NCI Data Jamboree (Project Abstract Submission)

Filter submissions
64 submissions
# Created User IP address First Name Middle Initial Last Name Degree(s) Position/Title/Career Status Organization Organization Address Email List of Additional Authors Abstract Category Abstract Keywords Abstract Title Abstract Operations
24 Tue, 07/21/2026 - 01:46 Anonymous 10.208.24.20 Natalie M Tenge MPH Early-Career Public Health Professional/Researcher Independent (Recent University of Wisconsin-Milwaukee MPH Graduate) Milwaukee, WI nmtenge01@gmail.com
  • First Name: N/A
    Last Name: N/A
    Affiliation: N/A
 Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Project Seeker I recently graduated from the University of Wisconsin-Milwaukee with my Master of Public Health (MPH) degree in the Environmental Health Sciences track. I’ve taken several applied epidemiology courses, including environmental and cancer epidemiology, as well as courses that have allowed me to build additional competency in quantitative data analysis and statistical software utilization (SAS), including biostatistics, environmental risk assessment, and my own final capstone project, which has notably been accepted for poster presentation at the 2026 American Public Health Association’s (APHA) Annual Meeting and Expo. This public health education has reinforced both my interest in research and appreciation for the population health perspective that epidemiologists employ to solve public health problems. Thus, I intend to further my education through an epidemiology doctoral program in the future, and I’m eager to continue expanding my public health knowledge and building new skills, especially as they relate to epidemiologic research methods, in the meantime. Participating in this data jamboree will, therefore, provide me with meaningful practical experience working with real-world data while likely also improving my awareness of the various data sources available to be analyzed and used to inform public health decision-making.
23 Mon, 07/20/2026 - 22:49 Anonymous 10.208.24.20 Karthikeyan Raman Ph.D Postdoctoral Research Associate Northeastern University Boston k.raman@northeastern.edu Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Cancer Immunology, Transcriptomics, Multi-omics, Immunotherapy, Data Integration. Bridging Experimental Cancer Immunology, Epigenomics, and Multi-omics Data Analysis I am a Senior Research Associate in the Konry Laboratory at Northeastern University with a background in cancer immunology, epigenomics, and functional genomics. My current research integrates functional immune-cell assays, transcriptomic profiling, and multi-omics approaches to investigate the molecular mechanisms governing natural killer (NK) cell and T-cell responses in cancer immunotherapy.
My experience spans experimental genomics, epigenomics, and chromatin biology, including next-generation sequencing library preparation, bulk RNA-seq analysis, whole-genome sequencing, gene-expression and pathway analysis, chromatin profiling using NEED-seq, NicE-seq, CUT&RUN, and ChIP-seq, DNA methylation profiling, chromatin-state analysis, and biological interpretation of multi-omic datasets. I also have experience with molecular profiling of cancer tissues, including FFPE and laser-capture microdissected specimens from multiple cancer types, as well as mammalian cell culture, flow cytometry, fluorescence and confocal microscopy, molecular biology, and immune-cell functional and cytotoxicity assays.
I am interested in joining interdisciplinary projects that use statistical, computational, and informatics approaches to analyze and integrate large-scale cancer datasets, particularly transcriptomic, epigenomic, single-cell, spatial, imaging, and proteomic data. The NCI Data Jamboree provides an opportunity to contribute my expertise in experimental cancer biology, epigenomics, and functional genomics while strengthening my skills in public cancer data resources, multimodal data integration, reproducible computational workflows, and cloud-based analysis.
Through this experience, I hope to strengthen my ability to translate complex cancer datasets into biologically meaningful insights relevant to tumor–immune interactions and immunotherapy, expand my computational expertise, and establish productive interdisciplinary collaborations for future translational cancer research.
22 Mon, 07/20/2026 - 21:57 Anonymous 10.208.24.20 Jacob Krive Ph.D. MS MBA FAMIA Clinical Associate Professor University of Illinois at Chicago Chicago krive@uic.edu Building study cohorts (e.g., with visualization capabilities) cancer survivorship, cardiotoxicity, metabolic toxicity, CTR-CVT, cardio-oncology National real-world cancer regimens toxicity database and decision tools to support cancer survivorship Advances in oncology care have created a large patient population of cancer survivors. Survivorship is a rising challenge due to complexity and prolonged side-effects of the oncology regimens and lack of attention to toxicities frequently discovered in widespread community medical practice. These complexities produce complications observed in conventional chemotherapies and modern therapeutic regimens. Cardio-oncology fills the care gap in treating toxicities related to cardiovascular side effects of the oncology regimens, aimed at identification and management of the short- and long-term cancer therapy related cardiovascular toxicities (CTR-CVT). There are other toxicities, such as metabolic toxicity, affecting cancer survivorship.

