About

Evgeny G. Izumchenko, PhD, is an Assistant Professor of Medicine at the University of Chicago, with a research focus on understanding the complex interplay between genetic and epigenetic alterations in carcinogenesis and disease progression. His work aims to develop novel biomarkers for diagnosis and risk stratification, as well as to identify targets for therapeutic intervention. Dr. Izumchenko specializes in cancers of the upper aerodigestive tract, a particularly challenging area of oncology, and actively collaborates with researchers and oncologists worldwide to advance discovery in early cancer detection, personalized therapy, and anti-cancer interventions. He received his Bachelor of Laboratory Medicine and Master degree in Clinical Biochemistry from Ben-Gurion University in Israel, graduating summa cum laude, and earned his PhD through a partnership graduate research program at Ben-Gurion University and Fox Chase Cancer Center. His thesis work provided early insights into the role of NEDD9 in cancer development. Dr. Izumchenko completed postdoctoral training at the University of Florida, where he described mechanisms by which genomic stability dysregulation drives cancer. He later joined Johns Hopkins University, where he conducted seminal research on clonal evolution and heterogeneity in solid tumors at the genetic and epigenetic levels. Since joining the University of Chicago in 2019, his research has continued to focus on understanding carcinogenesis, with particular emphasis on premalignant progression and early immune evasion.

Research topics

• Biology
• Medicine
• Bioinformatics
• Genetics
• Internal medicine
• Computer Science
• Pathology
• Neuroscience
• Microbiology
• Cancer research
• Computational biology
• Pharmacology
• Gastroenterology
• Immunology

Selected publications

• Integrating AI and causal genetics to prioritize therapeutic targets for aging and age-related diseases

  bioRxiv (Cold Spring Harbor Laboratory) · 2026-02-16

  articleOpen access

  Aging is increasingly viewed as a pathologic process and a principal driver of diverse age-related diseases (ARDs). Framing aging as a disease offers an opportunity to identify therapeutic targets capable of modifying multiple chronic disorders simultaneously. Here, we developed an AI-driven target discovery framework that integrates large-scale multi-omic datasets to prioritise therapeutic targets shared between aging and 12 ARDs across four major disease areas: neurological, inflammatory, metabolic, and fibrotic disorders. We identified 29 high-confidence and 16 previously unrecognised aging-associated targets implicated across selected disease areas, together with convergent pathway perturbations characterized by robust upregulation of interferon and inflammatory signalling, alongside coordinated downregulation of MYC-driven proliferative programs, consistent with heightened inflammatory activation and reduced anabolic activity during aging. Hallmarks of aging assessment revealed chronic inflammation as the most enriched hallmark across aging and ARDs. Mendelian randomisation provided genetic causal support for IL6, IL6R, NLRP3, NOS2, TLR4, and GLP1R in aging-related traits and multiple ARDs, highlighting potential opportunities for drug repurposing. Co-localisation analysis further demonstrated a shared genetic signal at the IL6R locus between gene expression levels and parental survival. Together, our findings outline a scalable AI-guided multi-omic framework for identifying causal and repurposable therapeutic targets for aging and ARDs.

  PublisherDOI

• Target identification and assessment in the era of AI

  Nature Reviews Drug Discovery · 2026-04-20

  article
  PublisherDOI

• Advancing target discovery through disease-specific integration of multi-modal target identification models and comprehensive benchmarking system

  Scientific Reports · 2026-04-12 · 1 citations

  articleOpen access

  Target identification is crucial for drug development. AI-driven approaches leveraging multi-omics and computational modeling can accelerate this process. However, integrating multi-modal data for disease-specific target identification and predicting translational potential remains challenging. Moreover, the absence of a systematic evaluation framework for model performance limits confidence in target reliability. This study presents a unified framework combining machine learning-based target identification with comprehensive benchmarking. We first developed Target Identification Pro (TargetPro), a disease-specific model spanning 38 diseases across oncology, metabolic, immune, fibrotic, and neurological categories. TargetPro shows strong predictive performance for clinical-stage targets and reveals disease-specific patterns, underscoring the need for tailored target detection models. We next created Target Identification Benchmark (TargetBench 1.0) to assess target identification systems, including large language models, based on their ability to recover established targets and find high-quality novel candidates. This integrated approach offers a streamlined strategy to evaluate target discovery models, ultimately improving drug development efficiency.

