Search

Background: More than half of Breast Cancer (BC) patients take chronically used non-cancer treatments (denoted as comedications) at BC diagnosis. Epidemiological evidence has reported that several non-cancer treatments may modify BC risk, BC recurrence, and overall survival (OS). The ADRENALINE project (Atlas for DRug and brEast caNcer survivAL INtEraction) analyses the impact of the use of each commonly prescribed non-cancer treatment at BC diagnosis on OS using the French social security system data on a comprehensive cohort of French BC patients. Methods: We identified all women diagnosed with an incident BC treated with surgery in France from 2011 to 2017 and affiliated to the general health insurance scheme. Women with concomitant cancer or metastases at diagnosis were discarded from the analyses. Comedication intake was defined as the delivery in pharmacy of at least 3 months of full treatment (e.g. 90 pills) the 6 months preceding BC diagnosis. A Cox proportional hazard model was used to estimate the hazard ratio (HR) for each molecule. The model was adjusted on more than 100 confounding variables: social factors, comorbidities and other comedications by Inverse Probability of Treatment Weighting (IPTW). We assumed that the adjustment was sufficient to control for confounding if the standardized mean difference of each confounder after adjustment did not exceed 0.1. Molecules which did not pass the adjustment quality test were discarded. Results: Overall, 235,368 patients were included in the study. Among 219 selected drugs, 91 passed the adjustment quality test. The full set of results is available on a web application (https://adrenaline.curie.fr). Several drugs or drug classes were associated with an improved survival: statins (e.g. rosuvastatin, HR=0.65, p< 0.001); proton-pump inhibitors (HR=0.93; p=0.002); or beta-blocking agents (atenolol, HR=0.78, p=0.003). Conversely, anti-anemic preparations (folic acid and ferrous sulfate) had a significant deleterious effect (HR = 1.63; p< 0.001). Drugs from the same therapeutic class, could have different effects: within benzodiazepines, bromazepam was protective (HR = 0.91; p = 0.038) while oxazepam was deleterious (HR = 1.37; p < 0.001). Conclusion: ADRENALINE reports the impact on BC survival of 219 widely prescribed drugs. It can be used to identify molecules with a potential protective or deleterious effect relative to BC. Some of them are currently under mechanistical investigation within a drug screening program. This atlas highlights candidates to drug-repurposing trials or pharmacovigilance warnings, and will be extended to cancers of other localizations in a near future. Citation Format: Elise Dumas, Beatriz Grandal, Paul Gougis, Sophie Houzard, Aurélien Latouche, Aullène Toussaint, Samar Alsafadi, Judith Abecassis, Lidia Delrieu, Thierry Dubois, Nadir Sella, Marc Espie, Bernard Asselain, Annabelle Ballesta, Benjamin Marande, Eric Daoud, Enora Laas, Amyn Kassara, Floriane Jochum, Elaine Del Nery, Elodie Anthony, Christine Le Bihan-Benjamin, Philippe-Jean Bousquet, Chloé-Agathe Azencott, Fabien Reyal, Anne-Sophie Hamy. Comedications at Breast Cancer diagnosis impact overall survival: results from the ADRENALINE (Atlas for DRug and brEast caNcer survivAL INtEraction) study (n=235,368) [abstract]. In: Proceedings of the 2022 San Antonio Breast Cancer Symposium; 2022 Dec 6-10; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2023;83(5 Suppl):Abstract nr P3-07-06.