Survivorship care suffers from a lack of standards, quality indicators, focus on toxicity during and after clinical trials, and comprehensive ways to identify and clinically manage patients at risk. Each medical practice is small to build true evidence of toxicity. I propose a partnership to utilize and extend the existing data sources to (1) store and analyze real-world toxicity, (2) translate analyses into community medical practice by building decision support tools aiding clinicians in the process of crafting the safest oncology care plans, and (3) support development of the cardio-oncology quality standards based on real data.

I would like to build a multi-institutional team and require additional members. Abeer Mohamed is UIC endocrinologist committed to the project. I need data engineering and machine learning expertise, specific language and tools agnostic – and welcome clinical and basic science researchers. I need access to large oncology datasets with discrete and (optionally) unstructured clinical and genomic data with at least diagnoses, procedures, labs, and medications useful for tracking toxicity. The aim of this initiative is unleashing the power of data to tell an oncology toxicity story while tracking real-world patient survivorship journeys to improve the quality of cancer survivorship care – immediately translatable into community practice.
21 Thu, 07/16/2026 - 12:45 Anonymous 10.208.24.67 Christina Sisti DPS, MPH, MS Research Ethics Patient Advocate Advocates for Collaborative Education Santa Clara christina.sisti@advocatecollaborative.org
  • First Name: Stacey
    Last Name: Tiniavov
    Post-nominal letters: MPH
    Affiliation: Advocates for Collaborative Education
 Developing tutorials, workbooks, infographics, or creative use of data for educational and engagement purposes ethics, patient, healthcare, clinical trials Comprehensive Access to Clinical Trials For Rare and Hyperaggressive Cancers Rare and hyperaggressive cancers are treated with the accepted standard of care. However, many of these treatments are known to have little to no effect on stopping, maintaining, or curing these cancers. Decentralizing clinical trials will increase access to potentially groundbreaking treatments for those in vulnerable populations.
Often, those with rare or hyperaggressive cancers are faced with limited options and statistically are confronted with a high morbidity rate. The goal of this project is to change how access to clinical trials is determined. To achieve this, it is vital to consider the statistics surrounding rare or hyper-aggressive cancers, the number of clinical trials available, and those trials that offer compassionate use.
Traditionally, clinical trials are administered at research, comprehensive cancer, or university centers. However, many cannot access this care due to a lack of transportation, childcare, and the ability to take time off from work. The alternative to the lack of access is to create a decentralized clinical trial system, allowing patients, regardless of their socio-economic situation, to access care at the center that offers the best possible outcome for their type of cancer. By doing so, not only is access increased, but so is equal opportunity to care. Equal access is a key component of the ethical considerations surrounding health care.
The goal is to discover how pairing clinical trials in once-inaccessible locations will increase participation in clinical trials as well as the use of compassionate care.
20 Thu, 07/16/2026 - 11:53 Anonymous 10.208.24.67 Jenny Ozga Ph.D. Senior Research Associate Westat, Inc. Bethesda, MD jennyozga@westat.com Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Jenny Ozga, PhD Project Abstract Submission I am a public health researcher with over 10 years of experience conducting behavioral epidemiology and tobacco regulatory science research using large-scale population health datasets. My work focuses on leveraging nationally representative surveys and longitudinal cohorts to better understand behavioral risk factors, disparities, and patterns of health-related behaviors. I have extensive experience analyzing data from NCI-supported studies, including the Population Assessment of Tobacco and Health (PATH) Study and the National Health Interview Survey (NHIS). My research has involved survey-weighted methods, regression modeling, and integration of multiple data domains, including behavioral measures, social and environmental determinants of health, and biomarker data. Through this work, I have developed expertise in addressing common challenges associated with complex health datasets, including missing data and developing documentation to support reproducible research.

I am interested in participating in the NCI Data Jamboree because it provides an opportunity to collaborate with researchers from diverse disciplines and expand my understanding of emerging approaches in biomedical data science. My current work relies heavily on large survey datasets, and I am interested in learning how artificial intelligence and machine learning approaches can complement traditional epidemiologic methods to address increasingly complex research questions. I am particularly interested in approaches that integrate multimodal data, including behavioral, social, environmental, and biological measures.

