Biology subjects

Mohammed Ali, L. K.

Publications and source records attributed to Mohammed Ali, L. K..

3 recordsLinked to original sources

bioRxiv2024

Biophysical Simulation Enables Multi-Scale Segmentation and Atlas Mapping for Top-Down Spatial Omics of the Nervous System

Spatial omics (SO) has produced high-definition mapping of subcellular molecules (like transcripts or proteins) within tissue samples. Mapping transcripts to anatomical regions requires segmentation, but even segmenting nuclei remains challenging for tissues like nerve cross sections, let alone for larger regions such as within the spinal cord. Neural networks could address this but need extensive human annotations--a bottleneck. We present SiDoLa-NS (Simulate, Dont Label - Nervous System), an image-driven (top-down) approach to SO analysis in the nervous system. We utilize biophysical properties of tissue architectures to design synthetic images mimicking tissue samples. With these in silico samples, we train supervised instance segmentation convolutional neural networks (CNNs) for nucleus segmentation, achieving precision and F1-scores > 0.95. We take this a step further with generalizable CNNs that can identify macroscopic tissue structures in the mouse brain (mAP50 = 0.869), spinal cord (mAP50 = 0.96), and pig sciatic nerve (mAP50 = 0.995). Short SummaryThe SiDoLa-NS micro-, meso-, and macro-scale models are generalizable, supervised CNNs for neuronal segmentation in cell to tissue-level contexts. SiDoLa-NS is novel in its combination of three core ideas: it is top-down (image first), trained solely on synthetic images, and it is multi-scale. The tool is validated on brain, spinal cord, and sciatic nerve for advanced segmentation tasks.

neuroscience↗

bioRxiv2023

Classification of iPSC-Derived Cultures Using Convolutional Neural Networks to Identify Single Differentiated Neurons for Isolation or Measurement

Understanding neurodegenerative disease pathology depends on a close examination of neurons and their processes. However, image-based single-cell analyses of neurons often require laborious and time-consuming manual classification tasks. Here, we present a machine learning approach leveraging convolutional neural network (CNN) classifiers that have the capability to accurately identify various classes of neuronal images, including single neurons. We developed the Single Neuron Identification Model 20-Class (SNIM20) which was trained on a dataset of induced pluripotent stem cell (iPSC)-derived motor neurons, containing over 12,000 images from 20 distinct classes. SNIM20 is built in TensorFlow and trained on images of differentiated iPSC cultures stained for nuclei and microtubules. This classifier demonstrated high predictive accuracy (AUC = 0.99) for distinguishing single neurons. Additionally, the 2-stage training framework can be used more broadly for cellular classification tasks. A variation was successfully trained on images of a human osteosarcoma cell line (U2OS) for single-cell classification (AUC = 0.99). While this framework was primarily designed for single-cell microraft-based identification and capture, it also works with cells in standard plate formats. We additionally explore the impact of specific fluorescent channels and brightfield images, class groupings, and transfer learning on the quality of the classification. This framework can both assist in high throughput neuronal or cellular identification and be used to train a custom classifier for the users needs.

neuroscience↗

bioRxiv2023

Pathogenic Morphological Signatures of Perturbations in Mitochondrial-Related Genes Revealed by Pooled Imaging Assay

Mutations in mitochondrial-related genes underlie numerous neurodegenerative diseases, yet the significance of most variants remains uncertain concerning disease phenotypes. Several thousand genes have been shown to regulate mitochondria in eukaryotic cells, but which of these genes are necessary for proper mitochondrial dynamics? We investigated the degree of morphological disruptions in mitochondrial gene-silenced cells to understand the magnitude of genetic contribution to properly functioning mitochondria and to identify pathogenic variants. We analyzed 5,835 gRNAs in a high dimensional phenotypic dataset produced by the image-based pooled analysis platform Raft-Seq. Using the MFN2-mutant cell phenotype, we identified several genes, including TMEM11, TIMM8A, and three NADH Ubiquinone proteins, as crucial for normal mitochondrial morphology in human U2OS cells. Additionally, we found several missense and UTR variants within the genes SLC25A19 and ATAD3A as drivers of mitochondrial aggregation. By examining multiple features instead of a single readout, this analysis was powered to detect genes which had morphological signatures aligned with MFN2-mutant phenotypes. Reanalysis with anomaly detection revealed other critical genes, including APOOL, MCEE, NIT, PHB, and SLC16A7, which perturb mitochondrial network morphology in a manner divergent from MFN2. These studies offer insights into the molecular basis for mitochondrial dysfunction, setting the stage for new genomic diagnostics and therapeutic discovery.

genetics↗