Network discovery software tools | Biomedical text mining

A web tool that extracts a network of interactions from a set of PubMed abstracts given by a user, and allows filtering the interaction network according to user-defined concepts. PESCADOR uses pre-compiled dictionaries of terms (from Entrez Gene and UniProt) for every organism with deposited genes (NCBI Taxonomy Database) and dictionaries of biological concepts (Medical Subject Headings, MeSH). Therefore, biologists need to simply load (copy/paste) their literature of interest (a list of PubMed identifiers, PMIDs) to launch the text-mining analysis.

Provides a similarity fusion approach. disease-similarity-fusion is a method to integrate biological data across multiple domains through conversion of feature sets into normalized similarity scores. This method accounts for differences in information content between different data types, allowing combination of each data type in a balanced manner.

Extracts automatically “surface area” and “pore volume” data from a metal-organic frameworks (MOF). This software exploits natural language processing (NLP) to facilitate the text mining of potentially thousands of MOF. “surface area” and “pore volume” are the criteria identified because they relate the adsorption properties of MOF and are the most basic quantities obtained from most MOF experiments.

Automatically extracts information from biological literature to build a topology of the plant defense signaling (PDS) model. Bio3graph is based on a domain specific vocabulary that is composed of two parts: a list of components and a list of reactions together with their synonyms. It is composed of a series of text mining, information extraction, graph construction and graph visualization steps, offering reusability, repeatability, and extension with additional components.

Supports flexible network data association specification using rules, integrates data processing through relational databases and GML data files, and scalable data visualization through layered annotations. ProteoLens is a JAVA-based visual analytic software tool for creating, annotating and exploring multi-scale biological networks. It supports graph/network represented data in standard Graph Modeling Language (GML) formats, and this enables interoperation with a wide range of other visual layout tools.

Accelerates information extraction from the biomedical literature and curate causal and correlative relationships encoded into biological expression language. BELIEF uses a text mining pipeline to extract relation-ships from literature and a web curation that supports the visualization and curation of statements and context annotations automatically extracted by the pipeline. The curation interface was evaluated based on its performance and a user survey. Result showed that the BELIEF dashboard increased the curation efficiency when compared with manual curation.

A network visualization and curation tool to assist metastasis researchers retrieve network information of interest while browsing through the large volume of studies in PubMed. MAT can recognize relations among genes, cancers, tissues and organs of metastasis mentioned in the literature through text-mining techniques, and then produce a visualization of all mined relations in a metastasis network. A MAT network consists of different biological relationships between the concepts such as gene-gene regulation, gene-cancer regulation and the organs of the metastasis. This text mining service uses the principle-pattern-based approach to extract these relations. MET could prove very useful, especially in the construction of a database for metastasis networks.

An approach for relation extraction from free text. RelEx is based on natural language preprocessing producing dependency parse trees and applying a small number of simple rules to these trees.