Integrating Biological Networks for Drug Target Prediction and Prioritization
Computational prediction of the clinical success or failure of a potential drug target for therapeutic use is a challenging problem. Novel network propagation algorithms that integrate heterogeneous biological networks are proving useful for drug target identification and prioritization. These approaches typically utilize a network describing relationships between targets, a method to disseminate the relevant information through the network, and a method to elucidate new associations between targets and diseases. Here, we utilize one such network propagation-based approach, DTINet, which starts with diffusion component analysis of networks of both potential drug targets and diseases. Then an inductive matrix completion algorithm is applied to identify novel disease targets based on their network topological similarities with known disease targets with successfully launched drugs. DTINet performed well as assessed with area under the precision-recall curve (AUPR = 0.88 ± 0.007) and area under the receiver operating characteristic curve (AUROC = 0.86 ± 0.008). These metrics improved when we combined data from multiple networks in the target space but reduced significantly when we used a more conservative method to define negative controls (AUPR = 0.56 ± 0.007, AUROC = 0.57 ± 0.007). We are optimistic that integration of more relevant and cleaner datasets and networks, careful calibration of model parameters, as well as algorithmic improvements will improve prediction accuracy. However, we also recognize that predicting drug targets that are likely to be successful is an extremely challenging problem due to its complex nature and sparsity of known disease targets.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2019 |
---|---|
Erschienen: |
2019 |
Enthalten in: |
Zur Gesamtaufnahme - volume:1903 |
---|---|
Enthalten in: |
Methods in molecular biology (Clifton, N.J.) - 1903(2019) vom: 13., Seite 203-218 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Ji, Xiao [VerfasserIn] |
---|
Links: |
---|
Themen: |
Disease prioritization |
---|
Anmerkungen: |
Date Completed 10.06.2019 Date Revised 13.06.2019 published: Print Citation Status MEDLINE |
---|
doi: |
10.1007/978-1-4939-8955-3_12 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM29177394X |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM29177394X | ||
003 | DE-627 | ||
005 | 20231225071618.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231225s2019 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1007/978-1-4939-8955-3_12 |2 doi | |
028 | 5 | 2 | |a pubmed24n0972.xml |
035 | |a (DE-627)NLM29177394X | ||
035 | |a (NLM)30547444 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Ji, Xiao |e verfasserin |4 aut | |
245 | 1 | 0 | |a Integrating Biological Networks for Drug Target Prediction and Prioritization |
264 | 1 | |c 2019 | |
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 10.06.2019 | ||
500 | |a Date Revised 13.06.2019 | ||
500 | |a published: Print | ||
500 | |a Citation Status MEDLINE | ||
520 | |a Computational prediction of the clinical success or failure of a potential drug target for therapeutic use is a challenging problem. Novel network propagation algorithms that integrate heterogeneous biological networks are proving useful for drug target identification and prioritization. These approaches typically utilize a network describing relationships between targets, a method to disseminate the relevant information through the network, and a method to elucidate new associations between targets and diseases. Here, we utilize one such network propagation-based approach, DTINet, which starts with diffusion component analysis of networks of both potential drug targets and diseases. Then an inductive matrix completion algorithm is applied to identify novel disease targets based on their network topological similarities with known disease targets with successfully launched drugs. DTINet performed well as assessed with area under the precision-recall curve (AUPR = 0.88 ± 0.007) and area under the receiver operating characteristic curve (AUROC = 0.86 ± 0.008). These metrics improved when we combined data from multiple networks in the target space but reduced significantly when we used a more conservative method to define negative controls (AUPR = 0.56 ± 0.007, AUROC = 0.57 ± 0.007). We are optimistic that integration of more relevant and cleaner datasets and networks, careful calibration of model parameters, as well as algorithmic improvements will improve prediction accuracy. However, we also recognize that predicting drug targets that are likely to be successful is an extremely challenging problem due to its complex nature and sparsity of known disease targets | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Disease prioritization | |
650 | 4 | |a Drug discovery | |
650 | 4 | |a Drug repositioning | |
650 | 4 | |a Inductive matrix completion | |
650 | 4 | |a Machine learning | |
650 | 4 | |a Network propagation | |
650 | 4 | |a Protein-protein interaction | |
650 | 4 | |a Random walk | |
650 | 4 | |a Target identification | |
700 | 1 | |a Freudenberg, Johannes M |e verfasserin |4 aut | |
700 | 1 | |a Agarwal, Pankaj |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Methods in molecular biology (Clifton, N.J.) |d 1984 |g 1903(2019) vom: 13., Seite 203-218 |w (DE-627)NLM074849794 |x 1940-6029 |7 nnns |
773 | 1 | 8 | |g volume:1903 |g year:2019 |g day:13 |g pages:203-218 |
856 | 4 | 0 | |u http://dx.doi.org/10.1007/978-1-4939-8955-3_12 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 1903 |j 2019 |b 13 |h 203-218 |