Drugst.One - a plug-and-play solution for online systems medicine and network-based drug repurposing.

In recent decades, the development of new drugs has become increasingly expensive and inefficient, and the molecular mechanisms of most pharmaceuticals remain poorly understood. In response, computational systems and network medicine tools have emerged to identify potential drug repurposing candidates. However, these tools often require complex installation and lack intuitive visual network mining capabilities. To tackle these challenges, we introduce Drugst.One, a platform that assists specialized computational medicine tools in becoming user-friendly, web-based utilities for drug repurposing. With just three lines of code, Drugst.One turns any systems biology software into an interactive web tool for modeling and analyzing complex protein-drug-disease networks. Demonstrating its broad adaptability, Drugst.One has been successfully integrated with 21 computational systems medicine tools. Available at https://drugst.one, Drugst.One has significant potential for streamlining the drug discovery process, allowing researchers to focus on essential aspects of pharmaceutical treatment research.

Cancer driver drug interaction explorer.

Cancer is a heterogeneous disease characterized by unregulated cell growth and promoted by mutations in cancer driver genes some of which encode suitable drug targets. Since the distinct set of cancer driver genes can vary between and within cancer types, evidence-based selection of drugs is crucial for targeted therapy following the precision medicine paradigm. However, many putative cancer driver genes can not be targeted directly, suggesting an indirect approach that considers alternative functionally related targets in the gene interaction network. Once potential drug targets have been identified, it is essential to consider all available drugs. Since tools that offer support for systematic discovery of drug repurposing candidates in oncology are lacking, we developed CADDIE, a web application integrating six human gene-gene and four drug-gene interaction databases, information regarding cancer driver genes, cancer-type specific mutation frequencies, gene expression information, genetically related diseases, and anticancer drugs. CADDIE offers access to various network algorithms for identifying drug targets and drug repurposing candidates. It guides users from the selection of seed genes to the identification of therapeutic targets or drug candidates, making network medicine algorithms accessible for clinical research. CADDIE is available at https://exbio.wzw.tum.de/caddie/ and programmatically via a python package at https://pypi.org/project/caddiepy/.

Federated Random Forests can improve local performance of predictive models for various healthcare applications.

MOTIVATION: Limited data access has hindered the field of precision medicine from exploring its full potential, e.g. concerning machine learning and privacy and data protection rules.Our study evaluates the efficacy of federated Random Forests (FRF) models, focusing particularly on the heterogeneity within and between datasets. We addressed three common challenges: (i) number of parties, (ii) sizes of datasets and (iii) imbalanced phenotypes, evaluated on five biomedical datasets. RESULTS: The FRF outperformed the average local models and performed comparably to the data-centralized models trained on the entire data. With an increasing number of models and decreasing dataset size, the performance of local models decreases drastically. The FRF, however, do not decrease significantly. When combining datasets of different sizes, the FRF vastly improve compared to the average local models. We demonstrate that the FRF remain more robust and outperform the local models by analyzing different class-imbalances.Our results support that FRF overcome boundaries of clinical research and enables collaborations across institutes without violating privacy or legal regulations. Clinicians benefit from a vast collection of unbiased data aggregated from different geographic locations, demographics and other varying factors. They can build more generalizable models to make better clinical decisions, which will have relevance, especially for patients in rural areas and rare or geographically uncommon diseases, enabling personalized treatment. In combination with secure multi-party computation, federated learning has the power to revolutionize clinical practice by increasing the accuracy and robustness of healthcare AI and thus paving the way for precision medicine. AVAILABILITY AND IMPLEMENTATION: The implementation of the federated random forests can be found at https://featurecloud.ai/. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

The FeatureCloud Platform for Federated Learning in Biomedicine: Unified Approach.

