ProPythia: A Python package for protein classification based on machine and deep learning

Sequeira, Ana Marta; Lousa, Diana; Rocha, Miguel

doi:10.1016/j.neucom.2021.07.102

Cited by 16 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Gradient Boosting (GBC) and K-nearest neighbor (KNN) models also performed well. Our study further supported the evidence that tree-based models outperformed other algorithms in classi cation tasks using tabular data such as modlAMP descriptors 49,[73][74][75] or other features 76 . Aware of the possible over-representation of α-helices among AMPs 29 , we estimated the structural landscapes of our model datasets, revealing a majority of peptides assuming α-helical and loose structures (subset I − 53.9%), two minorly represented coiled structures (III − 33.1%) and mixed structures (IV -13.0%), and the complete absence of β-stranded peptides (II).…”

Section: Discussionsupporting

confidence: 82%

Structure-aware machine learning strategies for antimicrobial peptide discovery

Aguilera-Puga,

Plisson

2024

Preprint

View full text Add to dashboard Cite

Machine learning models are revolutionizing our approaches to discovering and designing bioactive peptides. However, these models often need protein structure awareness, as they heavily rely on sequential data. The models excel at identifying sequences of a particular biological nature or activity, but they frequently fail to comprehend their intricate mechanism(s) of action. To solve two problems at once, we studied the mechanisms of action and structural landscape of antimicrobial peptides as (i) membrane-disrupting peptides, (ii) membrane-penetrating peptides, and (iii) protein-affine peptides. Our in-depth analysis revealed that our preliminary best-performing classifiers (86–88% accuracy) trained on datasets with an over-represented distribution of α-helical and coiled structures. Consequently, our models would predict the antimicrobial activity of these structure classes more accurately. We mitigated this structural bias by implementing two strategies: subset selection and data reduction. The former gave three structure-specific models predicting the mechanisms of action of peptide sequences likely to fold into α-helices, coils, or mixed structures. The latter depleted over-represented structures, leading to general structure-agnostic predictors.

show abstract

Section: Discussionsupporting

confidence: 82%

Structure-aware machine learning strategies for antimicrobial peptide discovery

Aguilera-Puga,

Plisson

2024

Preprint

View full text Add to dashboard Cite

show abstract

“…These observations support the recent statement that tree-based models RFC and GBC performed very well in classifying tabular data 72 . Previous studies have previously demonstrated that tree-based models outperformed other algorithms in classification or regression tasks using modlAMP descriptors 49 , 73 – 75 or other features 76 .…”

Section: Resultsmentioning

confidence: 99%

Structure-aware machine learning strategies for antimicrobial peptide discovery

Aguilera-Puga,

Plisson

2024

Sci Rep

View full text Add to dashboard Cite

Machine learning models are revolutionizing our approaches to discovering and designing bioactive peptides. These models often need protein structure awareness, as they heavily rely on sequential data. The models excel at identifying sequences of a particular biological nature or activity, but they frequently fail to comprehend their intricate mechanism(s) of action. To solve two problems at once, we studied the mechanisms of action and structural landscape of antimicrobial peptides as (i) membrane-disrupting peptides, (ii) membrane-penetrating peptides, and (iii) protein-binding peptides. By analyzing critical features such as dipeptides and physicochemical descriptors, we developed models with high accuracy (86–88%) in predicting these categories. However, our initial models (1.0 and 2.0) exhibited a bias towards α-helical and coiled structures, influencing predictions. To address this structural bias, we implemented subset selection and data reduction strategies. The former gave three structure-specific models for peptides likely to fold into α-helices (models 1.1 and 2.1), coils (1.3 and 2.3), or mixed structures (1.4 and 2.4). The latter depleted over-represented structures, leading to structure-agnostic predictors 1.5 and 2.5. Additionally, our research highlights the sensitivity of important features to different structure classes across models.

show abstract

“…These are sequence-based features, which are elemental to any protein and are widely employed in different protein identification and classification tasks. − Additionally, other descriptor sets like PAAC (Pseudo amino acid composition), CKSAAP (Amino acid composition), and Moran (Autocorrelation) were also identified among the important features, which are also known to play a significant role in the classification of proteins, including NR. − PAAC, which represents the positional and compositional pattern of an amino acid in protein sequences, preserves the evolutionary patterns within the protein families. Therefore, it is widely used in problems like predicting various post-translational modification sites or identifying protein subcellular localization where evolutional relationships of residues are important. − …”

Section: Resultsmentioning

confidence: 99%

NRPreTo: A Machine Learning-Based Nuclear Receptor and Subfamily Prediction Tool

et al. 2023

View full text Add to dashboard Cite

The nuclear receptor (NR) superfamily includes phylogenetically related ligand-activated proteins, which play a key role in various cellular activities. NR proteins are subdivided into seven subfamilies based on their function, mechanism, and nature of the interacting ligand. Developing robust tools to identify NR could give insights into their functional relationships and involvement in disease pathways. Existing NR prediction tools only use a few types of sequence-based features and are tested on relatively similar independent datasets; thus, they may suffer from overfitting when extended to new genera of sequences. To address this problem, we developed Nuclear Receptor Prediction Tool (NRPreTo), a two-level NR prediction tool with a unique training approach where in addition to the sequence-based features used by existing NR prediction tools, six additional feature groups depicting various physiochemical, structural, and evolutionary features of proteins were utilized. The first level of NRPreTo allows for the successful prediction of a query protein as NR or non-NR and further subclassifies the protein into one of the seven NR subfamilies in the second level. We developed Random Forest classifiers to test on benchmark datasets, as well as the entire human protein datasets from RefSeq and Human Protein Reference Database (HPRD). We observed that using additional feature groups improved the performance. We also observed that NRPreTo achieved high performance on the external datasets and predicted 59 novel NRs in the human proteome. The source code of NRPreTo is publicly available at .

show abstract

ProPythia: A Python package for protein classification based on machine and deep learning

Cited by 16 publications

References 45 publications

Structure-aware machine learning strategies for antimicrobial peptide discovery

Structure-aware machine learning strategies for antimicrobial peptide discovery

Structure-aware machine learning strategies for antimicrobial peptide discovery

NRPreTo: A Machine Learning-Based Nuclear Receptor and Subfamily Prediction Tool

Contact Info

Product

Resources

About