/tools

MULAN is a multimodal protein language model that encodes both sequence and structural information of proteins. It utilizes pre-trained models to enhance protein representations, making it suitable for various downstream tasks in molecular biology.

BagPype is a Python package designed for constructing atomistic, energy-weighted graphs from biomolecular structures. It allows for detailed modeling of molecular properties by incorporating various types of interactions, making it useful for studying proteins and nucleic acids.

This repository implements a method for aggregating residue-level embeddings from protein language models using optimal transport. It aims to improve the representation of protein sequences for various prediction tasks, such as drug-target interactions and protein-protein interactions.

MolEnc is a molecular encoder that uses RDKit and OCaml to create chemical fingerprints, specifically the Signature Molecular Descriptor. It allows for encoding databases of molecules and can reuse feature dictionaries, making it useful for various molecular property prediction and design tasks.

This repository offers an automated workflow for converting SMILES representations of homopolymers to BigSMILES format and vice versa. It includes a dataset of BigSMILES representations, facilitating research in molecular representation and potential applications in deep learning.

The esmjax repository provides a JAX/Flax reimplementation of the ESM-2 protein language model, enabling efficient inference and embeddings for protein sequences. It includes features for model parallelism and weight porting from PyTorch, making it a useful tool for researchers in protein-related computational tasks.

The ESPF tool provides a method for generating explainable substructure partition fingerprints for proteins and drugs, facilitating molecular property prediction. It includes datasets and examples for customizing the fingerprint generation process, making it useful for drug discovery and protein design.

The SMILES Featurizers repository offers a set of tools to extract molecular embeddings from SMILES strings using pre-trained language models like BERT and BART. This functionality is useful for applications in molecular property prediction and virtual screening.

GlyLES is a Python tool that converts IUPAC representations of glycans into SMILES strings, facilitating the representation and analysis of glycan structures in computational chemistry. It supports various input formats and is currently in development to enhance its functionality.

The 'react-ocl' repository offers React components that integrate OpenChemLib for visualizing and editing molecular structures in formats like molfile and SMILES. This tool is useful for developers working on applications that require molecular visualization and manipulation.

DockTGrid is a Python package designed to generate customized voxel representations of protein-ligand complexes, facilitating deep learning applications. It supports GPU acceleration and is compatible with various file formats, making it a useful tool for molecular docking and virtual screening tasks.

TopoteinWorkshop is a topological deep learning extension to the ProteinWorkshop framework, designed for protein structure representation learning. It incorporates novel geometric topological neural network architectures and provides benchmarking capabilities for evaluating these models against existing ones.

The molecule-representation repository offers React components for rendering interactive 2D representations of molecules. It allows users to visualize molecular structures with features like zooming and highlighting specific atoms and bonds.

The mol2ecfp4 tool converts molecular structures into their ECFP4 bitstring representation using the RDKit library. This representation is useful for various applications in molecular property prediction and cheminformatics.

Radium is a Haskell library designed for chemistry, offering features such as a periodic table and support for various molecular formats like SMILES. It facilitates the representation and manipulation of chemical data, making it useful for cheminformatics applications.

Coho is a C library designed for parsing SMILES strings according to the OpenSMILES standard. It includes Python bindings, making it accessible for various cheminformatics applications.

Foldbender provides functions to convert Alphafold PDB molecules into graph representations suitable for graph network models. It facilitates tasks related to protein function prediction and analysis using machine learning techniques.

The rdkit-provider repository initializes an RDKit web worker in a React context, allowing developers to utilize RDKit's cheminformatics capabilities within their applications. It provides caching options and helper functions for validating molecular structures, making it a useful tool for molecular representation.

The 'smiles' repository offers a Haskell implementation that fully supports the OpenSMILES specification, allowing users to parse and work with SMILES representations of molecules. This functionality is essential for various applications in computational chemistry and molecular biology.

MoleculeTransformer is a BERT-based embedding model designed for representing SMILES notation of molecules. It focuses on predicting drug-target interactions and provides a framework for molecular representation using deep learning techniques.

The SMILES repository offers a simple validator and parser for SMILES codes, which are essential for representing molecular structures. It aims to create bond and connectivity matrices and generate xyz files for quantum chemistry applications.

Chem-MRL is a SMILES-based embedding model that utilizes Matryoshka Representation Learning to create efficient molecular embeddings. It supports tasks such as classification and clustering, making it useful for molecular property prediction and design.

CA-2-HCOMB is a tool that simplifies single-chain protein structures from PDB files into various manageable models, such as honeycombs. It enhances computational efficiency for large datasets and is user-friendly for both research and educational purposes.

This repository contains experiments with low-dimensional projections of chemical fingerprints from the ChEMBL and ZINC databases. It aims to create a universal chemical space for projecting various chemical structures, utilizing clustering and PCA techniques.