Design of New Dispersants Using Machine Learning and Visual Analytics
Artificial intelligence (AI) is an emerging technology that is revolutionizing the discovery of new materials. One key application of AI is virtual screening of chemical libraries, which enables the accelerated discovery of materials with desired properties. In this study, we developed computational models to predict the dispersancy efficiency of oil and lubricant additives, a critical property in their design that can be estimated through a quantity named blotter spot. We propose a comprehensive approach that combines machine learning techniques with visual analytics strategies in an interactive tool that supports domain experts' decision-making. We evaluated the proposed models quantitatively and illustrated their benefits through a case study. Specifically, we analyzed a series of virtual polyisobutylene succinimide (PIBSI) molecules derived from a known reference substrate. Our best-performing probabilistic model was Bayesian Additive Regression Trees (BART), which achieved a mean absolute error of 5.50±0.34 and a root mean square error of 7.56±0.47, as estimated through 5-fold cross-validation. To facilitate future research, we have made the dataset, including the potential dispersants used for modeling, publicly available. Our approach can help accelerate the discovery of new oil and lubricant additives, and our interactive tool can aid domain experts in making informed decisions based on blotter spot and other key properties.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2023 |
---|---|
Erschienen: |
2023 |
Enthalten in: |
Zur Gesamtaufnahme - volume:15 |
---|---|
Enthalten in: |
Polymers - 15(2023), 5 vom: 06. März |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Martínez, María Jimena [VerfasserIn] |
---|
Links: |
---|
Themen: |
Artificial intelligence |
---|
Anmerkungen: |
Date Revised 14.03.2023 published: Electronic Citation Status PubMed-not-MEDLINE |
---|
doi: |
10.3390/polym15051324 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM354102028 |
---|
LEADER | 01000naa a22002652 4500 | ||
---|---|---|---|
001 | NLM354102028 | ||
003 | DE-627 | ||
005 | 20231226061509.0 | ||
007 | cr uuu---uuuuu | ||
008 | 231226s2023 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.3390/polym15051324 |2 doi | |
028 | 5 | 2 | |a pubmed24n1180.xml |
035 | |a (DE-627)NLM354102028 | ||
035 | |a (NLM)36904566 | ||
035 | |a (PII)1324 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Martínez, María Jimena |e verfasserin |4 aut | |
245 | 1 | 0 | |a Design of New Dispersants Using Machine Learning and Visual Analytics |
264 | 1 | |c 2023 | |
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 Revised 14.03.2023 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status PubMed-not-MEDLINE | ||
520 | |a Artificial intelligence (AI) is an emerging technology that is revolutionizing the discovery of new materials. One key application of AI is virtual screening of chemical libraries, which enables the accelerated discovery of materials with desired properties. In this study, we developed computational models to predict the dispersancy efficiency of oil and lubricant additives, a critical property in their design that can be estimated through a quantity named blotter spot. We propose a comprehensive approach that combines machine learning techniques with visual analytics strategies in an interactive tool that supports domain experts' decision-making. We evaluated the proposed models quantitatively and illustrated their benefits through a case study. Specifically, we analyzed a series of virtual polyisobutylene succinimide (PIBSI) molecules derived from a known reference substrate. Our best-performing probabilistic model was Bayesian Additive Regression Trees (BART), which achieved a mean absolute error of 5.50±0.34 and a root mean square error of 7.56±0.47, as estimated through 5-fold cross-validation. To facilitate future research, we have made the dataset, including the potential dispersants used for modeling, publicly available. Our approach can help accelerate the discovery of new oil and lubricant additives, and our interactive tool can aid domain experts in making informed decisions based on blotter spot and other key properties | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Bayesian regression | |
650 | 4 | |a artificial intelligence | |
650 | 4 | |a blotter spot | |
650 | 4 | |a polyisobutylene | |
700 | 1 | |a Naveiro, Roi |e verfasserin |4 aut | |
700 | 1 | |a Soto, Axel J |e verfasserin |4 aut | |
700 | 1 | |a Talavante, Pablo |e verfasserin |4 aut | |
700 | 1 | |a Kim Lee, Shin-Ho |e verfasserin |4 aut | |
700 | 1 | |a Gómez Arrayas, Ramón |e verfasserin |4 aut | |
700 | 1 | |a Franco, Mario |e verfasserin |4 aut | |
700 | 1 | |a Mauleón, Pablo |e verfasserin |4 aut | |
700 | 1 | |a Lozano Ordóñez, Héctor |e verfasserin |4 aut | |
700 | 1 | |a Revilla López, Guillermo |e verfasserin |4 aut | |
700 | 1 | |a Bernabei, Marco |e verfasserin |4 aut | |
700 | 1 | |a Campillo, Nuria E |e verfasserin |4 aut | |
700 | 1 | |a Ponzoni, Ignacio |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Polymers |d 2010 |g 15(2023), 5 vom: 06. März |w (DE-627)NLM205507980 |x 2073-4360 |7 nnns |
773 | 1 | 8 | |g volume:15 |g year:2023 |g number:5 |g day:06 |g month:03 |
856 | 4 | 0 | |u http://dx.doi.org/10.3390/polym15051324 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 15 |j 2023 |e 5 |b 06 |c 03 |