Auto-PyTorch vs JADBio

Auto-PyTorch is a free, self-hosted machine-learning toolkit based on PyTorch. It automates algorithm selection and hyperparameter tuning, including neural-network architecture and training settings, within a user-defined search budget. Documented search methods include Bayesian optimisation, meta-learning, SMAC and Hyperband. Supported work includes tabular classification, tabular regression and time-series forecasting. Tabular preprocessing can perform imputation, categorical encoding, scaling and feature processing, while related hyperparameters are tuned. The toolkit can build ensembles from validation-set predictions, with controls for ensemble size and candidate limits. Users can set estimator memory limits and total wall time. Parallel Bayesian optimisation uses Dask.distributed; workers need shared filesystem access to training data and models. Installation documentation specifies Linux, Python 3.7 or later, a C++11-capable compiler and SWIG 3.0. SWIG 4.0 or later is unsupported. Forecasting needs extra dependencies. A Docker image and PyPI installation are documented, under the 3-clause BSD license.

JADBio is a no-code automated machine learning platform for life scientists analyzing public or study data. It accepts curated CSV and other delimited files, and users choose the outcome to predict. Supported data includes genomics, transcriptome, metagenome, proteome, metabolome, clinical data, and images. Analysis features include automated preprocessing, feature selection, survival analysis, predictive modeling, and model interpretation; outputs can include predictive models, biomarkers or biosignatures, visualizations, and information for applying models. The REST API can add AutoML, including image analysis, to applications and automate workflows, with a Python client available through GitHub, PyPI, and Anaconda. JADBio offers web, API, and self-hosted options. Basic is free and includes one seat, three projects, a 50 MB upload limit, 500 MB storage, and one model export. Team is listed at $2,199 a year, billed annually, and includes a 14-day free trial. Business Pro has custom pricing and lists SaaS, AWS container, and on-premise delivery.