Kemal Özkırşehirli

Kemal Özkırşehirli

- International student from İstanbul, Türkiye · B.Sc. candidate at MIT · GPA 5.0/5.0 · Computer Science and Engineering · concentration in Writing · expected May 2027

- Principal Investigator, Özkırşehirli Group

- Research across MIT Chemistry, MIT CSAIL, MIT Physics, A*STAR EDDC, PRISM/W2D2, and Harvard Medical School

- Teaching Fellow, MIT EECS

- Cambridge, MA, USA - kemalozk@mit.edu

Awards:

Bronze Medal, 56th International Chemistry Olympiad — 105th of 327
Bronze Medal, 58th International Mendeleev Chemistry Olympiad — 73rd of 151
Silver Medal, TÜBİTAK National Chemistry Olympiad
Columbia Science Research Fellow Scholarship
AIME qualification and AMC Hall of Fame recognition
YC Startup School 2026 acceptance
CHEM13 global 2nd of 1,551
Oxford PAT 93/100

My work and the Özkırşehirli Group aim to make difficult scientific systems parsable, computable, verifiable, and decision-ready. (1) We develop MeshAnyOrder, an order-agnostic autoregressive transformer for topology-aware 3D mesh generation from point clouds. (2) We build multi-stage CADD pipelines for TBXT/brachyury, integrating docking, QSAR, CNN rescoring, co-folding, free-energy scaffolding, selectivity, and sourceability. (3) Scientific-software directions include VeriQSM + QSMBench for artifact-grounded verification of scientific false success, Kadanoff-GNN-RG for learned coarse-graining and phase analysis, Kupcinet–Getz Reaction–Diffusion AI for solver-faithful benchmarking, DFT → kMC for auditable multiscale kinetics, and a structure-informed antibody-RL scaffold. (4) I develop and evaluate generative, foundation, and agentic systems for protein design, chromatin organization, autoimmune target discovery, molecular simulation, and robust scientific decision-making.

Professional

About me - Professional - Education - Recognition - Activities - Contact - Resume

Research - MeshAnyOrder - TBXT / CADD - Protein Safety - Chromatin - Target Discovery - Protein Design - VeriQSM / QSMBench - Antibody RL - Kadanoff-GNN-RG - Reaction–Diffusion AI - DFT → kMC

Teaching - 6.1200[J] - Renormalization Group

Writing - About - Collection of Prose and Poems

Skills - Computational Stack - CADD - Languages - Interests

Profiles - Google Scholar - GitHub - LinkedIn

Community - AI@MIT - MIT BioMakers - Schwarzman Advisor - MIT Student Council - ClubChem - MIT Gala

AI/ML for Science - Selected Work

Molecular Simulation, CADD, and Chemical Physics

TBXT - 11-person chordoma/TBXT hit-identification project targeting PDB 6F59 site F; 2,274 prior-art compounds, 737 analogs, 30,000 BRICS recombinations, a 570-compound novelty-filtered pool, and a docking/QSAR/GNINA/Boltz-2/MMGBSA-FEP/selectivity funnel

VeriQSM + QSMBench - v0.3 research release for artifact-grounded verification of scientific false success in quantum-chemistry and statistical-mechanics agents: typed workflow IR, allowlisted execution, an independent evaluator, 240 authoring seeds, and a 24-case evaluator-conformance mini; not a sealed benchmark or completed multi-model scientific result

Kadanoff-GNN-RG - Alpha research software combining symmetry-adapted Kadanoff coarse-graining, periodic Monte Carlo spin configurations, typed-edge GNNs, calibrated phase classification, empirical RG-flow reconstruction, and finite-grid fixed-point candidates; scientific conclusions require conventional finite-size and statistical-mechanics validation

Buchwald Lab - CuH-catalyst development for asymmetric methylation and alkylation of vinyl boronate esters, with 1H-NMR, chiral-HPLC, substrate-scope expansion, and multi-gram scale-up

Pedal AI - Python/LangGraph and FastAPI infrastructure for chemistry agents, molecular-prediction engines, inspectable retrosynthesis trees, provenance, and decision-ready synthesis workflows

Kupcinet–Getz Reaction–Diffusion AI - Solver-faithful scientific-AI benchmark for nonlinear chemical oscillators, traveling waves, and synthetic morphogenesis, spanning deterministic, chemical-Langevin, Gillespie, and spatial-SSA solvers with convergence audits, calibrated abstention, and reproducibility contracts