PURPOSE Administering systemic anticancer treatment (SACT) to patients near death can negatively affect their health-related quality of life. Late SACT administrations should be avoided in these cases. Machine learning techniques could be used to build decision support tools leveraging registry data for clinicians to limit late SACT administration. MATERIALS AND METHODS Patients with advanced lung cancer who were treated at the Department of Oncology, Aalborg University Hospital and died between 2010 and 2019 were included (N = 2,368). Diagnoses, treatments, biochemical data, and histopathologic results were used to train predictive models of 30-day mortality using logistic regression with elastic net penalty, random forest, gradient tree boosting, multilayer perceptron, and long short-term memory network. The importance of the variables and the clinical utility of the models were evaluated. RESULTS The random forest and gradient tree boosting models outperformed other models, whereas the artificial neural network–based models underperformed. Adding summary variables had a modest effect on performance with an increase in average precision from 0.500 to 0.505 and from 0.498 to 0.509 for the gradient tree boosting and random forest models, respectively. Biochemical results alone contained most of the information with a limited degradation of the performances when fitting models with only these variables. The utility analysis showed that by applying a simple threshold to the predicted risk of 30-day mortality, 40% of late SACT administrations could have been prevented at the cost of 2% of patients stopping their treatment 90 days before death. CONCLUSION This study demonstrates the potential of a decision support tool to limit late SACT administration in patients with cancer. Further work is warranted to refine the model, build an easy-to-use prototype, and conduct a prospective validation study.

We present a network-based protocol to discover susceptibility genes in case-control genome-wide association studies (GWASs). In short, this protocol looks for biomarkers that are informative of disease status and interconnected in an underlying biological network. This boosts discovery and interpretability. Moreover, the protocol tackles the instability of network methods, producing a stable set of genes most likely to replicate in external cohorts. To apply the procedure to a provided GWAS dataset, install the required software and execute our command-line tool. For complete details on the use and execution of this protocol, please refer to Climente-González et al.

Background For the most part, genome-wide association studies (GWAS) have only partially explained the heritability of complex diseases. One of their limitations is to assume independent contributions of individual variants to the phenotype. Many tools have therefore been developed to investigate the interactions between distant loci, or epistasis. Among them, the recently proposed EpiGWAS models the interactions between a target variant and the rest of the genome. However, applying this approach to studying interactions along all genes of a disease map is not straightforward. Here, we propose a pipeline to that effect, which we illustrate by investigating a multiple sclerosis GWAS dataset from the Wellcome Trust Case Control Consortium 2 through 19 disease maps from the MetaCore pathway database. Results For each disease map, we build an epistatic network by connecting the genes that are deemed to interact. These networks tend to be connected, complementary to the disease maps and contain hubs. In addition, we report 4 epistatic gene pairs involving missense variants, and 25 gene pairs with a deleterious epistatic effect mediated by eQTLs. Among these, we highlight the interaction of GLI-1 and SUFU, and of IP10 and NF-$$\kappa$$ κ B, as they both match known biological interactions. The latter pair is particularly promising for therapeutic development, as both genes have known inhibitors. Conclusions Our study showcases the ability of EpiGWAS to uncover biologically interpretable epistatic interactions that are potentially actionable for the development of combination therapy.

BackgroundBreast cancer (BC) is the most frequent cancer and the leading cause of cancer-related death in women. The French National Cancer Institute has created a national cancer cohort to promote cancer research and improve our understanding of cancer using the National Health Data System (SNDS). This cohort amalgamates all cancer sites, with no detailed separate data for early BC.ObjectivesWe describe the French Early Breast Cancer Cohort (FRESH).MethodsAll French women aged 18 years or over, with early-stage BC newly diagnosed between January 1, 2011 and December 31, 2017, treated by surgery and registered in the general health insurance coverage plan were included in the cohort. Patients with suspected locoregional or distant metastases at diagnosis were excluded. BC treatments (surgery, chemotherapy, targeted therapy, radiotherapy, endocrine therapy), and diagnostic procedures (biopsy, cytology, imaging) were extracted from hospital discharge reports, outpatient care notes or pharmacy drug delivery data. BC subtype was inferred from the treatments received.ResultsWe included 235,368 patients with early BC in the cohort (median age: 60 years). BC subtype distribution was as follows: luminal (80.2%), triple-negative (TNBC, 9.5%); HER2+ (10.3%), or unidentifiable (n=44,388, 18.9% of the cohort). Most patients underwent radiotherapy (n=200,685, 85.3%) and endocrine therapy (n=165,655, 70.4%), and 38.3% (n=90,252) received chemotherapy. Treatments and care pathways are described.ConclusionThe FRESH Cohort is an unprecedented population-based resource facilitating future large-scale real-life studies aiming to improve care pathways and quality of care for BC patients.

