Doctor of Philosophy (PhD) in Engineering
Faculty of Engineering, Bar-Ilan University · Ramat Gan, Israel
- Thesis topic: design of machine-learning and graph-theory algorithms for adaptive immune receptor analysis.
- Direct-track PhD.
Curriculum vitae
Thomas Konstantinovsky · PhD candidate · Yaari Lab, Faculty of Engineering, Bar-Ilan University · thomas.konstat@gmail.com · ORCID · Google Scholar
Generated from thomaskon.com on 2026-10-03
- 9publications
- 2patents
- 13talks and posters
- 5fellowships and scholarships
2018201920202021202220232024202520262027
- Education
- Research
- Teaching
- Industry
Education
Master of Science (MSc) in Electrical Engineering
Bar-Ilan University · Ramat Gan, Israel
- Direct-track PhD, no separate thesis. Research from this period was published as LZGraphs (Bioinformatics, 2023).
Bachelor of Science (BSc) in Computer Science
Holon Institute of Technology · Holon, Israel
- Emphasis on computational methods, machine learning, and digital logic design.
Positions
Research
Graduate Researcher
Yaari Lab, Faculty of Engineering, Bar-Ilan University
Computational immunology. Immune-receptor repertoire representation, sequence alignment and simulation.
Researcher and Data Scientist (part-time)
Sagol Center for Epigenetics of Aging and Metabolism, Tel Aviv Sourasky Medical Center · PI: Dr. Elad Segev and Prof. Naftali Stern
Data science and machine learning within a multidisciplinary team of biologists and clinicians studying epigenetic aging.
- Analyzed DNA-methylation and other genomic data to find patterns, trends and anomalies relevant to the research questions.
- Designed and implemented custom machine-learning algorithms and analysis pipelines tailored to the needs of the biological and medical staff.
Research Assistant (internship)
Holon Institute of Technology · PI: Dr. Elad Segev
Statistical and Bayesian analysis of DNA-methylation data. Automated data-collection pipelines.
Teaching
Teaching Assistant (part-time)
Faculty of Engineering, Bar-Ilan University
- Big Data and Machine Learning
- Statistics and Data Analysis
- Biological Control Systems
Industry
Lead Data Scientist
Altooro
Built the startup's machine-learning capability from the ground up, for AI-based assessment of software developers.
- Developed new mathematical approaches to developer assessment; the core model was later granted a US patent.
- Built NLP pipelines over source code for regression tasks, and researched deep-learning NLP models for generative and discriminative goals.
- Planned, ran and analyzed statistical experiments to identify new measurable developer traits.
- Deployed models to production and maintained the backend services supporting the platform's data pipelines.
Publications
First author
2026Flashback: a reversible bilateral run-peeling decomposition of stringsarXivPreprint
We introduce Flashback, a reversible string decomposition that repeatedly peels the maximal leading and trailing character runs from a sentinel-wrapped input, recording each pair as one bilateral token. Decomposition and reconstruction both run in linear time and space. The central result is a run-pairing theorem: Flashback pairs the first run of the string with the last, the second with the second-to-last, and so on, giving an exact token count that matches a lower bound for any admissible bilateral run-peeling scheme. Structural properties follow as corollaries, including a two-symbol irreducible kernel, a characterization of palindromes, a finite-state description of the image, and edit locality.
Cite
@misc{konstantinovsky2026flashback,
title = {{Flashback: a reversible bilateral run-peeling decomposition of strings}},
author = {Thomas Konstantinovsky and Gur Yaari},
year = {2026},
eprint = {2604.26190},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2604.26190}
}
Click the entry to select it, then copy.
2025Enhancing sequence alignment of adaptive immune receptors through multi-task deep learningNucleic Acids Research
Sequence alignment of immunoglobulin (Ig) sequences is central to the computational analysis of adaptive immune receptor repertoire sequencing (AIRR-seq) data, impacting adaptive immunity research and antibody engineering. Traditional Ig sequence aligners often struggle with the complexities of V(D)J recombination and somatic hypermutation (SHM), resulting in suboptimal allele assignment accuracy and sequence segmentation. We introduce AlignAIR, a deep learning-based aligner that leverages simulation and a multi-task learning framework. AlignAIR improves allele assignment accuracy, productivity assessment, sequence segmentation and speed, and its latent space captures SHM characteristics. It integrates with existing AIRR-seq pipelines and ships with a web interface and a container image for local processing of millions of sequences.
Cite
@article{konstantinovsky2025enhancing,
title = {{Enhancing sequence alignment of adaptive immune receptors through multi-task deep learning}},
author = {Thomas Konstantinovsky and Ayelet Peres and Ran Eisenberg and Pazit Polak and Ofir Lindenbaum and Gur Yaari},
journal = {Nucleic Acids Research},
volume = {53},
number = {13},
pages = {gkaf651},
year = {2025},
doi = {10.1093/nar/gkaf651},
url = {https://doi.org/10.1093/nar/gkaf651}
}
Click the entry to select it, then copy.
