CCL-DTI : contributing the contrastive loss in drug-target interaction prediction
© 2024. The Author(s)..
BACKGROUND: The Drug-Target Interaction (DTI) prediction uses a drug molecule and a protein sequence as inputs to predict the binding affinity value. In recent years, deep learning-based models have gotten more attention. These methods have two modules: the feature extraction module and the task prediction module. In most deep learning-based approaches, a simple task prediction loss (i.e., categorical cross entropy for the classification task and mean squared error for the regression task) is used to learn the model. In machine learning, contrastive-based loss functions are developed to learn more discriminative feature space. In a deep learning-based model, extracting more discriminative feature space leads to performance improvement for the task prediction module.
RESULTS: In this paper, we have used multimodal knowledge as input and proposed an attention-based fusion technique to combine this knowledge. Also, we investigate how utilizing contrastive loss function along the task prediction loss could help the approach to learn a more powerful model. Four contrastive loss functions are considered: (1) max-margin contrastive loss function, (2) triplet loss function, (3) Multi-class N-pair Loss Objective, and (4) NT-Xent loss function. The proposed model is evaluated using four well-known datasets: Wang et al. dataset, Luo's dataset, Davis, and KIBA datasets.
CONCLUSIONS: Accordingly, after reviewing the state-of-the-art methods, we developed a multimodal feature extraction network by combining protein sequences and drug molecules, along with protein-protein interaction networks and drug-drug interaction networks. The results show it performs significantly better than the comparable state-of-the-art approaches.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:25 |
---|---|
Enthalten in: |
BMC bioinformatics - 25(2024), 1 vom: 30. Jan., Seite 48 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Dehghan, Alireza [VerfasserIn] |
---|
Links: |
---|
Themen: |
Contrastive loss function |
---|
Anmerkungen: |
Date Completed 01.02.2024 Date Revised 01.02.2024 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1186/s12859-024-05671-3 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM367816814 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM367816814 | ||
003 | DE-627 | ||
005 | 20240201232243.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240131s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1186/s12859-024-05671-3 |2 doi | |
028 | 5 | 2 | |a pubmed24n1277.xml |
035 | |a (DE-627)NLM367816814 | ||
035 | |a (NLM)38291364 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Dehghan, Alireza |e verfasserin |4 aut | |
245 | 1 | 0 | |a CCL-DTI |b contributing the contrastive loss in drug-target interaction prediction |
264 | 1 | |c 2024 | |
336 | |a Text |b txt |2 rdacontent | ||
337 | |a ƒaComputermedien |b c |2 rdamedia | ||
338 | |a ƒa Online-Ressource |b cr |2 rdacarrier | ||
500 | |a Date Completed 01.02.2024 | ||
500 | |a Date Revised 01.02.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024. The Author(s). | ||
520 | |a BACKGROUND: The Drug-Target Interaction (DTI) prediction uses a drug molecule and a protein sequence as inputs to predict the binding affinity value. In recent years, deep learning-based models have gotten more attention. These methods have two modules: the feature extraction module and the task prediction module. In most deep learning-based approaches, a simple task prediction loss (i.e., categorical cross entropy for the classification task and mean squared error for the regression task) is used to learn the model. In machine learning, contrastive-based loss functions are developed to learn more discriminative feature space. In a deep learning-based model, extracting more discriminative feature space leads to performance improvement for the task prediction module | ||
520 | |a RESULTS: In this paper, we have used multimodal knowledge as input and proposed an attention-based fusion technique to combine this knowledge. Also, we investigate how utilizing contrastive loss function along the task prediction loss could help the approach to learn a more powerful model. Four contrastive loss functions are considered: (1) max-margin contrastive loss function, (2) triplet loss function, (3) Multi-class N-pair Loss Objective, and (4) NT-Xent loss function. The proposed model is evaluated using four well-known datasets: Wang et al. dataset, Luo's dataset, Davis, and KIBA datasets | ||
520 | |a CONCLUSIONS: Accordingly, after reviewing the state-of-the-art methods, we developed a multimodal feature extraction network by combining protein sequences and drug molecules, along with protein-protein interaction networks and drug-drug interaction networks. The results show it performs significantly better than the comparable state-of-the-art approaches | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Contrastive loss function | |
650 | 4 | |a Drug discovery | |
650 | 4 | |a Drug–target interaction | |
650 | 4 | |a Multimodal deep learning | |
700 | 1 | |a Abbasi, Karim |e verfasserin |4 aut | |
700 | 1 | |a Razzaghi, Parvin |e verfasserin |4 aut | |
700 | 1 | |a Banadkuki, Hossein |e verfasserin |4 aut | |
700 | 1 | |a Gharaghani, Sajjad |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t BMC bioinformatics |d 2000 |g 25(2024), 1 vom: 30. Jan., Seite 48 |w (DE-627)NLM109215982 |x 1471-2105 |7 nnns |
773 | 1 | 8 | |g volume:25 |g year:2024 |g number:1 |g day:30 |g month:01 |g pages:48 |
856 | 4 | 0 | |u http://dx.doi.org/10.1186/s12859-024-05671-3 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 25 |j 2024 |e 1 |b 30 |c 01 |h 48 |