Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 1

Investigation on low-performance tuned-regressor of inhibitory concentration targeting the SARS-CoV-2 polyprotein 1ab

IAES International Journal of Artificial Intelligence · Vol. 14 No. 4 (2025) · hlm. 3003–3013

DOI
10.11591/ijai.v14.i4.pp3003-3013
ISSN
2252-8938, 2089-4872
Terbit
2025-08-01
Penerbit
Institute of Advanced Engineering and Science
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

Hyperparameter tuning is a key optimization strategy in machine learning (ML), often used with GridSearchCV to find optimal hyperparameter combinations. This study aimed to predict the half-maximal inhibitory concentration (IC50) of small molecules targeting the SARS-CoV-2 replicase polyprotein 1ab (pp1ab) by optimizing three ML algorithms: histogram gradient boosting regressor (HGBR), light gradient boosting regressor (LGBR), and random forest regressor (RFR). Bioactivity data, including duplicates, were processed using three approaches: untreated, aggregation of quantitative bioactivity, and duplicate removal. Molecular features were encoded using twelve types of molecular fingerprints. To optimize the models, hyperparameter tuning with GridSearchCV was applied across a broad parameter space. The results showed that the performance of the models was inconsistent, despite comprehensive hyperparameter tuning. Further analysis showed that the distribution of Murcko fragments was uneven between the training and testing datasets. Key fragments were underrepresented in the testing phase, leading to a mismatch in model predictions. The study demonstrates that hyperparameter tuning alone may not be sufficient to achieve high predictive performance when the distribution of molecular fragments is unbalanced between training and testing datasets. Ensuring fragment diversity across datasets is crucial for improving model reliability in drug discovery applications.

Kata kunci

Jaringan kolaborasi para penulis

29 penulis · 86 tautan kepenulisan bersama · 20 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Sam Ratulangi University
  • Indonesia University of Education
  • Bandung Institute of Technology
  • BGC Trust University Bangladesh
  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Beivy Jonathan KolondamSam Ratulangi University3
Fabian Johanes ManoppoSam Ratulangi University2
Diah KusumawatyIndonesia University of Education2
Juliet Merry Eva MamahitSam Ratulangi University2
Muhdad BachmidSam Ratulangi University1
Bambang SupriatnoIndonesia University of Education1
Talha Bin EmranBGC Trust University Bangladesh1
Tri SuwandiIndonesia University of Education1
Aurellyallodia Faiza KusumaAfiliasi tidak diketahui1
Muhammad Farhan ShadiqAfiliasi tidak diketahui1
RizarullahAfiliasi tidak diketahui1
Reza AditamaBandung Institute of Technology1
Fifi Fitriyah MasdukiAfiliasi tidak diketahui1
Didik PriyandokoIndonesia University of Education1
Azzania FibrianiBandung Institute of Technology1
Nurul FaridahIndonesia University of Education1
Hanina DzikrinaIndonesia University of Education1
Diah Rochana PuspitasariIndonesia University of Education1
Any AryaniIndonesia University of Education1
Endrile Golmen BalansaSam Ratulangi University1
Christina Leta SalakiSam Ratulangi University1
Dantje TaroreSam Ratulangi University1
Roni KoneriSam Ratulangi University1
Agustinus JacobusSam Ratulangi University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) http://ijai.iaescore.com/index.php/IJAI/oai, pertama di-harvest 8 Nov 2026, terakhir terlihat 16 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en-US">Investigation on low-performance tuned-regressor of inhibitory concentration targeting the SARS-CoV-2 polyprotein 1ab</dc:title>
	<dc:creator>Sengkey, Daniel Febrian</dc:creator>
	<dc:creator>Regina Masengi, Angelina Stevany</dc:creator>
	<dc:creator>Sambul, Alwin Melkie</dc:creator>
	<dc:creator>Tallei, Trina Ekawati</dc:creator>
	<dc:creator>Unsratdianto Sompie, Sherwin Reinaldo</dc:creator>
	<dc:subject xml:lang="en-US">Machine Learning; Bioinformatics; Drug Discovery</dc:subject>
	<dc:subject xml:lang="en-US">Hyperparameter tuning; Inhibitory concentration 50; Murcko fragments; Quantitative structure-activity relationship; SARS-CoV-2 polyprotein 1ab</dc:subject>
	<dc:description xml:lang="en-US">Hyperparameter tuning is a key optimization strategy in machine learning (ML), often used with GridSearchCV to find optimal hyperparameter combinations. This study aimed to predict the half-maximal inhibitory concentration (IC50) of small molecules targeting the SARS-CoV-2 replicase polyprotein 1ab (pp1ab) by optimizing three ML algorithms: histogram gradient boosting regressor (HGBR), light gradient boosting regressor (LGBR), and random forest regressor (RFR). Bioactivity data, including duplicates, were processed using three approaches: untreated, aggregation of quantitative bioactivity, and duplicate removal. Molecular features were encoded using twelve types of molecular fingerprints. To optimize the models, hyperparameter tuning with GridSearchCV was applied across a broad parameter space. The results showed that the performance of the models was inconsistent, despite comprehensive hyperparameter tuning. Further analysis showed that the distribution of Murcko fragments was uneven between the training and testing datasets. Key fragments were underrepresented in the testing phase, leading to a mismatch in model predictions. The study demonstrates that hyperparameter tuning alone may not be sufficient to achieve high predictive performance when the distribution of molecular fragments is unbalanced between training and testing datasets. Ensuring fragment diversity across datasets is crucial for improving model reliability in drug discovery applications.</dc:description>
	<dc:publisher xml:lang="en-US">Institute of Advanced Engineering and Science</dc:publisher>
	<dc:contributor xml:lang="en-US">Office of Research and Community Service, Universitas Sam Ratulangi</dc:contributor>
	<dc:date>2025-08-01</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en-US"></dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://ijai.iaescore.com/index.php/IJAI/article/view/27196</dc:identifier>
	<dc:identifier>10.11591/ijai.v14.i4.pp3003-3013</dc:identifier>
	<dc:source xml:lang="en-US">IAES International Journal of Artificial Intelligence (IJ-AI); Vol 14, No 4: August 2025; 3003-3013</dc:source>
	<dc:source>2252-8938</dc:source>
	<dc:source>2089-4872</dc:source>
	<dc:source>10.11591/ijai.v14.i4</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://ijai.iaescore.com/index.php/IJAI/article/view/27196/14634</dc:relation>
	<dc:rights xml:lang="en-US">Copyright (c) 2025 Institute of Advanced Engineering and Science</dc:rights>
	<dc:rights xml:lang="en-US">http://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>