Maria Markaki
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Maria Markaki has a total of 28 co-authors. Here are the top co-authors by number of shared publications:
Yannis Stylianou
6 shared publicationsMichael I. Taroudakis
Institute of Applied and Computational Mathematics, FO.R.T.H., P.O. Box 1527, 71110 Heraklion, Greece
3 shared publicationsIoannis Tsamardinos
University of Crete, Department of Computer Science, Voutes Campus, Heraklion, GR 70013, Greece; Gnosis Data Analysis PC, Palaiokapa 64, Heraklion, GR 71305, Greece
2 shared publications- Julián David Arias Londoño
Departamento de Ingeniería de Sistemas y Ciencias Computacionales, Universidad de Antioquia, Medellín, Colombia
2 shared publications Y. Stylianou
Computer Science Department, University of Crete, Greece
2 shared publications- Anastasios Koutsopoulos
Department of Pathology, University General Hospital of Heraklion, 71500 Heraklion, Greece
1 shared publication
Latest Publications
- Open Access
MicroRNA Expression Analysis and Biological Pathways in Chemoresistant Non-Small Cell Lung Cancer
Background/Objectives: Alterations in DNA damage repair mechanisms can impair the therapeutic effectiveness of cisplatin. MicroRNAs (miRNAs), key regulators of DNA damage repair processes, have been proposed as promising biomarkers for predicting the response to platinum-based chemotherapy (CT) in non-small cell lung cancer (NSCLC). In this study, by using a bioinformatics approach, we identified six miRNAs, which were differentially expressed (DE) between NSCLC patients characterized as responders and non-responders to platinum-based CT. We further validated the differential expression of the selected miRNAs on tumor and matched normal tissues from patients with resected NSCLC. Methods: Two miRNA microarray expression datasets were retrieved from the Gene Expression Omnibus (GEO) repository, comprising a total of 69 NSCLC patients (N = 69) treated with CT and annotated data from their response to treatment. Differential expression analysis was performed using the Linear Models for Microarray Analysis (Limma) package in R to identify DE miRNAs between responders (N = 33) and non-responders (N = 36). Quantitative real-time PCR (qRT-PCR) was used to assess miRNA expression levels in clinical tissue samples (N = 20). Results: Analysis with the Limma package revealed 112 DE miRNAs between responders and non-responders. A random-effects meta-analysis further identified 24 miRNAs that were consistently up- or downregulated in at least two studies. Survival analysis using the Kaplan–Meier plotter (KM plotter) indicated that 22 of these miRNAs showed significant associations with prognosis in NSCLC. Functional and pathway enrichment analysis revealed that several of the identified miRNAs were linked to key pathways implicated in DNA damage repair, including the p53, Hippo, PI3K and TGF-β signaling pathways. We finally distinguished a six-miRNA signature consisting of miR-26a, miR-29c, miR-34a, miR-30e-5p, miR-30e-3p and miR-497, which were downregulated in non-responders and are involved in at least three DNA damage repair pathways. Comparative expression analysis on tumor and matched normal tissues from surgically treated NSCLC patients confirmed their differential expression in clinical samples. Conclusions: In summary, we identified a signature of six miRNAs that are suppressed in NSCLC and may serve as a predictor of cisplatin response in NSCLC.
Open AccessMicroRNA Expression Analysis and Biological Pathways in Chemoresistant Non-Small Cell Lung Cancer
Background/Objectives: Alterations in DNA damage repair mechanisms can impair the therapeutic effectiveness of cisplatin. MicroRNAs (miRNAs), key regulators of DNA damage repair processes, have been proposed as promising biomarkers for predicting the response to platinum-based chemotherapy (CT) in non-small cell lung cancer (NSCLC). In this study, by using a bioinformatics approach, we identified six miRNAs, which were differentially expressed (DE) between NSCLC patients characterized as responders and non-responders to platinum-based CT. We further validated the differential expression of the selected miRNAs on tumor and matched normal tissues from patients with resected NSCLC. Methods: Two miRNA microarray expression datasets were retrieved from the Gene Expression Omnibus (GEO) repository, comprising a total of 69 NSCLC patients (N = 69) treated with CT and annotated data from their response to treatment. Differential expression analysis was performed using the Linear Models for Microarray Analysis (Limma) package in R to identify DE miRNAs between responders (N = 33) and non-responders (N = 36). Quantitative real-time PCR (qRT-PCR) was used to assess miRNA expression levels in clinical tissue samples (N = 20). Results: Analysis with the Limma package revealed 112 DE miRNAs between responders and non-responders. A random-effects meta-analysis further identified 24 miRNAs that were consistently up- or downregulated in at least two studies. Survival analysis using the Kaplan–Meier plotter (KM plotter) indicated that 22 of these miRNAs showed significant associations with prognosis in NSCLC. Functional and pathway enrichment analysis revealed that several of the identified miRNAs were linked to key pathways implicated in DNA damage repair, including the p53, Hippo, PI3K and TGF-β signaling pathways. We finally distinguished a six-miRNA signature consisting of miR-26a, miR-29c, miR-34a, miR-30e-5p, miR-30e-3p and miR-497, which were downregulated in non-responders and are involved in at least three DNA damage repair pathways. Comparative expression analysis on tumor and matched normal tissues from surgically treated NSCLC patients confirmed their differential expression in clinical samples. Conclusions: In summary, we identified a signature of six miRNAs that are suppressed in NSCLC and may serve as a predictor of cisplatin response in NSCLC.
