Search Results for "training"

BioNeMo is an AI-powered framework developed by NVIDIA for protein and molecular generation using deep learning models. It provides researchers and developers with tools to design, analyze, and optimize biological molecules, aiding in drug discovery and synthetic biology applications.

...According to the repository, it uses the StripedHyena 2 architecture, was pretrained with Savanna, and was trained autoregressively on the OpenGenome2 dataset containing 8.8 trillion tokens. The codebase is focused on local inference and generation through the Vortex inference stack rather than serving as a full training framework alone, although it also points users to training and fine-tuning resources. It supports multiple ways of working with the model, including forward passes, embeddings, generation workflows, notebooks, hosted APIs, and self-hosted deployment through NVIDIA NIM.

The Collaborative Computational Project for NMR (CCPN) provides tools and knowledge to maximise the impact of the biological NMR studies. The CCPN software facilitates data analysis and software integration. The project actively promotes the exchange of knowledge and provides training and best practices for the NMR community. CCPN also has a leading role in the development of a NMR data-sharing standard and coordination of NMR instrumentation proposals for RCUK and BIS. The 28 partners of CCPN jointly cover all aspects of biomolecular NMR and together they promote excellence in science in their respective fields.

The General Hidden Markov Model Library (GHMM) is a C library with additional Python bindings implementing a wide range of types of Hidden Markov Models and algorithms: discrete, continous emissions, basic training, HMM clustering, HMM mixtures.