  PublisherOA PDFDOI

• Abstract 6807: Mitochondrial genome alterations as early drivers of lung adenocarcinoma evolution

  Cancer Research · 2026-04-03

  article

  Abstract Lung adenocarcinoma (LUAD) is thought to arise gradually, beginning as atypical adenomatous hyperplasia (AAH) and advancing through adenocarcinoma in situ (AIS) toward minimally invasive adenocarcinoma (MIA). Although this progression is well-described, the biological events that trigger and sustain these early transitions remain unclear Mitochondrial DNA (mtDNA) is present in many copies, lacks histone protection, and is continually exposed to oxidative stress, making it more prone to mutation than nuclear DNA. Consequently, alterations in the mitochondrial genome may provide an opportunity to identify and classify potentially aggressive preneoplastic lesions long before they reach an invasive stage. We analyzed 109 lesions from 37 non-small-cell lung cancer (NSCLC) patients, encompassing the continuum of AAH, AIS, MIA, and ACA. Whole mitochondrial genome (16.5kb) was sequenced from formalin fixed paraffin embedded (FFPE) tumor and matched normal samples using an amplicon-based Illumina NextSeq approach. Variant detection was performed with a custom pipeline (BWA, SAMtools, GATK Mutect2). We observed that somatic mtDNA alterations arise very early in the neoplastic sequence, with AAH lesions carrying numerous changes across the non-coding tRNA, rRNA, and D-loop regions, as well as repeated nonsynonymous variants in OXPHOS coding genes such as MT-ND5, MT-ATP8, and MT-CYB. Several of these mutations appeared in lesions located in different areas of the same lung, pointing to an early clonal expansion rather than isolated, random events. As lesions advanced into AIS and then MIA, the number of mitochondrial alterations increased steadily. MIA, in particular, showed the greatest accumulation of non-coding changes, and coding variants such as A8860G (ATP6) were frequent across most cases, suggesting that these alterations are not simply incidental. The expression data followed a similar trend. Specifically, in AAH and AIS, numerous mtDNA encoded OXPHOS genes showed higher expression, reflecting an early compensatory response to emerging dysfunction. By the time lesions reached the MIA stage, this pattern became less consistent, with greater variability among patient samples. Once the disease progressed to fully invasive adenocarcinoma, mitochondrial transcripts dropped broadly, fitting with at least partial metabolic shift toward glycolysis known to accompany invasion. Taken together, these patterns point toward early mtDNA instability and evolving mitochondrial transcription as features that accompany and possibly shape the stepwise development of LUAD. Acknowledgements: We extend our special thanks to patients and clinical teams at Johns Hopkins, supported by NCI EDRN grant U01CA271896 . We also acknowledge ANID for providing scholarship funding (21222011, 242230375, 752230204) and Swiss Cancer League grant (BIL KLS-3649-02-2015). Citation Format: Alvaro Gutierrez, Ido Sloma, Adrian Daniel Schubert, Karthik Suresh, Mohammad Obaidul Hoque, Carmen Gloria Ili, Evgeny Izumchenko, Santanu Dasgupta, David Sidransky. Mitochondrial genome alterations as early drivers of lung adenocarcinoma evolution [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2026; Part 1 (Regular Abstracts); 2026 Apr 17-22; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2026;86(7 Suppl):Abstract nr 6807.

  PublisherDOI

• Evaluating Peptide Binding and Functional Inhibition of PDCD10 in SCC-1 Cancer Cells

  Knowledge@UChicago (University of Chicago) · 2026-01-01

  otherOpen access

  Programmed Cell Death 10 (PDCD10) is a signaling protein involved in pathways regulating cancer cell proliferation and survival and has emerged as a potential therapeutic target in oral cavity squamous cell carcinoma (OCSCC). This study aimed to determine whether a candidate PDCD10-inhibiting peptide, peptide 3 (P3), can directly bind PDCD10 in SCC-1 protein lysates and whether this binding leads to functional inhibition of PDCD10, measured through changes in cell proliferation. SCC-1 wild-type cancer cells were cultured and harvested. Protein lysates were prepared using native and denaturing (RIPA) lysis buffers supplemented with protease and phosphatase inhibitors, and protein concentrations were measured using a BCA assay. Equal amounts of protein (75 µg) were incubated overnight at 4°C with PDCD10-inhibiting peptides. Peptide–protein complexes were captured using Strep-TactinXT high-capacity resin beads through an immunoprecipitation (IP) protocol. After washing to remove unbound proteins, the bound complexes were eluted and analyzed by Western blot. A PDCD10-specific antibody was used to detect PDCD10 in the elution fractions. To evaluate functional effects, SCC-1 cells were treated with both peptides, and cell proliferation was compared with that of untreated controls. Immunoprecipitation results demonstrated that P3 showed strong and reproducible binding to PDCD10, since PDCD10 was detected in the elution fractions of P3 after immunoprecipitation. In proliferation assays, P3-treated SCC-1 cells displayed reduced growth relative to DMSO controls, while an additional candidate peptide, peptide 1 (P1), showed minimal inhibitory effect. These findings identify P3 as the lead PDCD10-binding candidate and support further investigation of peptide-mediated PDCD10 inhibition as a therapeutic strategy in OCSCC.