Genome-Wide Association Studies, or GWAS, aim at finding Single Nucleotide Polymorphisms (SNPs) that are associated with a phenotype of interest. GWAS are known to suffer from the large dimensionality of the data with respect to the number of available samples. Other limiting factors include the dependency between SNPs, due to linkage disequilibrium (LD), and the need to account for population structure, that is to say, confounding due to genetic ancestry.We propose an efficient approach for the multivariate analysis of multi-population GWAS data based on a multitask group Lasso formulation. Each task corresponds to a subpopulation of the data, and each group to an LD-block. This formulation alleviates the curse of dimensionality, and makes it possible to identify disease LD-blocks shared across populations/tasks, as well as some that are specific to one population/task. In addition, we use stability selection to increase the robustness of our approach. Finally, gap safe screening rules speed up computations enough that our method can run at a genome-wide scale.To our knowledge, this is the first framework for GWAS on diverse populations combining feature selection at the LD-groups level, a multitask approach to address population structure, stability selection, and safe screening rules. We show that our approach outperforms state-of-the-art methods on both a simulated and a real-world cancer datasets.

To address the lack of statistical power and interpretability of genome-wide association studies (GWAS), gene-level analyses combine the p-values of individual single nucleotide polymorphisms (SNPs) into gene statistics. However, using all SNPs mapped to a gene, including those with low association scores, can mask the association signal of a gene.We therefore propose a new two-step strategy, consisting in first selecting the SNPs most associated with the phenotype within a given gene, before testing their joint effect on the phenotype. The recently proposed kernelPSI framework for kernel-based post-selection inference makes it possible to model non-linear relationships between features, as well as to obtain valid p-values that account for the selection step.In this paper, we show how we adapted kernelPSI to the setting of quantitative GWAS, using kernels to model epistatic interactions between neighboring SNPs, and post-selection inference to determine the joint effect of selected blocks of SNPs on a phenotype. We illustrate this tool on the study of two continuous phenotypes from the UKBiobank.We show that kernelPSI can be successfully used to study GWAS data and detect genes associated with a phenotype through the signal carried by the most strongly associated regions of these genes. In particular, we show that kernelPSI enjoys more statistical power than other gene-based GWAS tools, such as SKAT or MAGMA.kernelPSI is an effective tool to combine SNP-based and gene-based analyses of GWAS data, and can be used successfully to improve both statistical performance and interpretability of GWAS.

More and more biologists and bioinformaticians turn to machine learning to analyze large amounts of data. In this context, it is crucial to understand which is the most suitable data analysis pipeline for achieving reliable results. This process may be challenging, due to a variety of factors, the most crucial ones being the data type and the general goal of the analysis (e.g., explorative or predictive). Life science data sets require further consideration as they often contain measures with a low signal-to-noise ratio, high-dimensional observations, and relatively few samples. In this complex setting, regularization, which can be defined as the introduction of additional information to solve an ill-posed problem, is the tool of choice to obtain robust models. Different regularization practices may be used depending both on characteristics of the data and of the question asked, and different choices may lead to different results. In this article, we provide a comprehensive description of the impact and importance of regularization techniques in life science studies. In particular, we provide an intuition of what regularization is and of the different ways it can be implemented and exploited. We propose four general life sciences problems in which regularization is fundamental and should be exploited for robustness. For each of these large families of problems, we enumerate different techniques as well as examples and case studies. Lastly, we provide a unified view of how to approach each data type with various regularization techniques.