Through participation in the jamboree, I hope to develop a stronger understanding of how AI/ML approaches can be applied to epidemiologic research questions and how diverse health data sources can be integrated to generate new insights. I hope to contribute my experience working with complex longitudinal and nationally representative datasets while gaining exposure to methods that extend beyond traditional analytic approaches. Ultimately, I hope to build expertise and establish new interdisciplinary collaborations that allow me to bridge behavioral epidemiology and emerging data science approaches.
19 Wed, 07/15/2026 - 12:10 Anonymous 10.208.24.175 Hongyi Liu Ph.D. Johns Hopkins University Baltimore hliu173@jh.edu
  • First Name: Yingwei
    Last Name: Hu
    Affiliation: Johns Hopkins University
  • First Name: Mamie
    Last Name: Lih
    Affiliation: Johns Hopkins University
  • First Name: Effram
    Last Name: Wei
    Affiliation: Johns Hopkins University
  • First Name: Liyuan
    Last Name: Jiao
    Affiliation: Johns Hopkins University
  • First Name: Lijun
    Last Name: Chen
    Affiliation: Johns Hopkins University
  • First Name: Yuefan
    Last Name: Wang
    Affiliation: Johns Hopkins University
  • First Name: Xiangning
    Last Name: Li
    Affiliation: Johns Hopkins University
  • First Name: Zhenyu
    Last Name: Sun
    Affiliation: Johns Hopkins University
  • First Name: Yuanyu
    Last Name: Huang
    Affiliation: Johns Hopkins University
  • First Name: Yuanwei
    Last Name: Xu
    Affiliation: Johns Hopkins University
  • First Name: Hui
    Last Name: Zhang
    Affiliation: Johns Hopkins University
 Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Prostate cancer, proteomics, glycoproteomics, phosphoproteomics, crosstalk Unlocks the Biological Insights into Aggressive Prostate Cancer Using Multi-omic Approach Scientific Questions: This project integrates large-scale multi-omics to address: (1) how multi-layer genomics, proteomics (TMT/DIA), and post-translational modifications (PTMs) correlate globally; (2) how to digitally deconvolve tumor microenvironment (TME) cell fractions; and (3) how to map the causal directional regulatory cascades between cell-surface glycosylation and intracellular phosphorylation to identify therapeutic targets.
Community Significance: Prostate cancer has profound molecular heterogeneity. Providing a reproducible, open-source computational framework for integrating mass-spectrometry-based proteomics and dual-PTM networks allows the broader cancer research community to uncover targetable biological pathways and patient subclusters obscured in genomic-only studies.
Datasets & Tools: We leverage clinical cohorts (244 samples) with comprehensive transcriptomics, global proteomics (TMT/DIA), and deeply enriched PTMs (phospho, intact glycopeptide, ubiquitin, p-Tyr, acetyl). Key informatics tools include xCell/CIBERSORTx for cellular deconvolution, Random Forest and Lasso-logistic regression for tumor grading classifiers (NAT vs. Low/High Gleason grades), human interactome mapping for protein-protein interaction (PPI) topology, and Bayesian modeling for causal dual-PTM network inference.
18 Wed, 07/15/2026 - 02:55 Anonymous 10.208.24.175 ABDUL KAREEM SHAIK PHARM.D GLENFIELD MALLA REDDY BRAIN HEART HOSPITAL HYDERABAD abdulkareemgmbhh@gmail.com Building study cohorts (e.g., with visualization capabilities) clinical pharmacy, cohort building, stroke, pharmacovigilance, real-world evidence Clinical Pharmacist Seeking Collaboration on Cohort Building and Visualization for Neuro-Cardiac Real-World Data I am a Clinical Pharmacist at Glenfield Malla Reddy Brain Heart Hospital, Hyderabad, a tertiary neuro-cardiac referral centre with a high volume of stroke, acute coronary syndrome, and critical care admissions. My routine work involves medication reconciliation, therapeutic drug monitoring, adverse drug reaction (ADR) documentation, and antimicrobial stewardship, which regularly generates rich longitudinal patient-level data that remains under-utilised for research.
I am particularly interested in projects that build structured study cohorts from real-world hospital data and layer intuitive visualization on top, so that clinicians can explore treatment patterns, ADR signals, and outcomes interactively. I want to contribute a frontline pharmacy perspective on data quality, medication coding, and clinically meaningful variables, while learning cohort definition workflows, common data models, and dashboarding tools from the wider team.
My current skills include Excel-based data curation, structured ADR reporting, and introductory R; I am comfortable working with de-identified clinical datasets and standard drug/disease terminologies. I do not yet have a ready-to-go team and am seeking to join an existing project.
Through the 3-day jamboree, I hope to gain hands-on experience in end-to-end cohort construction and visualization, build collaborations with clinicians, data scientists, and bioinformaticians, and return equipped to lead pharmacy-driven cohort and pharmacovigilance research at my institution including a planned ADR surveillance and thrombolysis outcomes cohort at Glenfield Malla Reddy Brain Heart Hospital.
17 Tue, 07/14/2026 - 17:19 Anonymous 10.208.24.175 SUGY CHOI PhD Assistant Professor New York University Grossman School of Medicine New York SUGY.CHOI@NYULANGONE.ORG
  • First Name: Jae man
