+ - 0:00:00
Notes for current slide
Notes for next slide

An Open Science Approach to Machine Learning in Biomedical Research

Batool Almarzouq- @batool664

A little bit about me!

  • A computational biologist affiliated with the University of Liverpool.
  • Founder of RLadies Chapter in Saudi Arabia (Dammam).
  • A curator in the R Weekly team.
  • Member of MiR accessibility committee.
  • Member in the turing way community.
  • Working on establishing an Open Science community in Saudi Arabia.

Acknowledgment

  • Anelda Van der
  • Malvika Sharan, Kirstie Whitaker and Martina G. Vilas
  • The Turing Way Community
  • Alison Presmanes Hill (slides)

Why do we use ML in Biomedical Research?

Image Credit: ABC Science

Image Credit: ABC Science

DNA

  • DNA sequence alignment
  • DNA sequence classification
  • DNA sequence clustering
  • DNA pattern mining

Algorithms includes fuzzy sets, neural networks, genetic algorithms.

Image Credit: ABC Science

DNA

  • DNA sequence alignment
  • DNA sequence classification
  • DNA sequence clustering
  • DNA pattern mining

Algorithms includes fuzzy sets, neural networks, genetic algorithms.

RNA

  • Mainly RNA-sequencing (RNA-seq)
  • Differentially expressed genes (DEGs)
  • Alternative splicing
  • Small RNA expression

Algorithms include Logistic Regression, Random Forest, LMT, Random Subspace.

Solving the sequence is not enough!

We need to know the structure and function of the protein!

Image Credit: doi:10.1021/cr400525m

Image Credit: doi:10.1021/cr400525m

How can we predict function from structure?

To predict the function from the structure, scientists use different approaches including machine learning (ML) and deep learning algorithms .

Credit: Supriyo Bhattacharya/Beckman Research Institute at City of Hope

Credit: Supriyo Bhattacharya/Beckman Research Institute at City of Hope

Prediction of protein structure is important to develop small molecules and targeted therapy for diseases.

.

Why not only rely on Experemtal Methods?

Credit: Data for UniProtKB obtained form Claire O'Donovan via EBI database support

Credit: Data for UniProtKB obtained form Claire O'Donovan via EBI database support

Because of the growing gap between the newly-sequenced and characterized sequences in the genome databases, computational methods in gene functional annotation are indispensable. Moreover, given the drop in the genome sequencing techniques' cost, this gap is only destined to grow.

.

Biology has become a highly data-intensive science, dependent on complex, computational, and statistical methods!

So, how can we make these methods available and accessible for researchers, while ensuring that scientific results remain reproducible?

What is the percentage of reproducible research?

Credit: Key results of the survey on reproducibility conducted by Nature in 2016

How can we overcome the reproducibility crisis?

How can you improve the reproducibility of your data science project?

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

Share Computational ENVIRONMENT

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

Share Computational ENVIRONMENT

VERSION CONTROL

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

Share Computational ENVIRONMENT

VERSION CONTROL

TESTING

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

Share Computational ENVIRONMENT

VERSION CONTROL

TESTING

DOCUMENTATION

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

Share Computational ENVIRONMENT

VERSION CONTROL

TESTING

DOCUMENTATION

OPEN DATA/FAIR DATA

How can you improve the reproducibility of your data science project?

OPEN SOURCE SOFTWARE

SHARE CODE/ANALYSIS

Share Computational ENVIRONMENT

VERSION CONTROL

TESTING

DOCUMENTATION

OPEN DATA/FAIR DATA

OPEN ACCESS

This is called Open Science.

Open Science is about extending the principles of openness to the whole research cycle, fostering sharing and collaboration as early as possible thus entailing a systemic change to the way science and research is done

-- FOSTER Plus

What are the FAIR principles?

* The Turing Way project illustration by Scriberia. Zenodo. http://doi.org/10.5281/zenodo.3332807

Why do we use version control (git)?

Version Control in the Old Days ..

Real Version Control (including backup)

In the pandemic, some publishers have “opened” their journals to make certain articles freely available.

In the pandemic, some publishers have “opened” their journals to make certain articles freely available.

Databases have been created that are completely open access, such as the Open COVID Pledge.

UNESCO is launching international consultations aimed at developing a Recommendation on Open Science for adoption by member states in 2021

UNESCO is launching international consultations aimed at developing a Recommendation on Open Science for adoption by member states in 2021

There is a network of Open Science Communities in Netherlands, Sweden, Germany, UK and others

In line with vision 2030, we are starting an Open Science Community in Saudi Arabia.

It's created and developed with the help of the "Open Life Sciences"

Open Life Sciences (OLS3) program helps individuals and stakeholders in research to become Open Science ambassadors.

We want to provide a place where newcomers and experienced peers interact, inspire each other to embed open science (research) practices and values in their workflows and provide feedback on policies, infrastructures and support services. Together working to make Open Science the norm. So we are calling out to researchers and colleagues in Saudi Arabia.

Batool Almarzouq The University of Liverpool

Founder and director of Talarify, Mentor OLS3

Paula Moraga, Assistant Professor in Statistics for Public Health (KAUST)

Join me on the 24th of Feb for a workshop titled "Collaborating on Open Data Science Projects" as part of the Datathon for WiDS2021.

How can you start learning about Open Science?

How can you start learning about Open Science?

* The Turing Way project illustration by Scriberia. Zenodo. http://doi.org/10.5281/zenodo.3332807

Kirstie Whitaker, Project Lead

Malvika Sharan, Community Manager

So, What is the turing way?

Join the next book dash event!

Book Dash November 2020

Review README.md Arabic translation

Upcoming Workshop by the turing way

Register for the free workshop 'Boost your research reproducibility with Binder' run by Sarah Gibson from the Turing Way as part of our Research Software Camp on research accessibility.

Resources:

Thank you so much!

batool@liverpool.ac.uk

Twitter: @batool664

Join RLadiesDammam: @RLadiesDammam

A little bit about me!

  • A computational biologist affiliated with the University of Liverpool.
  • Founder of RLadies Chapter in Saudi Arabia (Dammam).
  • A curator in the R Weekly team.
  • Member of MiR accessibility committee.
  • Member in the turing way community.
  • Working on establishing an Open Science community in Saudi Arabia.

Acknowledgment

  • Anelda Van der
  • Malvika Sharan, Kirstie Whitaker and Martina G. Vilas
  • The Turing Way Community
  • Alison Presmanes Hill (slides)
Paused

Help

Keyboard shortcuts

↑, ←, Pg Up, k Go to previous slide
↓, →, Pg Dn, Space, j Go to next slide
Home Go to first slide
End Go to last slide
Number + Return Go to specific slide
b / m / f Toggle blackout / mirrored / fullscreen mode
c Clone slideshow
p Toggle presenter mode
t Restart the presentation timer
?, h Toggle this help
Esc Back to slideshow