- Menu
- Passa a palavra.
Partilha esta página. - Linked in
- Copiar Url
-
2017
Autores
Saha A.; Kim Y.; Gewirtz A.D.H.; Jo B.; Gao C.; McDowell I.C.; Engelhardt B.E.; Battle A.; Aguet F.; Ardlie K.G.; Cummings B.B.; Gelfand E.T.; Getz G.; Hadley K.; Handsaker R.E.; Huang K.H.; Kashin S.; Karczewski K.J.; Lek M.; Li X.; MacArthur D.G.; Nedzel J.L.; Nguyen D.T.; Noble M.S.; Segrè A.V.; Trowbridge C.A.; Tukiainen T.; Abell N.S.; Balliu B.; Barshir R.; Basha O.; Battle A.; Bogu G.K.; Brown A.; Brown C.D.; Castel S.E.; Chen L.S.; Chiang C.; Conrad D.F.; Cox N.J.; Damani F.N.; Davis J.R.; Delaneau O.; Dermitzakis E.T.; Engelhardt B.E.; Eskin E.; Ferreira P.G.; Frésard L.; Gamazon E.R.; Garrido-Martín D.; Gliner G.; Gloudemans M.J.; Guigo R.; Hall I.M.; Han B.; He Y.; Hormozdiari F.; Howald C.; Im H.K.; Kang E.Y.; Kim-Hellmuth S.; Lappalainen T.; Li G.; Li X.; Liu B.; Mangul S.; McCarthy M.I.; Mohammadi P.; Monlong J.; Montgomery S.B.; Muñoz-Aguirre M.; Ndungu A.W.; Nicolae D.L.; Nobel A.B.; Oliva M.; Ongen H.; Palowitch J.J.; Panousis N.; Papasaikas P.; Park Y.S.; Parsana P.; Payne A.J.; Peterson C.B.; Quan J.; Reverter F.; Sabatti C.; Sammeth M.; Scott A.J.; Shabalin A.A.; Sodaei R.; Stephens M.; Stranger B.E.; Strober B.J.; Sul J.H.; Tsang E.K.; Urbut S.; van de Bunt M.; Wang G.; Wen X.; Wright F.A.;
Publicação
Genome Research
Abstract
Gene co-expression networks capture biologically important patterns in gene expression data, enabling functional analyses of genes, discovery of biomarkers, and interpretation of genetic variants. Most network analyses to date have been limited to assessing correlation between total gene expression levels in a single tissue or small sets of tissues. Here, we built networks that additionally capture the regulation of relative isoform abundance and splicing, along with tissue-specific connections unique to each of a diverse set of tissues. We used the Genotype-Tissue Expression (GTEx) project v6 RNA sequencing data across 50 tissues and 449 individuals. First, we developed a framework called Transcriptome-Wide Networks (TWNs) for combining total expression and relative isoform levels into a single sparse network, capturing the interplay between the regulation of splicing and transcription. We built TWNs for 16 tissues and found that hubs in these networks were strongly enriched for splicing and RNA binding genes, demonstrating their utility in unraveling regulation of splicing in the human transcriptome. Next, we used a Bayesian biclustering model that identifies network edges unique to a single tissue to reconstruct Tissue-Specific Networks (TSNs) for 26 distinct tissues and 10 groups of related tissues. Finally, we found genetic variants associated with pairs of adjacent nodes in our networks, supporting the estimated network structures and identifying 20 genetic variants with distant regulatory impact on transcription and splicing. Our networks provide an improved understanding of the complex relationships of the human transcriptome across tissues.
