Recent advances on constraint-based models by integrating machine learning

Rana, Pratip; Berry, Z. Carter; Ghosh, Preetam; Fong, Stephen S.

doi:10.1016/j.copbio.2019.11.007

Cited by 57 publications

(44 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Simulations were carried out using flux balance analysis (FBA), allowing us to depict cellular processes based on cellular reconstructions (Rana et al, 2020). Briefly, FBA follows the law of mass conservation and consider the metabolic framework as a static stoichiometric matrix (metabolites × reactions).…”

Section: Simulations Of Growth and Degradation Of Linuron Using Flux Balance Analysismentioning

confidence: 99%

Strategies for Enhancing in vitro Degradation of Linuron by Variovorax sp. Strain SRS 16 Under the Guidance of Metabolic Modeling

Dhakar

Zarecki

Bommel

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

Phenyl urea herbicides are being extensively used for weed control in both agricultural and non-agricultural applications. Linuron is one of the key herbicides in this family and is in wide use. Like other phenyl urea herbicides, it is known to have toxic effects as a result of its persistence in the environment. The natural removal of linuron from the environment is mainly carried through microbial biodegradation. Some microorganisms have been reported to mineralize linuron completely and utilize it as a carbon and nitrogen source. Variovorax sp. strain SRS 16 is one of the known efficient degraders with a recently sequenced genome. The genomic data provide an opportunity to use a genome-scale model for improving biodegradation. The aim of our study is the construction of a genome-scale metabolic model following automatic and manual protocols and its application for improving its metabolic potential through iterative simulations. Applying flux balance analysis (FBA), growth and degradation performances of SRS 16 in different media considering the influence of selected supplements (potential carbon and nitrogen sources) were simulated. Outcomes are predictions for the suitable media modification, allowing faster degradation of linuron by SRS 16. Seven metabolites were selected for in vitro validation of the predictions through laboratory experiments confirming the degradation-promoting effect of specific amino acids (glutamine and asparagine) on linuron degradation and SRS 16 growth. Overall, simulations are shown to be efficient in predicting the degradation potential of SRS 16 in the presence of specific supplements. The generated information contributes to the understanding of the biochemistry of linuron degradation and can be further utilized for the development of new cleanup solutions without any genetic manipulation.

show abstract

Section: Simulations Of Growth and Degradation Of Linuron Using Flux Balance Analysismentioning

confidence: 99%

Strategies for Enhancing in vitro Degradation of Linuron by Variovorax sp. Strain SRS 16 Under the Guidance of Metabolic Modeling

Dhakar

Zarecki

Bommel

et al. 2021

Front. Bioeng. Biotechnol.

View full text Add to dashboard Cite

show abstract

“…These omics technologies provide the ability to interpret and explain the genome through DNA sequencing, genome expression based transcriptome studies, protein identification from the proteome, and others. However, such individual data can only provide a limited information of the molecular complexity occurring inside the organisms due to the multi-level regulation inside biological units [1]. For example, we observe the combined effects of transcripts and methylome in the tumor cell due to genomics defect [2].…”

Section: Introductionmentioning

confidence: 89%

Performance Comparison of Deep Learning Autoencoders for Cancer Subtype Detection Using Multi-Omics Data

Franco¹,

Rana²,

Cruz³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

A heterogeneous disease like cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), patients’ survival vary significantly and show different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score. We observed that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we also compared the effect of feature selection and similarity measures for subtype detection. To evaluate the results obtained, we selected the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes identified by the autoencoders; the obtained results coincide well with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

show abstract

“…These omics technologies provide the ability to interpret and explain the genome through DNA sequencing, genome expression based transcriptome studies, protein identification from the proteome, and others. However, such individual data can only provide limited information on the molecular complexity occurring inside the organisms due to the multi-level regulation inside biological units [ 1 ]. For example, we observe the combined effects of transcripts and methylome in the tumor cell due to genomics defect [ 2 ].…”

Section: Introductionmentioning

confidence: 99%

Performance Comparison of Deep Learning Autoencoders for Cancer Subtype Detection Using Multi-Omics Data

Franco

Rana

Cruz

et al. 2021

Cancers

Self Cite

View full text Add to dashboard Cite

A heterogeneous disease such as cancer is activated through multiple pathways and different perturbations. Depending upon the activated pathway(s), the survival of the patients varies significantly and shows different efficacy to various drugs. Therefore, cancer subtype detection using genomics level data is a significant research problem. Subtype detection is often a complex problem, and in most cases, needs multi-omics data fusion to achieve accurate subtyping. Different data fusion and subtyping approaches have been proposed over the years, such as kernel-based fusion, matrix factorization, and deep learning autoencoders. In this paper, we compared the performance of different deep learning autoencoders for cancer subtype detection. We performed cancer subtype detection on four different cancer types from The Cancer Genome Atlas (TCGA) datasets using four autoencoder implementations. We also predicted the optimal number of subtypes in a cancer type using the silhouette score and found that the detected subtypes exhibit significant differences in survival profiles. Furthermore, we compared the effect of feature selection and similarity measures for subtype detection. For further evaluation, we used the Glioblastoma multiforme (GBM) dataset and identified the differentially expressed genes in each of the subtypes. The results obtained are consistent with other genomic studies and can be corroborated with the involved pathways and biological functions. Thus, it shows that the results from the autoencoders, obtained through the interaction of different datatypes of cancer, can be used for the prediction and characterization of patient subgroups and survival profiles.

show abstract

Recent advances on constraint-based models by integrating machine learning

Cited by 57 publications

References 48 publications

Strategies for Enhancing in vitro Degradation of Linuron by Variovorax sp. Strain SRS 16 Under the Guidance of Metabolic Modeling

Strategies for Enhancing in vitro Degradation of Linuron by Variovorax sp. Strain SRS 16 Under the Guidance of Metabolic Modeling

Performance Comparison of Deep Learning Autoencoders for Cancer Subtype Detection Using Multi-Omics Data

Performance Comparison of Deep Learning Autoencoders for Cancer Subtype Detection Using Multi-Omics Data

Contact Info

Product

Resources

About