  PublisherOA PDFDOI

• Integrated analysis of stemness-associated immune modulatory circuits in squamous cell carcinomas

  bioRxiv (Cold Spring Harbor Laboratory) · 2026-04-06

  articleOpen access

  ABSTRACT Emerging evidence indicates that a subset of cancer cells enriched for stemness-related gene signatures possess distinct immunomodulatory capacities, enabling these tumor-initiating stem cells (tSCs) to more effectively evade or resist anti-tumor immunity. Despite these advances, the tSC-specific molecular circuits orchestrating their specialized immune privilege program are not well defined. Here, in squamous cell carcinomas of the skin and oral cavity, we comprehensively delineate the unique immune-evasive properties of tSCs and dissect the transcriptional regulation shaping their immunomodulatory programs. By integrating transcriptome profiling, chromatin landscape mapping, genetic perturbation, and single-cell RNA sequencing, we found that the tSC-specific immune program is broadly governed by SOX2, a stemness-associated transcription factor. We demonstrate that SOX2 enables tSCs to sustain immature tumor-associated neutrophils (TANs) and subsequently trigger these myeloid cells to foster the development of tumor-associated macrophages (TAMs). This SOX2-directed tSC-TAN-TAM axis establishes a localized immunosuppressive niche for protecting tSC. SIGNIFICANCE Here, we uncover SOX2 as a master regulator that orchestrates conserved immune modulatory circuits in tSCs to sustain pro-tumor myeloid cell states. These findings place tSCs at the apex of immune landscape remodeling, asserting a central role of stemness-associated program in organizing the immunosuppressive tumor microenvironment.

  PublisherOA PDFDOI

• Tumor-initiating stem cells fine-tune the plasticity of neutrophils to sculpt a protective niche

  Cancer Cell · 2025-12-04 · 2 citations

  articleOpen access

  ) signaling in TANs, which can disrupt the interferon response and prevent the interferon-induced anti-tumor functions in TANs. By fine-tuning the plasticity of neutrophils, tSCs shape neutrophil heterogeneity and sculpt a protective micro-niche to survive from immunotherapy and drive cancer relapse.

  PublisherDOI

• Early Dynamics of Circulating Tumor HPV-DNA with Neoadjuvant Chemotherapy and Response-Adapted De-escalation in Human Papillomavirus–Associated Oropharyngeal Cancer

  Clinical Cancer Research · 2025-05-27 · 7 citations

  articleOpen access

  PURPOSE: Human papillomavirus-associated (HPV+) oropharyngeal carcinoma is associated with excellent survival, yet treatment drives substantial toxicity. Improved biomarkers are needed to select patients for de-escalated treatment. Circulating tumor HPV DNA (ctHPV-DNA) represents a promising noninvasive biomarker to gauge treatment response and surveil for disease recurrence. PATIENTS AND METHODS: A prospective biomarker clinical trial of response-stratified de-escalation was conducted. Eligible patients with non-metastatic HPV+ oropharyngeal carcinoma received neoadjuvant chemotherapy, followed by risk/response-stratified de-escalation with transoral robotic surgery, de-escalated radiation with or without chemotherapy to 50 Gy, or standard chemoradiation to 70 Gy. Deep response (≥50% tumor shrinkage per RECIST v1.1) qualified patients for de-escalation. ctHPV-DNA was measured using HPV-SEQ in plasma at baseline, during neoadjuvant chemotherapy, radiation, and following treatment. The primary endpoint was the correlation of ctHPV-DNA kinetics and radiographic response. RESULTS: Forty-six eligible patients were enrolled, and 488 ctHPV-DNA samples were analyzed (median 11 per patient). The median follow-up was 30 months, and five recurrences were observed (10.9%). Baseline ctHPV-DNA was detected in 95% of evaluable patients. Rapid early ctHPV-DNA clearance after one cycle of neoadjuvant therapy (≥95% reduction) predicted radiographic deep response (P = 0.04). Detection of ctHPV-DNA 3 months or later after treatment was associated with worse progression-free and overall survival (P < 0.001). Sensitivity, specificity, and positive and negative predictive values of longitudinal ctHPV-DNA were 100%. The longest lead time from positive ctHPV-DNA to detection of recurrent disease was 25 months. CONCLUSIONS: Rapid early clearance of ctHPV-DNA during neoadjuvant therapy demonstrates utility in predicting response to treatment. Detectable ctHPV-DNA following treatment is predictive of both disease recurrence and worse survival.