To address the lack of statistical power and interpretability of genome-wide association studies (GWAS), gene-level analyses combine the p-values of individidual single nucleotide polymorphisms (SNPs) into gene statistics. However, using all SNPs mapped to a gene, including those with low association scores, can mask the association signal of a gene. We therefore propose a new two-step strategy, consisting in first selecting the SNPs most associated with the phenotype within a given gene, before testing their joint effect on the phenotype. The recently proposed kernelPSI framework for kernel-based post-selection inference makes it possible to model non-linear relationships between features, as well as to obtain valid p-values that account for the selection step. In this paper, we show how we adapted kernelPSI to the setting of quantitative GWAS, using kernels to model epistatic interactions between neighboring SNPs, and post-selection inference to determine the joint effect of selected blocks of SNPs on a phenotype. We illustrate this tool on the study of two continuous phenotypes from the UKBiobank. We show that kernelPSI can be successfully used to study GWAS data and detect genes associated with a phenotype through the signal carried by the most strongly associated regions of these genes. In particular, we show that kernelPSI enjoys more statistical power than other gene-based GWAS tools, such as SKAT or MAGMA. kernelPSI is an effective tool to combine SNP-based and gene-based analyses of GWAS data, and can be used successfully to improve both statistical performance and interpretability of GWAS.

BackgroundAccess to health services plays a key role in cancer survival. Uneven distributions of populations and health facilities lead to geographical disparities. Location-allocation algorithms can address these disparities by finding new locations and capacities for health facilities. However, in oncology, opening new hospitals or moving them is difficult in practice, and should be handled carefully.MethodsWe propose a method to measure the spatial accessibility to oncology care and identify the hospitals to grow to reduce disparities. We first ran a clustering algorithm to automatically label the hospitals in terms of oncology specialization. Then, we computed an accessibility score to these hospitals for every population location. Finally, we introducedCAMION, an optimization algorithm based on Linear Programming that reduces disparities in oncology accessibility by identifying health facilities that should increase their capacities.ResultsWe demonstrate our algorithm in metropolitan France. The clustering step let us identify different oncology specialization levels for hospitals. Most of the population in metropolitan France lived in good accessibility areas, especially in large cities. Lower accessibility zones are often rural or suburban municipalities. The optimization algorithm effectively manages to identify hospitals to grow, based on current oncology specialization and accessibility scores.DiscussionThere is a tradeoff to be found by patients, between care center proximity and care center expertise, which is less likely to happen for patients living in good accessibility areas. The accessibility score is deliberately non-specific to cancer type but can be adapted to more precise pathologies. Our method is replicable in any country, given hospitals and population locations data. We developed a web application intended for healthcare professionals to let them to run the optimization algorithm with the desired parameters and visualize the results.

Background: Cancer caused nearly 10 million deaths in 2020. While most of the ongoing research focuses on finding new treatments, accessibility to oncology care receives less attention. However, access to health services plays a key role in cancer survival. Spatial accessibility methods have been successfully applied to measure accessibility to primary care. Yet, little research to date focused on oncology care specifically. Methods: We focused on all care centers with medicine, surgery, or obstetric activity in metropolitan France. We propose a clustering algorithm to automatically label the hospitals in terms of oncology specialization. Then, we computed an accessibility score to these hospitals for every municipality in metropolitan France. Finally, we proposed an optimization algorithm to increase the oncology accessibility by identifying centers which should increase their capacity. Results: We labelled 1,662 care centers into 8 clusters. Half of them were eligible for oncology care and 118 centers were identified as experts. We computed the oncology accessibility score for 34,877 municipalities in metropolitan France. Half of the population lived in the top 20% accessibility areas, and 6.3% in the bottom 20% zones. Accessibility was higher near dense cities, where the experts care centers were located. By combining the care centers clusters and the accessibility distributions, our optimization algorithm could identify hospitals to grow, to reduce accessibility disparities. Conclusion: Our method made it possible to quantify oncology care accessibility across all metropolitan France, as well as to make suggestions on where to increase hospital capacity to improve accessibility, especially in more populated suburban areas. Our approach was deliberately non-specific to cancer type nor to the kind of stays, but it could be adapted to more specific scenarios. We packaged our method into a web application allowing the users to run the algorithms with various parameters and visualize the results. Citation Format: Eric Daoud, Anne-Sophie Hamy, Elise Dumas, Lidia Delrieu, Beatriz Grandal, Christine Le Bihan-Benjamin, Sophie Houzard, Philippe-Jean Bousquet, Judicael Hotton, Aude-Marie Savoye, Christelle Jouannaud, Chloé-Agathe Azencott, Marc Lelarge, Reyal Fabien. Disparities in accessibility to oncology care centers in France [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 1022.

