To apply federated learning to drug discovery we developed a novel platform in the context of European Innovative Medicines Initiative (IMI) project MELLODDY (grant n°831472), which was comprised of 10 pharmaceutical companies, academic research labs, large industrial companies and startups. The MELLODDY platform was the first industry-scale platform to enable the creation of a global federated model for drug discovery without sharing the confidential data sets of the individual partners. The federated model was trained on the platform by aggregating the gradients of all contributing partners in a cryptographic, secure way following each training iteration. The platform was deployed on an Amazon Web Services (AWS) multi-account architecture running Kubernetes clusters in private subnets. Organisationally, the roles of the different partners were codified as different rights and permissions on the platform and administrated in a decentralized way. The MELLODDY platform generated new scientific discoveries which are described in a companion paper.

MOTIVATION: Modern bioinformatics is facing increasingly complex problems to solve, and we are indeed rapidly approaching an era in which the ability to seamlessly integrate heterogeneous sources of information will be crucial for the scientific progress. Here, we present a novel non-linear data fusion framework that generalizes the conventional matrix factorization paradigm allowing inference over arbitrary entity-relation graphs, and we applied it to the prediction of protein-protein interactions (PPIs). Improving our knowledge of PPI networks at the proteome scale is indeed crucial to understand protein function, physiological and disease states and cell life in general. RESULTS: We devised three data fusion-based models for the proteome-level prediction of PPIs, and we show that our method outperforms state of the art approaches on common benchmarks. Moreover, we investigate its predictions on newly published PPIs, showing that this new data has a clear shift in its underlying distributions and we thus train and test our models on this extended dataset. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Modeling real-world multidimensional time series can be particularly challenging when these are sporadically observed (i.e., sampling is irregular both in time and across dimensions)—such as in the case of clinical patient data. To address these challenges, we propose (1) a continuous-time version of the Gated Recurrent Unit, building upon the recent Neural Ordinary Differential Equations (Chen et al., 2018), and (2) a Bayesian update network that processes the sporadic observations. We bring these two ideas together in our GRU-ODE-Bayes method. We then demonstrate that the proposed method encodes a continuity prior for the latent process and that it can exactly represent the Fokker-Planck dynamics of complex processes driven by a multidimensional stochastic differential equation. Additionally, empirical evaluation shows that our method outperforms the state of the art on both synthetic data and real-world data with applications in healthcare and climate forecast. What is more, the continuity prior is shown to be well suited for low number of samples settings.

SUMMARY: Inferring a Gene Regulatory Network (GRN) from gene expression data is a computationally expensive task, exacerbated by increasing data sizes due to advances in high-throughput gene profiling technology, such as single-cell RNA-seq. To equip researchers with a toolset to infer GRNs from large expression datasets, we propose GRNBoost2 and the Arboreto framework. GRNBoost2 is an efficient algorithm for regulatory network inference using gradient boosting, based on the GENIE3 architecture. Arboreto is a computational framework that scales up GRN inference algorithms complying with this architecture. Arboreto includes both GRNBoost2 and an improved implementation of GENIE3, as a user-friendly open source Python package. AVAILABILITY AND IMPLEMENTATION: Arboreto is available under the 3-Clause BSD license at http://arboreto.readthedocs.io. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Motivation: Most gene prioritization methods model each disease or phenotype individually, but this fails to capture patterns common to several diseases or phenotypes. To overcome this limitation, we formulate the gene prioritization task as the factorization of a sparsely filled gene-phenotype matrix, where the objective is to predict the unknown matrix entries. To deliver more accurate gene-phenotype matrix completion, we extend classical Bayesian matrix factorization to work with multiple side information sources. The availability of side information allows us to make non-trivial predictions for genes for which no previous disease association is known. Results: Our gene prioritization method can innovatively not only integrate data sources describing genes, but also data sources describing Human Phenotype Ontology terms. Experimental results on our benchmarks show that our proposed model can effectively improve accuracy over the well-established gene prioritization method, Endeavour. In particular, our proposed method offers promising results on diseases of the nervous system; diseases of the eye and adnexa; endocrine, nutritional and metabolic diseases; and congenital malformations, deformations and chromosomal abnormalities, when compared to Endeavour. Availability and implementation: The Bayesian data fusion method is implemented as a Python/C++ package: https://github.com/jaak-s/macau. It is also available as a Julia package: https://github.com/jaak-s/BayesianDataFusion.jl. All data and benchmarks generated or analyzed during this study can be downloaded at https://owncloud.esat.kuleuven.be/index.php/s/UGb89WfkZwMYoTn. Supplementary information: Supplementary data are available at Bioinformatics online.

The deployment of Genome-wide association studies (GWASs) requires genomic information of a large population to produce reliable results. This raises significant privacy concerns, making people hesitate to contribute their genetic information to such studies. We propose two provably secure solutions to address this challenge: (1) a somewhat homomorphic encryption (HE) approach, and (2) a secure multiparty computation (MPC) approach. Unlike previous work, our approach does not rely on adding noise to the input data, nor does it reveal any information about the patients. Our protocols aim to prevent data breaches by calculating the χ 2 statistic in a privacy-preserving manner, without revealing any information other than whether the statistic is significant or not. Specifically, our protocols compute the χ 2 statistic, but only return a yes/no answer, indicating significance. By not revealing the statistic value itself but only the significance, our approach thwarts attacks exploiting statistic values. We significantly increased the efficiency of our HE protocols by introducing a new masking technique to perform the secure comparison that is necessary for determining significance. We show that full-scale privacy-preserving GWAS is practical, as long as the statistics can be computed by low degree polynomials. Our implementations demonstrated that both approaches are efficient. The secure multiparty computation technique completes its execution in approximately 2 ms for data contributed by one million subjects.

The massive growth of biomedical text makes it very challenging for researchers to review all relevant work and generate all possible hypotheses in a reasonable amount of time. Many text mining methods have been developed to simplify this process and quickly present the researcher with a learned set of biomedical hypotheses that could be potentially validated. Previously, we have focused on the task of identifying genes that are linked with a given disease by text mining the PubMed abstracts. We applied a word-based concept profile similarity to learn patterns between disease and gene entities and hence identify links between them. In this work, we study an alternative approach based on topic modelling to learn different patterns between the disease and the gene entities and measure how well this affects the identified links. We investigated multiple input corpuses, word representations, topic parameters, and similarity measures. On one hand, our results show that when we (1) learn the topics from an input set of gene-clustered set of abstracts, and (2) apply the dot-product similarity measure, we succeed to improve our original methods and identify more correct disease-gene links. On the other hand, the results also show that the learned topics remain limited to the diseases existing in our vocabulary such that scaling the methodology to new disease queries becomes non trivial.