In silico HCT116 human colon cancer cell-based models en route to the discovery of lead-like anticancer drugs

Sara Cruz, Sofia E. Gomes, Pedro M. Borralho, Cecília M. P. Rodrigues, Susana P. Gaudêncio, Florbela Pereira

Research output: Contribution to journalArticle

3 Citations (Scopus)

Abstract

To discover new inhibitors against the human colon carcinoma HCT116 cell line, two quantitative structure–activity relationship (QSAR) studies using molecular and nuclear magnetic resonance (NMR) descriptors were developed through exploration of machine learning techniques and using the value of half maximal inhibitory concentration (IC50). In the first approach, A, regression models were developed using a total of 7339 molecules that were extracted from the ChEMBL and ZINC databases and recent literature. The performance of the regression models was successfully evaluated by internal and external validations, the best model achieved R2 of 0.75 and 0.73 and root mean square error (RMSE) of 0.66 and 0.69 for the training and test sets, respectively. With the inherent time-consuming efforts of working with natural products (NPs), we conceived a new NP drug hit discovery strategy that consists in frontloading samples with 1D NMR descriptors to predict compounds with anticancer activity prior to bioactivity screening for NPs discovery, approach B. The NMR QSAR classification models were built using 1D NMR data (1H and13C) as descriptors, from 50 crude extracts, 55 fractions and five pure compounds obtained from actinobacteria isolated from marine sediments collected off the Madeira Archipelago. The overall predictability accuracies of the best model exceeded 63% for both training and test sets.

Original languageEnglish
Article number56
JournalBiomolecules
Volume8
Issue number3
DOIs
Publication statusPublished - 1 Sep 2018

Fingerprint

Computer Simulation
Colonic Neoplasms
Magnetic Resonance Spectroscopy
Biological Products
Cells
Nuclear magnetic resonance
Pharmaceutical Preparations
Geologic Sediments
HCT116 Cells
Actinobacteria
Drug Discovery
Complex Mixtures
Inhibitory Concentration 50
Colon
Bioactivity
Mean square error
Databases
Learning systems
Carcinoma
Screening

Keywords

  • Anticancer activity
  • HCT116 cell line
  • Machine learning (ML)
  • Marine natural products (MNPs)
  • Marine-derived actinobacteria
  • Molecular descriptors
  • NMR descriptors
  • Quantitative structure-Activity relationship (QSAR)

Cite this

Cruz, Sara ; Gomes, Sofia E. ; Borralho, Pedro M. ; Rodrigues, Cecília M. P. ; Gaudêncio, Susana P. ; Pereira, Florbela. / In silico HCT116 human colon cancer cell-based models en route to the discovery of lead-like anticancer drugs. In: Biomolecules. 2018 ; Vol. 8, No. 3.
@article{182ead14a73c4acfbb71b6396d1d5c0c,
title = "In silico HCT116 human colon cancer cell-based models en route to the discovery of lead-like anticancer drugs",
abstract = "To discover new inhibitors against the human colon carcinoma HCT116 cell line, two quantitative structure–activity relationship (QSAR) studies using molecular and nuclear magnetic resonance (NMR) descriptors were developed through exploration of machine learning techniques and using the value of half maximal inhibitory concentration (IC50). In the first approach, A, regression models were developed using a total of 7339 molecules that were extracted from the ChEMBL and ZINC databases and recent literature. The performance of the regression models was successfully evaluated by internal and external validations, the best model achieved R2 of 0.75 and 0.73 and root mean square error (RMSE) of 0.66 and 0.69 for the training and test sets, respectively. With the inherent time-consuming efforts of working with natural products (NPs), we conceived a new NP drug hit discovery strategy that consists in frontloading samples with 1D NMR descriptors to predict compounds with anticancer activity prior to bioactivity screening for NPs discovery, approach B. The NMR QSAR classification models were built using 1D NMR data (1H and13C) as descriptors, from 50 crude extracts, 55 fractions and five pure compounds obtained from actinobacteria isolated from marine sediments collected off the Madeira Archipelago. The overall predictability accuracies of the best model exceeded 63{\%} for both training and test sets.",
keywords = "Anticancer activity, HCT116 cell line, Machine learning (ML), Marine natural products (MNPs), Marine-derived actinobacteria, Molecular descriptors, NMR descriptors, Quantitative structure-Activity relationship (QSAR)",
author = "Sara Cruz and Gomes, {Sofia E.} and Borralho, {Pedro M.} and Rodrigues, {Cec{\'i}lia M. P.} and Gaud{\^e}ncio, {Susana P.} and Florbela Pereira",
note = "info:eu-repo/grantAgreement/FCT/5876/147218/PT# info:eu-repo/grantAgreement/FCT/5876/147258/PT# info:eu-repo/grantAgreement/FCT/3599-PPCDT/127013/PT# Financial support from Fundacao para a Ciencia e Tecnologia (FCT) Portugal, under Project PTDC/QUIQUI/119116/2010 and grants SFRH/BPD/108237/2015 (F.P.) and IF/00700/2014 (S.P.G.) are greatly appreciated. This work was also supported by the LAQV and UCIBIO, which are financed by national funds from FCT/MEC (UID/QUI/50006/2013 and UID/Multi/04378/2013), respectively) and co-financed by the ERDF under the PT2020 Partnership Agreement (POCI-01-0145-FEDER-007265 and POCI-010145-FEDER-007728, respectively), and by Programme grant SAICTPAC/0019/2015 funded by European Structural and Investment Funds through the COMPETE Programme and by National Funds through FCT. The NMR spectrometers are part of The National NMR Facility, supported by FCT (RECI/BBB-BQB/0230/2012).",
year = "2018",
month = "9",
day = "1",
doi = "10.3390/biom8030056",
language = "English",
volume = "8",
journal = "Biomolecules",
issn = "2218-273X",
publisher = "MDPI",
number = "3",

}

In silico HCT116 human colon cancer cell-based models en route to the discovery of lead-like anticancer drugs. / Cruz, Sara; Gomes, Sofia E.; Borralho, Pedro M.; Rodrigues, Cecília M. P.; Gaudêncio, Susana P.; Pereira, Florbela.