2017
Autores
Aguet, F; Brown, AA; Castel, SE; Davis, JR; He, Y; Jo, B; Mohammadi, P; Park, Y; Parsana, P; Segre, AV; Strober, BJ; Zappala, Z; Cummings, BB; Gelfand, ET; Hadley, K; Huang, KH; Lek, M; Li, X; Nedzel, JL; Nguyen, DY; Noble, MS; Sullivan, TJ; Tukiainen, T; MacArthur, DG; Getz, G; Management, NP; Addington, A; Guan, P; Koester, S; Little, AR; Lockhart, NC; Moore, HM; Rao, A; Struewing, JP; Volpi, S; Collection, B; Brigham, LE; Hasz, R; Hunter, M; Johns, C; Johnson, M; Kopen, G; Leinweber, WF; Lonsdale, JT; McDonald, A; Mestichelli, B; Myer, K; Roe, B; Salvatore, M; Shad, S; Thomas, JA; Walters, G; Washington, M; Wheeler, J; Bridge, J; Foster, BA; Gillard, BM; Karasik, E; Kumar, R; Miklos, M; Moser, MT; Jewell, SD; Montroy, RG; Rohrer, DC; Valley, D; Mash, DC; Davis, DA; Sobin, L; Barcus, ME; Branton, PA; Grp, EMW; Abell, NS; Balliu, B; Delaneau, O; Fresard, L; Gamazon, ER; Garrido Martin, D; Gewirtz, ADH; Gliner, G; Gloudemans, MJ; Han, B; He, AZ; Hormozdiari, F; Li, X; Liu, B; Kang, EY; McDowell, IC; Ongen, H; Palowitch, JJ; Peterson, CB; Quon, G; Ripke, S; Saha, A; Shabalin, AA; Shimko, TC; Sul, JH; Teran, NA; Tsang, EK; Zhang, H; Zhou, YH; Bustamante, CD; Cox, NJ; Guigo, R; Kellis, M; McCarthy, MI; Conrad, DF; Eskin, E; Li, G; Nobel, AB; Sabatti, C; Stranger, BE; Wen, X; Wright, FA; Ardlie, KG; Dermitzakis, ET; Lappalainen, T; Battle, A; Brown, CD; Engelhardt, BE; Montgomery, SB; Aguet, F; Ardlie, KG; Cummings, BB; Gelfand, ET; Getz, G; Hadley, K; Handsaker, RE; Huang, KH; Kashin, S; Karczewski, KJ; Lek, M; Li, X; MacArthur, DG; Nedzel, JL; Nguyen, DT; Noble, MS; Segre, AV; Trowbridge, CA; Tukiainen, T; Abell, NS; Balliu, B; Barshir, R; Basha, O; Battle, A; Bogu, GK; Brown, A; Brown, CD; Castel, SE; Chen, LS; Chiang, C; Conrad, DF; Cox, NJ; Damani, FN; Davis, JR; Delaneau, O; Dermitzakis, ET; Engelhardt, BE; Eskin, E; Ferreira, PG; Fresard, L; Gamazon, ER; Garrido Martin, D; Gewirtz, ADH; Gliner, G; Gloudemans, MJ; Guigo, R; Hall, IM; Han, B; He, Y; Hormozdiari, F; Howald, C; Im, HK; Jo, B; Kang, EY; Kim, Y; Kim Hellmuth, S; Lappalainen, T; Li, G; Li, X; Liu, B; Mangul, S; McCarthy, MI; McDowell, IC; Mohammadi, P; Monlong, J; Montgomery, SB; Munoz Aguirre, M; Ndungu, AW; Nicolae, DL; Nobel, AB; Oliva, M; Ongen, H; Palowitch, JJ; Panousis, N; Papasaikas, P; Park, Y; Parsana, P; Payne, AJ; Peterson, CB; Quan, J; Reverter, F; Sabatti, C; Saha, A; Sammeth, M; Scott, AJ; Shabalin, AA; Sodaei, R; Stephens, M; Stranger, BE; Strober, BJ; Sul, JH; Tsang, EK; Urbut, S; De Bunt, MV; Wang, G; Wen, X; Wright, FA; Xi, HS; Yeger Lotem, E; Zappala, Z; Zaugg, JB; Zhou, YH; Akey, JM; Bates, D; Chan, J; Chen, LS; Claussnitzer, M; Demanelis, K; Diegel, M; Doherty, JA; Feinberg, AP; Fernando, MS; Halow, J; Hansen, KD; Haugen, E; Hickey, PF; Hou, L; Jasmine, F; Jian, R; Jiang, L; Johnson, A; Kaul, R; Kellis, M; Kibriya, MG; Lee, K; Li, JB; Li, Q; Li, X; Lin, J; Lin, S; Linder, S; Linke, C; Liu, Y; Maurano, MT; Molinie, B; Montgomery, SB; Nelson, J; Neri, FJ; Oliva, M; Park, Y; Pierce, BL; Rinaldi, NJ; Rizzardi, LF; Sandstrom, R; Skol, A; Smith, KS; Snyder, MP; Stamatoyannopoulos, J; Stranger, BE; Tang, H; Tsang, EK; Wang, L; Wang, M; Van