Machine learning papers on predict RNA post-transcriptional modificatios



N6-methyladenosine

  1. iRNA-Methyl: Identifying N6-methyladenosine sites using pseudo nucleotide composition

    2. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  2. Improving N6-methyladenosine site prediction with heuristic selection of nucleotide physicalechemical properties

    3. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  3. pRNAm-PC: Predicting N6-methyladenosine sites in RNA sequences via physicalechemical properties

    4. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  4. TargetM6A: Identifying N6-Methyladenosine Sites From RNA Sequences via Position-Specific Nucleotide Propensities and a Support Vector Machine

    5. ⭕ Samples：Met 2614 (1307 positive and 1307 negative ), Train1664 (832 positive and 832 negative), Test 5225 (475 positive and 4750 negative).

    ⭕ Data Download

  5. Identifying N6-methyladenosine sites using multi-interval nucleotide pair position specificity and support vector machine

    6. ⭕ Samples：S. cerevisiae (1307 positive and 1307 negative), H. sapiens (8366 positive and 8366 negative), A. thaliana (394 positive and 394 negative).

    ⭕ Data Download

  6. Detecting N6-methyladenosine sites from RNA transcriptomes using ensemble Support Vector Machines

    7. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  7. RFAthM6A: a new tool for predicting m6A sites in Arabidopsis thaliana

    8. ⭕ Samples：2518 positive samples, 2518 negative samples.

    ⭕ Data Download

  8. M6APred-EL: A Sequence-Based Predictor for Identifying N6-methyladenosine Sites Using Ensemble Learning

    9. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  9. M6AMRFS: Robust Prediction of N6-Methyladenosine Sites With Sequence-Based Features in Multiple Species

    10. ⭕ Samples：S. cerevisiae (1307 positive and 1307 negative ), H. sapiens (1130 positive and 1130 negative), M. musculus (725 positive and 725 negative),A. thaliana(1000 positive and 1000 negative).

    ⭕ Data Download

  10. iRNA-3typeA: Identifying Three Types of Modification at RNA's Adenosine Sites

    11. ⭕ Samples：H. sapiens (1130 positive and 1130 negative), M. musculus (725 positive and 725 negative).

    ⭕ Data Download

  11. DeepM6ASeq: prediction and characterization of m6A-containing sequences using deep learning

    12. ⭕ Samples：H. sapiens (30839 positive and 30822 negative), M. musculus (23563 positive and 23554 negative), Zebrafish (13881 positive and 13878 negative).

    ⭕ Data Download

  12. iRNA(m6A)-PseDNC: Identifying N6-methyladenosine sites using pseudo dinucleotide composition

    13. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  13. Gene2vec: gene subsequence embedding for prediction of mammalian N6-methyladenosine sites from mRNA

    14. ⭕ Samples： 769876 sequences (positive:negative=1:10), 88579 sequences (positive:negative=1:1) .

    ⭕ Data Download

  14. Integration of deep feature representations and handcrafted features to improve the prediction of N6-methyladenosine sites

    15. ⭕ Samples：1307 positive samples, 1307 negative samples.

    ⭕ Data Download

  15. BERMP: a cross-species classifier for predicting m6A sites by integrating a deep learning algorithm and a random forest approach

    16. ⭕ Samples：S. cerevisiae (1307 positive and 1307 negative ), A. thaliana (2518 positive and 2518 negative), mammalian (50000 positive and 500000 negative).

    ⭕ Data Download

  16. HLMethy: a machine learning‑based model to identify the hidden labels of m6A candidates

    17. ⭕ Samples：14775 positive samples, 14775 negative samples.

    ⭕ Data Download

  17. iMethyl-Deep: N6 Methyladenosine Identification of Yeast Genome with Automatic Feature Extraction Technique by Using Deep Learning Algorithm

    18. ⭕ Samples：M6A2614 (1307 positive and 1307 negative), M6A6540 (3270 positive and 3270 negative).

    ⭕ Data Download

N1-methyladenosine

  1. iRNA-3typeA: Identifying Three Types of Modification at RNA's Adenosine Sites

    2. ⭕ Samples：H. sapiens (6366 positive and 6366 negative), M. musculus (1064 positive and 1064 negative).