In: Biomolecules, Vol. 8, No. 3, 56, 01.09.2018.

Research output: Contribution to journalArticle

TY - JOUR

T1 - In silico HCT116 human colon cancer cell-based models en route to the discovery of lead-like anticancer drugs

AU - Cruz, Sara

AU - Gomes, Sofia E.

AU - Borralho, Pedro M.

AU - Rodrigues, Cecília M. P.

AU - Gaudêncio, Susana P.

AU - Pereira, Florbela

N1 - info:eu-repo/grantAgreement/FCT/5876/147218/PT# info:eu-repo/grantAgreement/FCT/5876/147258/PT# info:eu-repo/grantAgreement/FCT/3599-PPCDT/127013/PT# Financial support from Fundacao para a Ciencia e Tecnologia (FCT) Portugal, under Project PTDC/QUIQUI/119116/2010 and grants SFRH/BPD/108237/2015 (F.P.) and IF/00700/2014 (S.P.G.) are greatly appreciated. This work was also supported by the LAQV and UCIBIO, which are financed by national funds from FCT/MEC (UID/QUI/50006/2013 and UID/Multi/04378/2013), respectively) and co-financed by the ERDF under the PT2020 Partnership Agreement (POCI-01-0145-FEDER-007265 and POCI-010145-FEDER-007728, respectively), and by Programme grant SAICTPAC/0019/2015 funded by European Structural and Investment Funds through the COMPETE Programme and by National Funds through FCT. The NMR spectrometers are part of The National NMR Facility, supported by FCT (RECI/BBB-BQB/0230/2012).

PY - 2018/9/1

Y1 - 2018/9/1

N2 - To discover new inhibitors against the human colon carcinoma HCT116 cell line, two quantitative structure–activity relationship (QSAR) studies using molecular and nuclear magnetic resonance (NMR) descriptors were developed through exploration of machine learning techniques and using the value of half maximal inhibitory concentration (IC50). In the first approach, A, regression models were developed using a total of 7339 molecules that were extracted from the ChEMBL and ZINC databases and recent literature. The performance of the regression models was successfully evaluated by internal and external validations, the best model achieved R2 of 0.75 and 0.73 and root mean square error (RMSE) of 0.66 and 0.69 for the training and test sets, respectively. With the inherent time-consuming efforts of working with natural products (NPs), we conceived a new NP drug hit discovery strategy that consists in frontloading samples with 1D NMR descriptors to predict compounds with anticancer activity prior to bioactivity screening for NPs discovery, approach B. The NMR QSAR classification models were built using 1D NMR data (1H and13C) as descriptors, from 50 crude extracts, 55 fractions and five pure compounds obtained from actinobacteria isolated from marine sediments collected off the Madeira Archipelago. The overall predictability accuracies of the best model exceeded 63% for both training and test sets.

AB - To discover new inhibitors against the human colon carcinoma HCT116 cell line, two quantitative structure–activity relationship (QSAR) studies using molecular and nuclear magnetic resonance (NMR) descriptors were developed through exploration of machine learning techniques and using the value of half maximal inhibitory concentration (IC50). In the first approach, A, regression models were developed using a total of 7339 molecules that were extracted from the ChEMBL and ZINC databases and recent literature. The performance of the regression models was successfully evaluated by internal and external validations, the best model achieved R2 of 0.75 and 0.73 and root mean square error (RMSE) of 0.66 and 0.69 for the training and test sets, respectively. With the inherent time-consuming efforts of working with natural products (NPs), we conceived a new NP drug hit discovery strategy that consists in frontloading samples with 1D NMR descriptors to predict compounds with anticancer activity prior to bioactivity screening for NPs discovery, approach B. The NMR QSAR classification models were built using 1D NMR data (1H and13C) as descriptors, from 50 crude extracts, 55 fractions and five pure compounds obtained from actinobacteria isolated from marine sediments collected off the Madeira Archipelago. The overall predictability accuracies of the best model exceeded 63% for both training and test sets.

KW - Anticancer activity

KW - HCT116 cell line

KW - Machine learning (ML)

KW - Marine natural products (MNPs)

KW - Marine-derived actinobacteria

KW - Molecular descriptors

KW - NMR descriptors

KW - Quantitative structure-Activity relationship (QSAR)

UR - http://www.scopus.com/inward/record.url?scp=85050362659&partnerID=8YFLogxK

U2 - 10.3390/biom8030056

DO - 10.3390/biom8030056

M3 - Article

VL - 8

JO - Biomolecules

JF - Biomolecules

SN - 2218-273X

IS - 3

M1 - 56

ER -