- Open Access
- 1 May 2018
- Published by Elsevier in EBioMedicine
- Vol. 31, 36-46
A Validated Clinical Risk Prediction Model for Lung Cancer in Smokers of All Ages and Exposure Types: A HUNT Study
- 1 May 2018
- Published by Elsevier in EBioMedicine
- Vol. 31, 36-46
Open AccessA Validated Clinical Risk Prediction Model for Lung Cancer in Smokers of All Ages and Exposure Types: A HUNT Study
- Open Access
- 12 June 2017
- Published by Springer Nature in Scientific Reports
- Vol. 7 (1) , 1-12
MatureP: prediction of secreted proteins with exclusive information from their mature regions
More than a third of the cellular proteome is non-cytoplasmic. Most secretory proteins use the Sec system for export and are targeted to membranes using signal peptides and mature domains. To specifically analyze bacterial mature domain features, we developed MatureP, a classifier that predicts secretory sequences through features exclusively computed from their mature domains. MatureP was trained using Just Add Data Bio, an automated machine learning tool. Mature domains are predicted efficiently with ~92% success, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC). Predictions were validated using experimental datasets of mutated secretory proteins. The features selected by MatureP reveal prominent differences in amino acid content between secreted and cytoplasmic proteins. Amino-terminal mature domain sequences have enhanced disorder, more hydroxyl and polar residues and less hydrophobics. Cytoplasmic proteins have prominent amino-terminal hydrophobic stretches and charged regions downstream. Presumably, secretory mature domains comprise a distinct protein class. They balance properties that promote the necessary flexibility required for the maintenance of non-folded states during targeting and secretion with the ability of post-secretion folding. These findings provide novel insight in protein trafficking, sorting and folding mechanisms and may benefit protein secretion biotechnology.
- 12 June 2017
- Published by Springer Nature in Scientific Reports
- Vol. 7 (1) , 1-12
Open AccessMatureP: prediction of secreted proteins with exclusive information from their mature regions
More than a third of the cellular proteome is non-cytoplasmic. Most secretory proteins use the Sec system for export and are targeted to membranes using signal peptides and mature domains. To specifically analyze bacterial mature domain features, we developed MatureP, a classifier that predicts secretory sequences through features exclusively computed from their mature domains. MatureP was trained using Just Add Data Bio, an automated machine learning tool. Mature domains are predicted efficiently with ~92% success, as measured by the Area Under the Receiver Operating Characteristic Curve (AUC). Predictions were validated using experimental datasets of mutated secretory proteins. The features selected by MatureP reveal prominent differences in amino acid content between secreted and cytoplasmic proteins. Amino-terminal mature domain sequences have enhanced disorder, more hydroxyl and polar residues and less hydrophobics. Cytoplasmic proteins have prominent amino-terminal hydrophobic stretches and charged regions downstream. Presumably, secretory mature domains comprise a distinct protein class. They balance properties that promote the necessary flexibility required for the maintenance of non-folded states during targeting and secretion with the ability of post-secretion folding. These findings provide novel insight in protein trafficking, sorting and folding mechanisms and may benefit protein secretion biotechnology.
- 1 May 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 1301-1305
Automatic classification of systolic heart murmurs
This paper describes a system for discriminating innocent from pathologic systolic heart murmurs in children based on auscultation recordings. For sound signal analysis the use of reassigned spectrogram is suggested. Both dimensions and noise of the time-frequency representation were significantly reduced using higher order singular value decomposition. Optimal dimensions were selected through cross-validation experiments on a database of auscultation recordings with systolic murmurs from the University Hospital of Heraklion. The database only consisted with recordings of high misclassification rate by general practitioners. Using support vector machines for classification, the suggested approach achieved an Equal Error Rate of 6.71 ± 1.18% and an Area Under the Curve score of 0.9758 ± 0.0053 (95% confidence intervals). The performance of the suggested classification system is comparable to the reported accuracy of experienced pediatric cardiologists on the same database, while it outperforms alternative signal representations based on simple STFT schemes.
