AI-Assisted Forward Modeling of Biological Structures

Abstract

The rise of machine learning and deep learning technologies have allowed researchers to automate image classification. We describe a method that incorporates automated image classification and principal component analysis to evaluate computational models of biological structures. We use a computational model of the kinetochore to demonstrate our artificial-intelligence (AI)-assisted modeling method. The kinetochore is a large protein complex that connects chromosomes to the mitotic spindle to facilitate proper cell division. The kinetochore can be divided into two regions: the inner kinetochore, including proteins that interact with DNA; and the outer kinetochore, comprised of microtubule-binding proteins. These two kinetochore regions have been shown to have different distributions during metaphase in live budding yeast and therefore act as a test case for our forward modeling technique. We find that a simple convolutional neural net (CNN) can correctly classify fluorescent images of inner and outer kinetochore proteins and show a CNN trained on simulated, fluorescent images can detect difference in experimental images. A polymer model of the ribosomal DNA locus serves as a second test for the method. The nucleolus surrounds the ribosomal DNA locus and appears amorphous in live-cell, fluorescent microscopy experiments in budding yeast, making detection of morphological changes challenging. We show a simple CNN can detect subtle differences in simulated images of the ribosomal DNA locus, demonstrating our CNN-based classification technique can be used on a variety of biological structures.

Deep Learning-Based 3D Shape Feature Extraction on Flash Animation Style

“…The role of the generator is to convert the random vectors in the potential space into the generated samples to deceive the discriminator, while the discriminator needs to distinguish the real samples from the generated samples. 5 Wireless Communications and Mobile Computing applied to deep learning models, such as views, point clouds, meshes, and voxels [22]. The representation of data geometry commonly used for deep learning models is given in Figure 8.…”

Polymer models reveal how chromatin modification can modulate force at the kinetochore

“…We utilized a three-dimensional kinetochore simulator representing the kinetochore as a 70 nm linear rod to distinguish mechanisms of kinetochore responsiveness to microtubule perturbations ( Lawrimore et al. , 2019 ).…”

“…This application allows users to generate custom three-dimensional models of the budding yeast mitotic spindle and kinetochore complex. The angle of the rod relative to the kinetochore microtubule to which it is bound can be increased to cause the inner kinetochore protein to become radially displaced ( Lawrimore et al. , 2019 ).…”

“…The entire kinetochore complex is simulated as a 70-nm-long vector. The number of vectors and their orientations in three-dimensional space can be specified by the user ( Lawrimore et al. , 2019 ).…”

Detection of Frog virus 3 via the system integrating RPA-CRISPR/Cas12a-SPM with deep learning

“…Recently, machine learning and deep learning are used to quantify the concentrations of virus DNA from fluorescence images (Shiaelis et al 2020), which makes the detection system integrated and time-consuming. Conventional neural networks (CNNs) are widely used to learn features from the raw pixelated images for a given classification task in an end-to-end manner (Liu et al 2022; Lawrimore et al 2019; Yang et al 2021; Zhang et al 2022). The most popular CNN-based deep learning models, such as AlexNet, DenseNet-121, and EfficientNet-B7, have been widely applied in medical image classification (Xie et al 2020; Wang et al 2021).…”