Transfer learning for drug-target interaction prediction
Utilizing AI-driven approaches for drug-target interaction (DTI) prediction require large volumes of training data which are not available for the majority of target proteins. In this study, we investigate the use of deep transfer learning for the prediction of interactions between drug candidate co...
Gespeichert in:
| Hauptverfasser: | , , , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
June 2023
|
| In: |
Bioinformatics
Year: 2023, Jahrgang: 39, Pages: i103-i110 |
| ISSN: | 1367-4811 |
| DOI: | 10.1093/bioinformatics/btad234 |
| Online-Zugang: | Verlag, kostenfrei, Volltext: https://doi.org/10.1093/bioinformatics/btad234
|
| Verfasserangaben: | Alperen Dalkıran, Ahmet Atakan, Ahmet S. Rifaioğlu, Maria J. Martin, Rengül Çetin Atalay, Aybar C. Acar, Tunca Doğan, Volkan Atalay |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1858155630 | ||
| 003 | DE-627 | ||
| 005 | 20240329080552.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 230829s2023 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1093/bioinformatics/btad234 |2 doi | |
| 035 | |a (DE-627)1858155630 | ||
| 035 | |a (DE-599)KXP1858155630 | ||
| 035 | |a (OCoLC)1425212431 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Dalkıran, Alperen |e VerfasserIn |0 (DE-588)1300371870 |0 (DE-627)1858159504 |4 aut | |
| 245 | 1 | 0 | |a Transfer learning for drug-target interaction prediction |c Alperen Dalkıran, Ahmet Atakan, Ahmet S. Rifaioğlu, Maria J. Martin, Rengül Çetin Atalay, Aybar C. Acar, Tunca Doğan, Volkan Atalay |
| 264 | 1 | |c June 2023 | |
| 300 | |a 8 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Veröffentlicht: 30. Juni 2023 | ||
| 500 | |a Gesehen am 29.08.2023 | ||
| 520 | |a Utilizing AI-driven approaches for drug-target interaction (DTI) prediction require large volumes of training data which are not available for the majority of target proteins. In this study, we investigate the use of deep transfer learning for the prediction of interactions between drug candidate compounds and understudied target proteins with scarce training data. The idea here is to first train a deep neural network classifier with a generalized source training dataset of large size and then to reuse this pre-trained neural network as an initial configuration for re-training/fine-tuning purposes with a small-sized specialized target training dataset. To explore this idea, we selected six protein families that have critical importance in biomedicine: kinases, G-protein-coupled receptors (GPCRs), ion channels, nuclear receptors, proteases, and transporters. In two independent experiments, the protein families of transporters and nuclear receptors were individually set as the target datasets, while the remaining five families were used as the source datasets. Several size-based target family training datasets were formed in a controlled manner to assess the benefit provided by the transfer learning approach.Here, we present a systematic evaluation of our approach by pre-training a feed-forward neural network with source training datasets and applying different modes of transfer learning from the pre-trained source network to a target dataset. The performance of deep transfer learning is evaluated and compared with that of training the same deep neural network from scratch. We found that when the training dataset contains fewer than 100 compounds, transfer learning outperforms the conventional strategy of training the system from scratch, suggesting that transfer learning is advantageous for predicting binders to under-studied targets.The source code and datasets are available at https://github.com/cansyl/TransferLearning4DTI. Our web-based service containing the ready-to-use pre-trained models is accessible at https://tl4dti.kansil.org. | ||