- 1 May 2013
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15206149,p. 1301-1305
Automatic classification of systolic heart murmurs
This paper describes a system for discriminating innocent from pathologic systolic heart murmurs in children based on auscultation recordings. For sound signal analysis the use of reassigned spectrogram is suggested. Both dimensions and noise of the time-frequency representation were significantly reduced using higher order singular value decomposition. Optimal dimensions were selected through cross-validation experiments on a database of auscultation recordings with systolic murmurs from the University Hospital of Heraklion. The database only consisted with recordings of high misclassification rate by general practitioners. Using support vector machines for classification, the suggested approach achieved an Equal Error Rate of 6.71 ± 1.18% and an Area Under the Curve score of 0.9758 ± 0.0053 (95% confidence intervals). The performance of the suggested classification system is comparable to the reported accuracy of experienced pediatric cardiologists on the same database, while it outperforms alternative signal representations based on simple STFT schemes.
- 1 May 2011
- Published by Elsevier in Speech Communication
- Vol. 53 (5) , 726-735
Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features
- 1 May 2011
- Published by Elsevier in Speech Communication
- Vol. 53 (5) , 726-735
Discrimination of speech from nonspeeech in broadcast news based on modulation frequency features
- 6 January 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 19 (7) , 1938-1948
Voice Pathology Detection and Discrimination Based on Modulation Spectral Features
In this paper, we explore the information provided by a joint acoustic and modulation frequency representation, referred to as modulation spectrum, for detection and discrimination of voice disorders. The initial representation is first transformed to a lower dimensional domain using higher order singular value decomposition (HOSVD). From this dimension-reduced representation a feature selection process is suggested using an information-theoretic criterion based on the mutual information between voice classes (i.e., normophonic/dysphonic) and features. To evaluate the suggested approach and representation, we conducted cross-validation experiments on a database of sustained vowel recordings from healthy and pathological voices, using support vector machines (SVMs) for classification. For voice pathology detection, the suggested approach achieved a classification accuracy of 94.1±0.28% (95% confidence interval), which is comparable to the accuracy achieved using cepstral-based features. However, for voice pathology classification the suggested approach significantly outperformed the performance of cepstral-based features.
- 6 January 2011
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Audio, Speech, and Language Processing
- Vol. 19 (7) , 1938-1948
Voice Pathology Detection and Discrimination Based on Modulation Spectral Features
In this paper, we explore the information provided by a joint acoustic and modulation frequency representation, referred to as modulation spectrum, for detection and discrimination of voice disorders. The initial representation is first transformed to a lower dimensional domain using higher order singular value decomposition (HOSVD). From this dimension-reduced representation a feature selection process is suggested using an information-theoretic criterion based on the mutual information between voice classes (i.e., normophonic/dysphonic) and features. To evaluate the suggested approach and representation, we conducted cross-validation experiments on a database of sustained vowel recordings from healthy and pathological voices, using support vector machines (SVMs) for classification. For voice pathology detection, the suggested approach achieved a classification accuracy of 94.1±0.28% (95% confidence interval), which is comparable to the accuracy achieved using cepstral-based features. However, for voice pathology classification the suggested approach significantly outperformed the performance of cepstral-based features.
- 12 November 2010
- Published by Taylor & Francis in Logopedics Phoniatrics Vocology
- Vol. 36 (2) , 60-69
On combining information from modulation spectra and mel-frequency cepstral coefficients for automatic detection of pathological voices
This work presents a novel approach for the automatic detection of pathological voices based on fusing the information extracted by means of mel-frequency cepstral coefficients (MFCC) and features derived from the modulation spectra (MS). The system proposed uses a two-stepped classification scheme. First, the MFCC and MS features were used to feed two different and independent classifiers; and then the outputs of each classifier were used in a second classification stage. In order to establish the best configuration which provides the highest accuracy in the detection, the fusion of information was carried out employing different classifier combination strategies. The experiments were carried out using two different databases: the one developed by The Massachusetts Eye and Ear Infirmary Voice Laboratory, and a database recorded by the Universidad Politécnica de Madrid. The results show that the combination of MFCC and MS features employing the proposed approach yields an improvement in the detection accuracy, demonstrating that both methods of parameterization are complementary.
- 12 November 2010
- Published by Taylor & Francis in Logopedics Phoniatrics Vocology
- Vol. 36 (2) , 60-69
On combining information from modulation spectra and mel-frequency cepstral coefficients for automatic detection of pathological voices
This work presents a novel approach for the automatic detection of pathological voices based on fusing the information extracted by means of mel-frequency cepstral coefficients (MFCC) and features derived from the modulation spectra (MS). The system proposed uses a two-stepped classification scheme. First, the MFCC and MS features were used to feed two different and independent classifiers; and then the outputs of each classifier were used in a second classification stage. In order to establish the best configuration which provides the highest accuracy in the detection, the fusion of information was carried out employing different classifier combination strategies. The experiments were carried out using two different databases: the one developed by The Massachusetts Eye and Ear Infirmary Voice Laboratory, and a database recorded by the Universidad Politécnica de Madrid. The results show that the combination of MFCC and MS features employing the proposed approach yields an improvement in the detection accuracy, demonstrating that both methods of parameterization are complementary.
