Tools & Resources

Our vision at SRTI is a connected healthcare ecosystem that extends from the clinic to the community and home. We aim to advance the use of digital and genomic technologies, incorporating deep, high-frequency, longitudinal, multi-modal data, in combination with artificial intelligence-based analytics, to provide both real-time diagnostics and prognostic health predictions.

Lohrasb is a package built to ease machine learning development. It uses Optuna, GridSearchCV and RandomizedSearchCV to tune most of the tree-based estimators of scikit-learn. It is compatible with scikit-learn pipeline.

Lohrasb

Zoish is a package built to ease machine learning development. One of its main parts is a class that uses SHAP (SHapley Additive exPlanation) for a better feature selection. It is compatible with scikit-learn pipeline. This package uses FastTreeSHAP while calculating SHAP values and SHAP for plotting. Zoish is made available by the Torkamani lab.

Zoish

Genotype imputation is a foundational tool for population genetics. Standard statistical imputation approaches rely on the co-location of large whole-genome sequencing-based reference panels, powerful computing environments, and potentially sensitive genetic study data. This results in computational resource and privacy-risk barriers to access to cutting-edge imputation techniques. Moreover, the accuracy of current statistical approaches is known to degrade in regions of low and complex linkage disequilibrium. Artificial neural network-based imputation approaches may overcome these limitations by encoding complex genotype relationships in easily portable inference models.

Imputation Autoencoder

iVar is a computational package from the Andersen lab that contains functions broadly useful for viral amplicon-based sequencing.

iVar

Freyja is a tool to estimate relative abundance of SARS-CoV-2 and other viral lineages from sequencing mixed-lineage virus samples, like wastewater. Freyja is made available by the Andersen lab.

Freyja

The BioThings suite of application programming interfaces (APIs) focuses on data integration for key biomedical entities, including genes, variants and chemicals which are collectively accessed millions of times per month. BioThings is made available by the Su lab.

BioThings API