GeneAI 3.0 : powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides
© 2024. The Author(s)..
Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint's GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences.
Medienart: |
E-Artikel |
---|
Erscheinungsjahr: |
2024 |
---|---|
Erschienen: |
2024 |
Enthalten in: |
Zur Gesamtaufnahme - volume:14 |
---|---|
Enthalten in: |
Scientific reports - 14(2024), 1 vom: 26. März, Seite 7154 |
Sprache: |
Englisch |
---|
Beteiligte Personen: |
Singh, Jaskaran [VerfasserIn] |
---|
Links: |
---|
Themen: |
Composite feature extraction |
---|
Anmerkungen: |
Date Completed 28.03.2024 Date Revised 28.03.2024 published: Electronic Citation Status MEDLINE |
---|
doi: |
10.1038/s41598-024-56786-9 |
---|
funding: |
|
---|---|
Förderinstitution / Projekttitel: |
|
PPN (Katalog-ID): |
NLM370214765 |
---|
LEADER | 01000caa a22002652 4500 | ||
---|---|---|---|
001 | NLM370214765 | ||
003 | DE-627 | ||
005 | 20240329001109.0 | ||
007 | cr uuu---uuuuu | ||
008 | 240328s2024 xx |||||o 00| ||eng c | ||
024 | 7 | |a 10.1038/s41598-024-56786-9 |2 doi | |
028 | 5 | 2 | |a pubmed24n1353.xml |
035 | |a (DE-627)NLM370214765 | ||
035 | |a (NLM)38531923 | ||
040 | |a DE-627 |b ger |c DE-627 |e rakwb | ||
041 | |a eng | ||
100 | 1 | |a Singh, Jaskaran |e verfasserin |4 aut | |
245 | 1 | 0 | |a GeneAI 3.0 |b powerful, novel, generalized hybrid and ensemble deep learning frameworks for miRNA species classification of stationary patterns from nucleotides |
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 28.03.2024 | ||
500 | |a Date Revised 28.03.2024 | ||
500 | |a published: Electronic | ||
500 | |a Citation Status MEDLINE | ||
520 | |a © 2024. The Author(s). | ||
520 | |a Due to the intricate relationship between the small non-coding ribonucleic acid (miRNA) sequences, the classification of miRNA species, namely Human, Gorilla, Rat, and Mouse is challenging. Previous methods are not robust and accurate. In this study, we present AtheroPoint's GeneAI 3.0, a powerful, novel, and generalized method for extracting features from the fixed patterns of purines and pyrimidines in each miRNA sequence in ensemble paradigms in machine learning (EML) and convolutional neural network (CNN)-based deep learning (EDL) frameworks. GeneAI 3.0 utilized five conventional (Entropy, Dissimilarity, Energy, Homogeneity, and Contrast), and three contemporary (Shannon entropy, Hurst exponent, Fractal dimension) features, to generate a composite feature set from given miRNA sequences which were then passed into our ML and DL classification framework. A set of 11 new classifiers was designed consisting of 5 EML and 6 EDL for binary/multiclass classification. It was benchmarked against 9 solo ML (SML), 6 solo DL (SDL), 12 hybrid DL (HDL) models, resulting in a total of 11 + 27 = 38 models were designed. Four hypotheses were formulated and validated using explainable AI (XAI) as well as reliability/statistical tests. The order of the mean performance using accuracy (ACC)/area-under-the-curve (AUC) of the 24 DL classifiers was: EDL > HDL > SDL. The mean performance of EDL models with CNN layers was superior to that without CNN layers by 0.73%/0.92%. Mean performance of EML models was superior to SML models with improvements of ACC/AUC by 6.24%/6.46%. EDL models performed significantly better than EML models, with a mean increase in ACC/AUC of 7.09%/6.96%. The GeneAI 3.0 tool produced expected XAI feature plots, and the statistical tests showed significant p-values. Ensemble models with composite features are highly effective and generalized models for effectively classifying miRNA sequences | ||
650 | 4 | |a Journal Article | |
650 | 4 | |a Composite feature extraction | |
650 | 4 | |a Ensemble deep learning | |
650 | 4 | |a Ensemble machine learning | |
650 | 4 | |a Statistical tests | |
650 | 4 | |a Validation | |
650 | 4 | |a miRNA classification | |
650 | 7 | |a MicroRNAs |2 NLM | |
650 | 7 | |a Nucleotides |2 NLM | |
700 | 1 | |a Khanna, Narendra N |e verfasserin |4 aut | |
700 | 1 | |a Rout, Ranjeet K |e verfasserin |4 aut | |
700 | 1 | |a Singh, Narpinder |e verfasserin |4 aut | |
700 | 1 | |a Laird, John R |e verfasserin |4 aut | |
700 | 1 | |a Singh, Inder M |e verfasserin |4 aut | |
700 | 1 | |a Kalra, Mannudeep K |e verfasserin |4 aut | |
700 | 1 | |a Mantella, Laura E |e verfasserin |4 aut | |
700 | 1 | |a Johri, Amer M |e verfasserin |4 aut | |
700 | 1 | |a Isenovic, Esma R |e verfasserin |4 aut | |
700 | 1 | |a Fouda, Mostafa M |e verfasserin |4 aut | |
700 | 1 | |a Saba, Luca |e verfasserin |4 aut | |
700 | 1 | |a Fatemi, Mostafa |e verfasserin |4 aut | |
700 | 1 | |a Suri, Jasjit S |e verfasserin |4 aut | |
773 | 0 | 8 | |i Enthalten in |t Scientific reports |d 2011 |g 14(2024), 1 vom: 26. März, Seite 7154 |w (DE-627)NLM215703936 |x 2045-2322 |7 nnns |
773 | 1 | 8 | |g volume:14 |g year:2024 |g number:1 |g day:26 |g month:03 |g pages:7154 |
856 | 4 | 0 | |u http://dx.doi.org/10.1038/s41598-024-56786-9 |3 Volltext |
912 | |a GBV_USEFLAG_A | ||
912 | |a GBV_NLM | ||
951 | |a AR | ||
952 | |d 14 |j 2024 |e 1 |b 26 |c 03 |h 7154 |