Overview of GeCo: A Project for Exploring and Integrating Signals from the Genome

Ceri, Stefano; Bernasconi, Anna; Canakoglu, Arif; Gulino, Andrea; Kaitoua, Abdulrahman; Masseroli, Marco; Nanni, Luca; Pinoli, Pietro

doi:10.1007/978-3-319-96553-6_4

Cited by 12 publications

(9 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…( 16 )), which recognizes a set of concepts that are supported by most genomic data sources in order to provide a common language for genomic dataset integration pipelines. The work is in line with the principles of the GeCo project ( 17 ) and sets the bases for inclusion of a relevant fraction of GEO within the META-BASE repository ( 18 ) and its search tools ( 19 ). Compared to a state-of-the-art tool for metadata annotation (Ontology Annotations and Semantic Similarity Software, OnASSiS ( 20 )), GeMI demonstrates a considerable improvement, especially when put in the context of downstream analysis pipelines (e.g.…”

Section: Introductionmentioning

confidence: 93%

GeMI: interactive interface for transformer-based Genomic Metadata Integration

et al. 2022

Self Cite

View full text Add to dashboard Cite

The Gene Expression Omnibus (GEO) is a public archive containing >4 million digital samples from functional genomics experiments collected over almost two decades. The accompanying metadata describing the experiments suffer from redundancy, inconsistency and incompleteness due to the prevalence of free text and the lack of well-defined data formats and their validation. To remedy this situation, we created Genomic Metadata Integration (GeMI; http://gmql.eu/gemi/), a web application that learns to automatically extract structured metadata (in the form of key-value pairs) from the plain text descriptions of GEO experiments. The extracted information can then be indexed for structured search and used for various downstream data mining activities. GeMI works in continuous interaction with its users. The natural language processing transformer-based model at the core of our system is a fine-tuned version of the Generative Pre-trained Transformer 2 (GPT2) model that is able to learn continuously from the feedback of the users thanks to an active learning framework designed for the purpose. As a part of such a framework, a machine learning interpretation mechanism (that exploits saliency maps) allows the users to understand easily and quickly whether the predictions of the model are correct and improves the overall usability. GeMI’s ability to extract attributes not explicitly mentioned (such as sex, tissue type, cell type, ethnicity and disease) allows researchers to perform specific queries and classification of experiments, which was previously possible only after spending time and resources with tedious manual annotation. The usefulness of GeMI is demonstrated on practical research use cases. Database URL http://gmql.eu/gemi/

show abstract

Section: Introductionmentioning

confidence: 93%

GeMI: interactive interface for transformer-based Genomic Metadata Integration

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…While primary and secondary are already well-defined disciplines, with many widely used algorithms and protocols [7], tertiary analysis has only recently acquired importance [8]; in the long term, however, we expect it to become the most crucial bioinformatics challenge. Given the increase in complexity, novel human-computer interaction paradigms (such as conversational agents) are also becoming more and more needed to bridge the gap with a growing community of tertiary data analysis users, which includes biologists and clinicians.…”

Section: Related Workmentioning

confidence: 99%

GeCoAgent: A Conversational Agent for Empowering Genomic Data Extraction and Analysis

Crovari

PidòSara

PinoliPietro

et al. 2021

ACM Trans. Comput. Healthcare

Self Cite

View full text Add to dashboard Cite

With the availability of reliable and low-cost DNA sequencing, human genomics is relevant to a growing number of end-users, including biologists and clinicians. Typical interactions require applying comparative data analysis to huge repositories of genomic information for building new knowledge, taking advantage of the latest findings in applied genomics for healthcare. Powerful technology for data extraction and analysis is available, but broad use of the technology is hampered by the complexity of accessing such methods and tools. This work presents GeCoAgent, a big-data service for clinicians and biologists. GeCoAgent uses a dialogic interface, animated by a chatbot, for supporting the end-users’ interaction with computational tools accompanied by multi-modal support. While the dialogue progresses, the user is accompanied in extracting the relevant data from repositories and then performing data analysis, which often requires the use of statistical methods or machine learning. Results are returned using simple representations (spreadsheets and graphics), while at the end of a session the dialogue is summarized in textual format. The innovation presented in this article is concerned with not only the delivery of a new tool but also our novel approach to conversational technologies, potentially extensible to other healthcare domains or to general data science.

show abstract

“…NoSQL, a new database model that differs from relational database, disposes of the limitation of ACID theory and belongs to non-relational database. NoSQL is seizing the dominant position occupied by relational database for a long time [11]. A NoSQL provides unstructured storage [12].…”

Section: Background and Related Work A Spatial Index Technology And Nosqlmentioning

confidence: 99%

Improving NoSQL Storage Schema Based on Z-Curve for Spatial Vector Data

et al. 2019

View full text Add to dashboard Cite

NoSQL database can provide massive, high concurrency, and scalable services for storing different types of data. HBase, a type of NoSQL database, in which columns are grouped into column families, is very suitable for storing semi-structured or unstructured spatial vector data. However, since there are few rules and constraints to be followed for the NoSQL database, the design of storage schema for spatial data based on NoSQL is difficult. In this paper, based on our early work, an improved Z-curve storage schema is proposed for spatial vector data. According to our new schema, row key of a geometric object is the Z-curve code of the spatial grids intersected with the geometric object. Moreover, geometric objects with the same row key are stored in a column family. Our proposed method has two features. First, geometric objects adjacent in the location are adjacent in physical storage. Second, redundant exists in storage for improving query accuracy. In our experiments, we compare the improved Z-curve storage schema with a Quadtree storage schema, an R-tree storage schema, and the previous Z-curve storage schema. Query response time, memory usage, and the query accuracy of spatial query on point and range are used to verify the validity of our proposed method. The experimental results show that the two storage schemas based on Z-curve achieve higher query efficiency than the two storage schemas based on tree-the Quadtree storage schema and the R-tree storage schema. More importantly, the query results of the improved Z-curve schema are completely correct, while the query results of the previous Z-curve schema are not.INDEX TERMS Cloud computing, geographic information system (GIS), HBase, NoSQL, spatial index.

show abstract

Overview of GeCo: A Project for Exploring and Integrating Signals from the Genome

Cited by 12 publications

References 19 publications

GeMI: interactive interface for transformer-based Genomic Metadata Integration

GeMI: interactive interface for transformer-based Genomic Metadata Integration

GeCoAgent: A Conversational Agent for Empowering Genomic Data Extraction and Analysis

Improving NoSQL Storage Schema Based on Z-Curve for Spatial Vector Data

Contact Info

Product

Resources

About