Background: Breast cancer (BC) incidence increases with age, as well as the incidence of many other chronic diseases. Between 42 and 68% of BC patients suffer from other chronic conditions -comorbidities- at BC diagnosis. Comorbidities may be associated with the intake of chronic medications -comedications. The French health insurance system routinely collects health care reimbursements of almost 98% of the population: hospital abstracts, long-term diseases, outpatient care (medical consults, drug purchases under prescription⋯) and death status. The project ADRENALINE (Atlas for DRug and brEast caNcer survivAL INtEraction) analyzes the impact of comedications at diagnosis on BC survival on a French cohort using data from the French social security system. Methods: We identified all women diagnosed with an incident BC treated with surgery in France from 2011 to 2017 and affiliated to the general health insurance scheme. Women with concomitant cancer or metastases at diagnosis were discarded from the analyses. Comedication intake was defined as the delivery in pharmacy of at least 3 months of full treatment (e.g. 90 pills) the 6 months preceding BC diagnosis. The analysis was restricted to drugs taken by at least 300 women. A Cox proportional hazard model was used to estimate the hazard ratio (HR) for each molecule. The model was adjusted on more than 100 confounding variables: social factors, comorbidities and other comedications. Two adjustment methods were tested: Inverse Probability of Treatment Weighting (IPTW) and matching. We assumed that the adjustment was sufficient to control for confounding if the standardized mean difference of each confounder after adjustment did not exceed 0.1. Molecules which did not pass the adjustment quality test were discarded. Results: 235,375 patients were included in the study. Among 219 selected drugs, 91 and 171 passed the adjustment quality test for IPTW and for matching, respectively. The full set of results is available on a web application. Among main findings, several drugs or drug classes were associated with an improved survival: proton-pump inhibitors (IPTW; HR=0.93; p=0.002); statins (e.g. rosuvastatin, IPTW, HR=0.65, p Conclusion: ADRENALINE reports the impact on BC survival of 219 widely prescribed drugs. It can be used to identify molecules with a potential protective or deleterious effect relative to BC. Some of them are currently under mechanistical investigation within a drug screening program. This atlas highlights candidates to drug-repurposing trials or pharmacovigilance warnings, and will be extended to cancers of other localizations in a near future. Citation Format: Elise Dumas, Beatriz Grandal, Lucie Laot, Eric Daoud, Lidia Delrieu, Marc Espié, Sophie Houzard, Christine Le Bihan-Benjamin, Philippe-Jean Bousquet, Elodie Anthony, Aurélien Latouche, Nadir Sella, Thierry Dubois, Annabelle Ballesta, Amyn Kassara, Elaine Del Nery, Benjamin Marande, Samar Alsafadi, Paul Gougis, Chloé-Agathe Azencott, Fabien Reyal, Anne-Sophie Hamy. ADRENALINE, an atlas for drug and breast cancer survival interaction: Comedications at diagnosis and impact on breast cancer mortality of the French breast cancer cohort (n=235,375) [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2022; 2022 Apr 8-13. Philadelphia (PA): AACR; Cancer Res 2022;82(12_Suppl):Abstract nr 4101.

(1) Background:Identification of hit molecules protein targets is essential in the drug discovery process. Target prediction with machine-learning algorithms can help accelerate this search, limiting the number of required experiments. However, Drug-Target Interactions databases used for training present high statistical bias, leading to a high number of false positive predicted targets, thus increasing time and cost of experimental validation campaigns. (2) Methods: To minimize the number of false positive predicted proteins, we propose a new scheme for choosing negative examples, so that each protein and each drug appears an equal number of times in positive and negative examples. We artificially reproduce the process of target identification for 3 particular drugs, and more globally for 200 approved drugs. (3) Results: For the detailed 3 drugs examples, and for the larger set of 200 drugs, training with the proposed scheme for the choice of negative examples improved target prediction results: the average number of false positive among the top ranked predicted targets decreased and overall the rank of the true targets was improved. (4) Conclusion: Our method enables to correct databases statistical bias and reduces the number of false positive predictions, and therefore the number of useless experiments potentially undertaken.

