Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders
In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: co...
Gespeichert in:
| Hauptverfasser: | , , , , , |
|---|---|
| Dokumenttyp: | Article (Journal) |
| Sprache: | Englisch |
| Veröffentlicht: |
October 16, 2019
|
| In: |
Molecular pharmaceutics
Year: 2019, Jahrgang: 16, Heft: 12, Pages: 4797-4806 |
| ISSN: | 1543-8392 |
| DOI: | 10.1021/acs.molpharmaceut.9b00520 |
| Online-Zugang: | Verlag, Volltext: https://doi.org/10.1021/acs.molpharmaceut.9b00520 Verlag, Volltext: https://pubs.acs.org/doi/10.1021/acs.molpharmaceut.9b00520# 
|
| Verfasserangaben: | Matteo Manica, Ali Oskooei, Jannis Born, Vigneshwari Subramanian, Julio Sáez-Rodríguez, and María Rodríguez Martínez |
MARC
| LEADER | 00000caa a2200000 c 4500 | ||
|---|---|---|---|
| 001 | 1687790361 | ||
| 003 | DE-627 | ||
| 005 | 20230427215308.0 | ||
| 007 | cr uuu---uuuuu | ||
| 008 | 200117s2019 xx |||||o 00| ||eng c | ||
| 024 | 7 | |a 10.1021/acs.molpharmaceut.9b00520 |2 doi | |
| 035 | |a (DE-627)1687790361 | ||
| 035 | |a (DE-599)KXP1687790361 | ||
| 035 | |a (OCoLC)1341298315 | ||
| 040 | |a DE-627 |b ger |c DE-627 |e rda | ||
| 041 | |a eng | ||
| 084 | |a 33 |2 sdnb | ||
| 100 | 1 | |a Manica, Matteo |d 1988- |e VerfasserIn |0 (DE-588)1177836726 |0 (DE-627)104894624X |0 (DE-576)517583828 |4 aut | |
| 245 | 1 | 0 | |a Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders |c Matteo Manica, Ali Oskooei, Jannis Born, Vigneshwari Subramanian, Julio Sáez-Rodríguez, and María Rodríguez Martínez |
| 264 | 1 | |c October 16, 2019 | |
| 300 | |a 10 | ||
| 336 | |a Text |b txt |2 rdacontent | ||
| 337 | |a Computermedien |b c |2 rdamedia | ||
| 338 | |a Online-Ressource |b cr |2 rdacarrier | ||
| 500 | |a Gesehen am 17.01.2020 | ||
| 520 | |a In line with recent advances in neural drug design and sensitivity prediction, we propose a novel architecture for interpretable prediction of anticancer compound sensitivity using a multimodal attention-based convolutional encoder. Our model is based on the three key pillars of drug sensitivity: compounds’ structure in the form of a SMILES sequence, gene expression profiles of tumors, and prior knowledge on intracellular interactions from protein-protein interaction networks. We demonstrate that our multiscale convolutional attention-based encoder significantly outperforms a baseline model trained on Morgan fingerprints and a selection of encoders based on SMILES, as well as the previously reported state-of-the-art for multimodal drug sensitivity prediction (R2 = 0.86 and RMSE = 0.89). Moreover, the explainability of our approach is demonstrated by a thorough analysis of the attention weights. We show that the attended genes significantly enrich apoptotic processes and that the drug attention is strongly correlated with a standard chemical structure similarity index. Finally, we report a case study of two receptor tyrosine kinase (RTK) inhibitors acting on a leukemia cell line, showcasing the ability of the model to focus on informative genes and submolecular regions of the two compounds. The demonstrated generalizability and the interpretability of our model testify to its potential for in silico prediction of anticancer compound efficacy on unseen cancer cells, positioning it as a valid solution for the development of personalized therapies as well as for the evaluation of candidate compounds in de novo drug design. | ||
| 700 | 1 | |a Oskooei, Ali |e VerfasserIn |4 aut | |