Wittenberghe, N; Wu, F; Zhang, R; Fund, NC; Nierras, CR; Nci, N; Branton, PA; Carithers, LJ; Guan, P; Moore, HM; Rao, A; Vaught, JB; Nhgri, N; Gould, SE; Lockart, NC; Martin, C; Struewing, JP; Volpi, S; Nimh, N; Addington, AM; Koester, SE; Nida, N; Little, AR; Brigham, LE; Hasz, R; Hunter, M; Johns, C; Johnson, M; Kopen, G; Leinweber, WF; Lonsdale, JT; McDonald, A; Mestichelli, B; Myer, K; Roe, B; Salvatore, M; Shad, S; Thomas, JA; Walters, G; Washington, M; Wheeler, J; Bridge, J; Foster, BA; Gillard, BM; Karasik, E; Kumar, R; Miklos, M; Moser, MT; Jewell, SD; Montroy, RG; Rohrer, DC; Valley, DR; Davis, DA; Mash, DC; Undale, AH; Smith, AM; Tabor, DE; Roche, NV; McLean, JA; Vatanian, N; Robinson, KL; Sobin, L; Barcus, ME; Valentino, KM; Qi, L; Hunter, S; Hariharan, P; Singh, S; Um, KS; Matose, T; Tomaszewski, MM; Study, E; Barker, LK; Mosavel, M; Siminoff, LA; Traino, HM; Flicek, P; Juettemann, T; Ruffier, M; Sheppard, D; Taylor, K; Trevanion, SJ; Zerbino, DR; Craft, B; Goldman, M; Haeussler, M; Kent, WJ; Lee, CM; Paten, B; Rosenbloom, KR; Vivian, J; Zhu, J;
Publicação
NATURE
Abstract
Characterization of the molecular function of the human genome and its variation across individuals is essential for identifying the cellular mechanisms that underlie human genetic traits and diseases. The Genotype-Tissue Expression (GTEx) project aims to characterize variation in gene expression levels across individuals and diverse tissues of the human body, many of which are not easily accessible. Here we describe genetic effects on gene expression levels across 44 human tissues. We find that local genetic variation affects gene expression levels for the majority of genes, and we further identify inter-chromosomal genetic effects for 93 genes and 112 loci. On the basis of the identified genetic effects, we characterize patterns of tissue specificity, compare local and distal effects, and evaluate the functional properties of the genetic effects. We also demonstrate that multi-tissue, multi-individual data can be used to identify genes and pathways affected by human disease-associated variation, enabling a mechanistic interpretation of gene regulation and the genetic basis of disease.
2017
Autores
Carvalho, S; Gueiral, N; Nogueira, E; Henrique, R; Oliveira, L; Tuchin, VV;
Publicação
DYNAMICS AND FLUCTUATIONS IN BIOMEDICAL PHOTONICS XIV
Abstract
Optical properties of biological tissues are unique and may be used for tissue identification, tissue discrimination or even to identify pathologies. Early stage colorectal cancer evolves from adenomatous polyps that arise in the inner layer of the colorectal tube - the mucosa. The identification of different optical properties between healthy and pathological colorectal tissues might be used to identify different tissue components and to develop an early stage diagnosis method using optical technologies. Since most of the biomedical optics techniques use light within the visible and near infrared wavelength ranges, we used the inverse adding-doubling method to make a fast estimation of the optical properties of colorectal mucosa and early stage adenocarcinoma between 400 and 1000 nm. The estimated wavelength dependencies have provided information about higher lipid content in healthy mucosa and higher blood content in pathological tissue. Such data has also indicated that the wavelength dependence of the scattering coefficient for healthy mucosa is dominated by Rayleigh scattering and for pathological mucosa it is dominated by Mie scattering. Such difference indicates smaller scatterer size in healthy mucosa tissue. Such information can now be used to develop new diagnosis or treatment methods for early cancer detection or removal. One possibility is to use optical clearing technique to improve tissue transparency and create localized and temporary tissue dehydration for image contrast improvement during diagnosis or polyp laser removal. Such techniques can now be developed based on the different results that we have found for healthy and pathological colorectal mucosa.
