NetMe 2.0: a web-based platform for extracting and modeling knowledge from biomedical literature as a labeled graph.

MOTIVATION: The rapid increase of bio-medical literature makes it harder and harder for scientists to keep pace with the discoveries on which they build their studies. Therefore, computational tools have become more widespread, among which network analysis plays a crucial role in several life-science contexts. Nevertheless, building correct and complete networks about some user-defined biomedical topics on top of the available literature is still challenging. RESULTS: We introduce NetMe 2.0, a web-based platform that automatically extracts relevant biomedical entities and their relations from a set of input texts-i.e. in the form of full-text or abstract of PubMed Central's papers, free texts, or PDFs uploaded by users-and models them as a BioMedical Knowledge Graph (BKG). NetMe 2.0 also implements an innovative Retrieval Augmented Generation module (Graph-RAG) that works on top of the relationships modeled by the BKG and allows the distilling of well-formed sentences that explain their content. The experimental results show that NetMe 2.0 can infer comprehensive and reliable biological networks with significant Precision-Recall metrics when compared to state-of-the-art approaches. AVAILABILITY AND IMPLEMENTATION: https://netme.click/.

Machine learning to identify a composite indicator to predict cardiac death in ischemic heart disease.

BACKGROUND: Machine learning (ML) employs algorithms that learn from data, building models with the potential to predict events by aggregating a large number of variables and assessing their complex interactions. The aim of this study is to assess ML potential in identifying patients with ischemic heart disease (IHD) at high risk of cardiac death (CD). METHODS: 3987 (mean age 68 ± 11) hospitalized IHD patients were enrolled. We implemented and compared various ML models and their combination into ensembles. Model output constitutes a new ML indicator to be employed for stratification. Primary variable importance was assessed with ablation tests. RESULTS: An ensemble classifier combining three ML models achieved the best performance to predict CD (AUROC of 0.830, F1-macro of 0.726). ML indicator use through Cox survival analysis outperformed the 18 variables individually, producing a better stratification compared to standard multivariate analysis (improvement of ∼20%). Patients in the low risk group defined through ML indicator had a significantly higher survival (88.8% versus 29.1%). The main variables identified were Dyslipidemia, LVEF, Previous CABG, Diabetes, Previous Myocardial Infarction, Smoke, Documented resting or exertional ischemia, with an AUROC of 0.791 and an F1-score of 0.674, lower than that of 18 variables. Both code and clinical data are freely available with this article. CONCLUSION: ML may allow a faster, low-cost and reliable evaluation of IHD patient prognosis by inclusion of more predictors and identification of those more significant, improving outcome prediction towards the development of precision medicine in this clinical field.

ChatGPT and the rise of large language models: the new AI-driven infodemic threat in public health.

Large Language Models (LLMs) have recently gathered attention with the release of ChatGPT, a user-centered chatbot released by OpenAI. In this perspective article, we retrace the evolution of LLMs to understand the revolution brought by ChatGPT in the artificial intelligence (AI) field. The opportunities offered by LLMs in supporting scientific research are multiple and various models have already been tested in Natural Language Processing (NLP) tasks in this domain. The impact of ChatGPT has been huge for the general public and the research community, with many authors using the chatbot to write part of their articles and some papers even listing ChatGPT as an author. Alarming ethical and practical challenges emerge from the use of LLMs, particularly in the medical field for the potential impact on public health. Infodemic is a trending topic in public health and the ability of LLMs to rapidly produce vast amounts of text could leverage misinformation spread at an unprecedented scale, this could create an "AI-driven infodemic," a novel public health threat. Policies to contrast this phenomenon need to be rapidly elaborated, the inability to accurately detect artificial-intelligence-produced text is an unresolved issue.

BioTAGME: A Comprehensive Platform for Biological Knowledge Network Analysis.

The inference of novel knowledge and new hypotheses from the current literature analysis is crucial in making new scientific discoveries. In bio-medicine, given the enormous amount of literature and knowledge bases available, the automatic gain of knowledge concerning relationships among biological elements, in the form of semantically related terms (or entities), is rising novel research challenges and corresponding applications. In this regard, we propose BioTAGME, a system that combines an entity-annotation framework based on Wikipedia corpus (i.e., TAGME tool) with a network-based inference methodology (i.e., DT-Hybrid). This integration aims to create an extensive Knowledge Graph modeling relations among biological terms and phrases extracted from titles and abstracts of papers available in PubMed. The framework consists of a back-end and a front-end. The back-end is entirely implemented in Scala and runs on top of a Spark cluster that distributes the computing effort among several machines. The front-end is released through the Laravel framework, connected with the Neo4j graph database to store the knowledge graph.

NETME: on-the-fly knowledge network construction from biomedical literature.

BACKGROUND: The rapidly increasing biological literature is a key resource to automatically extract and gain knowledge concerning biological elements and their relations. Knowledge Networks are helpful tools in the context of biological knowledge discovery and modeling. RESULTS: We introduce a novel system called NETME, which, starting from a set of full-texts obtained from PubMed, through an easy-to-use web interface, interactively extracts biological elements from ontological databases and then synthesizes a network inferring relations among such elements. The results clearly show that our tool is capable of inferring comprehensive and reliable biological networks. SUPPLEMENTARY INFORMATION: The online version contains supplementary material available at 10.1007/s41109-021-00435-x.

