Relevance of systems biological approach in the differential diagnosis of invasive lobular carcinoma &amp; invasive ductal carcinoma

Ragunath, PK; Reddy, B Vanaja; Abhinand, P A; Ahmed, Shiek S. S. J.

doi:10.6026/97320630008357

Cited by 3 publications

(4 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These two sub-types show similarity in certain features such as tumour site, tumour size, stage and grade, but have different metastatic patterns, characteristic histology and malignant calcifications [5], [4]. IDC starts from ducts and spreads to the breast fatty tissue, whereas ILC is restricted to milk producing lobules [6]. These two sub-types are also discriminated at the molecular level with differential expression of gene encoding vimentin, cathespin D, thrombospondin, E-cadherin, vascular endothelial growth factor, cytokeratin 8, and cyclin A.…”

Section: Introductionmentioning

confidence: 99%

“…[4], [7], [8], [9],[10], [11], [12]. The pathological differences between the two sub-types arises as a result of separate gene regulatory networks, which warrants further exploration for the development of appropriate diagnostic and therapeutic treatment strategy [6]. According to reports, 75% cases of invasive breast carcinoma cases are accounted by IDC, however, advanced treatment of IDC patients still remains a challenge due to lack of molecular targets for IDC treatment [13], [14].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning

Roy

Kumar

Mittal

et al. 2019

Preprint

View full text Add to dashboard Cite

Phone: +91 26743007Fax: +91 26742316 Email -dinesh@icgeb.res.in (DG)Early detection of breast cancer and its correct stage determination are important for prognosis and rendering appropriate personalized clinical treatment to breast cancer patients.However, despite considerable efforts and progress, there is a need to identify the specific genomic factors responsible for, or accompanying Invasive Ductal Carcinoma (IDC) progression stages, which can aid the determination of the correct cancer stages. We have developed two-class machine-learning classification models to differentiate the early and late stages of invasive ductal carcinoma. The prediction models are trained with RNA-seq gene expression profiles representing different IDC stages of 610 patients, obtained from The Cancer Genome Atlas (TCGA). Different supervised learning algorithms were trained and evaluated with an enriched model learning, facilitated by different feature selection methods.We also developed a machine-learning classifier trained on the same datasets with training sets reduced data corresponding to IDC driver genes. Based on these two classifiers, we have developed a web-server Duct-BRCA-CSP to predict early stage from late stages of IDC based on input RNA-seq gene expression profiles. The analysis conducted by us also enables deeper insights into the stage-dependent molecular events accompanying breast ductal carcinoma progression. The server is publicly available at http://bioinfo.icgeb.res.in/duct-BRCA-CSP. Key PointsDifferent supervised machine-learning algorithms such as Random Forest, SVM and Naive Bayes were trained with enriched features of the TCGA RNA-seq datasets selected for the study.We have developed two-class classification models, trained with relevant gene expression profiles to efficiently discriminate between the early and late IDC stages.Finally, we also developed a web server using python scikit-learn to provide freely available GUI based access to the machine learning models developed by us. The server is publicly available at http://bioinfo.icgeb.res.in/duct-BRCA-CSP.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning

Roy

Kumar

Mittal

et al. 2019

Preprint

View full text Add to dashboard Cite

show abstract

“…These two sub-types show similarity in certain features such as tumour site, size, stage and grade, but have different metastatic patterns, characteristic histology and malignant calcifications 5,4 . IDC starts from ducts and spreads to the breast fatty tissue, whereas ILC is restricted to milk producing lobules 6 . These two sub-types are also discriminated at the molecular level with differential expression of gene encoding vimentin, cathepsin D, thrombospondin, E-cadherin, vascular endothelial growth factor, cytokeratin 8, and cyclin A 4,7-12 .…”

mentioning

confidence: 99%

“…These two sub-types are also discriminated at the molecular level with differential expression of gene encoding vimentin, cathepsin D, thrombospondin, E-cadherin, vascular endothelial growth factor, cytokeratin 8, and cyclin A 4,7-12 . The pathological differences between the two sub-types arises as a result of separate gene regulatory networks, which warrants further exploration for the development of appropriate diagnostic and therapeutic treatment strategy 6 . According to reports, 75% cases of invasive breast carcinoma cases are accounted by IDC, however, advanced treatment of IDC patients still remains a challenge due to lack of molecular targets for IDC treatment 13,14 .…”