BACKGROUND: Machine learning and artificial intelligence have shown promising results in many areas and are driven by the increasing amount of available data. However, these data are often distributed across different institutions and cannot be easily shared owing to strict privacy regulations. Federated learning (FL) allows the training of distributed machine learning models without sharing sensitive data. In addition, the implementation is time-consuming and requires advanced programming skills and complex technical infrastructures. OBJECTIVE: Various tools and frameworks have been developed to simplify the development of FL algorithms and provide the necessary technical infrastructure. Although there are many high-quality frameworks, most focus only on a single application case or method. To our knowledge, there are no generic frameworks, meaning that the existing solutions are restricted to a particular type of algorithm or application field. Furthermore, most of these frameworks provide an application programming interface that needs programming knowledge. There is no collection of ready-to-use FL algorithms that are extendable and allow users (eg, researchers) without programming knowledge to apply FL. A central FL platform for both FL algorithm developers and users does not exist. This study aimed to address this gap and make FL available to everyone by developing FeatureCloud, an all-in-one platform for FL in biomedicine and beyond. METHODS: The FeatureCloud platform consists of 3 main components: a global frontend, a global backend, and a local controller. Our platform uses a Docker to separate the local acting components of the platform from the sensitive data systems. We evaluated our platform using 4 different algorithms on 5 data sets for both accuracy and runtime. RESULTS: FeatureCloud removes the complexity of distributed systems for developers and end users by providing a comprehensive platform for executing multi-institutional FL analyses and implementing FL algorithms. Through its integrated artificial intelligence store, federated algorithms can easily be published and reused by the community. To secure sensitive raw data, FeatureCloud supports privacy-enhancing technologies to secure the shared local models and assures high standards in data privacy to comply with the strict General Data Protection Regulation. Our evaluation shows that applications developed in FeatureCloud can produce highly similar results compared with centralized approaches and scale well for an increasing number of participating sites. CONCLUSIONS: FeatureCloud provides a ready-to-use platform that integrates the development and execution of FL algorithms while reducing the complexity to a minimum and removing the hurdles of federated infrastructure. Thus, we believe that it has the potential to greatly increase the accessibility of privacy-preserving and distributed data analyses in biomedicine and beyond.

Identification of differentially expressed gene modules in heterogeneous diseases.

MOTIVATION: Identification of differentially expressed genes is necessary for unraveling disease pathogenesis. This task is complicated by the fact that many diseases are heterogeneous at the molecular level and samples representing distinct disease subtypes may demonstrate different patterns of dysregulation. Biclustering methods are capable of identifying genes that follow a similar expression pattern only in a subset of samples and hence can consider disease heterogeneity. However, identifying biologically significant and reproducible sets of genes and samples remain challenging for the existing tools. Many recent studies have shown that the integration of gene expression and protein interaction data improves the robustness of prediction and classification and advances biomarker discovery. RESULTS: Here, we present DESMOND, a new method for identification of Differentially ExpreSsed gene MOdules iN Diseases. DESMOND performs network-constrained biclustering on gene expression data and identifies gene modules-connected sets of genes up- or down-regulated in subsets of samples. We applied DESMOND on expression profiles of samples from two large breast cancer cohorts and have shown that the capability of DESMOND to incorporate protein interactions allows identifying the biologically meaningful gene and sample subsets and improves the reproducibility of the results. AVAILABILITY AND IMPLEMENTATION: https://github.com/ozolotareva/DESMOND. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

AITL: Adversarial Inductive Transfer Learning with input and output space adaptation for pharmacogenomics.

MOTIVATION: The goal of pharmacogenomics is to predict drug response in patients using their single- or multi-omics data. A major challenge is that clinical data (i.e. patients) with drug response outcome is very limited, creating a need for transfer learning to bridge the gap between large pre-clinical pharmacogenomics datasets (e.g. cancer cell lines), as a source domain, and clinical datasets as a target domain. Two major discrepancies exist between pre-clinical and clinical datasets: (i) in the input space, the gene expression data due to difference in the basic biology, and (ii) in the output space, the different measures of the drug response. Therefore, training a computational model on cell lines and testing it on patients violates the i.i.d assumption that train and test data are from the same distribution. RESULTS: We propose Adversarial Inductive Transfer Learning (AITL), a deep neural network method for addressing discrepancies in input and output space between the pre-clinical and clinical datasets. AITL takes gene expression of patients and cell lines as the input, employs adversarial domain adaptation and multi-task learning to address these discrepancies, and predicts the drug response as the output. To the best of our knowledge, AITL is the first adversarial inductive transfer learning method to address both input and output discrepancies. Experimental results indicate that AITL outperforms state-of-the-art pharmacogenomics and transfer learning baselines and may guide precision oncology more accurately. AVAILABILITY AND IMPLEMENTATION: https://github.com/hosseinshn/AITL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

MOLI: multi-omics late integration with deep neural networks for drug response prediction.