    Last Name: Park
    Post-nominal letters: PhD
    Affiliation: San Diego State University
  • First Name: Xiao
    Last Name: Li
    Post-nominal letters: PhD
    Affiliation: University of Nebraska Kearney
 Developing, refining, or validating tools, methods, algorithms, and pipelines Behavioral-health, substance use disorder, prevention, navigation, public data atlas “No Wrong Door” for cancer prevention: A public-data atlas of screening gaps and care-infrastructure mismatch We plan to develop a public data atlas identifying U.S. counties where tobacco- and alcohol-related cancer prevention needs and cancer screening gaps intersect with behavioral health and substance use disorder (SUD) treatment availability. By incorporating the availability of primary care, community health centers, and hospitals, the atlas will identify counties where behavioral health and treatment settings could serve as complementary access points for cancer prevention referral and navigation, as well as counties where broader health system capacity-building or alternative delivery strategies may be needed. A secondary objective is to create a simulation-ready framework by defining county typologies, target populations, intervention scenarios, and parameter templates to support future budget-impact and return-on-investment analyses of cancer screening interventions. The project will integrate multiple publicly available data sources, including CDC PLACES, SAMHSA National Directories of Drug and Alcohol Use Treatment Facilities and Mental Health Treatment Facilities, HRSA Health Center Program data, CMS Hospital General Information, County Health Rankings, Census TIGER/Line geographic files, the National Survey on Drug Use and Health (NSDUH), and the Behavioral Risk Factor Surveillance System (BRFSS). CDC PLACES will provide county-level measures of smoking, binge drinking, colorectal cancer screening, mammography, uninsured burden, and preventive care access. SAMHSA directories will characterize behavioral health and SUD treatment infrastructure, while HRSA, CMS, and County Health Rankings will capture broader healthcare capacity. NSDUH and BRFSS will provide individual-level context on substance use, cancer history, and screening behaviors. During the three-day Jamboree, our multidisciplinary team, Dr. Choi, Dr. Park, and Dr. Li, will harmonize data across sources, standardize county-level geography, develop care-context typologies, and produce visualization-ready outputs. Deliverables will include an integrated county-level analytic dataset, reproducible documentation, static and interactive maps identifying priority counties, tables highlighting potential implementation strategies, and a simulation roadmap with parameter templates to support future colorectal cancer screening budget-impact and return-on-investment modeling.
16 Tue, 07/14/2026 - 16:51 Anonymous 10.208.28.69 Jing Jin PhD, MPH Assistant Professor University of Arkansas for Medical Sciences Little Rock jjin@uams.edu
  • First Name: Jing
    Last Name: Jin
    Affiliation: University of Arkansas for Medical Sciences
 Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Integrative Secondary Analysis of Existing Data to Investigate Cancer Risk and Related Outcomes I am a project seeker and an early-stage researcher specializing in the integration of genomic datasets and the analysis of cancer-related multi-omics data. Through participating in the Jamboree, I hope to collaborate with researchers from diverse disciplinary backgrounds, become more familiar with publicly available cancer-related datasets, and gain inspiration from leading investigators in the field. I am eager to contribute to a team science project by providing expertise in biostatistics, data integration, and multi-omics analysis. I also hope that the collaborative work will help generate ideas and preliminary results that can support future grant proposal development.
15 Tue, 07/14/2026 - 11:37 Anonymous 10.208.24.175 Yuanyu Huang Ph.D. Postdoc fellow Johns Hopkins University Baltimore yhuan295@jh.edu
  • First Name: Lijun
    Last Name: Chen
    Affiliation: Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
  • First Name: Peter
    Last Name: Wu
    Affiliation: Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., Frederick, Maryland 21702, United States
  • First Name: Poorva
    Last Name: Juneja
    Affiliation: Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., Frederick, Maryland 21702, United States
  • First Name: Li
    Last Name: Chen
    Affiliation: Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., Frederick, Maryland 21702, United States
  • First Name: Yvonne
    Last Name: Evrard
    Affiliation: Frederick National Laboratory for Cancer Research, Leidos Biomedical Research, Inc., Frederick, Maryland 21702, United States
  • First Name: Liyuan
    Last Name: Jiao
    Affiliation: Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
  • First Name: Yingwei
    Last Name: Hu
    Affiliation: Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
  • First Name: Xu
    Last Name: Zhang
    Affiliation: National Cancer Institute, National Institutes of Health, Bethesda, Maryland 20892, United States
  • First Name: James
    Last Name: Doroshow
    Affiliation: National Cancer Institute, National Institutes of Health, Bethesda, Maryland 20892, United States
  • First Name: Ratna
    Last Name: Thangudu
