MOTIVATION: The process of drug development is inherently complex, marked by extended intervals from the inception of a pharmaceutical agent to its eventual launch in the market. Additionally, each phase in this process is associated with a significant failure rate, amplifying the inherent challenges of this task. Computational virtual screening powered by machine learning algorithms has emerged as a promising approach for predicting therapeutic efficacy. However, the complex relationships between the features learned by these algorithms can be challenging to decipher. RESULTS: We have engineered an artificial neural network model designed specifically for predicting drug sensitivity. This model utilizes a biologically informed visible neural network, thereby enhancing its interpretability. The trained model allows for an in-depth exploration of the biological pathways integral to prediction and the chemical attributes of drugs that impact sensitivity. Our model harnesses multiomics data derived from a different tumor tissue sources, as well as molecular descriptors that encapsulate the properties of drugs. We extended the model to predict drug synergy, resulting in favorable outcomes while retaining interpretability. Given the imbalanced nature of publicly available drug screening datasets, our model demonstrated superior performance to state-of-the-art visible machine learning algorithms. AVAILABILITY AND IMPLEMENTATION: MOViDA is implemented in Python using PyTorch library and freely available for download at https://github.com/Luigi-Ferraro/MOViDA. Training data, RIS score and drug features are archived on Zenodo https://doi.org/10.5281/zenodo.8180380.

The stratification of patients at risk of progression of COVID-19 and their molecular characterization is of extreme importance to optimize treatment and to identify therapeutic options. The bioinformatics community has responded to the outbreak emergency with a set of tools and resource to identify biomarkers and drug targets that we review here. Starting from a consolidated corpus of 27 570 papers, we adopt latent Dirichlet analysis to extract relevant topics and select those associated with computational methods for biomarker identification and drug repurposing. The selected topics span from machine learning and artificial intelligence for disease characterization to vaccine development and to therapeutic target identification. Although the way to go for the ultimate defeat of the pandemic is still long, the amount of knowledge, data and tools generated so far constitutes an unprecedented example of global cooperation to this threat.

BACKGROUND: The investigation of molecular alterations associated with the conservation and variation of DNA methylation in eukaryotes is gaining interest in the biomedical research community. Among the different determinants of methylation stability, the DNA composition of the CpG surrounding regions has been shown to have a crucial role in the maintenance and establishment of methylation statuses. This aspect has been previously characterized in a quantitative manner by inspecting the nucleotidic composition in the region. Research in this field still lacks a qualitative perspective, linked to the identification of certain sequences (or DNA motifs) related to particular DNA methylation phenomena. RESULTS: Here we present a novel computational strategy based on short DNA motif discovery in order to characterize sequence patterns related to aberrant CpG methylation events. We provide our framework as a user-friendly, shiny-based application, CpGmotifs, to easily retrieve and characterize DNA patterns related to CpG methylation in the human genome. Our tool supports the functional interpretation of deregulated methylation events by predicting transcription factors binding sites (TFBS) encompassing the identified motifs. CONCLUSIONS: CpGmotifs is an open source software. Its source code is available on GitHub https://github.com/Greco-Lab/CpGmotifs and a ready-to-use docker image is provided on DockerHub at https://hub.docker.com/r/grecolab/cpgmotifs .

MOTIVATION: Omics technologies have the potential to facilitate the discovery of new biomarkers. However, only few omics-derived biomarkers have been successfully translated into clinical applications to date. Feature selection is a crucial step in this process that identifies small sets of features with high predictive power. Models consisting of a limited number of features are not only more robust in analytical terms, but also ensure cost effectiveness and clinical translatability of new biomarker panels. Here we introduce GARBO, a novel multi-island adaptive genetic algorithm to simultaneously optimize accuracy and set size in omics-driven biomarker discovery problems. RESULTS: Compared to existing methods, GARBO enables the identification of biomarker sets that best optimize the trade-off between classification accuracy and number of biomarkers. We tested GARBO and six alternative selection methods with two high relevant topics in precision medicine: cancer patient stratification and drug sensitivity prediction. We found multivariate biomarker models from different omics data types such as mRNA, miRNA, copy number variation, mutation and DNA methylation. The top performing models were evaluated by using two different strategies: the Pareto-based selection, and the weighted sum between accuracy and set size (w = 0.5). Pareto-based preferences show the ability of the proposed algorithm to search minimal subsets of relevant features that can be used to model accurate random forest-based classification systems. Moreover, GARBO systematically identified, on larger omics data types, such as gene expression and DNA methylation, biomarker panels exhibiting higher classification accuracy or employing a number of features much lower than those discovered with other methods. These results were confirmed on independent datasets. AVAILABILITY AND IMPLEMENTATION: github.com/Greco-Lab/GARBO. CONTACT: [email protected]. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