2017
Autores
Li, X; Kim, Y; Tsang, EK; Davis, JR; Damani, FN; Chiang, C; Hess, GT; Zappala, Z; Strober, BJ; Scott, AJ; Li, A; Ganna, A; Bassik, MC; Merker, JD; Aguet, F; Ardlie, KG; Cummings, BB; Gelfand, ET; Getz, G; Hadley, K; Handsaker, RE; Huang, KH; Kashin, S; Karczewski, KJ; Lek, M; Li, X; MacArthur, DG; Nedzel, JL; Nguyen, DT; Noble, MS; Segrè, AV; Trowbridge, CA; Tukiainen, T; Abell, NS; Balliu, B; Barshir, R; Basha, O; Battle, A; Bogu, GK; Brown, A; Brown, CD; Castel, SE; Chen, LS; Chiang, C; Conrad, DF; Cox, NJ; Damani, FN; Davis, JR; Delaneau, O; Dermitzakis, ET; Engelhardt, BE; Eskin, E; Ferreira, PG; Frésard, L; Gamazon, ER; Garrido-Martín, D; Gewirtz, AD; Gliner, G; Gloudemans, MJ; Guigo, R; Hall, IM; Han, B; He, Y; Hormozdiari, F; Howald, C; Kyung Im, H; Jo, B; Yong Kang, E; Kim, Y; Kim-Hellmuth, S; Lappalainen, T; Li, G; Li, X; Liu, B; Mangul, S; McCarthy, MI; McDowell, IC; Mohammadi, P; Monlong, J; Montgomery, SB; Muñoz-Aguirre, M; Ndungu, AW; Nicolae, DL; Nobel, AB; Oliva, M; Ongen, H; Palowitch, JJ; Panousis, N; Papasaikas, P; Park, Y; Parsana, P; Payne, AJ; Peterson, CB; Quan, J; Reverter, F; Sabatti, C; Saha, A; Sammeth, M; Scott, AJ; Shabalin, AA; Sodaei, R; Stephens, M; Stranger, BE; Strober, BJ; Sul, JH; Tsang, EK; Urbut, S; van de Bunt, M; Wang, G; Wen, X; Wright, FA; Xi, HS; Yeger-Lotem, E; Zappala, Z; Zaugg, JB; Zhou, Y; Akey, JM; Bates, D; Chan, J; Chen, LS; Claussnitzer, M; Demanelis, K; Diegel, M; Doherty, JA; Feinberg, AP; Fernando, MS; Halow, J; Hansen, KD; Haugen, E; Hickey, PF; Hou, L; Jasmine, F; Jian, R; Jiang, L; Johnson, A; Kaul, R; Kellis, M; Kibriya, MG; Lee, K; Billy Li, J; Li, Q; Li, X; Lin, J; Lin, S; Linder, S; Linke, C; Liu, Y; Maurano, MT; Molinie, B; Montgomery, SB; Nelson, J; Neri, FJ; Oliva, M; Park, Y; Pierce, BL; Rinaldi, NJ; Rizzardi, LF; Sandstrom, R; Skol, A; Smith, KS; Snyder, MP; Stamatoyannopoulos, J; Stranger, BE; Tang, H; Tsang, EK; Wang, L; Wang, M; Van Wittenberghe, N; Wu, F; Zhang, R; Nierras, CR; Branton, PA; Carithers, LJ; Guan, P; Moore, HM; Rao, A; Vaught, JB; Gould, SE; Lockart, NC; Martin, C; Struewing, JP; Volpi, S; Addington, AM; Koester, SE; Little, AR; Brigham, LE; Hasz, R; Hunter, M; Johns, C; Johnson, M; Kopen, G; Leinweber, WF; Lonsdale, JT; McDonald, A; Mestichelli, B; Myer, K; Roe, B; Salvatore, M; Shad, S; Thomas, JA; Walters, G; Washington, M; Wheeler, J; Bridge, J; Foster, BA; Gillard, BM; Karasik, E; Kumar, R; Miklos, M; Moser, MT; Jewell, SD; Montroy, RG; Rohrer, DC; Valley, DR; Davis, DA; Mash, DC; Undale, AH; Smith, AM; Tabor, DE; Roche, NV; McLean, JA; Vatanian, N; Robinson, KL; Sobin, L; Barcus, ME; Valentino, KM; Qi, L; Hunter, S; Hariharan, P; Singh, S; Um, KS; Matose, T; Tomaszewski, MM; Barker, LK; Mosavel, M; Siminoff, LA; Traino, HM; Flicek, P; Juettemann, T; Ruffier, M; Sheppard, D; Taylor, K; Trevanion, SJ; Zerbino, DR; Craft, B; Goldman, M; Haeussler, M; Kent, WJ; Lee, CM; Paten, B; Rosenbloom, KR; Vivian, J; Zhu, J; Hall, IM; Battle, A; Montgomery, SB;
Publicação
Nature
Abstract