2024An unbiased comparison of immunoglobulin sequence alignersBriefings in Bioinformatics
Reliable analysis of AIRR-seq data depends on accurate alignment of rearranged immunoglobulin (Ig) sequences, yet there is no unified benchmarking standard that represents the complexities of real data. We introduce GenAIRR, a modular simulation framework that generates Ig sequences alongside their ground truth, realistically simulating V(D)J recombination, somatic hypermutation and a range of sequence corruptions. Using GenAIRR we assess prominent Ig sequence aligners across a range of metrics and reveal distinct performance characteristics for each. The datasets and evaluation criteria provide a basis for unbiased benchmarking of immunogenetics tools.
Cite
@article{konstantinovsky2024unbiased,
title = {{An unbiased comparison of immunoglobulin sequence aligners}},
author = {Thomas Konstantinovsky and Ayelet Peres and Pazit Polak and Gur Yaari},
journal = {Briefings in Bioinformatics},
volume = {25},
number = {6},
pages = {bbae556},
year = {2024},
doi = {10.1093/bib/bbae556},
url = {https://doi.org/10.1093/bib/bbae556}
}
Click the entry to select it, then copy.
2023A novel approach to T-cell receptor beta chain (TCRB) repertoire encoding using lossless string compressionBioinformatics
T-cell receptor beta chain (TCRB) repertoires are crucial for understanding immune responses, but their diversity makes them hard to represent and analyze. We introduce an encoding of TCRB repertoires based on the Lempel-Ziv 76 algorithm that yields a graph-like model of a repertoire. The representation supports generation probability inference, feature-vector derivation, sequence generation, a new diversity estimate and a new sequence centrality measure, and requires no alignment or reference genotype. Applied to four large public TCRB datasets, it demonstrates a scalable approach for large sequencing data. Implemented in the LZGraphs Python package.
Cite
@article{konstantinovsky2023novel,
title = {{A novel approach to T-cell receptor beta chain (TCRB) repertoire encoding using lossless string compression}},
author = {Thomas Konstantinovsky and Gur Yaari},
journal = {Bioinformatics},
volume = {39},
number = {7},
pages = {btad426},
year = {2023},
doi = {10.1093/bioinformatics/btad426},
url = {https://doi.org/10.1093/bioinformatics/btad426}
}
Click the entry to select it, then copy.
2022Deconvolution of the epigenetic age discloses distinct inter-personal variability in epigenetic aging patternsEpigenetics & Chromatin
Cite
@article{shahal2022deconvolution,
title = {{Deconvolution of the epigenetic age discloses distinct inter-personal variability in epigenetic aging patterns}},
author = {Tamar Shahal and Elad Segev and Thomas Konstantinovsky and Yonit Marcus and Gabi Shefer and Metsada Pasmanik-Chor and Assaf Buch and Yuval Ebenstein and Paul Zimmet and Naftali Stern},
journal = {Epigenetics \& Chromatin},
volume = {15},
number = {1},
year = {2022},
doi = {10.1186/s13072-022-00441-y},
url = {https://doi.org/10.1186/s13072-022-00441-y}
}
Click the entry to select it, then copy.
2021A new approach to text rating classification using sentiment analysisarXivPreprint
Cite
@misc{konstantinovsky2021new,
title = {{A new approach to text rating classification using sentiment analysis}},
author = {Thomas Konstantinovsky},
year = {2021},
eprint = {2103.12368},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2103.12368}
}
Click the entry to select it, then copy.
2021On bi-gram graph attributesComputer and Information Science
Cite
@article{konstantinovsky2021bigram,
title = {{On bi-gram graph attributes}},
author = {Thomas Konstantinovsky and Matan Mizrachi},
journal = {Computer and Information Science},
volume = {14},
number = {3},
pages = {78},
year = {2021},
doi = {10.5539/cis.v14n3p78},
url = {https://doi.org/10.5539/cis.v14n3p78}
}
Click the entry to select it, then copy.
Flashback: a reversible bilateral run-peeling decomposition of strings
arXiv · Preprint
Cite
@misc{konstantinovsky2026flashback,
title = {{Flashback: a reversible bilateral run-peeling decomposition of strings}},
author = {Thomas Konstantinovsky and Gur Yaari},
year = {2026},
eprint = {2604.26190},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2604.26190}
}
Click the entry to select it, then copy.