Genome-wide association studies (GWAS) explore the genetic causes of complex diseases. However, classical approaches ignore the biological context of the genetic variants and genes under study. To address this shortcoming, one can use biological networks, which model functional relationships, to search for functionally related susceptibility loci. Many such network methods exist, each arising from different mathematical frameworks, pre-processing steps, and assumptions about the network properties of the susceptibility mechanism. Unsurprisingly, this results in disparate solutions. To explore how to exploit these heterogeneous approaches, we selected six network methods and applied them to GENESIS, a nationwide French study on familial breast cancer. First, we verified that network methods recovered more interpretable results than a standard GWAS. We addressed the heterogeneity of their solutions by studying their overlap, computing what we called the consensus. The key gene in this consensus solution was COPS5, a gene related to multiple cancer hallmarks. Another issue we observed was that network methods were unstable, selecting very different genes on different subsamples of GENESIS. Therefore, we proposed a stable consensus solution formed by the 68 genes most consistently selected across multiple subsamples. This solution was also enriched in genes known to be associated with breast cancer susceptibility (BLM, CASP8, CASP10, DNAJC1, FGFR2, MRPS30, and SLC4A7, P-value = 3 × 10−4). The most connected gene was CUL3, a regulator of several genes linked to cancer progression. Lastly, we evaluated the biases of each method and the impact of their parameters on the outcome. In general, network methods preferred highly connected genes, even after random rewirings that stripped the connections of any biological meaning. In conclusion, we present the advantages of network-guided GWAS, characterize their shortcomings, and provide strategies to address them. To compute the consensus networks, implementations of all six methods are available at https://github.com/hclimente/gwas-tools., Author summary Genome-wide association studies (GWAS) scan thousands of genomes to identify variants associated with a complex trait. Over the last 15 years, GWAS have advanced our understanding of the genetics of complex diseases, and in particular of cancers. However, they have led to an apparent paradox: the more we perform such studies, the more it seems that the entire genome is involved in every disease. The omnigenic model offers an appealing explanation: only a limited number of core genes are directly involved in the disease, but gene functions are deeply interrelated, and so many other genes can alter the function of the core genes. These interrelations are often modeled as networks, and multiple algorithms have been proposed to use these networks to identify the subset of core genes involved in a specific trait. This study applies and compares six such network methods on GENESIS, a GWAS dataset for familial breast cancer in the French population. Combining these approaches allows us to identify potentially novel breast cancer susceptibility genes and provides a mechanistic explanation for their role in the development of the disease. We provide ready-to-use implementations of all the examined methods.

BACKGROUND: Detecting epistatic interactions at the gene level is essential to understanding the biological mechanisms of complex diseases. Unfortunately, genome-wide interaction association studies involve many statistical challenges that make such detection hard. We propose a multi-step protocol for epistasis detection along the edges of a gene-gene co-function network. Such an approach reduces the number of tests performed and provides interpretable interactions while keeping type I error controlled. Yet, mapping gene interactions into testable single-nucleotide polymorphism (SNP)-interaction hypotheses, as well as computing gene pair association scores from SNP pair ones, is not trivial. RESULTS: Here we compare 3 SNP-gene mappings (positional overlap, expression quantitative trait loci, and proximity in 3D structure) and use the adaptive truncated product method to compute gene pair scores. This method is non-parametric, does not require a known null distribution, and is fast to compute. We apply multiple variants of this protocol to a genome-wide association study dataset on inflammatory bowel disease. Different configurations produced different results, highlighting that various mechanisms are implicated in inflammatory bowel disease, while at the same time, results overlapped with known disease characteristics. Importantly, the proposed pipeline also differs from a conventional approach where no network is used, showing the potential for additional discoveries when prior biological knowledge is incorporated into epistasis detection. ispartof: GIGASCIENCE vol:11 ispartof: location:United States status: published