MOTIVATION: Historically, gene expression has been shown to be the most informative data for drug response prediction. Recent evidence suggests that integrating additional omics can improve the prediction accuracy which raises the question of how to integrate the additional omics. Regardless of the integration strategy, clinical utility and translatability are crucial. Thus, we reasoned a multi-omics approach combined with clinical datasets would improve drug response prediction and clinical relevance. RESULTS: We propose MOLI, a multi-omics late integration method based on deep neural networks. MOLI takes somatic mutation, copy number aberration and gene expression data as input, and integrates them for drug response prediction. MOLI uses type-specific encoding sub-networks to learn features for each omics type, concatenates them into one representation and optimizes this representation via a combined cost function consisting of a triplet loss and a binary cross-entropy loss. The former makes the representations of responder samples more similar to each other and different from the non-responders, and the latter makes this representation predictive of the response values. We validate MOLI on in vitro and in vivo datasets for five chemotherapy agents and two targeted therapeutics. Compared to state-of-the-art single-omics and early integration multi-omics methods, MOLI achieves higher prediction accuracy in external validations. Moreover, a significant improvement in MOLI's performance is observed for targeted drugs when training on a pan-drug input, i.e. using all the drugs with the same target compared to training only on drug-specific inputs. MOLI's high predictive power suggests it may have utility in precision oncology. AVAILABILITY AND IMPLEMENTATION: https://github.com/hosseinshn/MOLI. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Proteomic meta-study harmonization, mechanotyping and drug repurposing candidate prediction with ProHarMeD.

Proteomics technologies, which include a diverse range of approaches such as mass spectrometry-based, array-based, and others, are key technologies for the identification of biomarkers and disease mechanisms, referred to as mechanotyping. Despite over 15,000 published studies in 2022 alone, leveraging publicly available proteomics data for biomarker identification, mechanotyping and drug target identification is not readily possible. Proteomic data addressing similar biological/biomedical questions are made available by multiple research groups in different locations using different model organisms. Furthermore, not only various organisms are employed but different assay systems, such as in vitro and in vivo systems, are used. Finally, even though proteomics data are deposited in public databases, such as ProteomeXchange, they are provided at different levels of detail. Thus, data integration is hampered by non-harmonized usage of identifiers when reviewing the literature or performing meta-analyses to consolidate existing publications into a joint picture. To address this problem, we present ProHarMeD, a tool for harmonizing and comparing proteomics data gathered in multiple studies and for the extraction of disease mechanisms and putative drug repurposing candidates. It is available as a website, Python library and R package. ProHarMeD facilitates ID and name conversions between protein and gene levels, or organisms via ortholog mapping, and provides detailed logs on the loss and gain of IDs after each step. The web tool further determines IDs shared by different studies, proposes potential disease mechanisms as well as drug repurposing candidates automatically, and visualizes these results interactively. We apply ProHarMeD to a set of four studies on bone regeneration. First, we demonstrate the benefit of ID harmonization which increases the number of shared genes between studies by 50%. Second, we identify a potential disease mechanism, with five corresponding drug targets, and the top 20 putative drug repurposing candidates, of which Fondaparinux, the candidate with the highest score, and multiple others are known to have an impact on bone regeneration. Hence, ProHarMeD allows users to harmonize multi-centric proteomics research data in meta-analyses, evaluates the success of the ID conversions and remappings, and finally, it closes the gaps between proteomics, disease mechanism mining and drug repurposing. It is publicly available at https://apps.cosy.bio/proharmed/ .

Drugst.One - A plug-and-play solution for online systems medicine and network-based drug repurposing.

In recent decades, the development of new drugs has become increasingly expensive and inefficient, and the molecular mechanisms of most pharmaceuticals remain poorly understood. In response, computational systems and network medicine tools have emerged to identify potential drug repurposing candidates. However, these tools often require complex installation and lack intuitive visual network mining capabilities. To tackle these challenges, we introduce Drugst.One, a platform that assists specialized computational medicine tools in becoming user-friendly, web-based utilities for drug repurposing. With just three lines of code, Drugst.One turns any systems biology software into an interactive web tool for modeling and analyzing complex protein-drug-disease networks. Demonstrating its broad adaptability, Drugst.One has been successfully integrated with 21 computational systems medicine tools. Available at https://drugst.one, Drugst.One has significant potential for streamlining the drug discovery process, allowing researchers to focus on essential aspects of pharmaceutical treatment research.

Privacy-aware multi-institutional time-to-event studies.

Clinical time-to-event studies are dependent on large sample sizes, often not available at a single institution. However, this is countered by the fact that, particularly in the medical field, individual institutions are often legally unable to share their data, as medical data is subject to strong privacy protection due to its particular sensitivity. But the collection, and especially aggregation into centralized datasets, is also fraught with substantial legal risks and often outright unlawful. Existing solutions using federated learning have already demonstrated considerable potential as an alternative for central data collection. Unfortunately, current approaches are incomplete or not easily applicable in clinical studies owing to the complexity of federated infrastructures. This work presents privacy-aware and federated implementations of the most used time-to-event algorithms (survival curve, cumulative hazard rate, log-rank test, and Cox proportional hazards model) in clinical trials, based on a hybrid approach of federated learning, additive secret sharing, and differential privacy. On several benchmark datasets, we show that all algorithms produce highly similar, or in some cases, even identical results compared to traditional centralized time-to-event algorithms. Furthermore, we were able to reproduce the results of a previous clinical time-to-event study in various federated scenarios. All algorithms are accessible through the intuitive web-app Partea (https://partea.zbh.uni-hamburg.de), offering a graphical user interface for clinicians and non-computational researchers without programming knowledge. Partea removes the high infrastructural hurdles derived from existing federated learning approaches and removes the complexity of execution. Therefore, it is an easy-to-use alternative to central data collection, reducing bureaucratic efforts but also the legal risks associated with the processing of personal data to a minimum.

