Acharjee Lab

About PI

Animesh Acharjee is an Assistant Professor of Integrative Analytics and AI and Deputy Programme Director, MSc in Health Data Science (Dubai) in the Cancer and Genomic Sciences. Dr. Acharjee did his undergraduate degree in Electrical Engineering from North Eastern Regional Institute of Technology (NERIST) , Itanagar, India and Masters in Bioinformatics from Institute of Bioinformatics and Applied Biotechnology[ , Bangalore , India. After his Masters, he earned his PhD from Wageningen University. The Netherlands, on applied machine learning and data analysis. After his PhD he moved to Lyon, France, for his post-doctoral study with Synergie Lyon Cancer Centre as a Biostatistician where he extensively worked on big data analytics, cloud computing. After his post-doctoral study he was offered a scientist position with BASF Cropdesign, Belgium. Before joining University of Birmingham and Queen Elizabeth Hospital he was working with University of Cambridge, Cambridge, UK focusing on metabolic driven diseases like Obesity, Type 2-diabetis using high throughput metabolomics, lipidomics technologies. His research interests includes integrative data analytics, predictive biomarker discovery, bioinformatics methods for diagnostics and network biology. Throughout his career, he was offered many fellowships from British Council, Dutch Government and Newton fellowships. He has published many papers in the international journals and actively collaborate with many Universities, for example Harvard University and University of Cambridge.

Acharjee Lab focuses on Integrative Analytics and AI and is divided into three major objectives

Multi-Omics and Multi-Modal Integration
Diagnostics and Biomarker Identification
Method and Workflow Development

Multi-Omics and Multi-Modal Integration

Dr. Acharjee and his team applies novel approaches to the diverse multi omics data e.g. clinical, genetics, transcriptomics, proteomics, metabolomics, single cell transcriptomics to integrate them and identify novel therapeutic mechanisms and disease mechanisms. The data sets used in those studies are often public (ex: TCGA, GEO etc) or stakeholders’ experimental data. To perform an integration, We use machine learning/AI methods derived from multiple experiments across cancer and metabolic diseases. Some of the examples of integration are microbiome and inflammatory markers in infant cohort, microbiome, metabolome and single cell sequence data in the colon cancer cohort , and multiple metabolomics data sets integration.

Novel Tool Development

Group is also interested to develop new bioinformatics tools and workflows that can be useful for the clinician or biologist. Some of the examples are microbiome analysis workflow, statistical power calculations online tool, automatic feature selection form high dimensional omics data sets .

Diagnostics

This aspect considers single omics or clinical data including variety of machine learning and AI methods to discover diagnostics markers. Some examples include identification of the markers from cytokine profiling data , diagnostic marker from miRNA, metabolomics biomarker identification .