Cancer stem cells (CSCs) are a subpopulation of cancer cells within tumors that exhibit stem-like properties and represent a potentially effective therapeutic target toward long-term remission by means of differentiation induction. By leveraging an artificial intelligence approach solely based on transcriptomics data, this study scored a large library of small molecules based on their predicted ability to induce differentiation in stem-like cells. In particular, a deep neural network model was trained using publicly available single-cell RNA-Seq data obtained from untreated human-induced pluripotent stem cells at various differentiation stages and subsequently utilized to screen drug-induced gene expression profiles from the Library of Integrated Network-based Cellular Signatures (LINCS) database. The challenge of adapting such different data domains was tackled by devising an adversarial learning approach that was able to effectively identify and remove domain-specific bias during the training phase. Experimental validation in MDA-MB-231 and MCF7 cells demonstrated the efficacy of five out of six tested molecules among those scored highest by the model. In particular, the efficacy of triptolide, OTS-167, quinacrine, granisetron and A-443654 offer a potential avenue for targeted therapies against breast CSCs.

MOTIVATION: Cancer is a very heterogeneous disease that can be difficult to treat without addressing the specific mechanisms driving tumour progression in a given patient. High-throughput screening and sequencing data from cancer cell-lines has driven many developments in drug development, however, there are important aspects crucial to precision medicine that are often overlooked, namely the inherent differences between tumours in patients and the cell-lines used to model them in vitro. Recent developments in transfer learning methods for patient and cell-line data have shown progress in translating results from cell-lines to individual patients in silico. However, transfer learning can be forceful and there is a risk that clinically relevant patterns in the omics profiles of patients are lost in the process. RESULTS: We present MODAE, a novel deep learning algorithm to integrate omics profiles from cell-lines and patients for the purposes of exploring precision medicine opportunities. MODAE implements patient survival prediction as an additional task in a drug-sensitivity transfer learning schema and aims to balance autoencoding, domain adaptation, drug-sensitivity prediction, and survival prediction objectives in order to better preserve the heterogeneity between patients that is relevant to survival. While burdened with these additional tasks, MODAE performed on par with baseline survival models, but struggled in the drug-sensitivity prediction task. Nevertheless, these preliminary results were promising and show that MODAE provides a novel AI-based method for prioritizing drug treatments for high-risk patients. AVAILABILITY AND IMPLEMENTATION: https://github.com/UEFBiomedicalInformaticsLab/MODAE.

SARS-CoV-2 caused the first severe pandemic of the digital era. Computational approaches have been ubiquitously used in an attempt to timely and effectively cope with the resulting global health crisis. In order to extensively assess such contribution, we collected, categorized and prioritized over 17 000 COVID-19-related research articles including both peer-reviewed and preprint publications that make a relevant use of computational approaches. Using machine learning methods, we identified six broad application areas i.e. Molecular Pharmacology and Biomarkers, Molecular Virology, Epidemiology, Healthcare, Clinical Medicine and Clinical Imaging. We then used our prioritization model as a guidance through an extensive, systematic review of the most relevant studies. We believe that the remarkable contribution provided by computational applications during the ongoing pandemic motivates additional efforts toward their further development and adoption, with the aim of enhancing preparedness and critical response for current and future emergencies.

MOTIVATION: Untargeted metabolomic approaches hold a great promise as a diagnostic tool for inborn errors of metabolisms (IEMs) in the near future. However, the complexity of the involved data makes its application difficult and time consuming. Computational approaches, such as metabolic network simulations and machine learning, could significantly help to exploit metabolomic data to aid the diagnostic process. While the former suffers from limited predictive accuracy, the latter is normally able to generalize only to IEMs for which sufficient data are available. Here, we propose a hybrid approach that exploits the best of both worlds by building a mapping between simulated and real metabolic data through a novel method based on Siamese neural networks (SNN). RESULTS: The proposed SNN model is able to perform disease prioritization for the metabolic profiles of IEM patients even for diseases that it was not trained to identify. To the best of our knowledge, this has not been attempted before. The developed model is able to significantly outperform a baseline model that relies on metabolic simulations only. The prioritization performances demonstrate the feasibility of the method, suggesting that the integration of metabolic models and data could significantly aid the IEM diagnosis process in the near future. AVAILABILITY AND IMPLEMENTATION: Metabolic datasets used in this study are publicly available from the cited sources. The original data produced in this study, including the trained models and the simulated metabolic profiles, are also publicly available (Messa et al., 2020).

