local Quality Assessment — University of Reading Symposium (Oral)
  • Design of metal ion-binding small peptides — 1st National Biosensor Congress, Turkey (Oral)
  • ReFOLD2/3 refinement posters — CASP13/14/16, ISMB 2021, 3D-SIG

References

Prof. Liam McGuffin

School of Biological Sciences, University of Reading

l.j.mcguffin@reading.ac.uk

Assist. Prof. Alper Yilmaz

Yildiz Technical University, Bioengineering Department

alyilmaz@yildiz.edu.tr

BS HF DK