| 700 | 1 | |a Born, Jannis |e VerfasserIn |4 aut | |
| 700 | 1 | |a Subramanian, Vigneshwari |e VerfasserIn |4 aut | |
| 700 | 1 | |a Sáez Rodríguez, Julio |d 1978- |e VerfasserIn |0 (DE-588)133764362 |0 (DE-627)555766632 |0 (DE-576)300083114 |4 aut | |
| 700 | 1 | |a Rodríguez Martínez, María |e VerfasserIn |4 aut | |
| 773 | 0 | 8 | |i Enthalten in |t Molecular pharmaceutics |d Washington, DC : American Chemical Society, 2004 |g 16(2019), 12, Seite 4797-4806 |h Online-Ressource |w (DE-627)377310573 |w (DE-600)2132489-X |w (DE-576)109403797 |x 1543-8392 |7 nnas |a Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders |
| 773 | 1 | 8 | |g volume:16 |g year:2019 |g number:12 |g pages:4797-4806 |g extent:10 |a Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders |
| 856 | 4 | 0 | |u https://doi.org/10.1021/acs.molpharmaceut.9b00520 |x Verlag |x Resolving-System |3 Volltext |
| 856 | 4 | 0 | |u https://pubs.acs.org/doi/10.1021/acs.molpharmaceut.9b00520# |x Verlag |3 Volltext |
| 951 | |a AR | ||
| 992 | |a 20200117 | ||
| 993 | |a Article | ||
| 994 | |a 2019 | ||
| 998 | |g 133764362 |a Sáez Rodríguez, Julio |m 133764362:Sáez Rodríguez, Julio |d 910000 |d 912900 |d 700000 |d 716000 |e 910000PS133764362 |e 912900PS133764362 |e 700000PS133764362 |e 716000PS133764362 |k 0/910000/ |k 1/910000/912900/ |k 0/700000/ |k 1/700000/716000/ |p 5 | ||
| 999 | |a KXP-PPN1687790361 |e 3576260870 | ||
| BIB | |a Y | ||
| SER | |a journal | ||
| JSO | |a {"origin":[{"dateIssuedDisp":"October 16, 2019","dateIssuedKey":"2019"}],"person":[{"given":"Matteo","display":"Manica, Matteo","role":"aut","family":"Manica"},{"role":"aut","display":"Oskooei, Ali","family":"Oskooei","given":"Ali"},{"family":"Born","display":"Born, Jannis","role":"aut","given":"Jannis"},{"given":"Vigneshwari","family":"Subramanian","role":"aut","display":"Subramanian, Vigneshwari"},{"given":"Julio","display":"Sáez Rodríguez, Julio","role":"aut","family":"Sáez Rodríguez"},{"given":"María","family":"Rodríguez Martínez","role":"aut","display":"Rodríguez Martínez, María"}],"title":[{"title_sort":"Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders","title":"Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encoders"}],"recId":"1687790361","language":["eng"],"physDesc":[{"extent":"10 S."}],"name":{"displayForm":["Matteo Manica, Ali Oskooei, Jannis Born, Vigneshwari Subramanian, Julio Sáez-Rodríguez, and María Rodríguez Martínez"]},"id":{"doi":["10.1021/acs.molpharmaceut.9b00520"],"eki":["1687790361"]},"type":{"bibl":"article-journal","media":"Online-Ressource"},"note":["Gesehen am 17.01.2020"],"relHost":[{"id":{"eki":["377310573"],"zdb":["2132489-X"],"issn":["1543-8392"]},"name":{"displayForm":["American Chemical Society"]},"disp":"Toward explainable anticancer compound sensitivity prediction via multimodal attention-based convolutional encodersMolecular pharmaceutics","part":{"extent":"10","year":"2019","text":"16(2019), 12, Seite 4797-4806","pages":"4797-4806","volume":"16","issue":"12"},"language":["eng"],"physDesc":[{"extent":"Online-Ressource"}],"recId":"377310573","title":[{"title":"Molecular pharmaceutics","title_sort":"Molecular pharmaceutics"}],"origin":[{"publisher":"American Chemical Society","dateIssuedKey":"2004","dateIssuedDisp":"2004-","publisherPlace":"Washington, DC"}],"note":["Gesehen am 22.03.23"],"type":{"bibl":"periodical","media":"Online-Ressource"},"pubHistory":["1.2004 -"]}]} | ||
| SRT | |a MANICAMATTTOWARDEXPL1620 | ||