Stars
Evidently is an open-source ML and LLM observability framework. Evaluate, test, and monitor any AI-powered system or data pipeline. From tabular data to Gen AI. 100+ metrics.
AlphaBind code + model accompanying pre-print
Orthrus is a mature RNA model for RNA property prediction. It uses a mamba encoder backbone, a variant of state-space models specifically designed for long-sequence data, such as RNA.
User friendly and accurate binder design pipeline
Code for the class, "Machine Learning for Regulatory Genomics"
BioNeMo NIMs example notebooks: for optimized inference at scale
A framework for state-of-the-art pre-trained bio foundation models on genomics and transcriptomics modalities.
Saprot: Protein Language Model with Structural Alphabet (AA+3Di)
GenSLMs: Genome-scale language models reveal SARS-CoV-2 evolutionary dynamics
Nature Methods: RNA foundation model (together with RhoFold)
Foundation Models for Genomics & Transcriptomics
Benchmarks for classification of genomic sequences
Chai-1, SOTA model for biomolecular structure prediction
Reproduction of OpenGenome dataset curated by the Evo team
Therapeutics Commons (TDC): Multimodal Foundation for Therapeutic Science
DREAM2022 competition for predicting promoter expression from DNA sequence.
Heart rate prediction from altitude changes, speed and cadence during running. Data collection was made using Garmin sports watch, fit files. LSTM implementation.
catch22: CAnonical Time-series CHaracteristics
Probabilistic time series modeling in Python
Lag-Llama: Towards Foundation Models for Probabilistic Time Series Forecasting
An offical implementation of PatchTST: "A Time Series is Worth 64 Words: Long-term Forecasting with Transformers." (ICLR 2023) https://arxiv.org/abs/2211.14730
Foundation Models for Time Series