Enhancing sequence alignment of adaptive immune receptors through multi-task deep learning
Nucleic Acids Research
Cite
@article{konstantinovsky2025enhancing,
title = {{Enhancing sequence alignment of adaptive immune receptors through multi-task deep learning}},
author = {Thomas Konstantinovsky and Ayelet Peres and Ran Eisenberg and Pazit Polak and Ofir Lindenbaum and Gur Yaari},
journal = {Nucleic Acids Research},
volume = {53},
number = {13},
pages = {gkaf651},
year = {2025},
doi = {10.1093/nar/gkaf651},
url = {https://doi.org/10.1093/nar/gkaf651}
}
Click the entry to select it, then copy.
An unbiased comparison of immunoglobulin sequence aligners
Briefings in Bioinformatics
Cite
@article{konstantinovsky2024unbiased,
title = {{An unbiased comparison of immunoglobulin sequence aligners}},
author = {Thomas Konstantinovsky and Ayelet Peres and Pazit Polak and Gur Yaari},
journal = {Briefings in Bioinformatics},
volume = {25},
number = {6},
pages = {bbae556},
year = {2024},
doi = {10.1093/bib/bbae556},
url = {https://doi.org/10.1093/bib/bbae556}
}
Click the entry to select it, then copy.
A novel approach to T-cell receptor beta chain (TCRB) repertoire encoding using lossless string compression
Bioinformatics
Cite
@article{konstantinovsky2023novel,
title = {{A novel approach to T-cell receptor beta chain (TCRB) repertoire encoding using lossless string compression}},
author = {Thomas Konstantinovsky and Gur Yaari},
journal = {Bioinformatics},
volume = {39},
number = {7},
pages = {btad426},
year = {2023},
doi = {10.1093/bioinformatics/btad426},
url = {https://doi.org/10.1093/bioinformatics/btad426}
}
Click the entry to select it, then copy.
Deconvolution of the epigenetic age discloses distinct inter-personal variability in epigenetic aging patterns
Epigenetics & Chromatin
Cite
@article{shahal2022deconvolution,
title = {{Deconvolution of the epigenetic age discloses distinct inter-personal variability in epigenetic aging patterns}},
author = {Tamar Shahal and Elad Segev and Thomas Konstantinovsky and Yonit Marcus and Gabi Shefer and Metsada Pasmanik-Chor and Assaf Buch and Yuval Ebenstein and Paul Zimmet and Naftali Stern},
journal = {Epigenetics \& Chromatin},
volume = {15},
number = {1},
year = {2022},
doi = {10.1186/s13072-022-00441-y},
url = {https://doi.org/10.1186/s13072-022-00441-y}
}
Click the entry to select it, then copy.
A new approach to text rating classification using sentiment analysis
arXiv · Preprint
Cite
@misc{konstantinovsky2021new,
title = {{A new approach to text rating classification using sentiment analysis}},
author = {Thomas Konstantinovsky},
year = {2021},
eprint = {2103.12368},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2103.12368}
}
Click the entry to select it, then copy.
On bi-gram graph attributes
Computer and Information Science
Cite
@article{konstantinovsky2021bigram,
title = {{On bi-gram graph attributes}},
author = {Thomas Konstantinovsky and Matan Mizrachi},
journal = {Computer and Information Science},
volume = {14},
number = {3},
pages = {78},
year = {2021},
doi = {10.5539/cis.v14n3p78},
url = {https://doi.org/10.5539/cis.v14n3p78}
}
Click the entry to select it, then copy.
Co-authored
2026The current landscape of adaptive immune receptor genomic and repertoire data: OGRDB and VDJbaseNucleic Acids Research
Cite
@article{lees2026current,
title = {{The current landscape of adaptive immune receptor genomic and repertoire data: OGRDB and VDJbase}},
author = {William D. Lees and Ayelet Peres and Vered Klein and Naama Amos and Uddalok Jana and Eric Engelbrecht and Zachary Vanwinkle and Yaniv Malach and Thomas Konstantinovsky and Pazit Polak and Corey T. Watson and Gur Yaari},
journal = {Nucleic Acids Research},
volume = {54},
number = {D1},
pages = {D932-D937},
year = {2026},
doi = {10.1093/nar/gkaf1094},
url = {https://doi.org/10.1093/nar/gkaf1094}
}
Click the entry to select it, then copy.
2022Epigenetic aging waves: artificial intelligence detects clustering of switch points in DNA methylation rate in defined sex-dependent age periodsbioRxivPreprint
Cite
@misc{segev2022epigenetic,
title = {{Epigenetic aging waves: artificial intelligence detects clustering of switch points in DNA methylation rate in defined sex-dependent age periods}},
author = {Elad Segev and Tamar Shahal and Thomas Konstantinovsky and Yonit Marcus and Gabi Shefer and Yuval Ebenstein and Metsada Pasmanik-Chor and Naftali Stern},
howpublished = {bioRxiv},
year = {2022},
doi = {10.1101/2022.10.02.510495},
url = {https://doi.org/10.1101/2022.10.02.510495}
}
Click the entry to select it, then copy.
