Skip to content
View vicknentura's full-sized avatar
🎯
Focusing
🎯
Focusing

Block or report vicknentura

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
vicknentura/README.md

👤 About Me

ventura = {
    "name"       : "Nicholas A. Ventura",
    "location"   : "United States 🇺🇸",
    "background" : ["Life Sciences Consulting", "Bachelor of Science in Cell, Molecular and Developmental Biology",
                    "Master of Business and Science in Biotechnology Management"],
    "goal"       : "Graduate research in Genetics, Genomics & Bioinformatics",
    "interests"  : ["Comparative Genomics", "Human Genetics",
                    "Quantitative Genetics", "AI & Data Science"],
    "currently"  : "Building CS foundations for computational biology research"
}

My current work sits at the intersection of Python application development and data tooling — building dashboards and pipelines that surface intelligence for research and ML investigations. I am targeting graduate programs in Genetics, Genomics & Bioinformatics (GGB) to extend this work into the computational biology domain.


🛠️ Tech Stack

Languages

Python SQL R Studio Excel Java

Tools & Frameworks

Skills

Visualizations

Matplotlib Seaborn Bokeh Plotly

Machine Learning

scikit-learn Keras

APIs

Google API AACT NCBI

Domain

Clinical Trials MeSH HTA


🔬 Featured Projects

📊 Clinical Trial Landscape Dashboard (private — active sprint)

Interactive Streamlit dashboard consuming the ClinicalTrials.gov v2 API and NIH MeSH ontology. Multi-filter search (status, phase, intervention type, agency class, date range), Plotly visualizations, LLM-assisted query refinement, and CSV/PDF export.

# Pull studies from ClinicalTrials.gov v2 API with field-level selection
params = {
    "fields": (
        "protocolSection.identificationModule.nctId,"
        "protocolSection.statusModule.overallStatus,"
        "protocolSection.designModule.phases,"
        "protocolSection.identificationModule.organization.class,"
        "protocolSection.contactsLocationsModule.locations.country"
    )
}
response = requests.get("https://clinicaltrials.gov/api/v2/studies", params=params)

Stack: Python · Streamlit · Pandas · Plotly · OpenAI API · ClinicalTrials.gov API · NIH MeSH XML


📈 GitHub Stats

  

GitHub Streak


🧬 Learning Roadmap

2024 ──── Clinical Research Analysis Tool.....................🔄 Active Sprint
           └─ Python, Streamlit, REST APIs, LLM integration
          Multiple Regression/Commercial Forecasting Tool.....🔄 Active Sprint
           └─ Python, Streamlit, REST APIs, LLM integration
2025 ──── Clinical Trial Analytics Platform ··················🔄 Active Sprint
           └─ Python, Streamlit, REST APIs, LLM integration

          Intro to Software Engineering (IBM & Coursera)······✅ Complete
           └─ Java OOP, Collections, File I/O, Date/Time API

2026 ──── Graduate Program (GGB) ······························🎯 Target
           └─ Comparative Genomics · Human Genetics
              Quantitative Genetics · AI & Data Science


         ── Bioinformatics Tooling ····························🔜 Next
           └─ Biopython, R/Bioconductor, GATK pipelines,
              FASTQ/BAM/VCF processing, genomic data structures

🤝 Let's Connect

Email


"[Enter themed quote here]"

Popular repositories Loading

  1. tripleten tripleten Public

    Sprint 4: Streamlit EDA and hypothesis testing on 50K US used-car listings — Z-tests, t-tests, proportion tests with statistical interpretation.

    Jupyter Notebook

  2. tripleten5 tripleten5 Public

    Sprint 5: Video game sales analytics — platform lifecycles, regional breakdowns, correlation matrix, t-test hypothesis testing across 36 years of global data.

    Python

  3. tripleten6 tripleten6 Public

    Sprint 6: Chicago taxi analytics with Bokeh — SQL to Python pipeline testing whether weather causally shifts ride durations. Deployed on Render.com.

    Jupyter Notebook

  4. Google-VertexAI-TF-Keras Google-VertexAI-TF-Keras Public

    Google Cloud ML engineering — distributed training with MirroredStrategy, TF Data Validation, TPU-accelerated pipelines, and Vertex AI model deployment.

    Jupyter Notebook

  5. tripleten7 tripleten7 Public

    Sprint 7: Mobile plan recommendation classifier — Decision Tree, Random Forest, Logistic Regression vs dummy baseline. Train/validation/test protocol.

    Jupyter Notebook

  6. Supervised-Unsupervised-Learning Supervised-Unsupervised-Learning Public

    SMOTE oversampling for class imbalance — credit card fraud detection with logistic regression, ROC-AUC evaluation, and precision-recall threshold sweep.