Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action

The rapid development of antimalarial resistance motivates the continued search for novel compounds with a mode of action (MoA) different to current antimalarials. Phenotypic screening has delivered thousands of promising hit compounds without prior knowledge of the compounds’ exact target or MoA. W...

Full description

Bibliographic Details
Main Authors: Ashleigh van Heerden, Roelof van Wyk, Lyn-Marie Birkholtz
Format: Article
Language:English
Published: Frontiers Media S.A. 2021-06-01
Series:Frontiers in Cellular and Infection Microbiology
Subjects:
Online Access:https://www.frontiersin.org/articles/10.3389/fcimb.2021.688256/full
id doaj-e0f47790a3474225adad2c7016b58e7c
record_format Article
spelling doaj-e0f47790a3474225adad2c7016b58e7c2021-06-29T07:14:31ZengFrontiers Media S.A.Frontiers in Cellular and Infection Microbiology2235-29882021-06-011110.3389/fcimb.2021.688256688256Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of ActionAshleigh van Heerden0Ashleigh van Heerden1Roelof van Wyk2Roelof van Wyk3Lyn-Marie Birkholtz4Lyn-Marie Birkholtz5Department of Biochemistry, Genetics and Microbiology, University of Pretoria, Hatfield, South AfricaUniversity of Pretoria Institute for Sustainable Malaria Control, University of Pretoria, Hatfield, South AfricaDepartment of Biochemistry, Genetics and Microbiology, University of Pretoria, Hatfield, South AfricaUniversity of Pretoria Institute for Sustainable Malaria Control, University of Pretoria, Hatfield, South AfricaDepartment of Biochemistry, Genetics and Microbiology, University of Pretoria, Hatfield, South AfricaUniversity of Pretoria Institute for Sustainable Malaria Control, University of Pretoria, Hatfield, South AfricaThe rapid development of antimalarial resistance motivates the continued search for novel compounds with a mode of action (MoA) different to current antimalarials. Phenotypic screening has delivered thousands of promising hit compounds without prior knowledge of the compounds’ exact target or MoA. Whilst the latter is not initially required to progress a compound in a medicinal chemistry program, identifying the MoA early can accelerate hit prioritization, hit-to-lead optimization and preclinical combination studies in malaria research. The effects of drug treatment on a cell can be observed on systems level in changes in the transcriptome, proteome and metabolome. Machine learning (ML) algorithms are powerful tools able to deconvolute such complex chemically-induced transcriptional signatures to identify pathways on which a compound act and in this manner provide an indication of the MoA of a compound. In this study, we assessed different ML approaches for their ability to stratify antimalarial compounds based on varied chemically-induced transcriptional responses. We developed a rational gene selection approach that could identify predictive features for MoA to train and generate ML models. The best performing model could stratify compounds with similar MoA with a classification accuracy of 76.6 ± 6.4%. Moreover, only a limited set of 50 biomarkers was required to stratify compounds with similar MoA and define chemo-transcriptomic fingerprints for each compound. These fingerprints were unique for each compound and compounds with similar targets/MoA clustered together. The ML model was specific and sensitive enough to group new compounds into MoAs associated with their predicted target and was robust enough to be extended to also generate chemo-transcriptomic fingerprints for additional life cycle stages like immature gametocytes. This work therefore contributes a new strategy to rapidly, specifically and sensitively indicate the MoA of compounds based on chemo-transcriptomic fingerprints and holds promise to accelerate antimalarial drug discovery programs.https://www.frontiersin.org/articles/10.3389/fcimb.2021.688256/fullmachine learningmode of actiongene expression profilebiomarkermultinominal logistic regressionchemo-transcriptomic fingerprint
collection DOAJ
language English
format Article
sources DOAJ
author Ashleigh van Heerden
Ashleigh van Heerden
Roelof van Wyk
Roelof van Wyk
Lyn-Marie Birkholtz
Lyn-Marie Birkholtz
spellingShingle Ashleigh van Heerden