Early outcome detection for COVID-19 patients.

With the outbreak of COVID-19 exerting a strong pressure on hospitals and health facilities, clinical decision support systems based on predictive models can help to effectively improve the management of the pandemic. We present a method for predicting mortality for COVID-19 patients. Starting from a large number of clinical variables, we select six of them with largest predictive power, using a feature selection method based on genetic algorithms and starting from a set of COVID-19 patients from the first wave. The algorithm is designed to reduce the impact of missing values in the set of variables measured, and consider only variables that show good accuracy on validation data. The final predictive model provides accuracy larger than 85% on test data, including a new patient cohort from the second COVID-19 wave, and on patients with imputed missing values. The selected clinical variables are confirmed to be relevant by recent literature on COVID-19.

Give more data, awareness and control to individual citizens, and they will help COVID-19 containment.

The rapid dynamics of COVID-19 calls for quick and effective tracking of virus transmission chains and early detection of outbreaks, especially in the "phase 2" of the pandemic, when lockdown and other restriction measures are progressively withdrawn, in order to avoid or minimize contagion resurgence. For this purpose, contact-tracing apps are being proposed for large scale adoption by many countries. A centralized approach, where data sensed by the app are all sent to a nation-wide server, raises concerns about citizens' privacy and needlessly strong digital surveillance, thus alerting us to the need to minimize personal data collection and avoiding location tracking. We advocate the conceptual advantage of a decentralized approach, where both contact and location data are collected exclusively in individual citizens' "personal data stores", to be shared separately and selectively (e.g., with a backend system, but possibly also with other citizens), voluntarily, only when the citizen has tested positive for COVID-19, and with a privacy preserving level of granularity. This approach better protects the personal sphere of citizens and affords multiple benefits: it allows for detailed information gathering for infected people in a privacy-preserving fashion; and, in turn this enables both contact tracing, and, the early detection of outbreak hotspots on more finely-granulated geographic scale. The decentralized approach is also scalable to large populations, in that only the data of positive patients need be handled at a central level. Our recommendation is two-fold. First to extend existing decentralized architectures with a light touch, in order to manage the collection of location data locally on the device, and allow the user to share spatio-temporal aggregates-if and when they want and for specific aims-with health authorities, for instance. Second, we favour a longer-term pursuit of realizing a Personal Data Store vision, giving users the opportunity to contribute to collective good in the measure they want, enhancing self-awareness, and cultivating collective efforts for rebuilding society.

Motif-Raptor: a cell type-specific and transcription factor centric approach for post-GWAS prioritization of causal regulators.

MOTIVATION: Genome-wide association studies (GWASs) have identified thousands of common trait-associated genetic variants but interpretation of their function remains challenging. These genetic variants can overlap the binding sites of transcription factors (TFs) and therefore could alter gene expression. However, we currently lack a systematic understanding on how this mechanism contributes to phenotype. RESULTS: We present Motif-Raptor, a TF-centric computational tool that integrates sequence-based predictive models, chromatin accessibility, gene expression datasets and GWAS summary statistics to systematically investigate how TF function is affected by genetic variants. Given trait-associated non-coding variants, Motif-Raptor can recover relevant cell types and critical TFs to drive hypotheses regarding their mechanism of action. We tested Motif-Raptor on complex traits such as rheumatoid arthritis and red blood cell count and demonstrated its ability to prioritize relevant cell types, potential regulatory TFs and non-coding SNPs which have been previously characterized and validated. AVAILABILITY AND IMPLEMENTATION: Motif-Raptor is freely available as a Python package at: https://github.com/pinellolab/MotifRaptor. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

A public data set of spatio-temporal match events in soccer competitions.

Soccer analytics is attracting increasing interest in academia and industry, thanks to the availability of sensing technologies that provide high-fidelity data streams for every match. Unfortunately, these detailed data are owned by specialized companies and hence are rarely publicly available for scientific research. To fill this gap, this paper describes the largest open collection of soccer-logs ever released, containing all the spatio-temporal events (passes, shots, fouls, etc.) that occured during each match for an entire season of seven prominent soccer competitions. Each match event contains information about its position, time, outcome, player and characteristics. The nature of team sports like soccer, halfway between the abstraction of a game and the reality of complex social systems, combined with the unique size and composition of this dataset, provide an ideal ground for tackling a wide range of data science problems, including the measurement and evaluation of performance, both at individual and at collective level, and the determinants of success and failure.

Compression-based classification of biological sequences and structures via the Universal Similarity Metric: experimental assessment.