mentioning

confidence: 99%

Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning

Roy

Kumar

Mittal

et al. 2020

Sci Rep

View full text Add to dashboard Cite

Early detection of breast cancer and its correct stage determination are important for prognosis and rendering appropriate personalized clinical treatment to breast cancer patients. However, despite considerable efforts and progress, there is a need to identify the specific genomic factors responsible for, or accompanying Invasive Ductal Carcinoma (IDC) progression stages, which can aid the determination of the correct cancer stages. We have developed two-class machine-learning classification models to differentiate the early and late stages of IDC. The prediction models are trained with RNA-seq gene expression profiles representing different IDC stages of 610 patients, obtained from The Cancer Genome Atlas (TCGA). Different supervised learning algorithms were trained and evaluated with an enriched model learning, facilitated by different feature selection methods. We also developed a machinelearning classifier trained on the same datasets with training sets reduced data corresponding to IDC driver genes. Based on these two classifiers, we have developed a web-server Duct-BRCA-CSP to predict early stage from late stages of IDC based on input RNA-seq gene expression profiles. The analysis conducted by us also enables deeper insights into the stage-dependent molecular events accompanying IDC progression. The server is publicly available at http://bioinfo.icgeb.res.in/duct-BRCA-CSP.

show abstract

From algae to angiosperms–inferring the phylogeny of green plants (Viridiplantae) from 360 plastid genomes

et al. 2014

View full text Add to dashboard Cite

BackgroundNext-generation sequencing has provided a wealth of plastid genome sequence data from an increasingly diverse set of green plants (Viridiplantae). Although these data have helped resolve the phylogeny of numerous clades (e.g., green algae, angiosperms, and gymnosperms), their utility for inferring relationships across all green plants is uncertain. Viridiplantae originated 700-1500 million years ago and may comprise as many as 500,000 species. This clade represents a major source of photosynthetic carbon and contains an immense diversity of life forms, including some of the smallest and largest eukaryotes. Here we explore the limits and challenges of inferring a comprehensive green plant phylogeny from available complete or nearly complete plastid genome sequence data.ResultsWe assembled protein-coding sequence data for 78 genes from 360 diverse green plant taxa with complete or nearly complete plastid genome sequences available from GenBank. Phylogenetic analyses of the plastid data recovered well-supported backbone relationships and strong support for relationships that were not observed in previous analyses of major subclades within Viridiplantae. However, there also is evidence of systematic error in some analyses. In several instances we obtained strongly supported but conflicting topologies from analyses of nucleotides versus amino acid characters, and the considerable variation in GC content among lineages and within single genomes affected the phylogenetic placement of several taxa.ConclusionsAnalyses of the plastid sequence data recovered a strongly supported framework of relationships for green plants. This framework includes: i) the placement of Zygnematophyceace as sister to land plants (Embryophyta), ii) a clade of extant gymnosperms (Acrogymnospermae) with cycads + Ginkgo sister to remaining extant gymnosperms and with gnetophytes (Gnetophyta) sister to non-Pinaceae conifers (Gnecup trees), and iii) within the monilophyte clade (Monilophyta), Equisetales + Psilotales are sister to Marattiales + leptosporangiate ferns. Our analyses also highlight the challenges of using plastid genome sequences in deep-level phylogenomic analyses, and we provide suggestions for future analyses that will likely incorporate plastid genome sequence data for thousands of species. We particularly emphasize the importance of exploring the effects of different partitioning and character coding strategies.

show abstract

Relevance of systems biological approach in the differential diagnosis of invasive lobular carcinoma & invasive ductal carcinoma

Cited by 3 publications

References 0 publications

Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning

Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning

Classification models for Invasive Ductal Carcinoma Progression, based on gene expression data-trained supervised machine learning

From algae to angiosperms–inferring the phylogeny of green plants (Viridiplantae) from 360 plastid genomes

Contact Info

Product

Resources

About