    Affiliation: Inner City Fund (ICF) International, Inc., Rockville, Maryland 20850, United States
  • First Name: Alexander
    Last Name: Pilozzi
    Affiliation: Inner City Fund (ICF) International, Inc., Rockville, Maryland 20850, United States
  • First Name: Hui
    Last Name: Zhang
    Affiliation: Department of Pathology, Johns Hopkins University School of Medicine, Baltimore, Maryland 21205, United States
 Enhancing data interoperability (e.g., data harmonization, data federation) mass spectrometry, cancer proteins, proteomics database, missing proteins, peptide identification Enhancing the Utility and AI-Readiness of MS-Detected Cancer Proteins through a Provenance-Aware MSCP Data Resource Mass spectrometry-based cancer proteomics datasets are widely available in public repositories, but protein evidence is often scattered across different studies, cancer types, model systems, acquisition modes, and database versions. This makes it difficult for researchers to quickly determine whether a protein has been detected by mass spectrometry in a specific cancer context or to compare protein evidence across datasets.
To address this gap, we developed the Mass Spectrometric Detected Cancer Proteins resource (MSCP), a cancer-focused proteomics database that integrates protein identifications from 27 public cancer proteomics sources, including human tumor cohorts, cancer cell lines, and patient-derived xenograft models. The current MSCP release contains 15,964 UniProtKB-Swiss-Prot-aligned human proteins and preserves source-level information, including dataset, cancer/model type, and acquisition mode.
This Jamboree project will extend MSCP into a more interactive and reusable data utility framework. During the 3-day event, the team will develop workflows to query, filter, visualize, and score MSCP protein evidence. Planned activities include generating cohort- and model-specific protein views, defining recurrence-based confidence tiers, comparing DDA and DIA evidence, visualizing protein detection across cancer types, and adding AI-readiness annotations based on identifier harmonization, provenance, reproducibility, and validation evidence.
The primary datatype is mass spectrometry-based proteomics. Datasets will include the MSCP integrated protein evidence table, source-resolved annotations, NCI Proteomic Data Commons datasets, ProteomeXchange/PRIDE datasets, UniProtKB, neXtProt, and Human Protein Atlas annotations. Expected outputs include public GitHub notebooks, harmonized export tables, protein evidence confidence scores, example visualizations, and documentation for community reuse.
This project will help the cancer research community transform dispersed proteomics evidence into an interpretable, provenance-aware, and analysis-ready resource for biomarker discovery, assay development, and proteogenomic interpretation.
14 Mon, 07/13/2026 - 07:04 Anonymous 10.208.28.212 Ayman Nadeem MBBS Surgery Research Fellow Glenfield Mallareddy Brain Heart Hospital Hyderabad maazayman@gmail.com
  • First Name: -
    Last Name: -
    Post-nominal letters: -
    Affiliation: -
 Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Project Seeker Experience and expertise
I am a Surgery Research Fellow at Glenfield Mallareddy Brain Heart Hospital, Hyderabad, focused on systematic reviews and meta-analysis in surgical oncology. My current work includes a systematic review comparing robotic-assisted and minimally invasive esophagectomy, involving ROBINS-I and RoB 2 assessment, GRADE evaluation, and pooled estimation across mixed RCT and observational evidence. I do not have formal bioinformatics training and see the jamboree as an opportunity to build that layer of skill.
Why I want to participate
Most of my work sits at the synthesis end of the evidence pipeline, evaluating what has already been generated from primary data. I want to move upstream and understand how large cancer datasets are actually accessed, harmonized, integrated, and analyzed, because that shapes the quality of everything downstream. Working alongside a senior investigator on a concrete problem using real NCI data resources is a faster way to build that understanding than reading about it in isolation.
What I hope to achieve
Hands-on familiarity with NCI data resources and cloud workspaces, including the credentialing and setup steps usually invisible from the outside. Practical exposure to statistical and informatics tools for integrating cancer data, so I can bring these methods back into my own surgical outcomes and evidence synthesis work. And interdisciplinary connections that ideally sustain into future joint work.
13 Fri, 07/10/2026 - 12:59 Anonymous 10.208.28.27 Joshua Shapiro Ph.D. Senior Data Scientist Alex's Lemonade Stand Foundation Wynnewood josh.shapiro@ccdatalab.org Developing, refining, or validating tools, methods, algorithms, and pipelines Project Seeker As a data scientist in the Childhood Cancer Data Lab of Alex's Lemonade Stand Foundation, I work on a variety of projects related to pediatric cancer. Most of my recent work has been with transcriptomic data, including single-cell RNA sequencing, but I have experience analysing other genomic and epigenomic data as well, and I have recently begun work with analysis of Cell Painting data. My work emphasizes reproducible analyses, mainly using R/Bioconductor and Python, with pipeline development in Nextflow and Snakemake.

