D2.2 - First Report of the Ethics Advisory Board

Following the introductory meeting of our Ethics Advisory Board (EAB) -you can read all about it here-, their first report (D2.2) has been publicly released.


This deliverable provides the first report of the GenoMed4All Ethical Advisory Board (EAB). The report has been compiled after the first meeting of the Ethical Advisory Board held on 19th January 2022. The meeting was presented with the current position with regards the project objectives and progress, data protection and ethics oversight and assessments for the project.

Photo by Fábio Lucas on Unsplash

D4.1 - Hybrid Federated Learning Model

D4.1 is finally out!

This deliverable is the result of months of intense discussions on GenoMed4All’s hybrid Federated Learning framework.


The main aim of this deliverable is to define GenoMed4All’s hybrid federated learning model specification expressed in terms of platform requirements, which have been acquired by analyzing in details the project’s objectives as well as by decomposing the stakeholders’ needs through the different use cases’ definition. It includes a description of the requirements elicitation methodology together with the set of technical requirements regarding the federated learning approach of the project’s platform. Moreover, it includes an extensive analysis of the most important federated learning framework solutions already available, and it finally defines the evaluation criteria that have helped in the selection of the most appropriate one for the project’s purposes and needs.

D6.2 - Preliminary conclusions about Federated Learning applied to clinical data

After an initial phase focused on literature mining and pre-processing, we are happy to share our preliminary conclusions about Federated Learning applied to clinical data as a part of deliverable D6.2.


This report comprises the first contributions from different partners on Federated Learning (FL). After a preliminary introductory section where the fundamental procedures and limitations are described, we detail the well-known mathematical foundation of Federated Learning for convex problems. In this case, we present a key algorithm, Alternating Direction Multipliers Method (ADMM), which is able to implement in a distributed way some fundamental problems such as regression (Ridge and LASSO) and classification (Logistic Regression and Support Vector Machines (SVM)). This procedure shares the fundamental approach of FL, which consists of performing some local processing, sharing some intermediate information and updating the local information with some global innovation. In a second step we introduce the extension of this approach to non-convex problems using Bayesian Neural Networks (BNN) where the update is based on the cooperative construction of the posterior of weights from different architectures. Several sections follow where different partners provide different contributions describing our first initiatives on the topic. Some preliminary code from all partners has been uploaded to a common repository to start creating a pool of methods and tools to foster incoming synergies.

D5.1 - Data homogenization requirements and specifications

D5.1 is now out!


Considering the wide range of repositories that GenoMed4All will need, homogenizing data formats from different sources and systems (e.g. EHRs, images, genomic data, etc.) is essential. This deliverable sets the requirements for the data homogenization processes paving the way to a common approach for a data lake, based on the FHIR standard. FHIR enables almost direct integration with most of the current information systems and automatic data homogenization and enrichment to facilitate data processing and analytics.

D2.1 – Data processing, Data Management Plan and GDPR compliance report

Deliverable D2.1 is officially out!


Monitoring data protection compliance for an initiative like GenoMed4All can only be successful if there is a swift understanding of compliance across all partners and a clear concordance. To that end, the need for a reliable and consistent approach to understand data flows, sources, recipients and roles with regards overall responsibility (including Data Controllers, Processors and Custodians) is clear. The consortium has therefore agreed that using a rigorous Data Protection Impact Assessment (DPIA) Template is key to help map out not only data flows, but also responsibilities and the prerequisites for ensuring data processing is lawful.

D6.1 - Literature mining and pre-processing

D6.1 has been uploaded to our community at Zenodo!


This deliverable contains the initial literature mining and the first version of the Artificial Intelligence (AI) software release. The literature mining consists of a review of the most important AI methods. The software is available for the entire consortium in the GenoMed4all GitLab repository and will be made publicly available at a later stage in the project.

Photo by Markus Winkler on Unsplash

D8.1 - Genomics Data Standardization Plan

Our second public deliverable -GenoMed4All’s Standardization Plan-has been uploaded to Zenodo!


Minimum set of recommended standards for the analysis and sharing of the genomics dataset for haematology and oncology to be utilized in the GenoMed4All project. Furthermore, guidelines are also described to share phenotypic and other metadata collected from different clinical partners. A brief description of data harmonization and sharing using GA4GH phenopackets and FHIR standards, evaluation of best suited exchange format for genomics data and how to adapt and calibrate standardized data on local sites according to evaluation of clinical data set and genomics interface.

Photo by Glen Carrie on Unsplash


D9.1 - Impact Master Plan

Our Impact Master Plan is already up at Zenodo and publicly accessible! Learn more about our vision for GenoMed4All’s Dissemination, Communication and Exploitation strategies moving forward.


This document outlines the project dissemination, communication exploitation strategies for the GenoMed4All H2020 project