From word models to executable models of signaling networks using automated assembly

Gyori, Benjamin M.; Bachman, John A.; Subramanian, Kartik; Muhlich, Jeremy; Galescu, Lucian; Sorger, Peter K.

doi:10.15252/msb.20177651

Cited by 155 publications

(151 citation statements)

References 100 publications

(161 reference statements)

Supporting

Mentioning

132

Contrasting

Unclassified

Order By: Relevance

“…The method returns the top grounding along with a dictionary including probabilities for all alternative groundings. Adeft has already been integrated into the Integrated Network and Dynamical Reasoning Assembler (INDRA), a system that assembles mechanistic information from multiple natural language processing systems (Gyori et al, 2017). INDRA uses Adeft in its grounding_mapper submodule to re-ground ambiguous entities from external NLP systems.…”

Section: Resultsmentioning

confidence: 99%

Adeft: Acromine-based Disambiguation of Entities from Text with applications to the biomedical literature

Steppi¹,

Gyori²,

Bachman³

2020

JOSS

Self Cite

View full text Add to dashboard Cite

Section: Resultsmentioning

confidence: 99%

Adeft: Acromine-based Disambiguation of Entities from Text with applications to the biomedical literature

Steppi¹,

Gyori²,

Bachman³

2020

JOSS

Self Cite

View full text Add to dashboard Cite

“…For example, matrix factorizationbased machine learning algorithms have applied to the prediction of novel drug-target interactions [26,27,91]. Pathway/network analysis tools have been developed to study drug effects [28,[92][93][94].…”

Section: Discussionmentioning

confidence: 99%

Mechanisms of Action of Autophagy Modulators Dissected by Quantitative Systems Pharmacology Analysis

Shi

Pei

Perlmutter

et al. 2020

Preprint

View full text Add to dashboard Cite

Autophagy plays an essential role in cell survival/death and functioning. Modulation of autophagy has been recognized as a promising therapeutic strategy against diseases/disorders associated with uncontrolled growth or accumulation of biomolecular aggregates, organelles or cells including those caused by cancer, aging, neurodegeneration, and liver diseases such as α1antitrypsin deficiency. Numerous pharmacological agents that enhance or suppress autophagy have been discovered. However, their molecular mechanisms of action are far from clear. Here we collected a set of 225 autophagy modulators and carried out a comprehensive quantitative systems pharmacology (QSP) analysis of their targets using both existing databases and predictions made by our machine learning algorithm. Autophagy modulators include several highly promiscuous drugs (e.g. artenimol and olanzapine acting as activator, fostamatinib as inhibitor, or melatonin as dual-modulator), as well as selected drugs uniquely targeting specific proteins (~30% of modulators). They are mediated by three layers of regulation: (i) pathways involving core autophagy-related (ATG) proteins such as mTOR, AKT, and AMPK; (ii) upstream signaling events that regulates the activity of ATG pathways such as calcium-, cAMP-, and MAPK-signaling pathways; and (iii) transcription factors regulating the expression ATG proteins such as TFEB, TFE3, HIF-1, FoxO, and NF-κB. Our results suggest that PKA serves as a linker bridging between various signal transduction events and autophagy. These new insights contribute to a better assessment of the mechanism of action of autophagy modulators as well as their side effects, development of novel polypharmacological strategies, and identification of drug repurposing opportunities.

show abstract

“…We applied our method to 5,066 regulatory interactions in TRRUST for which information on mode of regulation was available. As a benchmark, we developed an alternative pipeline using Integrated Network and Dynamical Reasoning Assembler (IN-DRA), a state-of-the-art text mining pipeline in biomedical domain, [48]. INDRA is an automated model assembly system interfacing with NLP systems and databases developed for molecular systems biology to collect knowledge and describe molecular mechanisms.…”

Section: Classification Performancementioning

confidence: 99%

ModEx: A text mining system for extracting mode of regulation of Transcription Factor-gene regulatory interaction

Farahmand

Riley

Zarringhalam

2019

Preprint

View full text Add to dashboard Cite

A B S T R A C T Background: Transcription factors (TFs) are proteins that are fundamental to transcription and regulation of gene expression. Each TF may regulate multiple genes and each gene may be regulated by multiple TFs. TFs can act as either activator or repressor of gene expression. This complex network of interactions between TFs and genes underlies many developmental and biological processes and is implicated in several human diseases such as cancer. Hence deciphering the network of TFgene interactions with information on mode of regulation (activation vs. repression) is an important step toward understanding the regulatory pathways that underlie complex traits. There are many experimental, computational, and manually curated databases of TF-gene interactions. In particular, high-throughput ChIP-Seq datasets provide a large-scale map or transcriptional regulatory interactions. However, these interactions are not annotated with information on context and mode of regulation. Such information is crucial to gain a global picture of gene regulatory mechanisms and can aid in developing machine learning models for applications such as biomarker discovery, prediction of response to therapy, and precision medicine. Methods: In this work, we introduce a text-mining system to annotate ChIP-Seq derived interaction with such meta data through mining PubMed articles. We evaluate the performance of our system using gold standard small scale manually curated databases. Results: Our results show that the method is able to accurately extract mode of regulation with F-score 0.77 on TRRUST curated interaction and F-score 0.96 on intersection of TRUSST and ChIP-network. We provide a HTTP REST API for our code to facilitate usage. Availibility: Source code and datasets are available for download on GitHub: https:

show abstract

From word models to executable models of signaling networks using automated assembly

Cited by 155 publications

References 100 publications

Adeft: Acromine-based Disambiguation of Entities from Text with applications to the biomedical literature

Adeft: Acromine-based Disambiguation of Entities from Text with applications to the biomedical literature

Mechanisms of Action of Autophagy Modulators Dissected by Quantitative Systems Pharmacology Analysis

ModEx: A text mining system for extracting mode of regulation of Transcription Factor-gene regulatory interaction

Contact Info

Product

Resources

About