Machine learning papers on predict Protein Post-translational modifications



Phosphorylation

  1. PlantPhos using maximal dependence decomposition to identify plant phosphorylation sites with substrate site specificity

    2. ⭕ Samples：S (2506 positive and 2506 negative), T (378 positive and 378 negative), Y (108 positive and 108 negative).

    ⭕ Data Download

  2. Incorporating substrate sequence motifs and spatial amino acid composition to identify kinase-specific phosphorylation sites on protein three-dimensional structures

    3. ⭕ Samples：11485 positive samples, 14263 negative samples.

    ⭕ Data Download

  3. PKIS Computational Identification of Protein Kinases for Experimentally Discovered Protein Phosphorylation Sites

    4. ⭕ Samples：1649 positive samples, 80909 negative samples.

    ⭕ Data Download

  4. Prediction of posttranslational modification sites from amino acid sequences with kernel methods

    5. ⭕ Samples：1694 positive samples, 54245 negative samples.

    ⭕ Data Download

  5. ViralPhos: incorporating a recursively statistical method to predict phosphorylation sites on virus proteins

    6. ⭕ Samples：450 positive samples, 450 negative samples.

    ⭕ Data Download

  6. PhosphoSVM: prediction of phosphorylation sites by integrating various protein sequence attributes with a support vector machine

    7. ⭕ Samples：36611 positive samples, 36611 negative samples.

    ⭕ Data Download

  7. MusiteDeep: a deep-learning framework for general and kinase-specific phosphorylation site prediction

    8. ⭕ Samples：General data (38405 positive and 875218 negative), Kinase-specific data (1827 positive and 82237).

    ⭕ Data Download

  8. PhosPred-RF: A Novel Sequence-Based Predictor for Phosphorylation Sites Using Sequential Information Only

    9. ⭕ Samples：S (21434 positive and 7089 negative), T (7809 positive and 2492 negative), Y (1763 positive and 849 negative).

    ⭕ Data Download

  9. PhosContext2vec: a distributed representation of residuelevel sequence contexts and its application to general and kinasespecific phosphorylation site prediction

    10. ⭕ Samples：3786 positive sanples, 232603 negative samples.

    ⭕ Data Download

  10. iPhoPred: A Predictor for Identifying Phosphorylation Sites in Human Protein

    11. ⭕ Samples：S (300 positive and 300 negative), T (100 positive and 100 negative), Y (110 positive and 110 negative).

    ⭕ Data Download

  11. GPS-PBS: A Deep Learning Framework to Predict Phosphorylation Sites that Specifically Interact with Phosphoprotein-Binding Domains

    12. ⭕ Samples：16146 positive samples, 702141 negative samples.

    ⭕ Data Download

Acetylation

  1. PLMLA: prediction of lysine methylation and lysine acetylation by combining multiple features

    2. ⭕ Samples：2842 positive samples, 2842 negative samples.

    ⭕ Data Download

  2. Position-Specific Analysis and Prediction for Protein Lysine Acetylation Based on Multiple Features

    3. ⭕ Samples：10300 positive samples, 146831 negative samples.

    ⭕ Data Download

  3. An Intelligent System for Identifying Acetylated Lysine on Histones and Nonhistone Proteins

    4. ⭕ Samples：Histone (209 positive and 2822 negative), Nonhistone (3391 positive and 74182 negative).

    ⭕ Data Download

  4. iPTM-mLys: identifying multiple lysine PTM sites and their different types

    5. ⭕ Samples：3991 positive samples, 2403 negative samples.

    ⭕ Data Download

  5. iAcet-Sumo: Identification of lysine acetylation and sumoylation sites in proteins by multi-class transformation methods

    6. ⭕ Samples：10185 positive samples, 13743 negative samples.

    ⭕ Data Download

  6. ProAcePred: prokaryote lysine acetylation sites prediction based on elastic net feature optimization

    7. ⭕ Samples：7288 positive samples, 41638 negative samples.

    ⭕ Data Download

  7. A deep learning method to more accurately recall known lysine acetylation sites

    8. ⭕ Samples：16107 positive samples, 16107 negative samples.