BACKGROUND: Similarity of sequences is a key mathematical notion for Classification and Phylogenetic studies in Biology. It is currently primarily handled using alignments. However, the alignment methods seem inadequate for post-genomic studies since they do not scale well with data set size and they seem to be confined only to genomic and proteomic sequences. Therefore, alignment-free similarity measures are actively pursued. Among those, USM (Universal Similarity Metric) has gained prominence. It is based on the deep theory of Kolmogorov Complexity and universality is its most novel striking feature. Since it can only be approximated via data compression, USM is a methodology rather than a formula quantifying the similarity of two strings. Three approximations of USM are available, namely UCD (Universal Compression Dissimilarity), NCD (Normalized Compression Dissimilarity) and CD (Compression Dissimilarity). Their applicability and robustness is tested on various data sets yielding a first massive quantitative estimate that the USM methodology and its approximations are of value. Despite the rich theory developed around USM, its experimental assessment has limitations: only a few data compressors have been tested in conjunction with USM and mostly at a qualitative level, no comparison among UCD, NCD and CD is available and no comparison of USM with existing methods, both based on alignments and not, seems to be available. RESULTS: We experimentally test the USM methodology by using 25 compressors, all three of its known approximations and six data sets of relevance to Molecular Biology. This offers the first systematic and quantitative experimental assessment of this methodology, that naturally complements the many theoretical and the preliminary experimental results available. Moreover, we compare the USM methodology both with methods based on alignments and not. We may group our experiments into two sets. The first one, performed via ROC (Receiver Operating Curve) analysis, aims at assessing the intrinsic ability of the methodology to discriminate and classify biological sequences and structures. A second set of experiments aims at assessing how well two commonly available classification algorithms, UPGMA (Unweighted Pair Group Method with Arithmetic Mean) and NJ (Neighbor Joining), can use the methodology to perform their task, their performance being evaluated against gold standards and with the use of well known statistical indexes, i.e., the F-measure and the partition distance. Based on the experiments, several conclusions can be drawn and, from them, novel valuable guidelines for the use of USM on biological data. The main ones are reported next. CONCLUSION: UCD and NCD are indistinguishable, i.e., they yield nearly the same values of the statistical indexes we have used, accross experiments and data sets, while CD is almost always worse than both. UPGMA seems to yield better classification results with respect to NJ, i.e., better values of the statistical indexes (10% difference or above), on a substantial fraction of experiments, compressors and USM approximation choices. The compression program PPMd, based on PPM (Prediction by Partial Matching), for generic data and Gencompress for DNA, are the best performers among the compression algorithms we have used, although the difference in performance, as measured by statistical indexes, between them and the other algorithms depends critically on the data set and may not be as large as expected. PPMd used with UCD or NCD and UPGMA, on sequence data is very close, although worse, in performance with the alignment methods (less than 2% difference on the F-measure). Yet, it scales well with data set size and it can work on data other than sequences. In summary, our quantitative analysis naturally complements the rich theory behind USM and supports the conclusion that the methodology is worth using because of its robustness, flexibility, scalability, and competitiveness with existing techniques. In particular, the methodology applies to all biological data in textual format. The software and data sets are available under the GNU GPL at the supplementary material web page.

The BioPrompt-box: an ontology-based clustering tool for searching in biological databases.

BACKGROUND: High-throughput molecular biology provides new data at an incredible rate, so that the increase in the size of biological databanks is enormous and very rapid. This scenario generates severe problems not only at indexing time, where suitable algorithmic techniques for data indexing and retrieval are required, but also at query time, since a user query may produce such a large set of results that their browsing and "understanding" becomes humanly impractical. This problem is well known to the Web community, where a new generation of Web search engines is being developed, like Vivisimo. These tools organize on-the-fly the results of a user query in a hierarchy of labeled folders that ease their browsing and knowledge extraction. We investigate this approach on biological data, and propose the so called The BioPrompt-boxsoftware system which deploys ontology-driven clustering strategies for making the searching process of biologists more efficient and effective. RESULTS: The BioPrompt-box (Bpb) defines a document as a biological sequence plus its associated meta-data taken from the underneath databank--like references to ontologies or to external databanks, and plain texts as comments of researchers and (title, abstracts or even body of) papers. Bpboffers several tools to customize the search and the clustering process over its indexed documents. The user can search a set of keywords within a specific field of the document schema, or can execute Blastto find documents relative to homologue sequences. In both cases the search task returns a set of documents (hits) which constitute the answer to the user query. Since the number of hits may be large, Bpbclusters them into groups of homogenous content, organized as a hierarchy of labeled clusters. The user can actually choose among several ontology-based hierarchical clustering strategies, each offering a different "view" of the returned hits. Bpbcomputes these views by exploiting the meta-data present within the retrieved documents such as the references to Gene Ontology, the taxonomy lineage, the organism and the keywords. Of course, the approach is flexible enough to leave room for future additions of other meta-information. The ultimate goal of the clustering process is to provide the user with several different readings of the (maybe numerous) query results and show possible hidden correlations among them, thus improving their browsing and understanding. CONCLUSION: Bpb is a powerful search engine that makes it very easy to perform complex queries over the indexed databanks (currently only UNIPROT is considered). The ontology-based clustering approach is efficient and effective, and could thus be applied successfully to larger databanks, like GenBank or EMBL.