Zain Ul Abideen

Scientific machine learning researcher · Building research software for AI-driven science

ML Interatomic Potentials · AI for Drug Discovery · NLP, Generative & Agentic AI

Zain Ul Abideen

About

Computational researcher working at the intersection of scientific machine learning, molecular modelling and artificial intelligence, with a focus on machine-learning interatomic potentials, AI-enabled drug discovery and generative AI systems.

I build open, reproducible scientific software so that others can train, test and use these models.

Core skills

All skills →
ML interatomic potentials
  • MACE
  • NequIP
  • Allegro
  • SchNet
  • PaiNN
Drug discovery and cheminformatics
  • RDKit
  • Chemprop
  • DeepChem
  • PyTorch Geometric
  • ChemBERTa
  • Mordred
Atomistic simulation
  • ASE
  • OpenMM
  • GROMACS
  • MDAnalysis
  • DScribe
Machine learning
  • Python
  • PyTorch
  • PyTorch Lightning
  • Scikit-learn
  • XGBoost
  • Hugging Face Transformers
Generative AI and agents
  • LangChain
  • LangGraph
  • CrewAI
  • LoRA
  • PEFT
  • FAISS
Research software and MLOps
  • SLURM
  • Docker
  • GitHub Actions
  • CI/CD pipelines
  • FastAPI
  • Git

Featured research software

QDSpace

Browser tools for building quantum dots with facet, shape and ligand-passivation control, plus a library of DFT-relaxed perovskite, II–VI and III–V structures with interactive PDOS and COOP plots.

QDSpace Desktop

The QDSpace quantum-dot tools as a standalone desktop application, with a built-in local property calculator based on MACE.

Research areas

Selected publications

  1. Preprint 2026 • arXiv

    Benchmarking Machine-Learning Interatomic Potentials for Dynamical Stability in Inorganic Semiconductor Nanocrystals: A CdSe Case Study

    M. Usman, M. Suleymanova, Z. U. Abideen, M. Fernández-Pendás, I. Infante · DOI

  2. Journal 2024 • Journal of Computer Science and Technology

    A Novel NLP-Based Stock Market Price Prediction and Risk Analysis Framework

    Z. Ul-Abideen, R. H. Ali, A. I. Zeeshan, T. A. Khan · 24, no. 2: e07 · DOI

Contact

↑