SUMMARY: Pathway-based expression profiles allow for high-level interpretation of transcriptomic data and systematic comparison of dysregulated cellular programs. We have previously demonstrated the efficacy of pathway-based approaches with two different applications: the Drug Set Enrichment Analysis and the Gene2drug analysis. Here we present a software tool that allows to easily convert gene-based profiles to pathway-based profiles and analyze them within the popular R framework. We also provide pre-computed profiles derived from the original Connectivity Map and its next generation release, i.e. the LINCS database. AVAILABILITY AND IMPLEMENTATION: the tool is implemented as the R/Bioconductor package gep2pep and can be freely downloaded from https://bioconductor.org/packages/gep2pep. SUPPLEMENTARY INFORMATION: Supplementary data are available at http://dsea.tigem.it/lincs.

Motivation: Drug repositioning has been proposed as an effective shortcut to drug discovery. The availability of large collections of transcriptional responses to drugs enables computational approaches to drug repositioning directly based on measured molecular effects. Results: We introduce a novel computational methodology for rational drug repositioning, which exploits the transcriptional responses following treatment with small molecule. Specifically, given a therapeutic target gene, a prioritization of potential effective drugs is obtained by assessing their impact on the transcription of genes in the pathway(s) including the target. We performed in silico validation and comparison with a state-of-art technique based on similar principles. We next performed experimental validation in two different real-case drug repositioning scenarios: (i) upregulation of the glutamate-pyruvate transaminase (GPT), which has been shown to induce reduction of oxalate levels in a mouse model of primary hyperoxaluria, and (ii) activation of the transcription factor TFEB, a master regulator of lysosomal biogenesis and autophagy, whose modulation may be beneficial in neurodegenerative disorders. Availability and implementation: A web tool for Gene2drug is freely available at http://gene2drug.tigem.it. An R package is under development and can be obtained from https://github.com/franapoli/gep2pep. Contact: [email protected]. Supplementary information: Supplementary data are available at Bioinformatics online.

BACKGROUND: Reproducibility in Data Analysis research has long been a significant concern, particularly in the areas of Bioinformatics and Computational Biology. Towards the aim of developing reproducible and reusable processes, Data Analysis management tools can help giving structure and coherence to complex data flows. Nonetheless, improved software quality comes at the cost of additional design and planning effort, which may become impractical in rapidly changing development environments. I propose that an adjustment of focus from processes to data in the management of Bioinformatic pipelines may help improving reproducibility with minimal impact on preexisting development practices. RESULTS: In this paper I introduce the repo R package for bioinformatic analysis management. The tool supports a data-centered philosophy that aims at improving analysis reproducibility and reusability with minimal design overhead. The core of repo lies in its support for easy data storage, retrieval, distribution and annotation. In repo the data analysis flow is derived a posteriori from dependency annotations. CONCLUSIONS: The repo package constitutes an unobtrusive data and flow management extension of the R statistical language. Its adoption, together with good development practices, can help improving data analysis management, sharing and reproducibility, especially in the fields of Bioinformatics and Computational Biology.

MOTIVATION: Automated screening approaches are able to rapidly identify a set of small molecules inducing a desired phenotype from large small-molecule libraries. However, the resulting set of candidate molecules is usually very diverse pharmacologically, thus little insight on the shared mechanism of action (MoA) underlying their efficacy can be gained. RESULTS: We introduce a computational method (Drug-Set Enrichment Analysis-DSEA) based on drug-induced gene expression profiles, which is able to identify the molecular pathways that are targeted by most of the drugs in the set. By diluting drug-specific effects unrelated to the phenotype of interest, DSEA is able to highlight phenotype-specific pathways, thus helping to formulate hypotheses on the MoA shared by the drugs in the set. We validated the method by analysing five different drug-sets related to well-known pharmacological classes. We then applied DSEA to identify the MoA shared by drugs known to be partially effective in rescuing mutant cystic fibrosis transmembrane conductance regulator (CFTR) gene function in Cystic Fibrosis. AVAILABILITY AND IMPLEMENTATION: The method is implemented as an online web tool publicly available at http://dsea.tigem.it. CONTACT: [email protected] SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

