skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: ChatGPT Translation of Program Code for Image Sketch Abstraction
In this comprehensive study, a novel MATLAB to Python (M-to-PY) conversion process is showcased, specifically tailored for an intricate image skeletonization project involving fifteen MATLAB files and a large dataset. The central innovation of this research is the adept use of ChatGPT-4 as an AI assistant, pivotal in crafting a prototype M-to-PY converter. This converter’s capabilities were thoroughly evaluated using a set of test cases generated by the Bard bot, ensuring a robust and effective tool. The culmination of this effort was the development of the Skeleton App, adept at image sketching and skeletonization. This live and publicly available app underscores the enormous potential of AI in enhancing the transition of scientific research from MATLAB to Python. The study highlights the blend of AI’s computational prowess and human ingenuity in computational research, making significant strides in AI-assisted scientific exploration and tool development.  more » « less
Award ID(s):
1953052
PAR ID:
10542631
Author(s) / Creator(s):
; ; ; ; ; ;
Publisher / Repository:
MDPI
Date Published:
Journal Name:
Applied Sciences
Volume:
14
Issue:
3
ISSN:
2076-3417
Page Range / eLocation ID:
992
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Bioinformatics Advances)
    Abstract MotivationVolumetric 3D object analyses are being applied in research fields such as structural bioinformatics, biophysics, and structural biology, with potential integration of artificial intelligence/machine learning (AI/ML) techniques. One such method, 3D Zernike moments, has proven valuable in analyzing protein structures (e.g., protein fold classification, protein–protein interaction analysis, and molecular dynamics simulations). Their compactness and efficiency make them amenable to large-scale analyses. Established methods for deriving 3D Zernike moments, however, can be inefficient, particularly when higher order terms are required, hindering broader applications. As the volume of experimental and computationally-predicted protein structure information continues to increase, structural biology has become a “big data” science requiring more efficient analysis tools. ResultsThis application note presents a Python-based software package, ZMPY3D, to accelerate computation of 3D Zernike moments by vectorizing the mathematical formulae and using graphical processing units (GPUs). The package offers popular GPU-supported libraries such as CuPy and TensorFlow together with NumPy implementations, aiming to improve computational efficiency, adaptability, and flexibility in future algorithm development. The ZMPY3D package can be installed via PyPI, and the source code is available from GitHub. Volumetric-based protein 3D structural similarity scores and transform matrix of superposition functionalities have both been implemented, creating a powerful computational tool that will allow the research community to amalgamate 3D Zernike moments with existing AI/ML tools, to advance research and education in protein structure bioinformatics. Availability and implementationZMPY3D, implemented in Python, is available on GitHub (https://github.com/tawssie/ZMPY3D) and PyPI, released under the GPL License. 
    more » « less
  2. (, Proceedings of the Human Factors and Ergonomics Society Annual Meeting)
    Voice-enabled technologies such as VoiceOver (screen reader) and the Seeing AI app (image recognition) have revolutionized daily tasks for people with visual disabilities, fostering greater independence and information access. However, a gap remains in understanding the user experience (UX) of these technologies. This study investigated how those with visual disabilities interacted with VoiceOver and the Seeing AI app. A convenience sample of eight participants with visual disabilities engaged in direct observations while using these technologies. The study utilized the System Usability Scale (SUS) to assess perceived usability and analyzed findings using descriptive statistics. Results indicated a poorer UX with VoiceOver compared to the Seeing AI app, with challenges identified in graphical user interfaces (GUIs), voice and gesture commands. Relevant recommendations were made to enhance usability. The study emphasizes the need for more intuitive GUIs and optimized voice/gesture interactions for users with visual disabilities. 
    more » « less
  3. ; (, PEARC '19: Proceedings of the Practice and Experience in Advanced Research Computing on Rise of the Machines (learning))
    Artificial intelligence (AI) has immense potential spanning research and industry. AI applications abound and are expanding rapidly, yet the methods, performance, and understanding of AI are in their infancy. Researchers face vexing issues such as how to improve performance, transferability, reliability, comprehensibility, and how better to train AI models with only limited data. Future progress depends on advances in hardware accelerators, software frameworks, system and architectures, and creating cross-cutting expertise between scientific and AI domains. Open Compass is an exploratory research project to conduct academic pilot studies on an advanced engineering testbed for artificial intelligence, the Compass Lab, culminating in the development and publication of best practices for the benefit of the broad scientific community. Open Compass includes the development of an ontology to describe the complex range of existing and emerging AI hardware technologies and the identification of benchmark problems that represent different challenges in training deep learning models. These benchmarks are then used to execute experiments in alternative advanced hardware solution architectures. Here we present the methodology of Open Compass and some preliminary results on analyzing the effects of different GPU types, memory, and topologies for popular deep learning models applicable to image processing. 
    more » « less
  4. ; ; ; (, The Biophysicist)
    ABSTRACT Biophysics research is exciting because physical approaches to biology can provide novel insights, and it is challenging because it requires knowledge and skills from multiple disciplines. We have developed an undergraduate biophysics laboratory module that teaches fundamental skills such as time-lapse microscopy, image analysis, programming, critical reading of scientific literature, and basics of scientific writing and peer review. The module is accessible to students who are familiar with introductory statistics, cell biology, and differential calculus. We used published research on the biomechanics ofHydramouth opening as a framework because it describes a stunning biological phenomenon:Hydra, a freshwater polyp, generates a multicell-wide mouth opening in an otherwise closed epithelium through extreme cell deformations within seconds. This publication was co–first authored by an undergraduate and was featured in the public press, thus providing multiple anchors that make the research accessible and motivating to undergraduates. Students start with a critical reading and discussion of the publication and then execute some of the experiments and analysis from the publication, thereby learning fluorescence time-lapse microscopy and image analysis by using ImageJ and/or MATLAB. Students quantify the kinematics of the tissue deformations during mouth opening and compare their data to the literature. The module culminates in the students writing a short paper about their results following themicroPublicationjournal style, a blinded peer review, and final paper submission. Here, we describe one possible implementation of the module with the necessary resources to reproduce it and summarize student feedback from a pilot run. We also provide suggestions for more advanced exercises and for using Python for data analysis. Several students expressed that repeating a published study completed by an undergraduate inspired and motivated them, thus creating buy-in and assurance that they can do it, which we expect to help with confidence and retention. 
    more » « less
  5. ; ; ; ; ; (, Bioinformatics Advances)
    Abstract SummaryMolecular mechanisms of biological functions and disease processes are exceptionally complex, and our ability to interrogate and understand relationships is becoming increasingly dependent on the use of computational modeling. We have developed “BioModME,” a standalone R-based web application package, providing an intuitive and comprehensive graphical user interface to help investigators build, solve, visualize, and analyze computational models of complex biological systems. Some important features of the application package include multi-region system modeling, custom reaction rate laws and equations, unit conversion, model parameter estimation utilizing experimental data, and import and export of model information in the Systems Biology Matkup Language format. The users can also export models to MATLAB, R, and Python languages and the equations to LaTeX and Mathematical Markup Language formats. Other important features include an online model development platform, multi-modality visualization tool, and efficient numerical solvers for differential-algebraic equations and optimization. Availability and implementationAll relevant software information including documentation and tutorials can be found at https://mcw.marquette.edu/biomedical-engineering/computational-systems-biology-lab/biomodme.php. Deployed software can be accessed at https://biomodme.ctsi.mcw.edu/. Source code is freely available for download at https://github.com/MCWComputationalBiologyLab/BioModME. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email