Biology subjects

Hyvarinen, A.

Publications and source records attributed to Hyvarinen, A..

3 recordsLinked to original sources

bioRxiv2024

Towards Interpretable Cryo-EM: Disentangling Latent Spaces of Molecular Conformations

Molecules are essential building blocks of life and their different conformations (i.e., shapes) crucially determine the functional role that they play in living organisms. Cryogenic Electron Microscopy (cryo-EM) allows for acquisition of large image datasets of individual molecules. Recent advances in computational cryo-EM have made it possible to learn latent variable models of conformation landscapes. However, interpreting these latent spaces remains a challenge as their individual dimensions are often arbitrary. The key message of our work is that this interpretation challenge can be viewed as an Independent Component Analysis (ICA) problem where we seek models that have the property of identifiability. That means, they have an essentially unique solution, representing a conformational latent space that separates the different degrees of freedom a molecule is equipped with in nature. Thus, we aim to advance the computational field of cryo-EM beyond visualizations as we connect it with the theoretical framework of (nonlinear) ICA and discuss the need for identifiable models, improved metrics, and benchmarks. Moving forward, we propose future directions for enhancing the disentanglement of latent spaces in cryo-EM, refining evaluation metrics and exploring techniques that leverage physics-based decoders of biomolecular systems. Moreover, we discuss how future technological developments in time-resolved single particle imaging may enable the application of nonlinear ICA models that can discover the true conformation changes of molecules in nature. The pursuit of interpretable conformational latent spaces will empower researchers to unravel complex biological processes and facilitate targeted interventions. This has significant implications for drug discovery and structural biology more broadly. More generally, latent variable models are deployed widely across many scientific disciplines. Thus, the argument we present in this work has much broader applications in AI for science if we want to move from impressive nonlinear neural network models to mathematically grounded methods that can help us learn something new about nature.

molecular biology↗

bioRxiv2019

PCA-based source-space contrast maps reveal psychologically meaningful individual differences in continuous MEG activity

Within the field of neuroimaging, there has been an increasing trend towards studying brain activity in naturalistic conditions, and it is possible to robustly estimate networks of on-going oscillatory activity in the brain. However, not many studies have focused on differences between individuals in on-going brain activity that would be associable to psychological or behavioral characteristics. Existing standard methods can perform well at single-participant level, but generalizing the methodology across many participants is challenging due to individual differences of brains. As an example of a clinically relevant, naturalistic condition we consider here mindfulness. Trait mindfulness, as well as a mindfulness-based intervention cultivating focused attention, is often associated with benefits for psychological health. Therefore, the manner in which the brain engages in focused attention vs. mind wandering is likely to associate with individual differences in psycho-behavioral tendencies.\n\nWe recorded MEG from 29 participants both in a state of focused attention and in a state of simulated mind wandering. We used Principal Component Analysis to decompose spatial average activation maps of focused attention contrasted with two different mind wandering states. The first principal component, which reflected differential engagement of bilateral parietal areas during focused attention vs. mind wandering, was associated with behavioral characteristics of inhibition, anxiousness and depression, as measured by standard questionnaires. We demonstrated that such decomposition of time-averaged contrast maps can overcome some of the challenges in methods based on concatenated data, especially from the perspective of behaviorally and clinically relevant characteristics in the ongoing brain oscillatory activity.\n\nHighlightsO_LIWe present a specific method to analyse/establish associations between brain oscillations and behavioral characteristics.\nC_LIO_LIWe found that activity levels in parietal areas during mind wandering compared to focused attention were associated with the behavioral trait of inhibition and anxiety.\nC_LI

neuroscience↗

bioRxiv2016

A mixture of sparse coding models explaining properties of face neurons related to holistic and parts-based processing

Experimental studies have revealed evidence of both parts-based and holistic representations of objects and faces in the primate visual system. However, it is still a mystery how such seemingly contradictory types of processing can coexist within a single system. Here, we propose a novel theory called mixture of sparse coding models, inspired by the formation of category-specific subregions in the inferotemporal (IT) cortex. We developed a hierarchical network that constructed a mixture of two sparse coding submodels on top of a simple Gabor analysis. The submodels were each trained with face or non-face object images, which resulted in separate representations of facial parts and object parts. Importantly, evoked neural activities were modeled by Bayesian inference, which had a top-down explaining-away effect that enabled recognition of an individual part to depend strongly on the category of the whole input. We show that this explaining-away effect was indeed crucial for the units in the face submodel to exhibit significant selectivity to face images over object images in a similar way to actual face-selective neurons in the macaque IT cortex. Furthermore, the model explained, qualitatively and quantitatively, several tuning properties to facial features found in the middle patch of face processing in IT as documented by Freiwald, Tsao, and Livingstone (2009). These included, in particular, tuning to only a small number of facial features that were often related to geometrically large parts like face outline and hair, preference and anti-preference of extreme facial features (e.g., very large/small inter-eye distance), and reduction of the gain of feature tuning for partial face stimuli compared to whole face stimuli. Thus, we hypothesize that the coding principle of facial features in the middle patch of face processing in the macaque IT cortex may be closely related to mixture of sparse coding models.

neuroscience↗