SUMMARY: Elucidation of molecular targets of a compound [mode of action (MoA)] and its off-targets is a crucial step in drug development. We developed an online collaborative resource (MANTRA 2.0) that supports this process by exploiting similarities between drug-induced transcriptional profiles. Drugs are organized in a network of nodes (drugs) and edges (similarities) highlighting 'communities' of drugs sharing a similar MoA. A user can upload gene expression profiles before and after drug treatment in one or multiple cell types. An automated processing pipeline transforms the gene expression profiles into a unique drug 'node' embedded in the drug-network. Visual inspection of the neighbouring drugs and communities helps in revealing its MoA and to suggest new applications of known drugs (drug repurposing). MANTRA 2.0 allows storing and sharing user-generated network nodes, thus making MANTRA 2.0 a collaborative ever-growing resource. AVAILABILITY AND IMPLEMENTATION: The web tool is freely available for academic use at http://mantra.tigem.it.

BACKGROUND: An incremental, loosely planned development approach is often used in bioinformatic studies when dealing with custom data analysis in a rapidly changing environment. Unfortunately, the lack of a rigorous software structuring can undermine the maintainability, communicability and replicability of the process. To ameliorate this problem we propose the Leaf system, the aim of which is to seamlessly introduce the pipeline formality on top of a dynamical development process with minimum overhead for the programmer, thus providing a simple layer of software structuring. RESULTS: Leaf includes a formal language for the definition of pipelines with code that can be transparently inserted into the user's Python code. Its syntax is designed to visually highlight dependencies in the pipeline structure it defines. While encouraging the developer to think in terms of bioinformatic pipelines, Leaf supports a number of automated features including data and session persistence, consistency checks between steps of the analysis, processing optimization and publication of the analytic protocol in the form of a hypertext. CONCLUSIONS: Leaf offers a powerful balance between plan-driven and change-driven development environments in the design, management and communication of bioinformatic pipelines. Its unique features make it a valuable alternative to other related tools.

Hight-Throughput Screening (HTS) is a powerful tool in drug discovery, but very expensive in terms of required equipment and running costs. The virtual equivalent of HTS is molecular databases with the ability to search between millions of molecules by means of a similarity measure. In this work we propose a new class of bounds, algorithms and storage strategies based on the Intersection Inequality [5] for the Tanimoto Similarity to improve state of the art performances in querying large repositories of binary fingerprints. We focus on a special case that we call the β = B algorithm. The performance of the algorithm is assessed by simulating queries over an excerpt of the ChemDB [7]. We show how the average search can be up to 37% faster than using the Bit-Bound[4] alone, depending on the amount of space dedicated to data structures needed by the algorithm.

Clustering of real-world data is often ill-posed. Because of noise and intrinsic ambiguity in data, optimization models attempting to maximize a fitness function can be misled by the assumption of uniqueness of the solution. In this work we present a methodology including classic and novel techniques to approach clustering in a systematic way, with two application examples to biological data sets. The methodology is based on a process that generates multiple clustering solutions (using global optimization), performs cluster analysis on such clusterings (i.e. meta clustering) and analyzes the obtained clusterings by the appropriate application of different consensus techniques. In order to validate the method, we seek for the solutions that best match the real class labels, exploiting only a random sample of them. Finally, we guess the class labels of the remaining patterns using cluster enrichment information and verify the percentage of correct assignments for each class. The optimization of clustering objective functions together with the use of partial labeling puts the described approach in between unsupervised and semi-supervised methods.

In this work a multi-step approach for clustering assessment, visualization and data validation is introduced. Three main approaches for data clustering are used and compared: K-means, self organizing maps and probabilistic principal surfaces. A model explorer approach with different similarity measures is used to obtain the best parameters of the methods. The approach is used to identify genes periodically expressed in tumors related to the human cell cycle. Finally, clusters are validated by using GO term information.