Omics Logic Transcriptomics NGS Training Workshop (A Workshop on Machine Learning Approaches for Ascertaining Transcriptomics Data using T-bioinfo & Code playground platform)
- Platform: Online
- Language: ENGLISH
- Presenters: Dr. Mohit Mazumder & Dr. Harpreet Kaur, Pine Biotech, Inc USA
With growing data availability, its heterogeneity, and complexity, it is not sufficient to have access to data. To go from patterns to insights, modern-day researchers in academia and industry need to be empowered to work with data independently. This innovative workshop will address the major gaps in the processing and analysis of high-throughput biomedical data and finding meaningful information from it. This will be achieved by participants applying algorithms to quantify gene expression and detect statistically significant variation from RNA-seq projects in oncology.
This workshop is aimed towards understanding the application of data-driven science in biology with a goal to apply the understanding by learning from high impact journals. The workshop demonstrates the use of machine learning on real transcriptomics datasets and showcases the application of data mining and classification on gene expression. The session covers the challenges associated with different kinds of machine learning and its application finding meaningful information from this heterogeneous data followed by the biological significance of the analysis.
Materials and Methods :
The workshop will be carried out using the T-BioInfo platform designed for bioinformatics analysis of big multi-omics data. Keeping in view of the complexities of data processing, analysis, and integration, we introduce a user-friendly and intuitive interface. The platform offers a consistent, logical web-based interface to process a variety of unstructured datasets. These include next-generation sequencing, mass spectroscopy, structural and phenotypic data. Organized by data type and analysis category, the interface offers AI guidance to help users select appropriate analysis
steps for the data inputs and pipeline execution. Developed by a team of renowned experts in computational biology at the Tauber Bioinformatics Research Center (University of Haifa, Israel), the platform is used by universities around the world and was instrumental in a variety of projects published in high-impact journals.
Results and Discussions :
The platform streamlines bioinformatics analysis and is used for automating standard pipelines, testing pipeline performance, integration of heterogeneous data as well for education and training purposes. The Omics online courses and projects are designed around various topics, we discuss bioinformatics approaches for processing, analysis, integration, and interpretation of multi-omics data from oncology, neuroscience, agrobiology, and infectious diseases.
We will be using a visual and intuitive platform that handles all types of ‘omics data without any coding background. We will be learning to apply advanced machine learning methods to big datasets to understand data structure and extract relevant features and to help student researchers by working collaboratively on various complex biological datasets using the t-bioinfo server. The Code Omics logic Playground will be used for the Training in Python & R to apply Data Science Skills. These exercises are designed to explain the code and help you adapt it to a project of your own with clean and efficient code practices. This specialized workshop is perfect for students and scientists working on various high throughput data around the world and is looking for
finding meaningful insights from it.
1. Mohit Mazumder, Ph.D.
Dr. Mohit Mazumder has over 10 years of research & industry experience. He completed a Masters in Bioinformatics from Jamia Millia Islamia and a Ph.D. in computational biology & chemistry from Jawaharlal Nehru University (JNU). He is an expert in machine learning in application to biomedical & chemical data. His core expertise is in Structural biology, Computational modeling of biological systems, and protein dynamics using long-range molecular dynamics simulation. Dr. Mazumder is a co-author in 25 international peer-reviewed research articles, 3 Book chapters, and numerous international conferences. He has been instrumental in developing Bioinformatics facilities at the School of Life Science, JNU, and is a recipient of multiple awards, including the Indo-Shastri award (Govt of India), Nvidia GPU award, Fujitsu, and others. He has 5 years of teaching experience working as a TA in JNU teaching Bioinformatics to M.Sc. & Ph.D. students. He is currently heading the Global Business Development for Pine Biotech, USA, and contributing to Marketing & Sales as well as mentoring participants from various programs.
2. Harpreet Kaur, Ph.D.
Harpreet Kaur has done her Ph.D. (Thesis Submitted) in Bioinformatics from the BioinformaticsCentre, CSIR-Institute of Microbial Technology, Chandigarh, India, and JNU, New Delhi, India. Her Doctoral Research is focused on the Domain of Cancer Genomics; specifically, “Computer-aided identification of genetic biomarkers for predicting liver cancer and its prognosis”. She has nearly 7 years of Research Experience and 1 year of teaching experience. She has received her Master’s Degree in Molecular Biology & Biochemistry from the G.N.D.U. Amritsar, Punjab, India. Her core field of research is Cancer Genomics and Machine learning. She has expertise in the application of statistical, Machine learning techniques on Biomedical data, and the development of Prediction tools and Databases. Her current research interests are in the areas of Artificial Intelligence, Machine Learning, Cancer Genomics, Biomarker Discovery, Database development on different aspects of human health. Harpreet has published 13 Research Articles in peer-reviewed International Journals and over 200+ citations on Google Scholar. She has received the EASL-Young Investigator full Bursary Award from the European Association for the Study of the Liver (EASL) to present her Research in The Digital-International Liver Congress 2020. She has received an “INSc-Young Researcher/Achiever Award-2020” from the Institute of Scholars (InSc), Bengaluru, India. She is currently a member of various scientific societies like EASL, BioClues, APBioNet, InSc. She has received CSIR-Fellowship from the Council of Scientific and Industrial Research, India for her Doctoral Research. She has qualified for various national level exams like CSIR-JRF-NET, CSIR-NET, GATE-2012.
Session 1: Introduction to Omics Logic Technology: 30 mins
> Introduction of the Speakers & Participants
> Introduction to Big Data Bioinformatics (Introduction to NGS data, History, File formats in NGS)
> Introduction to the T Bioinfo Platform (https://server.t-bio.info/) (Login to the server, Overview of the Data types, overview Multi-Omics & ML)
Introduction to Cancer Data Set: Case Study on Transcriptomics data from the PDX model (a human tumor sample is implanted into immune-deficient mice).
Samples from Breast cancer subtypes (ER+ & TN) (25 mins)
Session 2: Hands-on RNA Seq Data Analysis: 30 mins
Demonstration of Processing of Transcriptomics NGS data
> Role of pre-processing in standard RNA-seq pipelines (Trimmomatic and PCR-clean)
> Mapping techniques: mapping on the transcriptome, (Bowtie-t)
> Quantification and Generating a table of expression: RSEM
> Pipeline building & logical understanding
Session 3: Hands-on session on Machine Learning: Exploratory Data analysis: 30 mins
> Working with gene expression table
> Exploratory Data Analysis: PCA, K-Means & H-clustering
> Exploring multi-dimensional data using PCA visualization
Session 4: Hands-on Session on Omicslogic Code playground: 30 mins
> Demonstration of the Code omics logic platform (https://code.omicslogic.com/)
> PCA tutorial on R
> Q&A Feedback and review
Requirements / Prerequisites
The candidates should join the workshop with laptops with a decent Internet connection for the online meeting, demonstration, and hands-on experience.
Registration is only open to InCoB2020 participants, at no additional cost. Please register first as an InCoB2020 participant if you have not done so in order to register for this workshop. As seats are limited, allocation will be made on first-come-first-served basis.