Experimental & Computational Chemist | Data Science in Chemistry

• 🧪 Postdoctoral Researcher at Sigman Lab & The Alegre Group
  Automating data science tools for catalytic chemical reactions.

• 🎓 PhD in Chemistry at ISQCH (CSIC)-University of Zaragoza
  "New luminescent compounds based on amino acid precursors and derivatives" (2020 – 2025, Gobierno de Aragón PhD fellowship).

• 👨‍🏫 Codirector & Professor at CAMLC Workshop
  Promoting advanced methodologies in machine learning and automation in chemistry.

• Machine Learning in Chemistry: Predictive modeling, reaction optimization.
• Automation: Python workflows for DFT calculations and chemical descriptor extraction.
• Data Science: Big Data analysis & visualization (Matplotlib, Seaborn, Plotly).

• Computational Chemistry: Gaussian, ORCA, GoodVibes, RDKit, PyMOL, Avogadro, OBabel, CREST.
• Programming: Python (Pandas, NumPy, Scikit-learn, BoTorch), Jupyter Notebooks.
• Version Control: GitHub, Git.

• ROBERT – Automated ML for chemistry.

  When I first embarked on the journey of developing ROBERT, I had absolutely no experience in Python. Coming from an experimental chemistry background, I was an absolute beginner in the realm of programming. My thesis supervisor, Juan V. Alegre Requena, introduced me to this new world and encouraged me to explore beyond traditional experimental methods. Starting from zero in Python, I quickly found myself overwhelmed by the ambitious scope of the project, yet every challenge became a stepping stone in my journey towards creating ROBERT. In the early stages, every line of code felt like a challenge. I leaned heavily on resources like Stack Overflow and YouTube tutorials, committing countless errors along the way. Each mistake, though frustrating at times, became a stepping stone that gradually built my programming skills. The process was far from linear; it was a cycle of trial, error, and continuous learning. Looking back now, with the perspective of the knowledge I’ve gained over time, I realize that I might have approached certain challenges differently. However, it was through these very mistakes that I learned the intricacies of Python and machine learning, ultimately enabling me to create ROBERT. I am immensely proud of what ROBERT has evolved into—a tool that not only automates ML processes for chemistry but also aims to be accessible to users with little to no prior experience. I remain deeply involved in the project, continuously working to enhance its usability so that anyone, regardless of their technical background, can apply machine learning effortlessly in their studies.

• AQME – QDESCP module for chemical descriptor automation.

• ROBERT: Bridging the Gap Between Machine Learning and Chemistry
  WIREs Comput Mol Sci, 2024, 14: e1733.

• Integrating Digital Chemistry within the Broader Chemistry Community
  Trends in Chemistry, 2024, 6 (8), 459–469.

• Machine Learning Workflows beyond Linear Models in Low-Data Regimes
  Chem. Sci. 2025. https://doi.org/10.1039/D5SC00996K.

📖 Full list available on ORCID.

• 2023: 🥇 Chemical Structure Association (CSA) Trust Grant
• 2022: 🏅 PhD fellowship from the Government of Aragon (DGA) for the period 2021–2025
• 2020: 🥇 Best academic record in the Master's Degree in Molecular Chemistry and Homogeneous Catalysis (2019–2020 academic year)
• 2020: 🏅 1st prize for the best Master's thesis in the "RSEQ-Aragón 2020 Final Master's Thesis Awards"

• 🚀 Current Stage & Future Goals

I am at a stage where I am integrating machine learning and automation into chemical research, streamlining data-driven workflows for reaction optimization. My main goal is to bridge the gap between computational methodologies and experimental chemistry, making advanced tools more accessible to the community.

• 🌐 Long-term Vision

I aspire to continue developing innovative computational tools for chemistry while mentoring young researchers in digital chemistry and automation. I aim to contribute to the evolution of data-driven methodologies in catalysis and photophysics.

• 💡 Teaching & Collaboration

I am passionate about scientific communication and interdisciplinary collaboration. I hope to expand my involvement in educational initiatives such as workshops and training programs to equip researchers with the necessary skills for the digital transformation of chemistry.

• 📧 Email: ddalmau@unizar.es
• 📍 Address: C/Pedro Cerbuna 12, 50009 Zaragoza, Spain