Dr Animesh Acharjee PhD, PGCE, FHEA

• Postgraduate Certificate in Education (PGCE), Distinction, University of Birmingham, UK, 2025
• PhD in Omics data analysis, Wageningen University, The Netherlands
• MSc in Bioinformatics, IBAB, Bangalore, India
• BTech in Electrical Engineering, NERIST, India

I completed my 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 my Masters, I earned my PhD from Wageningen University, The Netherlands, on applied machine learning and data analysis. After my PhD I moved to Lyon, France, for my post-doctoral study with Synergie Lyon Cancer Centre as a Biostatistician where I extensively worked on big data analytics, cloud computing. After my post-doctoral study I was offered a scientist position with BASF Cropdesign, Belgium.

Before joining University of Birmingham and Queen Elizabeth Hospital I was working with University of Cambridge, Cambridge, UK focusing on metabolic driven diseases like Obesity, T2-diabetis using high throughput metabolomics, lipidomics technologies. My research interests includes integrative data analytics, predictive biomarker discovery, bioinformatics methods for diagnostics and network biology. Throughout my career, I was offered many fellowships from British Council, Dutch Government and Newton fellowships. I have published many papers in the international journals and actively collaborate with many Universities, for example Harvard University and University of Cambridge.

• Integrative Multimodal Data Analytics
• Health Data Fundamentals
• MRes - Cancer Science
• Genome Medicine
• Clinical Bioinformatics
• Foundation Year-2 (FY-2)

I am keen to supervise PhD students who are passionate and committed to making a meaningful impact in translational research.

1. Integrative analytics
My research integrates heterogeneous, high-dimensional data to uncover disease mechanisms that no single data layer can reveal. AI-based interaction modelling has resolved metabolite–microbiome interplay in IBD [1], and explainable machine learning applied jointly to plasma and faecal metabolomes has prioritised disease-associated metabolites and linked them to dietary intake [2]. Network-based integration of proteomic data has uncovered shared molecular mechanisms between IBD and colorectal cancer [3]. Associating transcriptomic profiles with inflammatory markers has characterised the tumour microenvironment in hepatocellular carcinoma [4].

References

1. Hodgkiss R, Acharjee A. Unravelling metabolite–microbiome interactions in inflammatory bowel disease through AI and interaction-based modelling. Biochim Biophys Acta Mol Basis Dis. 2025;1871(3)
2. Onwuka S, Bravo-Merodio L, Gkoutos GV, Acharjee A. Explainable AI-prioritized plasma and fecal metabolites in inflammatory bowel disease and their dietary associations. iScience. 2024;27(7):110298
3. Dhami J, Radhakrishnan SK, Russ D, Mondal S, Alzarooni A, Merodio LB, Duggal NA, Gupta R, Acharjee A. A network-based association of IBD and colorectal cancer using proteomics data. Proteomics Clin Appl. 2026;20(2):e70041
4. Bahcivanci B, Shafiha R, Gkoutos GV, Acharjee A. Associating transcriptomics data with inflammatory markers to understand tumour microenvironment in hepatocellular carcinoma. Cancer Med. 2022;12(1):696–711

2. Diagnostics
I develop data-driven biomarkers and stratification models that support earlier and more precise clinical decisions. Machine learning applied to UK Biobank proteomics has identified circulating markers of colorectal cancer [1], complementing candidate diagnostic genes for colon cancer derived from transcriptomic data [2]. Microbiome-based models stratify colon cancer patients and predict survival [3]. In IBD, machine-learning analysis of transcriptomic data has distinguished disease subtypes, supporting more precise diagnosis and treatment selection [4].

References

1. Radhakrishnan SK, Nath D, Russ D, Bravo-Merodio L, Lad P, Daisi FK, Acharjee A. Machine learning-based identification of proteomic markers in colorectal cancer using UK Biobank data. Front Oncol. 2025;14
2. Koppad S, Basava A, Nash K, Gkoutos GV, Acharjee A. Machine learning-based identification of colon cancer candidate diagnostic genes. Biology. 2022;11(3):365
3. Smyth J, Godet J, Choudhary A, Das A, Gkoutos GV, Acharjee A. Microbiome-based colon cancer patient stratification and survival analysis. Cancer Med. 2024;13(22)
4. Saini N, Acharjee A. Identifying inflammatory bowel disease subtypes: a comprehensive exploration of transcriptomic data and machine learning-based approaches. Ther Adv Gastroenterol. 2025;18

3. Computational methods and workflow development
I design machine-learning methods and reproducible workflows for settings where standard approaches fail: small samples, severe class imbalance and very high dimensionality. To address imbalance in omics data, my group developed a class-wise Wasserstein generative adversarial network [1] and the T-SMmOTE oversampling technique [2]. We have extended these into generative-AI workflows that augment transcriptomic and microbiome analysis across inflammatory and fibrotic states of Crohn’s disease [3]. In parallel, unsupervised learning pipelines combined with immune deconvolution enable data-driven stratification of hepatocellular carcinoma [4].

References

1. Cusworth S, Gkoutos GV, Acharjee A. A novel generative adversarial networks modelling for the class imbalance problem in high dimensional omics data. BMC Med Inform Decis Mak. 2024;24(1):90
2. Sadhukhan P, Acharjee A. T-SMmOTE: tweaked synthetic majority minority oversampling technique for data scarcity issue in multi omics studies. Bioinform Adv. 2026;6(1):vbag236
3. Philip D, Santos D, Mondal S, Alomar H, Gkoutos G, Acharjee A. Generative AI-augmented transcriptomic and microbiome analysis across inflammatory and fibrotic disease states in Crohn’s disease. Front Artif Intell. 2026;9:1881820
4. Reierson MM, Acharjee A. Unsupervised machine learning-based stratification and immune deconvolution of liver hepatocellular carcinoma. BMC Cancer. 2025;25(1)