/tools

GENiPPI is an interface-aware molecular generative framework aimed at designing modulators for protein-protein interactions. It utilizes a dataset of PPI interfaces to generate novel compounds, enhancing the capabilities of structure-based drug design.

MoSDeF Workflows is a collection of sample workflows that utilize the Molecular Simulation Design Framework to support reproducible molecular simulations across various engines. It includes tools for building molecules, applying forcefields, and managing simulation data, making it suitable for molecular dynamics and simulations.

TrimCI is a high-performance framework designed for quantum many-body and quantum chemistry calculations, enabling the discovery of accurate ground states from random Slater determinants. It achieves state-of-the-art accuracy and efficiency in molecular systems, making it a valuable tool for computational chemistry.

ESM2-RL Designer is a framework for controllable protein design that fine-tunes a pretrained protein language model using reinforcement learning. It aims to generate protein sequences with specific properties such as stability and diversity through a multi-objective reward system.

DeepAllo is a deep learning framework designed for predicting allosteric sites in proteins using a protein language model with multitask learning. It provides an inference pipeline that identifies potential allosteric pockets based on input protein structures.

SelfPAD is a framework designed to improve the prediction of antibody humanness by utilizing patent data. It includes functionalities for pre-training and fine-tuning models specifically for evaluating antibody sequences.

The 'qchem' repository is a framework for molecular modeling that combines machine learning and quantum chemistry to explore molecular properties and datasets. It provides tools for implementing models and datasets in a modular and extendable manner, facilitating research in molecular simulations and property predictions.

EquiHGNN is a framework for scalable rotationally equivariant hypergraph neural networks aimed at improving molecular modeling. It integrates symmetry-aware representations to enhance predictions of molecular properties using various datasets, including QM9 and PCQM4Mv2.

AIMNet-X2D is a scalable Graph Neural Network framework that enables multi-task learning for predicting various molecular properties. It is designed to handle datasets of varying sizes efficiently and supports the creation of domain-specific molecular foundation models.

AIRFold is a protein structure prediction system built on AlphaFold2, providing scalable solutions for predicting protein structures through various advanced models. It integrates modules for co-evolutionary information extraction and offers a user-friendly interface for researchers in the life sciences.

ALLSites is a deep learning framework that predicts protein binding sites using a transformer-based architecture combined with convolutional encoders. It utilizes advanced optimization techniques and pre-computed protein embeddings to enhance the accuracy of binding site predictions.