Sepal AI / Mercor - Graduate-level chemistry LLM data, retrosynthesis and reaction-mechanism tasks, chemical-validity rubrics, prompt analysis, and failure-mode annotation

DFT → kMC - Implementation scaffold linking Gaussian/ORCA transition-state thermochemistry to Eyring rates and exact Gillespie kinetic Monte Carlo across solvent pathways, with uncertainty analysis and provenance; the bundled example is synthetic and does not reproduce the original historical project

Coursework and Toolchain

Stack - Python, C/C++, CUDA, PyTorch, Transformers, GNNs, HPC/GPU programming, Linux, Bash, Git, SLURM/PBS/qsub, RDKit, OpenMM/OpenFE, PySCF, LangGraph, FastAPI, and LaTeX

MIT Coursework - 18.615 Stochastic Processes; 6.1220[J] Design and Analysis of Algorithms; 18.404[J] Theory of Computation; 6.1910 Computer Structures and Architectures; intensive Python and C/C++/Assembly programming labs; 18.600 Probability Theory and Random Variables; 18.06 Linear Algebra; 5.43 Advanced Organic Chemistry; 6.1200[J] Discrete Mathematics; 5.351 Spectroscopy and Physical Chemistry Lab

Columbia Coursework - Intensive Organic Chemistry I; Data Structures and Algorithms; Accelerated Multivariable Calculus; Mechanics and Thermodynamics; Electricity and Magnetism; Introductory Electrical Engineering and Lab

Columbia Core - University Writing: Gender and Sexuality / 21W.011 Writing and Rhetoric; Literature Humanities I & II; Frontiers of Science

Biomolecular AI, Protein, and Genome Modeling

MeshAnyOrder - Order-agnostic autoregressive transformer for point-cloud-conditioned 3D mesh generation with quantized face tokens, arbitrary traversal seeds, 3D RoPE, triangle/quad tokenization, topology-aware constraints, frontier-parallel decoding, and publication-grade ablations

PRISM - Adversarial evaluation of protein foundation models across biological plausibility, sequence-structure-function consistency, developability, uncertainty calibration, claimed mechanisms, and failure taxonomies

ChromoGen V2 - Conditional diffusion for small-molecule-perturbed single-cell 3D chromatin, integrating Plate-C / Easy Dip-C structures with CHARM-style same-cell multi-omics and leakage-aware evaluation

V2M - Calibrated genetics-to-mechanism autoimmune target discovery using single-cell foundation models, QTL/colocalization, retrodiction benchmarks, perturbation validation, and structure-aware prioritization

EVEdesign - Open-source, method-independent protein design across a 21-person, 18-institution, 8-country collaboration, with uncertainty-aware multi-objective candidate selection and lab-in-the-loop workflows

Antibody RL - Research scaffold for structure-informed cross-attention, ESM-2-compatible antigen embeddings, OAS/SAbDab/IEDB-style curation, PPO reward optimization with IGFold/AlphaFold-Multimer-style proxies, and PyTorch DDP/SuperCloud artifacts; no wet-lab binding or production-structure validation is claimed

Education and Recognition

MIT - B.Sc. in Computer Science and Engineering with a concentration in Writing; GPA 5.0/5.0; full-ride scholarship; expected May 2027

Columbia - B.A. studies in Chemical Physics and Computer Science-Mathematics; GPA 4.07/4.00; Likely Letter, full-ride scholarship, and Science Research Fellow designation before transferring to MIT

Oxford - Offer to the integrated MEng in Engineering Science, Information Engineering; all conditions met; PAT 93/100 and top-1% placement

School / IB - Üsküdar American Academy GPA 97/100 with a financial-merit scholarship and three school awards; IB Diploma 44/45 with 7/7 in HL Mathematics AA, Physics, and Chemistry

Olympiads - IChO bronze, 105th of 327; Mendeleev bronze, 73rd of 151; TÜBİTAK national chemistry silver; Istanbul Science Olympiad chemistry gold

AMC / Waterloo - AIME qualifier, 7th in Türkiye and top 5% on AMC 12; CHEM13 global 2nd of 1,551; Chem12 global 2nd; Galois 7th of 3,071 internationally and 20th of 6,595 globally; Sir Isaac Newton top-50 Book Prize

YC / Tests - YC Startup School 2026 acceptance; Oxford PAT 93/100; IB 44/45; SAT 1560 (760 EBRW, 800 Math)