- Open Access
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5162-5165
Dysphonia detection based on modulation spectral features and cepstral coefficients
In this paper, we combine modulation spectral features with mel-frequency cepstral coefficients for automatic detection of dysphonia. For classification purposes, dimensions of the original modulation spectra are reduced using higher order singular value decomposition (HOSVD). Most relevant features are selected based on their mutual information to discrimination between normophonic and dysphonic speakers made by experts. Features that highly correlate with voice alterations are associated then with a support vector machine (SVM) classifier to provide an automatic decision. Recognition experiments using two different databases suggest that the system provides complementary information to the standard mel-cepstral features.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 5162-5165
Open AccessDysphonia detection based on modulation spectral features and cepstral coefficients
In this paper, we combine modulation spectral features with mel-frequency cepstral coefficients for automatic detection of dysphonia. For classification purposes, dimensions of the original modulation spectra are reduced using higher order singular value decomposition (HOSVD). Most relevant features are selected based on their mutual information to discrimination between normophonic and dysphonic speakers made by experts. Features that highly correlate with voice alterations are associated then with a support vector machine (SVM) classifier to provide an automatic decision. Recognition experiments using two different databases suggest that the system provides complementary information to the standard mel-cepstral features.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Modulation spectral features for objective voice quality assessment
In this paper, we employ normalized modulation spectral features for objective voice quality assessment regarding grade (hoarseness). Modulation spectra usually produce a high-dimensionality space. For classification purposes, the size of the original space is reduced using Higher Order Singular Value Decomposition (SVD). Further, we select most relevant features based on the mutual information between subjective voice quality (the degree of hoarseness) and the computed features, which leads to an adaptive to the classification task modulation spectral representation. The adaptive modulation spectral features are used as input to a Naive Bayes (NB) classifier. By combining two NB classifiers based on different feature sets a global classification rate of 73.93% for hoarseness was achieved.
- 1 March 2010
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-4
Modulation spectral features for objective voice quality assessment
In this paper, we employ normalized modulation spectral features for objective voice quality assessment regarding grade (hoarseness). Modulation spectra usually produce a high-dimensionality space. For classification purposes, the size of the original space is reduced using Higher Order Singular Value Decomposition (SVD). Further, we select most relevant features based on the mutual information between subjective voice quality (the degree of hoarseness) and the computed features, which leads to an adaptive to the classification task modulation spectral representation. The adaptive modulation spectral features are used as input to a Naive Bayes (NB) classifier. By combining two NB classifiers based on different feature sets a global classification rate of 73.93% for hoarseness was achieved.
- 1 September 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. iv (1094687X) , 2514-2517
Using modulation spectra for voice pathology detection and classification
In this paper, we consider the use of Modulation Spectra for voice pathology detection and classification. To reduce the high-dimensionality space generated by Modulation spectra we suggest the use of Higher Order Singular Value Decomposition (SVD) and we propose a feature selection algorithm based on the Mutual Information between subjective voice quality and computed features. Using SVM with a radial basis function (RBF) kernel as classifier, we conducted experiments on a database of sustained vowel recordings from healthy and pathological voices. For voice pathology detection, the suggested approach achieved a detection rate of 94.1% and an Area Under the Curve (AUC) score of 97.8%. For voice pathology classification, an average detection rate and AUC of 88.6% and 94.8%, respectively, was achieved in classifying polyp against keratosis leukoplakia, adductor spasmodic dysphonia and vocal nodules.
- 1 September 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. iv (1094687X) , 2514-2517
Using modulation spectra for voice pathology detection and classification
In this paper, we consider the use of Modulation Spectra for voice pathology detection and classification. To reduce the high-dimensionality space generated by Modulation spectra we suggest the use of Higher Order Singular Value Decomposition (SVD) and we propose a feature selection algorithm based on the Mutual Information between subjective voice quality and computed features. Using SVM with a radial basis function (RBF) kernel as classifier, we conducted experiments on a database of sustained vowel recordings from healthy and pathological voices. For voice pathology detection, the suggested approach achieved a detection rate of 94.1% and an Area Under the Curve (AUC) score of 97.8%. For voice pathology classification, an average detection rate and AUC of 88.6% and 94.8%, respectively, was achieved in classifying polyp against keratosis leukoplakia, adductor spasmodic dysphonia and vocal nodules.