About Me

Adilbek Bazarkulov

Computational Biology & AI Researcher

Adilbek Bazarkulov avatar
SUMMARY

Building intelligent systems at the intersection of CS & Biology.

I am a Graduate Research Assistant at Ramsey Laboratory: Computational Systems Biology at Oregon State University, advised by Professor Stephen Ramsey. My work focuses on reasoning over vast amounts of biomedical data using Knowledge Graphs and AI to solve complex problems in disease diagnosis and treatment.

EDUCATION

M.S. Computer Science

2027

Oregon State University

GPA: 4.00

B.S. Computer Science

2023

Oregon State University

GPA: 3.83
INTERESTS
  • Knowledge Graphs
  • Artificial Intelligence
  • Computational Biology
  • Data Engineering
CURRENT PROJECTS

ARAX

Reasoning agent for NCATS Biomedical Data Translator. Integrates knowledge graphs to answer complex biomedical questions.

PythonNeo4jDockerAWS

PloverDB

High-performance in-memory knowledge graph database optimized for speed and scalability.

PythonDocker

Featured Projects

moleXa screenshot 1
moleXa screenshot 2
moleXa screenshot 3
moleXa screenshot 4
moleXa screenshot 5

moleXa

Jan 2025 – Present

A modern web application for 3D molecular visualization that makes chemistry accessible and engaging. It fetches real molecular data from PubChem and renders scientifically accurate 3D structures with educational explanations.

Next.js
React
Three.js
TypeScript
Tailwind
PubChem API
Zustand
RRadix UI
Polydebate screenshot 1
Polydebate screenshot 2
Polydebate screenshot 3
Polydebate screenshot 4
Polydebate screenshot 5
Polydebate screenshot 6

Polydebate

Nov 2025
3rd Place · QuackHacks 2025 (Polymarket Track)

Hackathon-built AI debate arena that streams Polymarket questions, orchestrates live LLM debates with synthesized voices, and produces Gemini-backed summaries so traders can compare reasoning across models in real time.

Next.js
TypeScript
Tailwind
Flask
Python
SSQLAlchemy
EElevenLabs
GGemini API
OOpenRouter
Greeney screenshot 1
Greeney screenshot 2
Greeney screenshot 3
Greeney screenshot 4
Greeney screenshot 5

Greeney

Apr 2025
Winner · BeaverHacks 2025 GDGC: Data-Driven Solutions

A modern carbon emissions companion that aggregates ride-hailing, delivery, and travel receipts, parses them via Gmail API, and translates them into actionable insights with rich charts and reduction tips.

Next.js
TypeScript
Tailwind
SShadcn UI
Python
Flask
GGoogle APIs
OOAuth
ARAX screenshot 1
ARAX screenshot 2
ARAX screenshot 3
ARAX screenshot 4
ARAX screenshot 5

ARAX

Dec 2024 – Present

A reasoning agent for the NCATS Biomedical Data Translator. ARAX integrates diverse biomedical knowledge to answer complex questions about disease, diagnosis, and treatment by reasoning over knowledge graphs.

Python
AWS
Neo4j
Docker
Scikit-learn
XGBoost
Pandas
Flask
NetworkX
OpenTelemetry

Professional Experience

Graduate Research Assistant & Software Engineer

Dec. 2024 - Present
Corvallis, OR
  • Contribute to ARAX (Expander Agent) and RTX-KG2/KG2c knowledge graphs in the NCATS Biomedical Data Translator ecosystem, improving reliability of graph based reasoning workflows.
  • Refined database build pipeline with additional validation checks and schema alignment, reducing ingest errors and improving knowledge graph data quality by 35%.
  • Supported AWS infrastructure for KG builds by tuning instance types, storage layout, and monitoring, reducing rebuild time and unplanned downtime for large scale graph updates.
  • Collaborated with cross institutional Translator teams to debug edge cases in graph exports and align predicates with the Biolink Model, ensuring consistent semantics across knowledge sources.

Software Engineering Intern

Jul. 2024 - Sep. 2024
Corvallis, OR
  • Developed features for a patient appointment scheduling system that automated booking and reminder flows, helping reduce average scheduling time by 70% for front desk staff.
  • Implemented backend logic and validation rules for appointment creation, cancellation, and rescheduling, improving reliability of day to day clinical workflows.
  • Assisted with medical records integration across internal applications by mapping fields and aligning identifiers, reducing duplicate data entry and inconsistencies between systems.
  • Worked with clinicians and IT stakeholders to gather requirements, perform QA on new releases, and deploy updates safely into production environments.
Sep. 2021 - Jun. 2023
Corvallis, OR
  • Built a data processing pipeline to clean, normalize, and aggregate 1M+ bee population records across 36 counties, improving reliability of downstream ecological analyses.
  • Standardized species names, locations, and collection metadata to resolve duplicates and missing values in historical observation datasets.
  • Created geographic and temporal visualizations that helped research teams explore trends in pollinator abundance and sampling effort 50% faster.
  • Documented data dictionaries and analysis steps so new lab members could reproduce results and extend the pipeline for future survey seasons.

Tech Stack

DevOps & Cloud
Docker
AWS
Terraform
Git
Languages
Python
C
C++
Bash
Kotlin
Tools & Frameworks
Jira
Figma
MicrosoftOffice

Let's Talk

Have a project in mind or just want to say hi? I'm always open to new opportunities and collaborations.

This site is protected by reCAPTCHA and the GooglePrivacy Policy andTerms of Service apply.

bazarkua

“I am not trying to be perfect today. I am trying to be consistent for years.”

© 2025 Adilbek Bazarkulov. All rights reserved.