Data Champions Search

I am a neuroscientist studying human speech perception with the aim of advancing assistive speech (neuro)technologies and AI speech recognition systems. My background is in cognitive neuroscience and medicine.

I am an expert in human neurophysiology methods (electro- and magnetoencephalography, EEG/MEG) combined with machine learning and artificial neural network modelling (deep learning).

Since the beginning of my PhD, I’ve been passionate about reproducible and open science practices such as data and code sharing, and good coding practices including version control. In my department I am leading the adoption of the standardised Brain Imaging Data Structure (BIDS) for storing and sharing human neurophysiology (MEG/EEG) data.

Qi received her PhD at the University of California, Los Angeles, where she developed computational methods to study alternative splicing and the evolution of HIV. Later she joined the UCLA Division of Dermatology to help identify the resistance mechanisms of targeted cancer therapies using computational tools. 
    
In 2011 she was awarded the Humboldt Research Fellowship to work in the Division of Theoretical Bioinformatics, and later the Division of Applied Bioinformatics, at the German Cancer Research Centre. There she worked on diverse bioinformatics projects with NGS data, such as studying genome-wide epigenetic regulation of cell differentiation, developing sequencing protocols and detecting somatic mutations from whole-genome sequencing data, as well as data integration and predictive modelling. 
    
Currently, she provides bioinformatics training and support to PhD students and postdoctoral researchers in the lab of Professor Beverley Glover.

I am a Research Associate at the University of Cambridge, UK. I am also a Postdoctoral Affiliate of Trinity College, Cambridge. I am currently working on several exciting research problems concerning codon usage, optimality and, in general, knowledge discovery from large-scale genomic data. I am focusing on developing novel ML approaches, such as Neuro-Symbolic Models and Deep Neural Networks, to learn from genomic sequences. For more details, please visit my homepage, which is usually updated often: https://tirtharajdash.github.io/