Inference of protein-protein interaction networks from multiple heterogeneous data

Huang, Lei; Liao, Li; Wu, Cathy

doi:10.1145/2808719.2814836

Cited by 4 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Often, in real-world scenarios, the graph structure is not known and in fields such as computational biology, network inference plays a key role in understanding how molecular interaction works. At the cellular level, for example, we may seek for evidence of regulatory functions (Lozano et al, 2009), coexpression edges, metabolic influence (Kanehisa, 2001), as well as protein/protein interaction networks (Huang et al, 2016). Learning the network structure from data may be hard due to the ratio between number of features and samples.…”

Section: Are There Relevant Relationships Between Variables? (A4)mentioning

confidence: 99%

Where Do We Stand in Regularization for Life Science Studies?

Tozzo

Azencott

Fiorini

et al. 2022

Journal of Computational Biology

View full text Add to dashboard Cite

More and more biologists and bioinformaticians turn to machine learning to analyze large amounts of data. In this context, it is crucial to understand which is the most suitable data analysis pipeline for achieving reliable results. This process may be challenging, due to a variety of factors, the most crucial ones being the data type and the general goal of the analysis (e.g., explorative or predictive). Life science data sets require further consideration as they often contain measures with a low signal-to-noise ratio, high-dimensional observations, and relatively few samples. In this complex setting, regularization, which can be defined as the introduction of additional information to solve an ill-posed problem, is the tool of choice to obtain robust models. Different regularization practices may be used depending both on characteristics of the data and of the question asked, and different choices may lead to different results. In this article, we provide a comprehensive description of the impact and importance of regularization techniques in life science studies. In particular, we provide an intuition of what regularization is and of the different ways it can be implemented and exploited. We propose four general life sciences problems in which regularization is fundamental and should be exploited for robustness. For each of these large families of problems, we enumerate different techniques as well as examples and case studies. Lastly, we provide a unified view of how to approach each data type with various regularization techniques.

show abstract

Section: Are There Relevant Relationships Between Variables? (A4)mentioning

confidence: 99%

Where Do We Stand in Regularization for Life Science Studies?

Tozzo

Azencott

Fiorini

et al. 2022

Journal of Computational Biology

View full text Add to dashboard Cite

show abstract

“…Each network was considered as an undirected graph (Zhu et al 2007), where each node represented a protein and was connected by the interactions, known as edges although the isolated and orphan nodes were removed. The graph is called connected if the nodes are connected by edges, and the nodes which are not connected with each other are known as disconnected component as described earlier in other studies (Huang et al 2016).…”

Section: Construction Of Chaperone Networkmentioning

confidence: 99%

Insights into archaeal chaperone machinery: a network-based approach

Rani

Sharma

Goel

2018

Cell Stress and Chaperones

View full text Add to dashboard Cite

Molecular chaperones are a diverse group of proteins that ensure proteome integrity by helping the proteins fold correctly and maintain their native state, thus preventing their misfolding and subsequent aggregation. The chaperone machinery of archaeal organisms has been thought to closely resemble that found in humans, at least in terms of constituent players. Very few studies have been ventured into system-level analysis of chaperones and their functioning in archaeal cells. In this study, we attempted such an analysis of chaperone-assisted protein folding in archaeal organisms through network approach using Picrophilus torridus as model system. The study revealed that DnaK protein of Hsp70 system acts as hub in protein-protein interaction network. However, DnaK protein was present only in a subset of archaeal organisms and absent from many archaea, especially members of Crenarchaeota phylum. Therefore, a similar network was created for another archaeal organism, Sulfolobus solfataricus, a member of Crenarchaeota. The chaperone network of S. solfataricus suggested that thermosomes played an integral part of hub proteins in archaeal organisms, where DnaK was absent. We further compared the chaperone network of archaea with that found in eukaryotic systems, by creating a similar network for Homo sapiens. In the human chaperone network, the UBC protein, a part of ubiquitination system, was the most important module, and interestingly, this system is known to be absent in archaeal organisms. Comprehensive comparison of these networks leads to several interesting conclusions regarding similarities and differences within archaeal chaperone machinery in comparison to humans.

show abstract

“…Moreover, there are numerous protein sequences in the natural environment and it is too expensive to verify all interactions among all pairs between proteins, which cause the incompleteness of current known PPI networks [38]. Given a dataset with M protein sequences, in order to predict the potential PPI among them, the current available methods compare each protein to the other proteins one by one in pairwise, which need to compare M (M −1) The proposed DHL-PPI method transforms a protein sequence into a binarized Hash code by using deep learning techniques.…”

Section: Introductionmentioning

confidence: 99%

Identification of All-to-All Protein-Protein Interactions Based on Deep Hash Learning

Jiang¹,

Shen²,

Jiang³

2021

Preprint

View full text Add to dashboard Cite

Background: Protein-protein interaction (PPI) is vital for life processes, diseases treatment and new drugs discovery. The computational prediction of PPI is well accepted for its inexpensive and efficient nature comparing to the wet-lab experiment. When a new protein comes, one try to find whether there is any PPI relationship between this new protein and existing proteins, the current computational prediction methods usually compare this new protein to existing proteins one by one in pairwise. This is time comsuming. Results: We proposed an more efficient model, Deep Hash Learning Protein-and-Protein Interaction (DHL-PPI) model, to predict all-to-all PPI relationship on a database. First, DHL-PPI encodes a protein sequence into a binary Hash code based on the features extracted from sequences by using deep learning technique. This encoding scheme enables the PPI discrimination problem to be a much simpler searching problem. A protein with a binary code can be regarded as a number. In the prescreen of PPI prediction stage, the string match problem of searching a string against a database with M proteins can be turned into a much more simpler problem: to find a number inside an sorted array with length M. This prescreen process narrows down proteins inside the whole database into a much smaller candidate set for further confirmation. At last, DHL-PPI uses the Hamming distance to determine the final PPI relationship. Conclusions: The experimental results confirmed that DHL-PPI is feasible and effective. Using a dataset with strictly negative PPI examples of four species, DHL-PPI is superior or competitive to the other state-of-the-art methods in terms of precision, recall or F1 score. Furthermore, in the prediction stage, the proposed DHL-PPI decrease the usual time compexity of O(M2 ) to O(MlogM) for predicting all-to-all PPI interactons between any pairs in M proteins on a database. A protein database can be stored in the proposed encoding scheme and waited to be searched, which is a potential novel encoding scheme to cope with current searching problem for a large volume of database.

show abstract

Inference of protein-protein interaction networks from multiple heterogeneous data

Cited by 4 publications

References 43 publications

Where Do We Stand in Regularization for Life Science Studies?

Where Do We Stand in Regularization for Life Science Studies?

Insights into archaeal chaperone machinery: a network-based approach

Identification of All-to-All Protein-Protein Interactions Based on Deep Hash Learning

Contact Info

Product

Resources

About