Didier Barradas Bautista
📍 Current Position
Data Scientist, CoreLabs Staff at KAUST
Data Scientist & Visualization Expert
NVIDIA Ambassador | Carpentries Certified Instructor | Scientific Research Advocate
About Me
I am a Data Scientist and Visualization Expert at KAUST with over 15 years of experience in machine learning, high-performance computing, and scientific research. My passion lies in bridging the gap between complex computational methods and practical applications in biology, chemistry, and materials science.
As an NVIDIA Ambassador and Certified Instructor with The Carpentries, I'm dedicated to democratizing AI and data science education. I combine strong technical expertise with a commitment to training the next generation of scientists and engineers.
My expertise spans machine learning model development, GPU-accelerated computing, data visualization, and educational outreach. I believe in making advanced technologies accessible and have trained over 100 students worldwide.
Academic & Professional Achievements
Ph.D. in Bioinformatics
Barcelona Supercomputing Center (2012-2017), Cum laude degree with focus on protein structure prediction and machine learning.
NVIDIA Ambassador
Recognized technical leader advancing GPU computing and AI solutions in the scientific community.
Carpentries Instructor
Certified instructor delivering hands-on training in data science, programming, and research skills to global audiences.
Funded Research
Secured USD $112k in KAUST AI Initiative grants for data curation, AI development, and exploratory research projects.
Published Researcher
Co-author of 8+ peer-reviewed publications in top-tier journals (Coral Reefs, Proteins, Proteomics, Nucleic Acids Research).
International Recognition
Member of National Researchers System (CONACYT) and ISCB with recognition from scientific institutions globally.
Featured Projects
Coral-CAT: Coral Color Analysis
Semi-automatic pipeline for coral health monitoring using color analysis from images with reference charts
ForamDeepSlice: Foraminifera Classification
AI framework using deep learning to classify 12 foraminifera species from micro-CT scans with high accuracy
Chem-Phen: Chemical Ligand Design
Machine learning pipeline for designing phenanthroline ligands with improved metal binding using PubChem data
GPU Profiling on Ibex
Comprehensive toolkit for profiling GPU workloads on KAUST Ibex cluster with NVIDIA tools and optimization utilities
RAPIDS-HPO: GPU Data Science
Advanced notebooks demonstrating GPU-accelerated data science using RAPIDS library, DASK, and Skorch
ESCience25 Tutorial
Advanced Data Science techniques leveraging GPU acceleration workshop presented at eScience 2025 conference
Skills & Technologies
Programming Languages
Machine Learning & AI
Data Visualization & BI
Tools & Platforms
Recent Publications
Peer-reviewed research contributions to top-tier scientific journals and conferences
Increasing the fraction of correct solutions in ensembles of protein–protein docking models
Authors: T. Ricciardelli, D. Barradas, Z. Cao, M. Chawla, L. Cavallo, R. Oliva
Protein Science
Iterative consensus algorithm for improving protein-protein docking model predictions.
View on Google ScholarForamDeepSlice: A High-Accuracy Deep Learning Framework for Foraminifera Species Classification
Authors: A. Halimi, A. Alibrahim, D. Barradas, R. Sicat, A. M. Afifi
arXiv
Deep learning framework for classifying foraminifera species from 2D micro-CT slices with high accuracy.
View on Google ScholarCoral-CAT: A semi-automatic coral color analysis tool
Authors: N. Garcias-Bonet, D. Barradas, M. Casartelli, A. Halimi, R. Peixoto
Coral Reefs
Semi-automatic pipeline for coral health monitoring using color analysis from images with reference charts.
View on Google ScholarOptimizing GAN Training for 3D Seismic Microstructure Generation
Authors: Y. Ghazal, M. Awadalla, D. Barradas, A. Ayyad, A. Nasr, S. Ghani
Eighth High Performance Computing Workshop
Optimization techniques for training generative adversarial networks on HPC systems.
View on Google ScholarThe LightDock Server: AI-powered modeling of macromolecular interactions
Authors: B. Jiménez-García, J. Roel-Touris, D. Barradas-Bautista
Nucleic Acids Research
Web server for artificial intelligence-powered protein docking and interaction modeling.
View on Google Scholar