    ⭕ Data Download

  8. Identifying Acetylation Protein by Fusing Its PseAAC and Functional Domain Annotation

    9. ⭕ Samples：725 positive samples, 2175 negative samples.

    ⭕ Data Download

  9. Prediction and functional analysis of prokaryote lysine acetylation site by incorporating six types of features into Chou’s general PseAAC

    10. ⭕ Samples：11148 positive samples, and 11148 negative samples.

    ⭕ Data Download

  10. DNNAce: Prediction of prokaryote lysine acetylation sites through deep neural networks with multi-information fusion

    11. ⭕ Samples：7288 positive samples, 7288 negative samples.

    ⭕ Data Download

Methylation

  1. PLMLA: prediction of lysine methylation and lysine acetylation by combining multiple features

    2. ⭕ Samples：546 positive samples, 546 negative samples.

    ⭕ Data Download

  2. iMethyl-PseAAC: Identification of Protein Methylation Sites via a Pseudo Amino Acid Composition Approach

    3. ⭕ Samples：Arg-methylation (205 positive and 1351 negative), Lys-methylation (240 positive and 1544 negative).

    ⭕ Data Download

  3. Identification and characterization of lysine-methylated sites on histones and non-histone proteins

    4. ⭕ Samples：Histones (225 positive and 985 negative), Non-histone proteins (1381 positive and 8088 negative).

    ⭕ Data Download

  4. Accurate in silico prediction of species-specific methylation sites based on information gain feature optimization

    5. ⭕ Samples：Arg-methylation (5700), Lys-methylation (2640)e).

    ⭕ Data Download

  5. iPTM-mLys: identifying multiple lysine PTM sites and their different types

    6. ⭕ Samples：127 positive samples, 6267 negative samples.

    ⭕ Data Download

  6. MusiteDeep: a deep-learning based webserver for protein post-translational modification site prediction and visualization

    7. ⭕ Samples：Arg-methylation (4944 positive and 106805 negative), Lys-methylation (2935 positive and 47525 negative).

    ⭕ Data Download

Ubiquitination

  1. Identification, Analysis and Prediction of Protein Ubiquitination Sites

    2. ⭕ Samples：265 positive samples, 4431 negative samples.

    ⭕ Data Download

  2. Prediction of Ubiquitination Sites by Using the Composition of k-Spaced Amino Acid Pairs

    3. ⭕ Samples：263 positive samples, 4345 negative samples.

    ⭕ Data Download

  3. hCKSAAP_UbSite: Improved prediction of human ubiquitination sites by exploiting amino acid pattern and properties

    4. ⭕ Samples：9537 positive samples, 9537 negative samples.

    ⭕ Data Download

  4. Incorporating key position and amino acid residue features to identify general and species-specific Ubiquitin conjugation sites

    5. ⭕ Samples：H. sapiens (18133 positive and 100408 negative), M. musculus (4022 positive and 40959 negative), S. cerevisiae (170 positive and 1006 negative).

    ⭕ Data Download

  5. iUbiq-Lys: prediction of lysine ubiquitination sites in proteins by extracting sequence evolutio information via a gray system model

    6. ⭕ Samples：659 positive samples, 7196 negative samples.

    ⭕ Data Download

  6. UbiSite: incorporating two-layered machine learning method with substrate motifs to predict ubiquitin-conjugation site on lysines

    7. ⭕ Samples：5925 positive samples, 11746 negative samples.

    ⭕ Data Download

  7. Large-scale prediction of protein ubiquitination sites using a multimodal deep architecture

    8. ⭕ Samples：15573 positive samples, 346144 negative samples.

    ⭕ Data Download

  8. UbiSitePred: A novel method for improving the accuracy of ubiquitination sites prediction by using LASSO to select the optimal Chou's pseudo components

    9. ⭕ Samples：9687 positive samples, 9687 negative samples.

    ⭕ Data Download

  9. MusiteDeep: a deep-learning based webserver for protein post-translational modification site prediction and visualization

    10. ⭕ Samples：4221 positive samples, 56584 negative samples.

    ⭕ Data Download

Succinylation

  1. iSuc-PseAAC: predicting lysine succinylation in proteins by incorporating peptide positionspecific propensity

    2. ⭕ Samples：1167 positive samples, 3553 negative samples.

