Deep-RBPPred: Predicting RNA binding proteins in the proteome scale based on deep learning
Abstract RNA binding protein (RBP) plays an important role in cell processes. Identifying RBPs by computation and experiment are both essential. Recently, RBPPred is proposed in our group to predict RBP with a high performance. However, RBPPred is too slow for that it will generate PSSM matrix as its feature. Herein, we develop a deep learning model called Deep-RBPPred. The model has three advantages comparing to previous models. 1. Deep-RBPPred only needs few physicochemical properties. 2. Deep-RBPPred runs much faster. 3. Deep-RBPPred has a good generalization ability. In the meantime, the performance is still as good as the stats-of-the-art method. In the testing in A. thaliana, S. cerevisiae and H. sapiens proteomics, MCC (AUC) are 0.6077 (0.9421), 0.573 (0.9034) and 0.8141(0.9515) respectively when the score cutoff is set to 0.5. In the verifying in Gerstberger-1538, the SN of our model is 90.38%. The running times are 9s, 7s, 8s and 10s, respectively, for H.sapiens, A.thaliana, S.cerevisiae and Gerstberger-1538 when it is tested in GPU. Deep-RBPPred forecasts 94.65% of 299 new RBP and about 8% higher sensitivity than RBPPred. We also apply deep-RBPPred in 19 eukaryotes proteomics and 11 bacteria proteomics downloaded from Uniprot. The result shows that rate of RBPs in eukaryotes proteome are much higher than bacteria proteome. Testing in 6 proteomics shows the many RBPs may be still undiscovered so far..
| Medienart: |
|
|---|
Preprint| Erscheinungsjahr: |
2024 |
|---|---|
| Erschienen: |
2024 |
| Enthalten in: |
bioRxiv.org - (2024) vom: 06. Mai Zur Gesamtaufnahme - year:2024 |
|---|
| Sprache: |
Englisch |
|---|
| Beteiligte Personen: |
Zheng, Jinfang [VerfasserIn] |
|---|
| Links: |
|---|
| Themen: |
|---|
| doi: |
10.1101/210153 |
|---|
| funding: |
|
|---|---|
| Förderinstitution / Projekttitel: |
|
| PPN (Katalog-ID): |
XBI000194948 |
|---|
| LEADER | 01000caa a22002652 4500 | ||
|---|---|---|---|
| 001 | XBI000194948 | ||
| 003 | DE-627 | ||
| 005 | 20240507094946.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200312s2024 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1101/210153 |2 doi | |
| 035 | |a (DE-627)XBI000194948 | ||
| 035 | |a (biorXiv)10.1101/210153 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
| 041 | |a eng | ||
| 100 | 1 | |a Zheng, Jinfang |e verfasserin |4 aut | |
| 245 | 1 | 0 | |a Deep-RBPPred: Predicting RNA binding proteins in the proteome scale based on deep learning |
| 264 | 1 | |c 2024 | |
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 520 | |a Abstract RNA binding protein (RBP) plays an important role in cell processes. Identifying RBPs by computation and experiment are both essential. Recently, RBPPred is proposed in our group to predict RBP with a high performance. However, RBPPred is too slow for that it will generate PSSM matrix as its feature. Herein, we develop a deep learning model called Deep-RBPPred. The model has three advantages comparing to previous models. 1. Deep-RBPPred only needs few physicochemical properties. 2. Deep-RBPPred runs much faster. 3. Deep-RBPPred has a good generalization ability. In the meantime, the performance is still as good as the stats-of-the-art method. In the testing in A. thaliana, S. cerevisiae and H. sapiens proteomics, MCC (AUC) are 0.6077 (0.9421), 0.573 (0.9034) and 0.8141(0.9515) respectively when the score cutoff is set to 0.5. In the verifying in Gerstberger-1538, the SN of our model is 90.38%. The running times are 9s, 7s, 8s and 10s, respectively, for H.sapiens, A.thaliana, S.cerevisiae and Gerstberger-1538 when it is tested in GPU. Deep-RBPPred forecasts 94.65% of 299 new RBP and about 8% higher sensitivity than RBPPred. We also apply deep-RBPPred in 19 eukaryotes proteomics and 11 bacteria proteomics downloaded from Uniprot. The result shows that rate of RBPs in eukaryotes proteome are much higher than bacteria proteome. Testing in 6 proteomics shows the many RBPs may be still undiscovered so far. | ||
| 650 | 4 | |a Biology |7 (dpeaa)DE-84 | |
| 650 | 4 | |a 570 |7 (dpeaa)DE-84 | |
| 700 | 1 | |a Zhang, Xiaoli |e verfasserin |4 aut | |
| 700 | 1 | |a Zhao, Xunyi |e verfasserin |4 aut | |
| 700 | 1 | |a Tong, Xiaoxue |e verfasserin |4 aut | |
| 700 | 1 | |a Hong, Xu |e verfasserin |4 aut | |
| 700 | 1 | |a Xie, Juan |e verfasserin |4 aut | |
| 700 | 1 | |a Liu, Shiyong |e verfasserin |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t bioRxiv.org |g (2024) vom: 06. Mai |
| 773 | 1 | 8 | |g year:2024 |g day:06 |g month:05 |
| 856 | 4 | 0 | |u https://doi.org/10.1038/s41598-018-33654-x |x 0 |z lizenzpflichtig |3 Volltext |
| 856 | 4 | 0 | |u http://dx.doi.org/10.1101/210153 |x 0 |z kostenfrei |3 Volltext |
| 912 | |a GBV_XBI | ||
| 951 | |a AR | ||
| 952 | |j 2024 |b 06 |c 05 | ||