Flimma: a federated and privacy-aware tool for differential gene expression analysis.

Aggregating transcriptomics data across hospitals can increase sensitivity and robustness of differential expression analyses, yielding deeper clinical insights. As data exchange is often restricted by privacy legislation, meta-analyses are frequently employed to pool local results. However, the accuracy might drop if class labels are inhomogeneously distributed among cohorts. Flimma ( https://exbio.wzw.tum.de/flimma/ ) addresses this issue by implementing the state-of-the-art workflow limma voom in a federated manner, i.e., patient data never leaves its source site. Flimma results are identical to those generated by limma voom on aggregated datasets even in imbalanced scenarios where meta-analysis approaches fail.

A Survey of Gene Prioritization Tools for Mendelian and Complex Human Diseases.

Modern high-throughput experiments provide us with numerous potential associations between genes and diseases. Experimental validation of all the discovered associations, let alone all the possible interactions between them, is time-consuming and expensive. To facilitate the discovery of causative genes, various approaches for prioritization of genes according to their relevance for a given disease have been developed. In this article, we explain the gene prioritization problem and provide an overview of computational tools for gene prioritization. Among about a hundred of published gene prioritization tools, we select and briefly describe 14 most up-to-date and user-friendly. Also, we discuss the advantages and disadvantages of existing tools, challenges of their validation, and the directions for future research.

Comorbidity of asthma and hypertension may be mediated by shared genetic dysregulation and drug side effects.

Asthma and hypertension are complex diseases coinciding more frequently than expected by chance. Unraveling the mechanisms of comorbidity of asthma and hypertension is necessary for choosing the most appropriate treatment plan for patients with this comorbidity. Since both diseases have a strong genetic component in this article we aimed to find and study genes simultaneously associated with asthma and hypertension. We identified 330 shared genes and found that they form six modules on the interaction network. A strong overlap between genes associated with asthma and hypertension was found on the level of eQTL regulated genes and between targets of drugs relevant for asthma and hypertension. This suggests that the phenomenon of comorbidity of asthma and hypertension may be explained by altered genetic regulation or result from drug side effects. In this work we also demonstrate that not only drug indications but also contraindications provide an important source of molecular evidence helpful to uncover disease mechanisms. These findings give a clue to the possible mechanisms of comorbidity and highlight the direction for future research.

GenCoNet - A Graph Database for the Analysis of Comorbidities by Gene Networks.

The prevalence of comorbid diseases poses a major health issue for millions of people worldwide and an enormous socio-economic burden for society. The molecular mechanisms for the development of comorbidities need to be investigated. For this purpose, a workflow system was developed to aggregate data on biomedical entities from heterogeneous data sources. The process of integrating and merging all data sources of the workflow system was implemented as a semi-automatic pipeline that provides the import, fusion, and analysis of the highly connected biomedical data in a Neo4j database GenCoNet. As a starting point, data on the common comorbid diseases essential hypertension and bronchial asthma was integrated. GenCoNet (https://genconet.kalis-amts.de) is a curated database that provides a better understanding of hereditary bases of comorbidities.

Search for New Candidate Genes Involved in the Comorbidity of Asthma and Hypertension Based on Automatic Analysis of Scientific Literature.

Comorbid states of diseases significantly complicate diagnosis and treatment. Molecular mechanisms of comorbid states of asthma and hypertension are still poorly understood. Prioritization is a way for identifying genes involved in complex phenotypic traits. Existing methods of prioritization consider genetic, expression and evolutionary data, molecular-genetic networks and other. In the case of molecular-genetic networks, as a rule, protein-protein interactions and KEGG networks are used. ANDSystem allows reconstructing associative gene networks, which include more than 20 types of interactions, including protein-protein interactions, expression regulation, transport, catalysis, etc. In this work, a set of genes has been prioritized to find genes potentially involved in asthma and hypertension comorbidity. The prioritization was carried out using well-known methods (ToppGene and Endeavor) and a cross-talk centrality criterion, calculated by analysis of associative gene networks from ANDSystem. The identified genes, including IL1A, CD40LG, STAT3, IL15, FAS, APP, TLR2, C3, IL13 and CXCL10, may be involved in the molecular mechanisms of comorbid asthma/hypertension. An analysis of the dynamics of the frequency of mentioning the most priority genes in scientific publications revealed that the top 100 priority genes are significantly enriched with genes with increased positive dynamics, which may be a positive sign for further studies of these genes.