    ⭕ Data Download

  2. pSuc-Lys: Predict lysine succinylation sites in proteins with PseAAC and ensemble random forest approach

    3. ⭕ Samples： 1167 positive samples, 3553 negative samples.

    ⭕ Data Download

  3. SuccinSite: a computational tool for the prediction of protein succinylation sites by exploiting the amino acid patterns and properties

    4. ⭕ Samples：5004 positive samples, 12477 negative samples.

    ⭕ Data Download

  4. iSuc-PseOpt: Identifying lysine succinylation sites in proteins by incorporating sequence-coupling effects into pseudo components and optimizing imbalanced training dataset

    5. ⭕ Samples：1167 positive samples, 3553 negative samples.

    ⭕ Data Download

  5. Detecting Succinylation sites from protein sequences using ensemble support vector machine

    6. ⭕ Samples：5009 positive samples, 53542 negative samples.

    ⭕ Data Download

  6. Characterization and Identification of Lysine Succinylation Sites based on Deep Learning Method

    7. ⭕ Samples：3216 positive samples, 16412 negative samples.

    ⭕ Data Download

S-sulfenylation

  1. MDD–SOH exploiting maximal dependence decomposition to identify S-sulfenylation sites with substrate motifs

    2. ⭕ Samples：1247 positive samples, 9446 negative samples.

    ⭕ Data Download

  2. iSulf-Cys: Prediction of S-sulfenylation Sites in Proteins with Physicochemical Properties of Amino Acids

    3. ⭕ Samples：1045 positive samples, 7124 negative samples.

    ⭕ Data Download

  3. Computational identification of protein S-sulfenylation sites by incorporating the multiple sequence features information

    4. ⭕ Samples：1243 positive samples, 9441 negative samples.

    ⭕ Data Download

  4. SVM-SulfoSite: A support vector machine based predictor for sulfenylation sites

    5. ⭕ Samples：1045 positive samples, 7124 negative samples.

    ⭕ Data Download

Pupylation

  1. Prediction of pupylation sites using the composition of k-spaced amino acid pairs

    2. ⭕ Samples：212 positive samples, 2666 negative samples.

    ⭕ Data Download

  2. Predicting pupylation sites in prokaryotic proteins using pseudo-amino acid composition and extreme learning machine

    3. ⭕ Samples：174 positive samples, 2207 negative samples.

    ⭕ Data Download

  3. Positive-Unlabeled Learning for Pupylation Sites Prediction

    4. ⭕ Samples：212 positive samples, 2666 negative samples.

    ⭕ Data Download

  4. Predicting pupylation sites in prokaryotic proteins using semi-supervised self-training support vector machine algorithm

    5. ⭕ Samples：278 positive samples, 3527 negative samples.

    ⭕ Data Download

Hydroxylation

  1. iHyd-PseAAC: Predicting Hydroxyproline and Hydroxylysine in Proteins by Incorporating Dipeptide Position-Specific Propensity into Pseudo Amino Acid Composition

    2. ⭕ Samples：743 positive samples, 3535 negative samples.

    ⭕ Data Download

  2. PredHydroxy: computational prediction of protein hydroxylation site locations based on the primar structure

    3. ⭕ Samples：598 positive samples, 3288 negative samples.

    ⭕ Data Download

  3. HydPred: a novel method for the identification of protein hydroxylation sites that reveals new insights into human inherited disease

    4. ⭕ Samples：Hydroxyproline (825 positive and 2600 negative ), Hydroxylysine (121 positive and 937 negative).

    ⭕ Data Download

  4. iHyd-PseCp: Identify hydroxyproline and hydroxylysine in proteins by incorporating sequence-coupled effects into general PseAAC

    5. ⭕ Samples：993 positive samples, 4485 negative samples.

    ⭕ Data Download

  5. MusiteDeep: a deep-learning based webserver for protein post-translational modification site predictio and visualization

    6. ⭕ Samples：Hydroxyproline (3195 positive and 12575 negative ), Hydroxylysine (365 positive and 2687 negative).

    ⭕ Data Download

Palmitoylation

  1. The prediction of palmitoylation site locations using a multiple feature extraction method

    2. ⭕ Samples：188 positive samples, 1246 negative samples.