  PublisherOA PDFDOI

• Building digital histology models of transcriptional tumor programs with generative deep learning for pathology-based precision medicine

  Genome Medicine · 2025-08-07 · 2 citations

  articleOpen access

  BACKGROUND: Precision oncology depends on identifying the biological vulnerabilities of a tumor. Molecular assays, like transcriptomics, provide an information-rich view of the tumor that can be leveraged to inform therapeutic selection. However, the costs of such assays can be prohibitive for clinical translation at scale. Histology-based imaging remains a predominant means of diagnosis that is widely accessible. To more broadly leverage limited molecular datasets, models have been trained to use histology to infer the expression of individual genes or pathways, with varying levels of accuracy and explainability. METHODS: Our approach detects expression of transcriptional programs from tumor histology and interprets the image features supporting program detection. Specifically, we used RNA-seq data from squamous cell carcinoma (SCC) patients to infer cohesive expression patterns of multiple genes. Then, we used deep learning techniques to train a computational model to predict the activity levels of the transcriptional programs directly from histology images. We exploited that predictive capability to generate synthetic digital models of the cellular histology of each transcriptional program, using generative adversarial networks to isolate image features supporting specific transcriptional predictions and pathologist review to interpret the images. RESULTS: Applying our histologically integrated latent space analysis to SCCs revealed sets of genes associated with both pathologist-interpretable image features and clinically relevant processes, including immune response, collagen remodeling, and fibrosis, going beyond predictions of individual molecular features. CONCLUSIONS: Our results demonstrate an approach for discovering clinically interpretable histological features that indicate molecular, potentially treatment-informing, biological processes. These features are detectable in widely available histology slides, allowing a standard microscope to deliver complex, patient-specific molecular information.

  PublisherOA PDFDOI

• Supplemental Table 3 from Early Dynamics of Circulating Tumor HPV-DNA with Neoadjuvant Chemotherapy and Response-Adapted De-escalation in Human Papillomavirus–Associated Oropharyngeal Cancer

  2025-08-01

  preprintOpen access

  &lt;p&gt;Supplemental Table 3. Discordance between deep radiographic response (&gt;50% tumor shrinkage per RECIST v1.1) and rapid ctHPV-DNA clearance (≥95% reduction) after 1 cycle.&lt;/p&gt;

  PublisherDOI

Recent grants

• PDCD10 as a novel driver for head and neck squamous cell carcinoma development

  NIH · $451k · 2023–2026

• Delineating chromatin-related gene expression signatures as a function of HNSCC progression

  NIH · $2.6M · 2020–2025

Frequent coauthors

• David Sidransky

  Johns Hopkins University

  236 shared

• Mohammad Obaidul Hoque

  Johns Hopkins Medicine

  117 shared

• Mariana Brait

  Johns Hopkins University

  112 shared

• Nishant Agrawal

  University of Chicago

  82 shared

• Elana J. Fertig

  Sidney Kimmel Comprehensive Cancer Center

  74 shared

• Alex Zhavoronkov

  72 shared

• Wayne M. Koch

  Johns Hopkins University

  71 shared

• Atul Bedi

  56 shared

Labs

• University of Chicago Department of Medicine-Hematology and OncologyPI

Education

• Other, Clinical Biochemistry and Pharmacology

  Ben-Gurion University, Dept of Clinical Biochemistry and Pharmacology

  2005

• Ph.D., Cancer Research

  Ben-Gurion University

  2010

• Other, Cancer Research

  University of Florida, Department of Biochemistry and Molecular Biology

  2012

• Other, Cancer Research

  Johns Hopkins University

  2016

Awards & honors

• Cancer Research Foundation (CRF) Breakthrough Board Team Sci…
• UCCCC Program Pilot Project Grant (2024)
• UCCCC Cancer Immunotherapy Team Science Award (2024)
• Institute for Translational Medicine (ITM) Pilot Award (2023…
• Cancer Research Foundation Breakthrough Award (2023)