BACKGROUND: Functional annotation of genes is an essential step in omics data analysis. Multiple databases and methods are currently available to summarize the functions of sets of genes into higher level representations, such as ontologies and molecular pathways. Annotating results from omics experiments into functional categories is essential not only to understand the underlying regulatory dynamics but also to compare multiple experimental conditions at a higher level of abstraction. Several tools are already available to the community to represent and compare functional profiles of omics experiments. However, when the number of experiments and/or enriched functional terms is high, it becomes difficult to interpret the results even when graphically represented. Therefore, there is currently a need for interactive and user-friendly tools to graphically navigate and further summarize annotations in order to facilitate results interpretation also when the dimensionality is high. RESULTS: We developed an approach that exploits the intrinsic hierarchical structure of several functional annotations to summarize the results obtained through enrichment analyses to higher levels of interpretation and to map gene related information at each summarized level. We built a user-friendly graphical interface that allows to visualize the functional annotations of one or multiple experiments at once. The tool is implemented as a R-Shiny application called FunMappOne and is available at https://github.com/grecolab/FunMappOne . CONCLUSION: FunMappOne is a R-shiny graphical tool that takes in input multiple lists of human or mouse genes, optionally along with their related modification magnitudes, computes the enriched annotations from Gene Ontology, Kyoto Encyclopedia of Genes and Genomes, or Reactome databases, and reports interactive maps of functional terms and pathways organized in rational groups. FunMappOne allows a fast and convenient comparison of multiple experiments and an easy way to interpret results.

Summary: Detecting and interpreting responsive modules from gene expression data by using network-based approaches is a common but laborious task. It often requires the application of several computational methods implemented in different software packages, forcing biologists to compile complex analytical pipelines. Here we introduce INfORM (Inference of NetwOrk Response Modules), an R shiny application that enables non-expert users to detect, evaluate and select gene modules with high statistical and biological significance. INfORM is a comprehensive tool for the identification of biologically meaningful response modules from consensus gene networks inferred by using multiple algorithms. It is accessible through an intuitive graphical user interface allowing for a level of abstraction from the computational steps. Availability and implementation: INfORM is freely available for academic use at https://github.com/Greco-Lab/INfORM. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: CpG sites in an individual molecule may exist in a binary state (methylated or unmethylated) and each individual DNA molecule, containing a certain number of CpGs, is a combination of these states defining an epihaplotype. Classic quantification based approaches to study DNA methylation are intrinsically unable to fully represent the complexity of the underlying methylation substrate. Epihaplotype based approaches, on the other hand, allow methylation profiles of cell populations to be studied at the single molecule level. For such investigations, next-generation sequencing techniques can be used, both for quantitative and for epihaplotype analysis. Currently available tools for methylation analysis lack output formats that explicitly report CpG methylation profiles at the single molecule level and that have suited statistical tools for their interpretation. RESULTS: Here we present ampliMethProfiler, a python-based pipeline for the extraction and statistical epihaplotype analysis of amplicons from targeted deep bisulfite sequencing of multiple DNA regions. CONCLUSIONS: ampliMethProfiler tool provides an easy and user friendly way to extract and analyze the epihaplotype composition of reads from targeted bisulfite sequencing experiments. ampliMethProfiler is written in python language and requires a local installation of BLAST and (optionally) QIIME tools. It can be run on Linux and OS X platforms. The software is open source and freely available at http://amplimethprofiler.sourceforge.net .

BACKGROUND: The analysis of complex diseases is an important problem in human genetics. Because multifactoriality is expected to play a pivotal role, many studies are currently focused on collecting information on the genetic and environmental factors that potentially influence these diseases. However, there is still a lack of efficient and thoroughly tested statistical models that can be used to identify implicated features and their interactions. Simulations using large biologically realistic data sets with known gene-gene and gene-environment interactions that influence the risk of a complex disease are a convenient and useful way to assess the performance of statistical methods. RESULTS: The Gene-Environment iNteraction Simulator 2 (GENS2) simulates interactions among two genetic and one environmental factor and also allows for epistatic interactions. GENS2 is based on data with realistic patterns of linkage disequilibrium, and imposes no limitations either on the number of individuals to be simulated or on number of non-predisposing genetic/environmental factors to be considered. The GENS2 tool is able to simulate gene-environment and gene-gene interactions. To make the Simulator more intuitive, the input parameters are expressed as standard epidemiological quantities. GENS2 is written in Python language and takes advantage of operators and modules provided by the simuPOP simulation environment. It can be used through a graphical or a command-line interface and is freely available from http://sourceforge.net/projects/gensim. The software is released under the GNU General Public License version 3.0. CONCLUSIONS: Data produced by GENS2 can be used as a benchmark for evaluating statistical tools designed for the identification of gene-gene and gene-environment interactions.