My goals for the jamboree are largely about forming and strengthening connections across the cancer data community, with specific focus on pediatric cancer. I hope to meet potential collaborators, as well as to explore problems outside my usual scope of work. In general, I am hoping to gain a better sense of the challenges that researchers are facing in data analysis, how AI and machine learning are being used to address those challenges, and where I can contribute my own skills most effectively.
12 Wed, 07/08/2026 - 10:26 Anonymous 10.208.28.146 Theodore L Reed Ph.D. Postdoctoral Fellow National Cancer Institute, Center for Cancer Research Frederick reedthl@nih.gov Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Project Seeker Abstract I am a second year postdoctoral fellow in the Cancer Innovation Laboratory in the Center for Cancer Research of the NCI with experience coding in both R and Linux. I have certifications and have completed coursework in machine learning algorithms and single cell RNA-sequencing analysis, and have performed the following types of data analyses on published and pre-publication data: microbiome 16s RNA-seq, bulk RNA-seq, single cell RNA-seq, additional statistical analyses. Participating in the jamboree will allow me to collaborate and network with other people working with computational approaches to cancer research, learn from those who have more experience and skill than me, and learn more about how people have made careers out of computational work so that I can take a similar path. From this jamboree, I hope to achieve connections with people in this region that will help me sharpen my computational skills and expand my community of computaionalists that can be used for troubleshooting, support, and idea generation, thus improving our collective approach and implementation of computational biology in the cancer field.
11 Tue, 07/07/2026 - 12:01 Anonymous 10.208.28.70 leroy williams MD physician HHS SILVER SPRING CTMRI3T@YAHOO.COM
  • First Name: NOT
    Last Name: APPICABLE
    Affiliation: NONE
 Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data STATISTICAL AND COMPUTATIONAL TO ANALYZE DATA WOULD LIKE TO JOIN STATISTICAL AND COMPUTATIONAL GROUP TO ANALYZE DATA STATISTICAL AND COMPUTATIONAL GROUP TO ANALYZE DATA
10 Tue, 07/07/2026 - 09:48 Anonymous 10.208.24.21 Morolake Okanlawon BSc. PhD Student George Mason University Fairfax mokanlaw@gmu.edu Developing, refining, or validating tools, methods, algorithms, and pipelines machine learning, artificial intelligence, reproducible pipelines, model validation, cancer data integration Developing and Validating Machine Learning and AI Pipelines for Integrating and Analyzing Cancer Research Data Reliable analysis of cancer research data depends not only on applying machine learning and artificial intelligence methods but on the tools and pipelines that make those methods reproducible and reusable. Building on prior experience employing statistical and computational methods to analyze data in my own research, this project focuses on developing, refining, and validating machine learning and AI pipelines for integrating and analyzing biomedical and cancer datasets. Proposed work includes constructing modular pipelines for data preprocessing, model training, and evaluation, along with validation procedures to assess reproducibility, robustness, and interpretability of AI models. Particular attention will be given to designing components that can be reused across clinical, genomic, or imaging datasets rather than tailored to a single analysis. As a PhD student with a background in Bioinformatics and Computational Biology, I aim to extend my analytical foundation toward the development of machine learning and AI tools within a collaborative team. The anticipated outcome is a set of validated, reusable pipeline components that support reproducible machine learning and AI workflows for cancer research.
9 Thu, 07/02/2026 - 12:25 Anonymous 10.208.28.16 Andrea R Molino ScM Ph.D. Candidate University of Washington Seattle amolino29@gmail.com Building study cohorts (e.g., with visualization capabilities) Project Seeker: Andrea R. Molino I am a PhD candidate in epidemiology and NCI T32 predoctoral fellow with an interest in improving care access along the entire cancer continuum in the United States. These interests drove me to pursue a dissertation focused on HPV self-sampling, specifically to understand a series of auxiliary questions that address how this novel tool might influence the broader healthcare landscape. I have exceptionally strong epidemiologic methods and study design skills, am a talented programmer, and pride myself in my ability to communicate complex results through effective data visualizations. Prior to my doctoral training, I was an epidemiologist at Johns Hopkins University on a longitudinal cohort study.

