/tools

Chembience is a Docker-based platform designed for the rapid development of cheminformatics-centric web applications and microservices. It leverages RDKit for molecular data processing and supports the creation of applications that can predict molecular properties and handle various molecule types.

DiffPhore is a tool that implements a knowledge-guided diffusion model for mapping ligands to pharmacophores in 3D space. It enhances virtual screening capabilities and provides datasets for pharmacophore-ligand pairs, making it useful for drug discovery applications.

QCMaquis is a C++ implementation of the DMRG algorithm designed for quantum chemical calculations. It allows for the optimization of wave functions and the calculation of various quantum properties, making it a valuable tool in computational chemistry.

Serenity is a quantum chemistry code designed for subsystem and embedding methods, enabling users to perform quantum chemical calculations. It supports various molecular simulations and property predictions, making it a valuable tool in computational chemistry.

eRMSF is a Python package designed for performing ensemble-based Root Mean Square Fluctuation (RMSF) analyses of molecular dynamics and structural ensembles. It allows users to customize atom and residue selections to gain insights into molecular motions and stability.

Runs N' Poses is a benchmark dataset designed for evaluating protein-ligand co-folding prediction methods. It includes various metrics and data formats to facilitate machine learning applications in molecular biology, particularly for assessing the generalization of prediction models.

ChemLIFT is a tool that leverages large language models to make predictions on chemical properties using few-shot learning and fine-tuning techniques. It allows users to input chemical data and receive predictions on various properties, making it relevant for computational chemistry applications.

The 'diffusion-conformer' repository provides a Python implementation for generating multiple conformers of drug-like molecules using a physics-informed generative model. It allows users to generate conformers for single or multiple molecules and includes training capabilities for custom models.

cp2k-output-tools is a Python library designed to handle and parse output files generated by CP2K, a software for molecular simulations. It includes tools for filtering trajectory data, converting band structure files to CSV format, and extracting key information from CP2K outputs, making it useful for researchers in computational chemistry.

SynPlanner is an open-source tool for computer-aided synthesis planning that enhances the flexibility of developing customized retrosynthetic solutions. It integrates advanced machine learning techniques to evaluate reaction rules and synthesizability of intermediate products, facilitating effective retrosynthetic planning.

Swarm-CG automates the optimization of bonded terms in MARTINI-based coarse-grained molecular models by using a reference all-atom trajectory. It includes modules for evaluating parametrization, optimizing parameters, and monitoring the optimization process, making it a valuable tool for molecular modeling and simulations.

Scopy is an integrated Python library that facilitates the screening of undesirable compounds in drug discovery. It includes modules for data preparation, screening filters, and the calculation of molecular properties, making it a valuable tool for designing high-quality chemical libraries.

ACANet is a deep learning model designed to improve molecular activity prediction by incorporating activity-cliff awareness into its training process. It utilizes a novel loss function to enhance the model's ability to learn from molecular data, making it suitable for predicting properties like binding affinity.

The Protein Structure Transformer (PST) enhances pretrained protein language models by incorporating structural knowledge, allowing for the extraction of protein structure representations. It can be used for various protein function prediction tasks and is trained on datasets like AlphaFold SwissProt.

CGCF-ConfGen is a tool for generating molecular conformations using neural generative dynamics. It allows users to train models and generate multiple conformations for molecules, making it useful for molecular design and optimization tasks.

This repository provides code and datasets for analyzing IC50 and Ki values from various sources, highlighting the noise in these measurements. It includes curated datasets from ChEMBL32 and tools for generating results related to molecular property prediction.

This repository serves as a programming guide for quantum chemistry, providing code examples and supplementary materials. It focuses on the application of Python in the field of quantum chemistry, which can be relevant for predicting molecular properties and conducting simulations.

FlashIPA is an implementation that improves the efficiency of the Invariant Point Attention module, focusing on reducing training and inference time for models that may be used in molecular simulations. It provides a framework for integrating edge embeddings, which can be crucial for modeling molecular interactions.

3D-MCTS is a framework for structure-based de novo drug design that utilizes a fragment-based molecular editing strategy. It efficiently generates molecules with improved binding affinity and synthesizability, making it a valuable tool in drug discovery.

The 'gromacs-on-colab' repository offers Google Colab notebooks designed for running molecular dynamics simulations using GROMACS. It includes functionalities for system preparation, production simulations, and trajectory analysis, facilitating research in molecular dynamics.

The uq_molecule repository implements methods for uncertainty quantification in molecular property predictions through Bayesian deep learning techniques. It utilizes MC-Dropout networks and augmented graph convolutional networks to enhance the reliability of molecular property predictions.

This repository provides a course on protein language modeling, covering topics such as sequence analysis, model training, and protein design. It includes hands-on notebooks for predicting features and classifying protein sequences using embeddings generated by language models.