Practical workflow helps non-programmers use published ai models easily

PRAISE: A Reproducible Workflow for Non-Programmer Scientists to Implement Published AI Models

Artificial IntelligenceMachine Learning

Summary

Many scientists want to use AI models published in research but don't know how to program or handle data properly. The authors created PRAISE, a step-by-step guide that helps beginners implement these AI models even without coding skills. PRAISE also plans for common problems and tells users how to fix them. They tested this with chemistry students who were able to reproduce and improve a complex AI model about enzymes, showing this method really works.

What this means in practice

  • For laboratory technicians: Implement published AI models in lab experiments without programming knowledge to enhance data analysis.
  • For bioinformatics analysts: Enable applying existing AI models on biological datasets more quickly by following an accessible, reproducible workflow.

Authors

Max Achterweust, Stefan Groot Nibbelink, Vincent J. de Beer, Stefan Schipper, Zeynep Yüksektepe, Pedro Andrade da Silva, Aurelia Peppelaar, Martijn J. van der Willigen, Christophe B. Minkenberg, Robert F. van der Willigen

Abstract

Artificial Intelligence (AI) models are increasingly developed, published and used across scientific fields. Researchers, students and industry professionals who want to apply these models to their own research questions often lack the programming and data science expertise to do so. Existing guidelines cover single steps, but not the route from a published model to working predictions on one's own data. Here we present the hands-on workflow PRAISE, a Practical, Reproducible AI-model Implementation for Science and Education, that helps non-programmers implement published AI models step by step. Because implementations rarely work the first time, PRAISE anticipates common failures and provides a fallback route for each. As a proof of principle, three BSc chemistry students and their tutor applied PRAISE without prior programming or data science knowledge. They reproduced, validated and extended a state-of-the-art model that predicts enzyme-substrate interactions. This shows that with PRAISE, implementing an AI model from the literature becomes a learnable skill, one that turns non-programmer scientists from users into evaluators and improvers of AI models.