My dissertation linked Kaiser Permanente EHR data with publicly available census-tract level information to capture variations in HPV self-sampling uptake by neighborhood socioeconomic status. This work inspired my passion for using publicly available data and showed me that identifying gaps in your own data can drive innovation. It also demonstrated how much more impactful our analyses can be when we simply know which tools and resources already exist and have the skills to use them. Participating in the NCI Data Jamboree will facilitate my ability to continue this type of work, and introduce me to other like-minded researchers.

Through participation, I hope to become more aware of tools available and ongoing research that aligns with my own, hopefully leading to collaborations that make my work stronger and interdisciplinary. Additionally, I have become a strong GitHub advocate for reproducible research and dissemination of open-source tools in epidemiology and hope to meet others who also aim to integrate version control more thoroughly into our field.

I look forward to bringing my skills to this collaborative space while learning from others equally invested in making cancer research more open, reproducible, and impactful.
8 Thu, 07/02/2026 - 04:29 Anonymous 10.208.24.90 Reda Mohamed Elbadawy MD Professor Gastroenterology , Hepatology&Executive Director for Center of Excellence of gut microbiome in fatty liver-fatty pancreas and haert diseases Center of excellence ,Benha University , Egypt Benha reda.albadawy@fmed.bu.edu.eg Developing, refining, or validating tools, methods, algorithms, and pipelines Fatty pancreas, Fibrosis ,FibroScan and Cancer Pancreas Early detection of pancreatic cancer due to fatty pancreas and pancreatic fibrosis diagnosed by FibroScan Project Describtion
o scientific or technical questions to address
Do we need simple , non invasive tool for early detection of pancreatic cancer?
So this project is applicable and important to others in the broader community because the use of FibroScan which is simple techeniuqe, novel and Unique to . Avilable now at most center of gastroenterology , hepatology . the time of examination of patients about 10minutes, without radiation , patients fasting only 3-5 hours , the results automatically . digital at the same sitting and not much time consuming.The data will be 5 Images for every patients plus other laboratory data.We are in need to expertise, computational tools, and/or computing environment needed to carry out your project.
Non – alcoholic fatty pancreatic disease ( NAFPD ) is a hot topic in gastroenterology. Just as obesity and metabolic syndrome are global problems, pancreatic steatosis especially in the form of NAFPD is an important challenge for pancreatologists, diabetologists, and nutritionists . Fatty pancreas could be an initial indicator of ectopic fat deposition and an earlier manifestation of metabolic syndrome than fatty liver . A role of NAFPD in the development of "prediabetes" and T2DM has also been suggested by most human studies and pancreatic cancer.Pancreatic cancer often presents late with vague symptoms and is associated with poor prognosis due to rapid metastasisUnfournately, it is one of the cancers that harbors delayed diagnosis.However, there are currently no screening tool for pancreatic cancer. NAFPD has been strongly suggested to be involved in pancreatic carcinogenesis. So the use of FibroScan as simple , non invasive , unique tool will add much valiable to pick up and screen cases , it also diagnosis pancreatic fibrosis which is has a crucial role in carcinogenesis .To date this project will be the first world wide .
7 Tue, 06/30/2026 - 13:13 Anonymous 10.208.28.16 Mingyu Yang Ph.D. Associate Research Scientist Yale University New Haven mingyu.yang@yale.edu Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Spatial omics; Computational biology; Machine learning; Cancer genomics; Data integration Computational Analysis of HTAN Spatial Multi-omics Data I have over 15 years of experience in bioinformatics, developing computational methods and analytical pipelines for large-scale sequencing data across cancer and other human diseases. My research has evolved from bulk genomics and transcriptomics to single-cell sequencing and, more recently, spatial multi-omics. At Yale University, I have been involved in developing computational methods for analyzing spatial transcriptomics and proteomics data, with a particular interest in applying AI and machine learning to understand tumor heterogeneity and the tumor microenvironment.

