國立虎尾科技大學 |

More is Better than One : = The Effect of Ensembling on Deep Learning Performance in Biochemical Prediction Problems.

紀錄類型:	書目-語言資料,手稿 : Monograph/item
正題名/作者:	More is Better than One :/
其他題名:	The Effect of Ensembling on Deep Learning Performance in Biochemical Prediction Problems.
作者:	Stern, Jacob A.
面頁冊數:	1 online resource (44 pages)
附註:	Source: Masters Abstracts International, Volume: 85-06.
Contained By:	Masters Abstracts International85-06.
標題:	Public health. -
電子資源:	click for full text (PQDT)
ISBN:	9798381018462

More is Better than One : = The Effect of Ensembling on Deep Learning Performance in Biochemical Prediction Problems.
Stern, Jacob A.

More is Better than One :The Effect of Ensembling on Deep Learning Performance in Biochemical Prediction Problems. - 1 online resource (44 pages)

Source: Masters Abstracts International, Volume: 85-06.

Thesis (M.Sc.)--Brigham Young University, 2023.

Includes bibliographical references

This thesis presents two papers addressing important biochemical prediction challenges. The first paper focuses on accurate protein distance predictions and introduces updates to the ProSPr network. We evaluate its performance in the Critical Assessment of techniques for Protein Structure Prediction (CASP14) competition, investigating its accuracy dependence on sequence length and multiple sequence alignment depth. The ProSPr network, an ensemble of three convolutional neural networks (CNNs), demonstrates superior performance compared to individual networks. The second paper addresses the issue of accurate ligand ranking in virtual screening for drug discovery. We propose MILCDock, a machine learning consensus docking tool that leverages predictions from five traditional molecular docking tools. MILCDock, an ensemble of eight neural networks, outperforms single-network approaches and other consensus docking methods on the DUD-E dataset. However, we find that LIT-PCBA targets remain challenging for all methods tested. Furthermore, we explore the effectiveness of training machine learning tools on the biased DUD-E dataset, emphasizing the importance of mitigating its biases during training. Collectively, this work emphasizes the power of ensembling in deep learning-based biochemical prediction problems, highlighting improved performance through the combination of multiple models. Our findings contribute to the development of robust protein distance prediction tools and more accurate virtual screening methods for drug discovery.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2024

Mode of access: World Wide Web

ISBN: 9798381018462Subjects--Topical Terms:

560998
Public health.
Index Terms--Genre/Form:

554714
Electronic books.

More is Better than One : = The Effect of Ensembling on Deep Learning Performance in Biochemical Prediction Problems.
LDR:02888ntm a22003617 4500 001 1143024
005 20240513061047.5
006 m o d
007 cr mn ---uuuuu
008 250605s2023 xx obm 000 0 eng d
020 $a 9798381018462
035 $a (MiAaPQ)AAI30725947
035 $a (MiAaPQ)BrighamYoung11132
035 $a AAI30725947
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Stern, Jacob A. $3 1467587
245 1 0 $a More is Better than One : $b The Effect of Ensembling on Deep Learning Performance in Biochemical Prediction Problems.
264 0 $c 2023
300 $a 1 online resource (44 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 85-06.
500 $a Advisor: Wingate, David;Corte, Dennis Della;Moody, James D.;Fulda, Nancy.
502 $a Thesis (M.Sc.)--Brigham Young University, 2023.
504 $a Includes bibliographical references
520 $a This thesis presents two papers addressing important biochemical prediction challenges. The first paper focuses on accurate protein distance predictions and introduces updates to the ProSPr network. We evaluate its performance in the Critical Assessment of techniques for Protein Structure Prediction (CASP14) competition, investigating its accuracy dependence on sequence length and multiple sequence alignment depth. The ProSPr network, an ensemble of three convolutional neural networks (CNNs), demonstrates superior performance compared to individual networks. The second paper addresses the issue of accurate ligand ranking in virtual screening for drug discovery. We propose MILCDock, a machine learning consensus docking tool that leverages predictions from five traditional molecular docking tools. MILCDock, an ensemble of eight neural networks, outperforms single-network approaches and other consensus docking methods on the DUD-E dataset. However, we find that LIT-PCBA targets remain challenging for all methods tested. Furthermore, we explore the effectiveness of training machine learning tools on the biased DUD-E dataset, emphasizing the importance of mitigating its biases during training. Collectively, this work emphasizes the power of ensembling in deep learning-based biochemical prediction problems, highlighting improved performance through the combination of multiple models. Our findings contribute to the development of robust protein distance prediction tools and more accurate virtual screening methods for drug discovery.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2024
538 $a Mode of access: World Wide Web
650 4 $a Public health. $3 560998
650 4 $a Medicine. $3 644133
650 4 $a Enzymes. $3 557408
650 4 $a Annotations. $3 1465627
650 4 $a Correlation analysis. $3 1214700
650 4 $a Amino acids. $3 1066910
650 4 $a Neural networks. $3 1011215
650 4 $a Biochemistry. $3 582831
650 4 $a Deep learning. $3 1127428
650 4 $a Diabetes. $3 582755
655 7 $a Electronic books. $2 local $3 554714
690 $a 0487
690 $a 0800
690 $a 0564
690 $a 0573
710 2 $a Brigham Young University. $3 1187870
710 2 $a ProQuest Information and Learning Co. $3 1178819
773 0 $t Masters Abstracts International $g 85-06.
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=30725947 $z click for full text (PQDT)