Back

Protocol for clustering of non-unified protein sequences through memory-map guided deep learning

Prakash, O.

2020-08-15 bioinformatics
10.1101/2020.08.15.252114 bioRxiv
Show abstract

Protocol established and validated for clustering of non-unified protein sequences through memorymap guided deep learning. Data evaluated belongs to the disease causing proteins/genes from human hormonal system. Possibilities for future experiments validation was found for genes as: ACTHR, AGMX1, ATK, BPK, DPDE3, ERBA2, FSHB, GH1, GHSR, GNAS1, GSP, HANF, LCGR, LGR2, LGR3, LHRHR, NR1A2, PKR1, PRKAR1, RNF216, SBP2, SECISBP2, THR1, THRB, TPIT, TRIAD3, TSE1, UBCE7IP1, XAP2, and ZIN. Protocol is recommended for implementation with small to large dataset (protein/ DNA/ RNA sequences of unified or non-unified length) with unclassified data flags.

Matching journals

The top 10 journals account for 50% of the predicted probability mass.

50% of probability mass above

"Similar papers" are the closest papers from that journal in the model's embedding space. They show what the match is built on, but the ranking comes mostly from a classifier over the whole training set, not from these examples alone.