Scribd
Upload
40 views29 pages

Bio in For Matics

This document provides an overview of bioinformatics and data science. It defines bioinformatics as using computers to make sense of large biological data. Common tasks in bioinformatics include searching databases, comparing sequences, modeling structures, and integrating heterogeneous data sources. Data science can be used for exploration, inference, and prediction to discover patterns and draw conclusions from data. The document discusses using data science techniques like quantitative structure-relationship modeling in applications like drug discovery and personalized medicine. It also covers exploratory data analysis, learning algorithms, tools for bioinformatics and data science, and ways to learn these fields.

Uploaded by

Immanuel Lourdu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
40 views29 pages

Bio in For Matics

This document provides an overview of bioinformatics and data science. It defines bioinformatics as using computers to make sense of large biological data. Common tasks in bioinformatics include searching databases, comparing sequences, modeling structures, and integrating heterogeneous data sources. Data science can be used for exploration, inference, and prediction to discover patterns and draw conclusions from data. The document discusses using data science techniques like quantitative structure-relationship modeling in applications like drug discovery and personalized medicine. It also covers exploratory data analysis, learning algorithms, tools for bioinformatics and data science, and ways to learn these fields.

Uploaded by

Immanuel Lourdu
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PPTX, PDF, TXT or read online on Scribd
You are on page 1/ 29

BIOINFORMATI

CS
“
I will argue that computational
thinking and computational
methods are so central to the quest
of understanding life that today all
biology is computational biology
-Florian Markowetz

2
1 What is Bioinformatics ?
Let’s start with the first set of slides
BIG
CONCEP
T
It’s an area where
Computers are used to
make sense of Big
Biological Data

4
1 What is Data Science ?
Let’s start with the Next set of slides
Common Task in Bioinformatics
 Search
 Search Public databases for information on genes/proteins/RNA/pathways.
 Compare
 Sequence alignment to discern similarity/differences among various genes/proteins/RNA.
 Model
 Build structural model of protein structure.
 Build predictive models using of retrospective data.
 Integrate and Curate
 Combine Heterogenous data sources, redundancy.

6
What is Data Science?

7
1 What can Data Science do ?
What can Data Science do ?
 Exploration
 Discover hidden patterns from data.
 Descriptive Statistics and Data Visualization.
 Inference
 Applies Statistics to draw conclusions from Data.
 Prediction
 Applies Machine learning to make Data-Driven guesses from New Data.

9
Data Science Life cycle

10
Data Science Life cycle

11
Skill sets of
a Data
Scientist

12
Why not use it
Use cases of
in New Drugs ?
Data science

13
Data Science in Drug Discovery
o To Discern Structure-activity relationship of chemical library.

o Computational models can be quickly built to predict the pharmacokinetics and


Bioactivity of query compounds.

o Models can be used to repurpose existing FDA approved drugs for new
therapeutic treatment.

o Models can be applied for developing Personalized Medicine.

14
QSAR Modeling

Quantitative Structure

Relationship Activity
15
Data Sets
⬢ A tabular dataset is an M*N
matrix.

16
Exploratory Data Analysis (EDA)

Data Visualisation
03
Heat maps, Box plots, Scatter
plots, PCA.

Descriptive Statistics
Mean, Mode, Median, Standard
Deviation.

01 02
Data Shaping
Pivoting, Group, Filtering Data,
etc.

17
18
Data Sets
⬢ A tabular dataset is an M*N
matrix.

19
Exploratory Data Analysis (EDA)

Data Visualisation
03
Heat maps, Box plots, Scatter
plots, PCA.

Descriptive Statistics
Mean, Mode, Median, Standard
Deviation.

01 02
Data Shaping
Pivoting, Group, Filtering Data,
etc.

20
21
Types of data shaping
⬢ Removing columns and rows in a table.
⬢ Adding an index column to a table 
⬢ Implementing a sort order.
⬢ Grouping rows.
⬢ Pivoting column.
⬢ Creating custom column.

22
Exploratory Data Analysis (EDA)

Data Visualisation
03
Heat maps, Box plots, Scatter
plots, PCA.

Descriptive Statistics
Mean, Mode, Median, Standard
Deviation.

01 02
Data Shaping
Pivoting, Group, Filtering Data,
etc.

23
24
Learning Algorithms
⬢Supervised Learning.
⬢Unsupervised Learning.
⬢Reinforcement Learning.

25
QSAR 
WORKFLO
W

26
Data Science Tools
⬢ No Code
• GUI Based – Such as WEKA, Orange, KNIME.
⬢ Low Code
• AutoML such as PYCaret,TPOT.
⬢ Code
• Python: scikit-learn, TensorFlow, PyTorch.
• R: caret, parsnip, TensorFlow.

27
How can you learn Data Science ?

28
Thank
You
30

You might also like