| 700 | 1 | |a Atakan, Ahmet |e VerfasserIn |4 aut | |
| 700 | 1 | |a Rifaioglu, Ahmet |e VerfasserIn |0 (DE-588)1300369957 |0 (DE-627)1858156408 |4 aut | |
| 700 | 1 | |a Martin, Maria J |e VerfasserIn |4 aut | |
| 700 | 1 | |a Atalay, Rengül Çetin |e VerfasserIn |4 aut | |
| 700 | 1 | |a Acar, Aybar C |e VerfasserIn |4 aut | |
| 700 | 1 | |a Doğan, Tunca |e VerfasserIn |4 aut | |
| 700 | 1 | |a Atalay, Volkan |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Bioinformatics |d Oxford : Oxford Univ. Press, 1998 |g 39(2023), Supplement_1, Seite i103-i110 |h Online-Ressource |w (DE-627)266884857 |w (DE-600)1468345-3 |w (DE-576)079420133 |x 1367-4811 |7 nnas |a Transfer learning for drug-target interaction prediction |
| 773 | 1 | 8 | |g volume:39 |g year:2023 |g supplement:Supplement_1 |g pages:i103-i110 |g extent:8 |a Transfer learning for drug-target interaction prediction |
| 856 | 4 | 0 | |u https://doi.org/10.1093/bioinformatics/btad234 |x Verlag |x Resolving-System |z kostenfrei |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20230829 | ||
| 993 | |a Article | ||
| 994 | |a 2023 | ||
| 998 | |g 1300369957 |a Rifaioğlu, Ahmet |m 1300369957:Rifaioğlu, Ahmet |d 50000 |e 50000PR1300369957 |k 0/50000/ |p 3 | ||
| 999 | |a KXP-PPN1858155630 |e 4370721997 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"language":["eng"],"note":["Veröffentlicht: 30. Juni 2023","Gesehen am 29.08.2023"],"type":{"bibl":"article-journal","media":"Online-Ressource"},"origin":[{"dateIssuedDisp":"June 2023","dateIssuedKey":"2023"}],"title":[{"title":"Transfer learning for drug-target interaction prediction","title_sort":"Transfer learning for drug-target interaction prediction"}],"person":[{"display":"Dalkıran, Alperen","family":"Dalkıran","role":"aut","given":"Alperen"},{"given":"Ahmet","role":"aut","family":"Atakan","display":"Atakan, Ahmet"},{"role":"aut","given":"Ahmet","display":"Rifaioglu, Ahmet","family":"Rifaioglu"},{"role":"aut","given":"Maria J","family":"Martin","display":"Martin, Maria J"},{"given":"Rengül Çetin","role":"aut","display":"Atalay, Rengül Çetin","family":"Atalay"},{"display":"Acar, Aybar C","family":"Acar","role":"aut","given":"Aybar C"},{"family":"Doğan","display":"Doğan, Tunca","given":"Tunca","role":"aut"},{"family":"Atalay","display":"Atalay, Volkan","role":"aut","given":"Volkan"}],"relHost":[{"disp":"Transfer learning for drug-target interaction predictionBioinformatics","language":["eng"],"origin":[{"dateIssuedKey":"1998","publisher":"Oxford Univ. Press","publisherPlace":"Oxford","dateIssuedDisp":"1998-"}],"note":["Gesehen am 26.07.2023","Fortsetzung der Druck-Ausgabe"],"titleAlt":[{"title":"Bioinformatics online"}],"type":{"bibl":"periodical","media":"Online-Ressource"},"title":[{"title":"Bioinformatics","title_sort":"Bioinformatics"}],"part":{"year":"2023","text":"39(2023), Supplement_1, Seite i103-i110","pages":"i103-i110","extent":"8","volume":"39"},"pubHistory":["14.1998 -"],"recId":"266884857","physDesc":[{"extent":"Online-Ressource"}],"id":{"issn":["1367-4811"],"eki":["266884857"],"zdb":["1468345-3"]}}],"id":{"doi":["10.1093/bioinformatics/btad234"],"eki":["1858155630"]},"recId":"1858155630","name":{"displayForm":["Alperen Dalkıran, Ahmet Atakan, Ahmet S. Rifaioğlu, Maria J. Martin, Rengül Çetin Atalay, Aybar C. Acar, Tunca Doğan, Volkan Atalay"]},"physDesc":[{"extent":"8 S."}]} | ||
| SRT | |a DALKIRANALTRANSFERLE2023 | ||