Latest Posts

One day in Python: Applications in Life Science

Where: Innoplexus
7th Floor, Midas Tower,
Beside STPI Building, Rajiv Gandhi Infotech Park,
Phase-1, Hinjewadi, Pune

When: Saturday, 23rd February 2019, At : 10:00 am to 5:30 pm

About the workshop

Why Python……?

Python is a great way to start your programming journey. It is an awesome language for working with
Big Data and use when sorting data sets and analyzing trends. It has a readable syntax, it is object
oriented, and it is used on the backend of lot of cool web apps like Youtube, Google, and Pinterest.

Why Innoplexus….?

At Innoplexus we harness the power of Python to solve complex research problems everyday. Python
helps us to effectively deal with large unstructured biological data, perform data retrieval and parsing,
automation, data manipulation as well as simulation of biological systems. As the core business of
Innoplexus is in Life sciences, we have lots of biological examples of Python usage to share with you all.

Learning objectives

The learning objective of today’s workshop is to provide a bird’s eye view to Python language, while
showcasing the capabilities of this versatile language with use cases and demonstrations, both within the
domain of Life science and outside.

The workshop is aimed at programming naive audience and hence will cover topics from basics of
language to application case studies.

Workshop Facilitator:

Gaurav

Dr. Sanika Bhide
Product Manager

Speakers

Rutuja Viregaonkar
Associate Data Scientist

Apurva Naik
Data Scientist

Akshita Negi
Associate Data Analyst

Swati Saini
Associate Data Scientist

Agenda:

(10:00 am – 10:30 am) – Registration formalities
(10:30 am – 10:40 am) – Welcome note by CTO
(10:40 am – 10:45 am) – Workshop kick off
(10:45 am – 11:00 am) – Ice breaker and Day’s agenda
(11:00 am – 12:15 pm)

Session 1: Just Enough Python Basics
Session Lead: Rutuja Viregaonkar, Associate Data Scientist

  • Characteristics of Python
  • Python vs. R
  • Python interpreter (aka “Python shell”), Jupyter
  • Running a simple script
  • Exploring data types, lists, functions
(12:15 pm – 12:45 pm) – Activity Break for Session 1
(12:45 pm – 1:00 pm) – Lunch
(1:00 pm – 2:15 pm) –

Session 2: A guide to Data Science pipeline
Session Lead: Apurva Naik, Data Scientist – Strategic Data Initiatives

  • Data Science Pipeline:
    1. Use case description
    2. Getting Data for a use case – Pharma/Fintech
      1. Data storage
      2. Public datasets in structured formats
      3. Accessing APIs
      4. Scraping websites
      5. Data types (Text, videos, pictures)
      6. Cleaning data
    3. Exploring Data
      1. Structured vs. Unstructured
      2. Exploring selected data: examining, summarizing,
        filtering, sorting, handling missing values
    4. Analyzing Data
      1. Machine Learning (train/ test split)
      2. Activity Break (NN game)
      3. Deep Learning
        1. Basic concepts
        2. Resources
    5. Storytelling through Data
      1. Presenting our results
(2:30 pm – 3:45 pm) –

Session 3: Data Visualization using Python and D3
Session Lead: Akshita Negi, Associate Data Analyst

  • Big data visualization vs Information Visualization.
  • Exploratory vs Explanatory analysis.
  • Data inspecting and modelling.
  • Activity break
  • Using visualization to capture patterns in datasets.
  • Using visualization to build a story on analyse data
  • Quiz
(3:45 pm – 4:00 pm) – Tea break
(4:00 pm – 5:00 pm) –

Session 4: Big data using Python
Session Lead: Swati Saini, Associate Data Scientist

  • Introduction to Big data
  • Cluster computing and Pyspark
  • Challenges in life science due to big data
  • Combating the challenge for Data Variety
  • Other open source tools
  • Quiz
(5:00 pm – 5:15 pm) – Learnings and Take home