Ph. D. Joel Ricci-López

  • Sr. Data scientist at AB InBev, Grupo Modelo.
  • Ph.D. in nanoscience and nanotechnology.
  • More than six years of experience working on data science and machine learning:
    • Applied to biological sciences, molecular modeling, and in silico drug discovery.
    • Experience on Python, R, SQL, Scikit-Learn, PySpark, TensorFlow, Azure Databricks, and PowerBI.
  • Passionate about programming, artificial intelligence, web development, and graphic design.

About me

About me

Hi, I’m Joel.

I was born in Oaxaca, México 🇲🇽. A magical place where you’ll find the best food you could ever eat.

I hold a Bachelor’s and a Master’s degree in Life Sciences 🧬. Currently, I’m finishing my Ph.D., working on computational molecular biology and data analysis focused on in silico drug discovery.

I have experience as a freelance web developer, data analyst, research assistant, and teacher.

During my career, I have developed skills in critical thinking, research, collaboration, problem-solving, project management, and self-organization.

I really love learning new things every day; programming, science, artificial intelligence, graphic design, etc.

I enjoy drawing, painting, and digital designing.

I love reading, especially science fiction and fantasy. Greg Egan, Carl Sagan, and George R. R. Martin are at the top of my favorite authors. I also like watching anime, playing chess, and playing video games.

My Projects

Current position:

Ph.D. Candidate in Nanoscience at Ensenada Center for Scientific Research and Higher Education (CICESE) and Nanoscience & Nanotechnology Centre (CNyN), UNAM. (2018 – present)

  • Thesis title:Virtual screening using machine learning techniques and ensemble docking-based molecular descriptors”.
  • Ph.D. Advisors: Dr. Carlos A. Brizuela and Sergio A. Águila.
  • Brief Synopsis of Research: 
    • We aimed to test and design a structure-based virtual screening pipeline combing molecular docking and machine learning to improve molecular virtual screening performance.
    • We employ High-Performance Computing resources, data analysis, and machine learning models to improve computer-aided drug discovery.

Research interests:

Machine learning, data science, computational biology, in silico drug discovery, molecular docking, molecular dynamics simulations, drug-target interaction prediction, ADMETox property prediction, QSAPR.

Professional experience:

  • Research Assistant
    • At Red nanoFAB:
      Working on molecular modeling and simulation of bionanomaterials under the supervision of Dr. Sergio A. Águila (redesnanofab@gmail.com). I employed python and bash scripting to perform data analysis over molecular simulations data, generated using HPC resources.
      January – April 2018.
  • Teaching
    • Assistant lecturer in Algorithms for Bioinformatics:
      Lectures related to Molecular Biology and Protein Bioinformatics. Under the supervision of Dr. Carlos A. Brizuela Rodríguez (cbrizuela@cicese.mx). M.Sc. in Computer Science, CICESE.
      January to February – 2022.
    • Assistant lecturer in Simulation of biological systems:
      Workshop on molecular dynamics and molecular docking simulations. Under the supervision of Dr. Sergio A. Águila. M.Sc. in Nanoscience and Nanotechnology, CNyN, UNAM. Workshop website .
      January to May – 2020 and 2021.
    • Assistant lecturer in Bioinformatics:
      Lectures and workshops related to Protein Bioinformatics. Under the supervision of Dr. M. Asunción Lago (alago@cicese.mx).  M.Sc. in Life Sciences, CICESE.
      January to February – 2019, 2020, and 2021.
  • Research Internship
    • High-performance molecular dynamics simulations and computational chemical studies:
      Under the supervision of Dr. Joel B. Alderete y la Dr. Verónica A. Jiménez Curihual (veronica.jimenez@unab.cl).
      Department of Chemical Sciences of Universidad Andrés Bello, Chile.
      March – April 2017.

Education:

  • Ph.D. Student in Nanoscience
    • Center for Scientific Research and Higher Education at Ensenada, B. C. México.
      Thesis: Virtual screening using machine learning techniques and ensemble docking-based molecular descriptors. 
      2018 – present
  • Deep Learning Summer School
    • Neuromatch Academy.
      International student in the Neuromatch Academy’s Deep Learning interactive course.
      120 hours of theoretical and practical projects on Neural Networks, CNNs, Sequential and Generative Models, and Reinforcement Learning. 

      August 2021
  • Artificial Intelligence Product Manager, Nanodegree
    • Udacity (view certificate )
      Nanodegree focused on the implementation and evaluation of the business value of an AI product.
      – Data acquisition and data curation using Appen.
      – ML models implementation using Google Cloud and AutoML.
      – AI project proposal focused on Drug Discovery.

