FIELD: bioinformatics.
SUBSTANCE: described is a computer-implemented method of classifying data, comprising: presenting, using a computing device, a convolutional neural network (CNN) data set, where the data set comprises a plurality of candidate polypeptide-MHC-I interactions, and where the CNN is trained based on positive simulated polypeptide-major histocompatibility complex I (MHC-I) data, positive real polypeptide-MHC-I interaction data and negative real polypeptide-MHC-I interaction data; and classifying, by CNN, at least one candidate polypeptide-MHC-I interaction from the plurality of candidate polypeptide-MHC-I interactions as positive or negative. Corresponding device for classifying data is disclosed, as well as a non-volatile machine-readable medium (CRM) for classifying data.
EFFECT: invention extends the range of means for identifying new data.
15 cl, 17 dwg, 2 tbl, 6 ex
| Title | Year | Author | Number |
|---|---|---|---|
| GAN-CNN FOR PREDICTION OF MHC-PEPTIDE BINDING | 2019 |
|
RU2777926C2 |
| METHOD AND SYSTEMS FOR PREDICTION OF HLA CLASS II-SPECIFIC EPITOPES AND CD4+ T-CELL CHARACTERIZATION | 2019 |
|
RU2826261C2 |
| METHOD OF TRANSMITTING MOTION OF A SUBJECT FROM A VIDEO TO AN ANIMATED CHARACTER | 2019 |
|
RU2708027C1 |
| MULTI-FRAME TRAINING OF REALISTIC NEURAL MODELS OF SPEAKERS HEADS | 2019 |
|
RU2720361C1 |
| FAST CALCULATION OF CONVOLUTIONAL NEURAL NETWORK | 2018 |
|
RU2722473C1 |
| SYSTEM AND METHOD FOR SUPPORTING PLANT DISEASE DETECTION | 2020 |
|
RU2815542C2 |
| A DEEP LEARNING FRAME FOR IDENTIFYING SEQUENCE PATTERNS THAT CAUSE SEQUENCE SPECIFIC ERRORS (SSE) | 2019 |
|
RU2745733C1 |
| SPLICING SITES CLASSIFICATION BASED ON DEEP LEARNING | 2018 |
|
RU2780442C2 |
| METHOD AND SYSTEM FOR AUTOMATIC ECG ANALYSIS | 2020 |
|
RU2767157C2 |
| REPEATED SYNTHESIS OF IMAGE USING DIRECT DEFORMATION OF IMAGE, PASS DISCRIMINATOR AND COORDINATE-BASED REMODELLING | 2019 |
|
RU2726160C1 |