    ⭕ Data Download

  2. DeepMRMP: A new predictor for multiple types of RNA modification sites using deep learning

    3. ⭕ Samples：H. sapiens 2574, M. musculus 1052, S. cerevisiae 1220.

    ⭕ Data Download

5-methylcytosine

  1. iRNAm5C-PseDNC: identifying RNA 5-methylcytosine sites by incorporating physical-chemical properties into pseudo dinucleotide composition

    2. ⭕ Samples：475 positive samples, 1425 negative samples.

    ⭕ Data Download

  2. Accurate RNA 5-methylcytosine site prediction based on heuristic physicalchemical properties reduction and classifier ensemble

    3. ⭕ Samples：Met1320 (120 positive and 120 negative), Met1900 (475 positive and 1425 negative).

    ⭕ Data Download

  3. DeepMRMP: A new predictor for multiple types of RNA modification sites using deep learning

    4. ⭕ Samples：H. sapiens 680, M. musculus 97, S. cerevisiae 211.

    ⭕ Data Download

  4. Evaluation of different computational methods on 5-methylcytosine sites identification

    5. ⭕ Samples：H. sapiens (120 positive and 120 negative ), A. thaliana (6289 positive and 6289 negative), M. musculus (97 positive and 97 negative), S. cerevisiae (211 positive and 211 negative).

    ⭕ Data Download

Pseudouridine

  1. PPUS: a web server to predict PUS-specific pseudouridine sites

    2. ⭕ Samples：464 positive samples, 46400 negative samples.

    ⭕ Data Download

  2. DeepMRMP: A new predictor for multiple types of RNA modification sites using deep learning

    3. ⭕ Samples：H. sapiens 4218, M. musculus 3320, S. cerevisiae 2122.

    ⭕ Data Download

  3. XG‑PseU: an eXtreme Gradient Boosting based method for identifying pseudouridine sites

    4. ⭕ Samples：H. sapiens (595 positive and 595 negative), M. musculus (472 positive and 472 negative), S. cerevisiae (414 positive and 413 negative).

    ⭕ Data Download

  4. RF-PseU: A Random Forest Predictor for RNA Pseudouridine Sites

    5. ⭕ Samples：H. sapiens (595 positive and 595 negative), M. musculus (472 positive and 472 negative), S. cerevisiae (414 positive and 414 negative).

    ⭕ Data Download

Adenosine-to-inosine (A-to-I)

  1. iRNA-3typeA: Identifying Three Types of Modification at RNA's Adenosine Sites

    2. ⭕ Samples：H. sapiens (3000 positive and 3000 negative), M. musculus (831 positive and 831 negative).

    ⭕ Data Download

2'-O-methylationation

  1. iRNA-2OM: A Sequence-Based Predictor for Identifying 2'-O-Methylation Sites in Homo sapiens

    2. ⭕ Samples：147 positive samples, 147 negative samples.

    ⭕ Data Download

5-hydroxymethylcytosine

  1. iRNA5hmC: The First Predictor to Identify RNA 5-Hydroxymethylcytosine Modifications Using Machine Learning

    2. ⭕ Samples：662 positive samples, 662 negative samples.

    ⭕ Data Download

N2-methylguanosine

  1. iRNA-m2G: Identifying N2-methylguanosine Sites Based on Sequence-Derived Information

    2. ⭕ Samples：H. sapiens (46 positive and 46 negative), M. musculus (30 posotive and 30 negative), S. cerevisiae (67 positive and 67 negative).

    ⭕ Data Download

Dihydrouridine

  1. Identification of D Modification Sites by Integrating Heterogeneous Features in Saccharomyces cerevisiae

    2. ⭕ Samples：68 positive samples, 68 negative samples.

    ⭕ Data Download

  2. iRNAD: a computational tool for identifying D modification sites in RNA sequence

    3. ⭕ Samples：H. sapiens (29 positive and 68 negative), M. musculus (13 positive and 48 negative), D.melanogaster (9 positive and 38 negative), S.cerevisiae (91 positive and 93 negative), E.coli (34 positive and 127 negative).

    ⭕ Data Download

last update: 2020-6-30

E-mail address:acy196707@163.com