      2020
  • MolSSI Software Summer School.
    • Best practices in software engineering – version control, continuous integration, data management and programming paradigms. By “The Molecular Sciences Software Institute” (MolSSI) at Texas Advanced Computing Center (TACC), Texas, USA.
      July 2019.
  • Master of Science degree in Life Sciences
  • Bachelor of degree in Biology
    • Universidad del Mar, Campus Puerto Escondido. Oaxaca, México.
      General exam to obtain bachelor’s degree in biology (EGEL-BIO).
      2009 – 2014

Scientific publications:

  • Research Articles
    • Ricci-Lopez, J., Aguila, S. A., Gilson, M. K. & Brizuela, C. A. (2021). Improving Structure-Based Virtual Screening with Ensemble Docking and Machine Learning. J. Chem. Inf. Model., doi: 10.1021/acs.jcim.1c00511
    • Ricci-Lopez, et al. (2019). Molecular modeling simulation studies reveal new potential inhibitors against HPV E6 protein. PLoS ONE 14(3), doi: 10.1371/journal.pone.0213028.
  • Scientific Posters:
  • Oral presentations:
    • Combining ensemble docking and machine learning to improve structure-based virtual screening.
      At American Chemical Society Fall 2021: Resilience of Chemistry, Division of Chemical Information. Atlanta, Georgia, USA.
      August 2021
    • Refining structured-based virtual screening through ensemble docking and machine learning.
      At III International Workshop On Computational Modeling of Biological Systems. Universidad del Quindio. Colombia.
      November 2020.
    • Aprendizaje de máquina aplicado a los scores de acoplamiento molecular en conglomerado.
      At III Coloquio de Simulaciones Computacionales en Ciencias, Universidad Nacional Autónoma de México, Ensenada, B. C., México. Best oral presentation award.
      August 2020.

Courses and Certificates:

  • Courses and Workshops
    • CABANA Workshop: Cheminformatics in Drug Discovery.
      Five days workshop. Structure-based drug design and Ligand-based drug design.
      By CABANA at CINVESTAV UGA LANGEBIO, México.
      October 2019
    • MOE workshop series: Ligand-Based Drug Design and SAR Analysis & Advanced Structure-Based Drug Design.
      By Chemical Computing Group. California, USA.
      September 2018
    • Computational Biology oriented to drug design, III.
      Two weeks course. Molecular docking and molecular dynamics simulations, fragment-based drug discovery, MD in mixed solvents and dynamic undocking, by CELFI Datos, University of Buenos Aires, Argentina.
      May 2018
  • Online Courses
    • Deep Learning Specialization (five courses).
      By Coursera – DeepLearning.Ai.  Certificate RK42DWNPUBD3
      January 2022
    • Applied Machine Learning with Python.
      By Coursera – University of Michigan. Credential Y8494V5ZL6Y5
      December 2021
    • AWS Machine Learning.
      By Udacity – AWS. Credential DG9NMPUA
      October 2021
    • Machine Learning.
      By Coursera – Stanford. License 5C9XH7E8RDDT
      June 2021
    • Machine Learning Scientist with Python (96 hours).
      By DataCampCredential 0236e8d560afd98ff6afbae32606b1c4f0369426
      March 2021
    • Using databases with Python.
      By Coursera – University of Michigan. Credential NEJJRT599V8J
      June 2019
    • Introduction to Data Science in Python.
      By Coursera – University of Michigan. Credential 6Z33HDXP553K
      January 2018
    • Python for Genomic Data Science.
      By Coursera: Johns Hopkins University.  Credential KT844NQQULF2
      May 2016

Language Proficency

  • Spanish: native language
  • English: proficient (TOEFL 603 pts)

Technical Skills

Programming Languages:

  • Python
  • R
  • Bash
  • JavaScript

Machine Learning:

  • Scikit-Learn
  • Keras
  • TensorFlow
  • PyTorch

Data Science:

  • SQL
  • Pandas
  • NumPy
  • Tidyverse
  • KNIME

Data Visualization:

  • Dash
  • Shiny
  • Plotly
  • Matplotlib
  • Bokeh

Version Control and Development:

  • Git
  • GitHub
  • Docker

Web Development:

  • WordPress
  • Elementor
  • HTML5
  • CSS3
  • React

Molecular Modelling:

  • Modeller
  • NAMD
  • AmberMD
  • AutoDock
  • VMD
  • UCSF Quimera
  • Bio3D
  • RDKit

Graphic Design:

  • Inkscape
  • Blender
  • Gimp

Soft Skills

  • Communication
  • Collaboration
  • Critical thinking
  • Curiosity
  • Creativity
  • Project management
  • Organization
  • Story Telling