The current landscape of adaptive immune receptor genomic and repertoire data: OGRDB and VDJbase
Nucleic Acids Research
Cite
@article{lees2026current,
title = {{The current landscape of adaptive immune receptor genomic and repertoire data: OGRDB and VDJbase}},
author = {William D. Lees and Ayelet Peres and Vered Klein and Naama Amos and Uddalok Jana and Eric Engelbrecht and Zachary Vanwinkle and Yaniv Malach and Thomas Konstantinovsky and Pazit Polak and Corey T. Watson and Gur Yaari},
journal = {Nucleic Acids Research},
volume = {54},
number = {D1},
pages = {D932-D937},
year = {2026},
doi = {10.1093/nar/gkaf1094},
url = {https://doi.org/10.1093/nar/gkaf1094}
}
Click the entry to select it, then copy.
Epigenetic aging waves: artificial intelligence detects clustering of switch points in DNA methylation rate in defined sex-dependent age periods
bioRxiv · Preprint
Cite
@misc{segev2022epigenetic,
title = {{Epigenetic aging waves: artificial intelligence detects clustering of switch points in DNA methylation rate in defined sex-dependent age periods}},
author = {Elad Segev and Tamar Shahal and Thomas Konstantinovsky and Yonit Marcus and Gabi Shefer and Yuval Ebenstein and Metsada Pasmanik-Chor and Naftali Stern},
howpublished = {bioRxiv},
year = {2022},
doi = {10.1101/2022.10.02.510495},
url = {https://doi.org/10.1101/2022.10.02.510495}
}
Click the entry to select it, then copy.
Patents
2026Scalable string set graph analysis (Phoenix)US provisional patent applicationPending
2024A novel machine learning model and mathematical framework for online candidate assessmentUS 11,989,552 B2Granted
Scalable string set graph analysis (Phoenix)
US provisional patent application, filed
A novel machine learning model and mathematical framework for online candidate assessment
US 11,989,552 B2, granted
Funding and awards
Fellowships and scholarships
Fellowship for Outstanding Doctoral Students in Artificial Intelligence and Data Science
Planning and Budgeting Committee (VATAT), Council for Higher Education of Israel
PhD Excellence Scholarship
Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA)
President's Scholarship for Outstanding PhD Students
Bar-Ilan University
Excellence Scholarship
Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA)
Faculty of Engineering MSc Scholarship
Bar-Ilan University
Awards
Publication Award
Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA)
Publication Award
Bar-Ilan Institute of Nanotechnology and Advanced Materials (BINA)
Talks and posters
FlashbackGraph: a foundation graph of human T cell receptor repertoires
AIRR Community Meeting VIII · Yale University, New Haven, USA
FlashbackGraph: exact repertoire statistics from a population-scale graph of human TCRs
AIRR Community Meeting VIII · Yale University, New Haven, USA
GenAIRR: simulating adaptive immune receptor sequences with full ground truth
AIRR Community Meeting VIII · Yale University, New Haven, USA
AlignAIR: deep-learning alignment of immunoglobulin sequences
The Fourth Israeli Data Science and AI Initiative Conference (IDSAI 2025) · Israel
AlignAIR: advancing immune sequence alignment through deep learning
AIRR Community Meeting VII · Porto, Portugal
Using LZGraphs to accelerate and unlock discovery of new AIRR attributes
AIRR Community Meeting VII · Porto, Portugal
A novel approach to T cell receptor (TCR) repertoire encoding using LZ-76 compression
Data, Models, Complexity Gathering · Ramat Gan, Israel
A novel approach to T cell receptor (TCR) repertoire encoding using LZ-76 compression
Bar-Ilan Data Science Institute Conference · Ramat Gan, Israel
LZGraphs, from theory to immunity: merging compression theory and immunology to understand the adaptive immune receptor repertoire
AIRR Community Seminar Series · Online
A novel approach to T cell receptor (TCR) repertoire encoding using LZ-76 compression
Israel Data Science Initiative Conference (IDSI 2023) · Ein Gedi, Israel
World-wide competition of AIRR sequence signal classification: tapping into collective intelligence for improved accuracy and understanding
Bar-Ilan Bioengineering Gathering · Bitan Aharon, Israel
A novel approach to T cell receptor (TCR) repertoire encoding using LZ-76 compression
Bar-Ilan Bioengineering Gathering · Bitan Aharon, Israel
A novel approach to T cell receptor (TCR) repertoire encoding using LZ-76 compression
Bar-Ilan Faculty of Engineering Annual Conference · Haifa, Israel
Service
Peer reviewer
Bioinformatics (Oxford University Press)
Co-organizer
Adaptive Immune Profiling Challenge 2025, AIRR Community machine learning working group (Kaggle)
Community benchmark for predicting immune state from adaptive immune receptor repertoires.