Ashleigh van Heerden
Roelof van Wyk
Roelof van Wyk
Lyn-Marie Birkholtz
Lyn-Marie Birkholtz
Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action
Frontiers in Cellular and Infection Microbiology
machine learning
mode of action
gene expression profile
biomarker
multinominal logistic regression
chemo-transcriptomic fingerprint
author_facet Ashleigh van Heerden
Ashleigh van Heerden
Roelof van Wyk
Roelof van Wyk
Lyn-Marie Birkholtz
Lyn-Marie Birkholtz
author_sort Ashleigh van Heerden
title Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action
title_short Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action
title_full Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action
title_fullStr Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action
title_full_unstemmed Machine Learning Uses Chemo-Transcriptomic Profiles to Stratify Antimalarial Compounds With Similar Mode of Action
title_sort machine learning uses chemo-transcriptomic profiles to stratify antimalarial compounds with similar mode of action
publisher Frontiers Media S.A.
series Frontiers in Cellular and Infection Microbiology
issn 2235-2988
publishDate 2021-06-01
description The rapid development of antimalarial resistance motivates the continued search for novel compounds with a mode of action (MoA) different to current antimalarials. Phenotypic screening has delivered thousands of promising hit compounds without prior knowledge of the compounds’ exact target or MoA. Whilst the latter is not initially required to progress a compound in a medicinal chemistry program, identifying the MoA early can accelerate hit prioritization, hit-to-lead optimization and preclinical combination studies in malaria research. The effects of drug treatment on a cell can be observed on systems level in changes in the transcriptome, proteome and metabolome. Machine learning (ML) algorithms are powerful tools able to deconvolute such complex chemically-induced transcriptional signatures to identify pathways on which a compound act and in this manner provide an indication of the MoA of a compound. In this study, we assessed different ML approaches for their ability to stratify antimalarial compounds based on varied chemically-induced transcriptional responses. We developed a rational gene selection approach that could identify predictive features for MoA to train and generate ML models. The best performing model could stratify compounds with similar MoA with a classification accuracy of 76.6 ± 6.4%. Moreover, only a limited set of 50 biomarkers was required to stratify compounds with similar MoA and define chemo-transcriptomic fingerprints for each compound. These fingerprints were unique for each compound and compounds with similar targets/MoA clustered together. The ML model was specific and sensitive enough to group new compounds into MoAs associated with their predicted target and was robust enough to be extended to also generate chemo-transcriptomic fingerprints for additional life cycle stages like immature gametocytes. This work therefore contributes a new strategy to rapidly, specifically and sensitively indicate the MoA of compounds based on chemo-transcriptomic fingerprints and holds promise to accelerate antimalarial drug discovery programs.
topic machine learning
mode of action
gene expression profile
biomarker
multinominal logistic regression
chemo-transcriptomic fingerprint
url https://www.frontiersin.org/articles/10.3389/fcimb.2021.688256/full
work_keys_str_mv AT ashleighvanheerden machinelearninguseschemotranscriptomicprofilestostratifyantimalarialcompoundswithsimilarmodeofaction
AT ashleighvanheerden machinelearninguseschemotranscriptomicprofilestostratifyantimalarialcompoundswithsimilarmodeofaction
AT roelofvanwyk machinelearninguseschemotranscriptomicprofilestostratifyantimalarialcompoundswithsimilarmodeofaction
AT roelofvanwyk machinelearninguseschemotranscriptomicprofilestostratifyantimalarialcompoundswithsimilarmodeofaction
AT lynmariebirkholtz machinelearninguseschemotranscriptomicprofilestostratifyantimalarialcompoundswithsimilarmodeofaction
AT lynmariebirkholtz machinelearninguseschemotranscriptomicprofilestostratifyantimalarialcompoundswithsimilarmodeofaction
_version_ 1721355474712920064