Speaker: Saer Samanipour, Assistant Professor at the University of Amsterdam and honorary research fellow at the UQ, Australia
High resolution mass spectrometry is one of the main tools for chemical characterization of complex samples. The samples analyzed with this instrument result into large datasets comprising of up to 8.0e12 variables that could potentially carry crucial structural information about the sample chemistry. At the same time there are different sources of signal redundancy in such datasets. In this talk I will present two case studies where machine learning enables the removal of the data redundancy without any information loss. The first case study will discuss the seamless conversion from the profile mode to centroided and vice versa. In this case, we developed a self adjusting centroiding algorithm to detect and extract the meaningful information in such complex datasets. Additionally, a regression model was developed to convert the extracted information to the raw data. The second case study, is related to the development of a stochastic classification model to detect the isotopic signal in the mass spectra and therefore increase the level of confidence in the generated identifications.
Date: 22-06-2021 14:00-1500 Central European Summer time
Speaker: Pratyush Tiwary, Asst. Prof University of Maryland, Washington DC
The ability to rapidly learn from high-dimensional data to make reliable predictions about the future is crucial in many contexts. This could be a fly avoiding predators, or the retina processing terabytes of data guiding complex human actions. Modern day artificial intelligence (AI) aims to mimic this fidelity and has been successful in many domains of life. It is tempting to ask if AI could also be used to understand and predict the dynamics of complex molecules with millions of atoms. In this talk I will show that certain flavors of AI can indeed help us understand generic molecular dynamics and also predict it even in situations with arbitrary long memories. However this requires close integration of AI with old and new ideas in statistical mechanics. I will talk about such methods developed by my group (1-3). I will demonstrate the methods on different problems, where we predict mechanisms at timescales much longer than milliseconds while keeping all-atom/femtosecond resolution. These include ligand dissociation from flexible protein/RNA and crystal nucleation with competing polymorphs. I will conclude by discussing some generic challenges and solutions regarding reliability, interpretability and extrapolative powers of AI when used to guide and complement simulations and perhaps even experiments in chemistry.
Watch Back ›
For an overview of more previous colloquia, please have a look at out blog.