I would like to participate in the HTAN Data Jamboree because I am passionate about cancer research and believe that the extensive HTAN datasets provide an exceptional opportunity to develop new computational methods by reusing existing high-quality data. I look forward to collaborating with researchers from diverse backgrounds, exchanging ideas, and learning from experts in cancer biology, spatial omics, and data science. I believe that combining complementary expertise will inspire innovative approaches that would be difficult to develop independently.

Through the Jamboree, I hope to identify an important computational challenge that can benefit from statistical and machine learning approaches and to brainstorm a novel analytical framework with potential collaborators. My goal is to leave the event with a well-defined project concept and a collaborative team that can continue working together beyond the Jamboree. Ultimately, I hope this effort will lead to new computational methods, open-source software, and publications that help maximize the value of HTAN data for the broader cancer research community.
6 Tue, 06/30/2026 - 10:29 Anonymous 10.208.28.16 Adam X Miranda Ph.D. Computational Genomics Specialist NIAID Bethesda, MD adam.miranda@nih.gov Employing statistical, computational, and informatics tools, algorithms, and methods to integrate or analyze data Sarcoma, Epigenetics, Transcriptomics, Bioinformatics, Multiomics Project Seeker My expertise is primarily in the analysis and integration of multiple types of NGS data. In my graduate studies, I integrated RNAseq, ATACseq, and CRISPRKO screen data to interrogate the distinct impacts of two different mutations of the PIK3CA gene in breast cancer. In my post doc, I continued this line of work by integrating DNA sequencing and RNA sequencing of dozens of sarcoma patients to define new molecular definitions of sarcoma subtypes. In my current role, I serve a variety of projects across NIAID and have broadened my skill set to include the analysis of single cell data sets including scRNA and scATAC-seq data. I also have some experience in the development of machine learning models.

For this data jamboree, I want to return to making an impact on the research subject matter that I am most passionate about. I care deeply about cancer research and my career goal is to expand treatment options for all cancer patients, especially those with rarer forms of the disease. I am excited to contribute to any project that I can, and I believe my broad bioinformatic expertise should allow me to contribute to a number of different kinds of projects.

My goals for the this jamboree are to apply my skills to new challenges and to meet like minded researchers in the cancer research space. I also want to learn from others at the event with regards to current trends in cancer research and different techniques of data analysis.
5 Mon, 06/22/2026 - 16:33 Anonymous 10.208.24.144 OSCAR MARINO Vidal Ph.D. PI Universidad del NOrte Barranquilla. Atlantico oorjuela@uninorte.edu.co
  • First Name: Jorge
    Last Name: Velez
    Affiliation: UNINORTE
 Evaluating data quality for reproducibility and AI-readiness Precision Oncology Machine Learning Multi-Modal Data Integration Predictive Modeling AI-Driven Patient Stratification Models for Personalized Treatment in Breast Cancer Using Multi-Omic and Clinical Data Breast cancer is a highly heterogeneous disease characterized by substantial variability in molecular profiles, treatment response, recurrence risk, and survival outcomes. Current clinical stratification approaches based on receptor status and tumor staging do not fully capture this complexity, often leading to suboptimal treatment selection. This project aims to develop and evaluate artificial intelligence (AI)-driven patient stratification models that identify clinically meaningful breast cancer subgroups using multi-omic and clinical data. The primary scientific question is whether integrated machine learning approaches can improve prediction of treatment response and patient outcomes compared with conventional classification methods.

During the 3-day jamboree, the team will construct and compare unsupervised and supervised learning frameworks for patient stratification. Planned analyses include clustering of patients based on genomic, transcriptomic, and clinical features; identification of molecular signatures associated with treatment response; and development of predictive models for outcomes such as overall survival, disease-free survival, and therapeutic response. We will evaluate the interpretability of resulting models using explainable AI techniques to identify key biomarkers and pathways driving subgroup assignments.

Developing reproducible workflows for integrating heterogeneous biomedical datasets can benefit researchers, clinicians, and data scientists working on cancer prognosis, biomarker discovery, and personalized medicine. The resulting analytical framework could be adapted to other malignancies and disease areas.Data Types and Repositories

publicly available datasets, including:

Clinical data: patient demographics, tumor characteristics, treatment records, and survival outcomes from the The Cancer Genome Atlas Breast Invasive Carcinoma (BRCA) cohort.
Transcriptomic data: RNA-sequencing gene expression profiles from The Cancer Genome Atlas.
Genomic data: somatic mutation and copy number variation data from The Cancer Genome Atlas.
Proteomic data (optional): protein expression profiles from Clinical Proteomic Tumor Analysis Consortium.
Validation datasets: independent breast cancer cohorts from Gene Expression Omnibus and/or International Cancer Genome Consortium.