Novel candidate genes important for asthma and hypertension comorbidity revealed from associative gene networks.

BACKGROUND: Hypertension and bronchial asthma are a major issue for people's health. As of 2014, approximately one billion adults, or ~ 22% of the world population, have had hypertension. As of 2011, 235-330 million people globally have been affected by asthma and approximately 250,000-345,000 people have died each year from the disease. The development of the effective treatment therapies against these diseases is complicated by their comorbidity features. This is often a major problem in diagnosis and their treatment. Hence, in this study the bioinformatical methodology for the analysis of the comorbidity of these two diseases have been developed. As such, the search for candidate genes related to the comorbid conditions of asthma and hypertension can help in elucidating the molecular mechanisms underlying the comorbid condition of these two diseases, and can also be useful for genotyping and identifying new drug targets. RESULTS: Using ANDSystem, the reconstruction and analysis of gene networks associated with asthma and hypertension was carried out. The gene network of asthma included 755 genes/proteins and 62,603 interactions, while the gene network of hypertension - 713 genes/proteins and 45,479 interactions. Two hundred and five genes/proteins and 9638 interactions were shared between asthma and hypertension. An approach for ranking genes implicated in the comorbid condition of two diseases was proposed. The approach is based on nine criteria for ranking genes by their importance, including standard methods of gene prioritization (Endeavor, ToppGene) as well as original criteria that take into account the characteristics of an associative gene network and the presence of known polymorphisms in the analysed genes. According to the proposed approach, the genes IL10, TLR4, and CAT had the highest priority in the development of comorbidity of these two diseases. Additionally, it was revealed that the list of top genes is enriched with apoptotic genes and genes involved in biological processes related to the functioning of central nervous system. CONCLUSIONS: The application of methods of reconstruction and analysis of gene networks is a productive tool for studying the molecular mechanisms of comorbid conditions. The method put forth to rank genes by their importance to the comorbid condition of asthma and hypertension was employed that resulted in prediction of 10 genes, playing the key role in the development of the comorbid condition. The results can be utilised to plan experiments for identification of novel candidate genes along with searching for novel pharmacological targets.

Molecular Relationships between Bronchial Asthma and Hypertension as Comorbid Diseases.

Comorbidity, a co-incidence of several disorders in an individual, is a common phenomenon. Their development is governed by multiple factors, including genetic variation. The current study was set up to look at associations between isolated and comorbid diseases of bronchial asthma and hypertension, on one hand, and single nucleotide polymorphisms associated with regulation of gene expression (eQTL), on the other hand. A total of 96 eQTL SNPs were genotyped in 587 Russian individuals. Bronchial asthma alone was found to be associated with rs1927914 (TLR4), rs1928298 (intergenic variant), and rs1980616 (SERPINA1); hypertension alone was found to be associated with rs11065987 (intergenic variant); rs2284033 (IL2RB), rs11191582 (NT5C2), and rs11669386 (CARD8); comorbidity between asthma and hypertension was found to be associated with rs1010461 (ANG/RNASE4), rs7038716, rs7026297 (LOC105376244), rs7025144 (intergenic variant), and rs2022318 (intergenic variant). The results suggest that genetic background of comorbidity of asthma and hypertension is different from genetic backgrounds of both diseases manifesting isolated.

Robotic QM/MM-driven maturation of antibody combining sites.

In vitro selection of antibodies from large repertoires of immunoglobulin (Ig) combining sites using combinatorial libraries is a powerful tool, with great potential for generating in vivo scavengers for toxins. However, addition of a maturation function is necessary to enable these selected antibodies to more closely mimic the full mammalian immune response. We approached this goal using quantum mechanics/molecular mechanics (QM/MM) calculations to achieve maturation in silico. We preselected A17, an Ig template, from a naïve library for its ability to disarm a toxic pesticide related to organophosphorus nerve agents. Virtual screening of 167,538 robotically generated mutants identified an optimum single point mutation, which experimentally boosted wild-type Ig scavenger performance by 170-fold. We validated the QM/MM predictions via kinetic analysis and crystal structures of mutant apo-A17 and covalently modified Ig, thereby identifying the displacement of one water molecule by an arginine as delivering this catalysis.