Skip to content

Join Project

e-BioDiv - Open Biodiversity FAIR-ification Services for Biospecimens stored in Swiss Natural History Museums

The Earth’s scholarly knowledge about species diversity (biodiversity) is included in a corpus of several hundred million pages of publications spanning over 250 years, with an arbitrary starting point of 1753 for plants and 1758 for animals. Each year an estimated 19,000 animal and plant species and a multiple of augmentations of data are added to the already approximately known 1.9M species. The data about each species are included in highly structured taxonomic treatments and figures. Increasingly these treatments include implicit links to the data used to describe and augment it, such as omic and digitized specimen data produced by SwissBioCollection.

CHEM::AI - Predicting and Exploring Novel Chemical Spaces Using Artificial Intelligence

With the support of the Swiss Innovation Agency Innosuisse, in this joint work with Douglas Teodoro's group and SpiroChem AG, a world leading organic/synthetic chemistry innovator in the life science industry, we aim to provide effective solutions for virtual synthesis of new molecules. This project will expand the current accessible chemical space and reduce costs and development time of new chemical entities.

Swiss Personalized Oncology

Being able, from a large collection of text-based reports, to offer a therapeutic answer to new patient-cases: this is the goal of the Text-Mining group as part of the Swiss Personalized Oncology project (SPHN). Thus, in collaboration with the five Swiss University Hospitals (CHUV, HUG, Insel, USB, USZ), we are experimenting a multiclass categorization tool using deep learning to mine huge collections of past clinical reports, identify therapeutic responses, generate hypotheses and ultimately support the understanding of cancer mechanisms.

Swiss Personalized Oncology

CINECA - Common Infrastructure for National Cohorts in Europe, Canada, and Africa

CINECA project aims to develop a federated cloud-based infrastructure for making genomic and biomolecular data accessible. This project has already assembled a virtual cohort from population, longitudinal and disease studies, such as the European Genome-phenome Archive (EGA), CanDIG, and H3Africa, and has contributed to harmonising metadata based on open global standards. The CINECA consortium will create one of the largest cross-continental implementations of human genetic and phenotypic data federation and interoperability for complex diseases. This project is funded by the European Union’s Horizon 2020 and the Canadian Institute of Health Research.

GOAssay - Gene Ontology Annotation of PubChem Assays

A joint collaboration with the University of Indiana.

An experiment to functionally annotate PubChem assays using the Gene Ontology Categorizer (GOCat). The assays are processed to filter out non functional information, then the textual content is sent to the categorizer, which provide a ranked list of GO descriptors based on a GOA-learned association model.

See 1

  1. Rajarshi Guha, Julien Gobeill, and Patrick Ruch. Goassay: from gene ontology to assays identifiers - towards automatic functional annotation of pubchem bioassays. Nature Precedings, Apr 2009. URL:, doi:10.1038/npre.2009.3176.1