Systems biology shows that genes related to the same phenotype are often functionally related. We can take advantage of this to discover new genes that affect a phenotype. However, the natural unit of analysis in genome-wide association studies (GWAS) is not the gene, but the single nucleotide polymorphism, or SNP. We introduce martini, an R package to build SNP co-function networks and use them to conduct GWAS. In SNP networks, two SNPs are connected if there is evidence they jointly contribute to the same biological function. By leveraging such information in GWAS, we search SNPs that are not only strongly associated with a phenotype, but also functionally related. This, in turn, boosts discovery and interpretability. Martini builds such networks using three sources of information: genomic position, gene annotations, and gene-gene interactions. The resulting SNP networks involve hundreds of thousands of nodes and millions of edges, making their exploration computationally intensive. Martini implements two network-guided biomarker discovery algorithms based on graph cuts that can handle such large networks: SConES and SigMod. They both seek a small subset of SNPs with high association scores with the phenotype of interest and densely interconnected in the network. Both algorithms use parameters that control the relative importance of the SNPs’ association scores, the number of SNPs selected, and their interconnection. Martini includes a cross-validation procedure to set these parameters automatically. Lastly, martini includes tools to visualize the selected SNPs’ network and association properties. Martini is available on GitHub (hclimente/martini) and Bioconductor (martini).

Network approaches to disease use biological networks, which model functional relationships between the molecules in a cell, to generate hypotheses about the genetics of complex diseases. Several among them jointly consider gene scores, representing the association between each gene and the disease, and the biological context of each gene, modeled by a network. Here, we study six such network methods using gene scores from GENESIS, a genome-wide association study (GWAS) on French women with non-BRCA familial breast cancer. We provide a critical comparison of these six methods, discussing the impact of their mathematical formulation and parameters. Using a biological network yields more compelling results than standard GWAS analyses. Indeed, we find significant overlaps between our solutions and the genes identified in the largest GWAS on breast cancer susceptibility. We further propose to combine these solutions into a consensus network, which brings further insights. The consensus network contains COPS5, a gene related to multiple hallmarks of cancer, and 14 of its neighbors. The main drawback of network methods is that they are not robust to small perturbations in their inputs. Therefore, we propose a stable consensus solution, formed by the most consistently selected genes in multiple subsamples of the data. In GENESIS, it is composed of 68 genes, enriched in known breast cancer susceptibility genes (BLM, CASP8, CASP10, DNAJC1, FGFR2, MRPS30, and SLC4A7, P-value = 3 × 10 4) and occupying more central positions in the network than most genes. The network is organized around CUL3, which is involved in the regulation of several genes linked to cancer progression. In conclusion, we showed how network methods help overcome the lack of statistical power of GWAS and improve their interpretation. Project-agnostic implementations of all methods are available at https://github.com/hclimente/gwas-tools.Author summaryGenome-wide association studies (GWAS) scan thousands of genomes to identify variants associated with a complex trait. Over the last 15 years, GWAS have advanced our understanding of the genetics of complex diseases, and in particular of hereditary cancers. However, they have led to an apparent paradox: the more we perform such studies, the more it seems that the entire genome is involved in every disease. The omnigenic model offers an appealing explanation: only a limited number of core genes are directly involved in the disease, but gene functions are deeply interrelated, and so many other genes can alter the function of the core genes. These interrelations are often modeled as networks, and multiple algorithms have been proposed to use these networks to identify the subset of core genes involved in a specific trait. This study applies and compares six such network methods on GENESIS, a GWAS dataset for familial breast cancer in the French population. Combining these approaches allows us to identify potentially novel breast cancer susceptibility genes and provides a mechanistic explanation for their role in the development of the disease. We provide ready-to-use implementations of all the examined methods.

