Biology subjects

Karpatne, A.

Publications and source records attributed to Karpatne, A..

4 recordsLinked to original sources

bioRxiv2025

HAVEN: Hierarchical Attention for Viral protEin-based host iNference

It is crucial to accurately predict hosts of viruses to understand and anticipate human infectious diseases that originate from animals. There is a lack of versatile models that handle out-of-distribution factors such as unseen hosts and viruses. We develop a machine learning model for predicting the host infected by a virus, given only the sequence of a protein encoded by the genome of that virus. Our approach, HAVEN, is the first to apply to multiple hosts and to generalize to unseen hosts and viruses. HAVEN is a transformer-based architecture coupled with hierarchical self-attention that can accept sequences of highly diverse lengths. We integrate HAVEN with a prototype-based few-shot learning classifier to predict rare classes. We demonstrate the accuracy, robustness, and generalizability of HAVEN through a comprehensive series of experiments. In particular, we show that HAVEN can achieve a median AUPRC of 0.67 while predicting common hosts. Moreover, HAVEN retains this AUPRC value even for rare hosts (median prevalence as low as 0.09%). Our model performs on par with state-of-the-art foundation models, which are 65 to 5, 000 times larger in size, and outperforms them in identifying hosts of SARS-CoV-2 variants of concern.

bioinformatics↗

bioRxiv2022

Deep Learning Enabled Label-free Cell Force Computation in Deformable Fibrous Environments

Cells move within tissues by pulling on and reshaping their fibrous surroundings. Measuring the associated forces has been a fundamental challenge in cell biology. Here, we develop deep-learning-enabled live-cell fiber-force microscopy (DLFM), which computes forces produced by living cells in real time as they interact with tissue-like fiber networks. DLFM combines basic phase microscopy with novel deep learning to simultaneously track cell movement and fiber deformation without disruptive fluorescent labels or chemical modifications. This allowed us to measure forces in real-time situations that were previously impossible to study, revealing an intricate mechanical landscape: cells generate ten-fold changes in force as they change shape during migration, create force-dipoles during cell-cell interactions, and dramatically alter their force patterns during stem cell differentiation. Through integrated experiments and mathematical modeling, we discovered that cells in fibrous environments form force-generating adhesions throughout their body, strikingly different from the edge-only adhesions seen in traditional petri dish experiments. Results clarify cytoskeletal pathways by which cells adapt force-generating machinery to navigate the fibrous architecture of tissues.

biophysics↗

bioRxiv2021

Biodiversity Image Quality Metadata Augments Convolutional Neural Network Classification of Fish Species

Biodiversity image repositories are crucial sources of training data for machine learning approaches to biological research. Metadata, specifically metadata about object quality, is putatively an important prerequisite to selecting sample subsets for these experiments. This study demonstrates the importance of image quality metadata to a species classification experiment involving a corpus of 1935 fish specimen images which were annotated with 22 metadata quality properties. A small subset of high quality images produced an F1 accuracy of 0.41 compared to 0.35 for a taxonomically matched subset of low quality images when used by a convolutional neural network approach to species identification. Using the full corpus of images revealed that image quality differed between correctly classified and misclassified images. We found the visibility of all anatomical features was the most important quality feature for classification accuracy. We suggest biodiversity image repositories consider adopting a minimal set of image quality metadata to support future machine learning projects.

evolutionary biology↗

bioRxiv2021

Hierarchy-guided Neural Networks for Species Classification

O_LISpecies classification is an important task that is the foundation of industrial, commercial, ecological, and scientific applications involving the study of species distributions, dynamics, and evolution. C_LIO_LIWhile conventional approaches for this task use off-the-shelf machine learning (ML) methods such as existing Convolutional Neural Network (ConvNet) architectures, there is an opportunity to inform the ConvNet architecture using our knowledge of biological hierarchies among taxonomic classes. C_LIO_LIIn this work, we propose a new approach for species classification termed Hierarchy-Guided Neural Network (HGNN), which infuses hierarchical taxonomic information into the neural networks training to guide the structure and relationships among the extracted features. We perform extensive experiments on an illustrative use-case of classifying fish species to demonstrate that HGNN outperforms conventional ConvNet models in terms of classification accuracy, especially under scarce training data conditions. C_LIO_LIWe also observe that HGNN shows better resilience to adversarial occlusions, when some of the most informative patch regions of the image are intentionally blocked and their effect on classification accuracy is studied. C_LI

evolutionary biology↗