MM-StackEns: A new deep multimodal stacked generalization approach for protein–protein interaction prediction

Albu, Alexandra-Ioana; Bocicor, Maria-Iuliana; Czibula, Gabriela

doi:10.1016/j.compbiomed.2022.106526

Cited by 10 publications

(11 citation statements)

References 59 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Albu et al 21 designed a deep multimodal stacked generalization approach for PPI prediction. A graph attention network is implemented to sequence the information for PPI prediction.…”

Section: Related Workmentioning

confidence: 99%

“…No. Key techniques Dataset used Advantages Disadvantages 19 network-based driver gene prediction Patient data Critical data identification Limited discussion on methodolgy 20 cancer-associated protein–protein interaction (PPI) PPI data Improved accuracy Limited explanation on deep learning 21 deep multimodal stacked generalization approach for PPI Trained protein data Reduced energy consumption Limited graph attention 22 MMR-CRC DNA-immunohistochemistry (IHC) testing Sustainability in CRC prediction Lack of detailed MMR 23 CNN based approach PPI network Improved accuracy Lack of protein sample structure 24 DNL cancer prediction Clinical data samples Improved energy efficiency Lack of feature selection technique 25 multi-gene genetic programming algorithm Biological information’s protein amino acid ratio Reduced time and energy consumption Limited information on genetic progression 26 miRNA and lncRNA Three EPs of miRNA, lncRNA and PCG in database of the cancer genome atlas (TCGA) Solves optimization problems Complexity due to bigger dataset 27 DNN based lung cancer prediction …”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Response score-based protein structure analysis for cancer prediction aided by the Internet of Things

Alruwaili,

Yousef,

Jumani

et al. 2024

Sci Rep

View full text Add to dashboard Cite

Medical diagnosis through prediction and analysis is par excellence in integrating modern technologies such as the Internet of Things (IoT). With the aid of such technologies, clinical assessments are eased with protracted computing. Specifically, cancer research through structure prediction and analysis is improved through human and machine interventions sustaining precision improvements. This article, therefore, introduces a Protein Structure Prediction Technique based on Three-Dimensional Sequence. This sequence is modeled using amino acids and their folds observed during the pre-initial cancer stages. The observed sequences and the inflammatory response score of the structure are used to predict the impact of cancer. In this process, ensemble learning is used to identify sequence and folding responses to improve inflammations. This score is correlated with the clinical data for structures and their folds independently for determining the structure changes. Such changes through different sequences are handled using repeated ensemble learning for matching and unmatching response scores. The introduced idea integrated with deep ensemble learning and IoT combination, notably employing stacking method for enhanced cancer prediction precision and interdisciplinary collaboration. The proposed technique improves prediction precision, data correlation, and change detection by 11.83%, 8.48%, and 13.23%, respectively. This technique reduces correlation time and complexity by 10.43% and 12.33%, respectively.

show abstract

“…Albu et al 21 designed a deep multimodal stacked generalization approach for PPI prediction. A graph attention network is implemented to sequence the information for PPI prediction.…”

Section: Related Workmentioning

confidence: 99%

Section: Related Workmentioning

confidence: 99%

Response score-based protein structure analysis for cancer prediction aided by the Internet of Things

Alruwaili,

Yousef,

Jumani

et al. 2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Albu et al [ 30 ] presented MM-StackEns, a deep multimodal stacked generalization approach for predicting PPIs, employing a Siamese neural network and graph attention networks, with superior performance on Yeast and Human datasets. Similarly, Jha et al [ 36 ] used Graph Convolutional Network (GCN) and Graph Attention Network (GAT) for PPI prediction, yielding superior results on Human and S. cerevisiae datasets.…”

Section: Graph Neural Network For Protein–protein Interactionsmentioning

confidence: 99%

“…Moreover, while the integration of multimodal data sources and diverse biological features has shown promise in enhancing prediction performance, as evidenced by Albu et al [ 30 ] and Kim et al [ 37 ], it also poses challenges. Managing and harmonizing heterogeneous data types to prevent information loss, while ensuring efficient computation, remains a non-trivial task.…”

Section: Challenges and Future Directions In Recent Studiesmentioning

confidence: 99%

Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review

Lee

2023

Molecules

View full text Add to dashboard Cite

Deep learning, a potent branch of artificial intelligence, is steadily leaving its transformative imprint across multiple disciplines. Within computational biology, it is expediting progress in the understanding of Protein–Protein Interactions (PPIs), key components governing a wide array of biological functionalities. Hence, an in-depth exploration of PPIs is crucial for decoding the intricate biological system dynamics and unveiling potential avenues for therapeutic interventions. As the deployment of deep learning techniques in PPI analysis proliferates at an accelerated pace, there exists an immediate demand for an exhaustive review that encapsulates and critically assesses these novel developments. Addressing this requirement, this review offers a detailed analysis of the literature from 2021 to 2023, highlighting the cutting-edge deep learning methodologies harnessed for PPI analysis. Thus, this review stands as a crucial reference for researchers in the discipline, presenting an overview of the recent studies in the field. This consolidation helps elucidate the dynamic paradigm of PPI analysis, the evolution of deep learning techniques, and their interdependent dynamics. This scrutiny is expected to serve as a vital aid for researchers, both well-established and newcomers, assisting them in maneuvering the rapidly shifting terrain of deep learning applications in PPI analysis.

show abstract

“…This allows for the assessment of a model’s performance on novel entities, ultimately contributing to enhanced generalizability and interpretability [53, 59]. Recent studies [59, 60] emphasize the importance of going beyond the PPI network topology in machine learning and advocate for the incorporation of inductive tests in constructing models with biological utility and interpretability. Yet, intricate calibration of these models via fine-tuning [61] and embedding regularization limit their generalizability within particular databases and families of proteins [59].…”

Section: Introductionmentioning

confidence: 99%

Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction Prediction

Chatterjee,

Ravandi,

Philip

et al. 2024

Preprint

View full text Add to dashboard Cite

Unraveling the human interactome to understand biological processes and uncover disease-specific patterns hinges on accurate protein-protein interaction (PPI) predictions. However, challenges persist in machine learning (ML) models due to a scarcity of quality hard negative samples, shortcut learning, and limited generalizability to novel proteins. Here, we introduce ComPPlete (Completing the Protein-Protein Interaction Network), a novel ML pipeline utilizing PPI network topology for strategic sampling of protein-protein non-interactions (PPNIs) by leveraging higher-order network characteristics that capture the inherent complementarity-driven mechanisms of PPIs. Integrating unsupervised pre-training in protein representation learning with topological PPNI samples, ComPPlete improves PPI prediction generalizability and interpretability, particularly in identifying potential binding sites locations on amino acid sequences. ComPPlete strengthens the prioritization of screening assays, facilitates the transferability of ML predictions across protein families and homodimers. ComPPlete establishes the foundation for a fundamental negative sampling methodology in graph machine learning by integrating insights from network topology.

show abstract

MM-StackEns: A new deep multimodal stacked generalization approach for protein–protein interaction prediction

Cited by 10 publications

References 59 publications

Response score-based protein structure analysis for cancer prediction aided by the Internet of Things

Response score-based protein structure analysis for cancer prediction aided by the Internet of Things

Recent Advances in Deep Learning for Protein-Protein Interaction Analysis: A Comprehensive Review

Topology-Driven Negative Sampling Enhances Generalizability in Protein-Protein Interaction Prediction

Contact Info

Product

Resources

About