List of Molecular and Material design using Generative AI and Deep Learning

Experiments with expanded ensembles to explore chemical space

Reinforcement Learning for Molecular Design Guided by Quantum Mechanics

DENOPTIM is a software package for de novo design and virtual screening of functional molecules of any kind.

GaudiMM: A modular optimization platform for molecular design

ChemBFN: Bayesian Flow Network Framework for Chemistry Tasks. Developed in Hiroshima University.

Molecular generation using diffusion models and autoregressive transformer models

GPT (Generative Pre-trained Transformer) for de novo molecular design by enforcing specified targets

Agent-driven molecular optimization over chemical space, using Rowan for property scoring and RDKit for constraint-aware candidate design.

MolMiner, a generative model for fragment-based, 3D-aware, inverse conditional molecular design

A generative AI framework for 3D molecular generation and data-driven molecular design in computational chemistry.

An interactive data exploration tool for json structured ionic liquid data from ILThermo (NIST)

A Quantitative Ring Complexity Index for Profiling Ring Topology and Chemical Diversity

Multi-objective generative AI for designing novel brain-targeting small molecules.

MARS, Molecular Assembling and Representation Suite, is a program for general purpose computer aided molecular design. This program uses an integer arry data structure to store the information of atom type, atom connectivity, and bond order of a molecule. There are also subroutines that can be used to modify the data structure in order to genera…

BioInsectiNet is a Python-based framework that uses neural networks and genetic algorithms to design and optimize bioinsecticides targeting specific proteins. It generates novel SMILES compounds, predicts toxicity and affinity using IC50 data from FASTA sequences, and performs molecular docking for 3D interaction analysis.

Deep Learning-Based Property Prediction and Generation of Molecules

Molecular design of solvents coupling variational autoencoder and nonlinear programming

My PhD dissertation

3D pharmacophore-conditioned molecular diffusion with an E(3)-equivariant EGNN backbone. Generates shape-complementary, drug-like molecules conditioned on pharmacophore point clouds and PMI/SSD shape descriptors. Inspired by ShEPhERD (Adams et al., ICLR Oral 2025). PyTorch · e3nn · RDKit.