My name is Timofei Ryko and here you can find a list of my coding and data science skills and my portfolio. Complete information about my work experience, achievements, etc can be found in my Master CV.

My nickname is timofeiryko on every platform except instagram (in inst it is rykotimofei, but it will be fixed soon) and I am just Timofei Ryko everywhere.

• LinkedIn
• Facebook
• Telegram
• Instagram
• Twitter
• VK
• Contact me by email

• Python — advanced level
• R — medium level
• MATLAB — medium level
• Rust — basic knowledge
• Java — basic knowledge

• HTML — medium level
• Bootstrap — medium level
• CSS — basic knowledge
• JavaScript — basic knowledge
• Markdown
• LaTex

• Python Asyncio — basic knowledge
• Web development
  • Django — medium
  • FastAPI — basic
  • SQLAclhemy — medium
  • AIOGram — advanced (telegram bots)
• Web scraping and API
  • Working with RESP API, JSON /LXML
  • Beautiful Soup
  • Selenium — medium
• Bash and Unix
• Git and GitHub

• Explorational Data Analysis (EDA) and statistics
  • Pandas — advanced
  • Seaborn and matplotlib — advanced
  • Statsmodels, SciPy
  • SQL — medium level
• Machine learning
  • Scikit-learn — advanced (custom transformers, encoders, etc)
  • Boosting algorithms (XGBoost, CatBoost, LightGBM)
  • TensorFlow and Keras — basic
  • Automation with featuretools and auto-sklearn
  • Bayesian hyperparameter tuning with Optuna
  • Simple NLP with SpaCy, tokens clusterization techniques
  • Computer Vision (application to histopathology)

• Single-cell analysis with Scanpy
• Working with Entrez APIs using biopython utilities
• ODE modeling with MATLAB
• Ensembl Variant Effect Predictor with plugins configuration
• Genes annotation with biomart, Ensembl REST API and other tools
• Analyzing sequence association data

• BioQuest  —  website on Django
  • Django 4
  • Bootstrap 5
  • OOP principles
• EDAwesome  —  my Python library for quick and nice explorational data analysis
  • EDA: pandas, seaborn, matplotlib
  • Packaging with poetry
• Home credit dataset analysis and loan repayment prediction  —  capstone project from the Turing College
  • EDA: pandas, seaborn, matplotlib
  • Scikit-learn  —  advanced (custom transformers, encoders, etc)
  • Automation with featuretools and auto-sklearn
  • Bayesian hyperparameter tuning with Optuna
  • Simple NLP with SpaCy, tokens clusterization techniques
  • I got 93/100 on code review at Turing College
• Podcast analysis  —  data analysis project from the Turing College
  • SQL
  • EDA: pandas, seaborn, matplotlib
• Science parser telegram bot
  • SQLAclhemy
  • AIOGram
  • Python Asyncio
  • Working with RESP API, JSON /LXML
  • Beautiful Soup
  • Selenium
  • Working with Entrez APIs using biopython utilities
• Tgscraper  —  Python package for telegram scraping
• Modeling for the iGEM competition
  • ODE modeling with MATLAB
• SMTB bioinformatics project
  • Analyzing sequence association data
  • EDA: pandas, seaborn, matplotlib
  • Beautiful Soup
  • Ensembl Variant Effect Predictor with plugins configuration
• Computer vision for histopathology
  • EDA: pandas, seaborn, matplotlib
  • TensorFlow and Keras
  • It was the final project for the course «Machine Learning in Synthetic Biology» at the University and I got an A for it
• Application of SpaCy to kaggle-nbme competition
• CITEseq data analysis
  • Single-cell analysis with Scanpy
  • Genes annotation with biomart, Ensembl REST API and other tools
• Outlook emails parser (the source code is unavailable for legal reasons)
• Machine learning system for determining SpO2 by video (the source code is unavailable for legal reasons)