SummaryVariability in datasets is not only the product of biological processes: they are also the product of technical biases. ComBat is one of the most widely used tool for correcting those technical biases, called batch effects, in microarray expression data.In this technical note, we present a new Python implementation of ComBat. While the mathematical framework is strictly the same, we show here that our implementation: (i) has similar results in terms of batch effects correction; (ii) is as fast or faster than the R implementation of ComBat and; (iii) offers new tools for the bioinformatics community to participate in its development.Availability and ImplementationpyComBat is implemented in the Python language and is available under GPL-3.0 (https://www.gnu.org/licenses/gpl-3.0.en.html) license at https://github.com/epigenelabs/pyComBat and https://pypi.org/project/combat/.Contactakpeli@epigenelabs.com

MotivationFinding nonlinear relationships between biomolecules and a biological outcome is computationally expensive and statistically challenging. Existing methods have crucial drawbacks, among others lack of parsimony, non-convexity, and computational overhead. Here we present the block HSIC Lasso, a nonlinear feature selector that does not present the previous drawbacks.ResultsWe compare the block HSIC Lasso to other state-of-the-art feature selection techniques in synthetic data and real data, including experiments over three common types of genomic data: gene-expression microarrays, single-cell RNA-seq, and GWAS. In all the cases, we observe that features selected by block HSIC Lasso retain more information about the underlying biology than features of other techniques. As a proof of concept, we applied the block HSIC Lasso to a single-cell RNA-seq experiment on mouse hippocampus. We discovered that many genes linked in the past to brain development and function are involved in the biological differences between the types of neurons.AvailabilityBlock HSIC Lasso is implemented in the Python 2/3 package pyHSICLasso, available in Github (https://github.com/riken-aip/pyHSICLasso) and PyPi (https://pypi.org/project/pyHSICLasso).Contactmyamada@i.kyoto-u.ac.jpSupplementary informationSupplementary data are available at Bioinformatics online.

International audience; As the size of genome-wide association studies (GWAS) increases, detecting interactions among single nucleotide polymorphisms (SNP) or genes associated to particular phenotypes is garnering more and more interest as a means to decipher the full genetic basis of complex diseases. Systematically testing interactions is however challenging both from a computational and from a statistical point of view, given the large number of possible interactions to consider. In this paper we propose a framework to identify pairwise interactions with a particular target variant, using a penalized regression approach. Narrowing the scope of interaction identification around a predetermined target provides increased statistical power and better interpretability, as well as computational scalability. We compare our new methods to state-of-the-art techniques for epistasis detection on simulated and real data, and demonstrate the benefits of our framework to identify pairwise interactions in several experimental settings.

Adverse drug reactions, also called side effects, range from mild to fatal clinical events and significantly affect the quality of care. Among other causes, side effects occur when drugs bind to proteins other than their intended target. As experimentally testing drug specificity against the entire proteome is out of reach, we investigate the application of chemogenomics approaches. We formulate the study of drug specificity as a problem of predicting interactions between drugs and proteins at the proteome scale. We build several benchmark datasets, and propose NN-MT, a multi-task Support Vector Machine (SVM) algorithm that is trained on a limited number of data points, in order to solve the computational issues or proteome-wide SVM for chemogenomics. We compare NN-MT to different state-of-the-art methods, and show that its prediction performances are similar or better, at an efficient calculation cost. Compared to its competitors, the proposed method is particularly efficient to predict (protein, ligand) interactions in the difficult double-orphan case, i.e. when no interactions are previously known for the protein nor for the ligand. The NN-MT algorithm appears to be a good default method providing state-of-the-art or better performances, in a wide range of prediction scenarii that are considered in the present study: proteome-wide prediction, protein family prediction, test (protein, ligand) pairs dissimilar to pairs in the train set, and orphan cases.

Machine learning applications in precision medicine are severely limited by the scarcity of data to learn from. Indeed, training data often contains many more features than samples. To alleviate the resulting statistical issues, the multitask learning framework proposes to learn different but related tasks jointly, rather than independently, by sharing information between these tasks. Within this framework, the joint regularization of model parameters results in models with few non-zero coefficients and that share similar sparsity patterns. We propose a new regularized multitask approach that incorporates task descriptors, hence modulating the amount of information shared between tasks according to their similarity. We show on simulated data that this method outperforms other multitask feature selection approaches, particularly in the case of scarce data. In addition, we demonstrate on peptide MHC-I binding data the ability of the proposed approach to make predictions for new tasks for which no training data is available.