    ⭕ Data Download

  2. In Silico Identification of Protein S‑Palmitoylation Sites and Their Involvement in Human Inherited Disease

    3. ⭕ Samples：361 positive samples, 2032 negative samples.

    ⭕ Data Download

  3. MDD-Palm: Identification of protein Spalmitoylation sites with substrate motifs based on maximal dependence decomposition

    4. ⭕ Samples：1323 positive samples, 11088 negative samples.

    ⭕ Data Download

  4. MusiteDeep: a deep-learning based webserver for protein post-translational modification site predictio and visualization

    5. ⭕ Samples：3963 positive samples, 27257 negative samples.

    ⭕ Data Download

Glycosylation

  1. A two-layered machine learning method to identify protein O-GlcNAcylation sites with OGlcNAc transferase substrate motifs

    2. ⭕ Samples：976 postive samples, 40033 negative samples.

    ⭕ Data Download

  2. O-GlcNAcPRED-II: an integrated classification algorithm for identifying O-GlcNAcylation sites based on fuzzy undersampling and a K-means PCA oversampling technique

    3. ⭕ Samples：1313 positive samples, 78053 negative samples.

    ⭕ Data Download

  3. N-GlyDE: a two-stage N-linked glycosylation site prediction incorporating gapped dipeptides and pattern-based encoding

    4. ⭕ Samples：682 positive samples, 5599 negative samples.

    ⭕ Data Download

  4. MusiteDeep: a deep-learning based webserver for protein post-translational modification site predictio and visualization

    5. ⭕ Samples：N-linked glycosylation (110866 positive and 632139 negative), O-lined glycosylation (4434 positive and 110019‬ negative).

    ⭕ Data Download

S-nitrosylation

  1. iSNO-AAPair: incorporating amino acid pairwise coupling into PseAAC for predicting cysteine S-nitrosylation sites in proteins

    2. ⭕ Samples：2381 positive samples, 11755 negative samples.

    ⭕ Data Download

  2. iSNO-PseAAC: Predict Cysteine S-Nitrosylation Sites in Proteins by Incorporating Position Specific Amino Acid Propensity into Pseudo Amino Acid Composition

    3. ⭕ Samples：731 positive samples, 810 negative samples.

    ⭕ Data Download

  3. Prediction of S-nitrosylation sites by integrating support vector machines and random forest

    4. ⭕ Samples：3734 positive samples, 20333 negative samples.

    ⭕ Data Download

SUMOylation

  1. mUSP: a high-accuracy map of the in situ crosstalk of ubiquitylation and SUMOylation proteome predicted via the feature enhancement approach

    2. ⭕ Samples：3363 positive samples, 123131 negative samples.

    ⭕ Data Download

  2. MusiteDeep: a deep-learning based webserver for protein post-translational modification site predictio and visualization

    3. ⭕ Samples：1290 positive samples, 25242 negative samples.

    ⭕ Data Download

Malonylation

  1. Mal-Lys: prediction of lysine malonylation sites in proteins integrated sequence-based features with mRMR feature selection

    2. ⭕ Samples：458 positive samples, 3974 negative samples.

    ⭕ Data Download

  2. Computational analysis and prediction of lysine malonylation sites by exploiting informative features in an integrative machine-learning framework

    3. ⭕ Samples：E.coli (1553 positive and 7830 negative), M. musculus (2609 positive and 26655), H. sapiens (3885 positive and 52027 negative).

    ⭕ Data Download

Carbonylation

  1. iCar-PseCp: identify carbonylation sites in proteins by Monte Carlo sampling and incorporating sequence coupled effects into general PseAAC

    2. ⭕ Samples：683 positive samples, 4320 negative samples.

    ⭕ Data Download

Tyrosine sulfation

  1. Computational Prediction and Analysis for Tyrosine Post-Translational Modifications via Elastic Computational Prediction and Analysis for Tyrosine Post-Translational Modifications via Elastic Net

    2. ⭕ Samples：90 positive samples, 865 negative samples.

    ⭕ Data Download

last update: 2020-6-30

E-mail address:acy196707@163.com