Implementation of Matcha: Multi-Stage Riemannian Flow Matching for Accurate and Physically Valid Molecular Docking

MULAN: Multimodal Protein Language Model for Sequence and Structure Encoding

Scripts to run AlphaFold3, Boltz-1 and Chai-1 with MMseqs2 MSAs and custom templates.

This project develops a machine learning model using Chebyshev graph convolutions within a Kernel-based Attention Network (KAN) to accurately predict Fukui indices, which are essential for assessin…

Merging, linking and placing compounds by stitching bound compounds together like a reanimated corpse

Training and inference code for ShEPhERD: Diffusing shape, electrostatics, and pharmacophores for bioisosteric drug design [ICLR 2025 oral]

Library for studying Cayley graphs and Schreier coset graphs

A meticulously curated resource list focused on computational methods for drug discovery.

Explainer for black box models that predict molecule properties

Automatic extraction of interacting compound-target pairs from ChEMBL.

The LPCE project is designed to purify and process PDB structures to extract and filter ligands and remove unwanted components such as water molecules and junk ligands.

My own Prompts for Custom instructions ChatGPT

AI molecular design tool for de novo design, scaffold hopping, R-group replacement, linker design and molecule optimization.

CReM: chemically reasonable mutations framework

Implementation of Lilly Medchem Rules - J Med Chem 2012

Docker image to run Samba (compatible Time Machine for macOS)

ChEMBL database structure pipelines

Lo-Hi Splitter for Modern Splits of Molecular Datasets

QSARtuna: QSAR model building with the optuna framework

Automated creation and manipulation of Chemical Reaction Networks (CRNs) in heterogeneous catalysis, allowing the evaluation of species and reaction properties with data-driven ML models and the ne…

A high-throughput and memory-efficient inference and serving engine for LLMs

TensorRT LLM provides users with an easy-to-use Python API to define Large Language Models (LLMs) and supports state-of-the-art optimizations to perform inference efficiently on NVIDIA GPUs. Tensor…

CGRs, molecules and reactions manipulation

Codebase and CLI for PLAPT: A state-of-the-art protein-ligand binding affinity model for drug discovery