Rare genetic variants are abundant in humans and are expected to contribute to individual disease risk1-4. While genetic association studies have successfully identified common genetic variants associated with susceptibility, these studies are not practical for identifying rare variants1,5. Efforts to distinguish pathogenic variants from benign rare variants have leveraged the genetic code to identify deleterious protein-coding alleles1,6,7, but no analogous code exists for non-coding variants. Therefore, ascertaining which rare variants have phenotypic effects remains a major challenge. Rare non-coding variants have been associated with extreme gene expression in studies using single tissues8-11, but their effects across tissues are unknown. Here we identify gene expression outliers, or individuals showing extreme expression levels for a particular gene, across 44 human tissues by using combined analyses of whole genomes and multi-tissue RNA-sequencing data from the Genotype-Tissue Expression (GTEx) project v6p release12. We find that 58% of underexpression and 28% of overexpression outliers have nearby conserved rare variants compared to 8% of non-outliers. Additionally, we developed RIVER (RNA-informed variant effect on regulation), a Bayesian statistical model that incorporates expression data to predict a regulatory effect for rare variants with higher accuracy than models using genomic annotations alone. Overall, we demonstrate that rare variants contribute to large gene expression changes across tissues and provide an integrative method for interpretation of rare variants in individual genomes.
2017
Autores
Tukiainen, T; Villani, A; Yen, A; Rivas, MA; Marshall, JL; Satija, R; Aguirre, M; Gauthier, L; Fleharty, M; Kirby, A; Cummings, BB; Castel, SE; Karczewski, KJ; Aguet, F; Byrnes, A; Aguet, F; Ardlie, KG; Cummings, BB; Gelfand, ET; Getz, G; Hadley, K; Handsaker, RE; Huang, KH; Kashin, S; Karczewski, KJ; Lek, M; Li, X; MacArthur, DG; Nedzel, JL; Nguyen, DT; Noble, MS; Segrè, AV; Trowbridge, CA; Tukiainen, T; Abell, NS; Balliu, B; Barshir, R; Basha, O; Battle, A; Bogu, GK; Brown, A; Brown, CD; Castel, SE; Chen, LS; Chiang, C; Conrad, DF; Cox, NJ; Damani, FN; Davis, JR; Delaneau, O; Dermitzakis, ET; Engelhardt, BE; Eskin, E; Ferreira, PG; Frésard, L; Gamazon, ER; Garrido-Martín, D; Gewirtz, ADH; Gliner, G; Gloudemans, MJ; Guigo, R; Hall, IM; Han, B; He, Y; Hormozdiari, F; Howald, C; Kyung Im, H; Jo, B; Yong Kang, E; Kim, Y; Kim-Hellmuth, S; Lappalainen, T; Li, G; Li, X; Liu, B; Mangul, S; McCarthy, MI; McDowell, IC; Mohammadi, P; Monlong, J; Montgomery, SB; Muñoz-Aguirre, M; Ndungu, AW; Nicolae, DL; Nobel, AB; Oliva, M; Ongen, H; Palowitch, JJ; Panousis, N; Papasaikas, P; Park, Y; Parsana, P; Payne, AJ; Peterson, CB; Quan, J; Reverter, F; Sabatti, C; Saha, A; Sammeth, M; Scott, AJ; Shabalin, AA; Sodaei, R; Stephens, M; Stranger, BE; Strober, BJ; Sul, JH; Tsang, EK; Urbut, S; van de Bunt, M; Wang, G; Wen, X; Wright, FA; Xi, HS; Yeger-Lotem, E; Zappala, Z; Zaugg, JB; Zhou, Y; Akey, JM; Bates, D; Chan, J; Chen, LS; Claussnitzer, M; Demanelis, K; Diegel, M; Doherty, JA; Feinberg, AP; Fernando, MS; Halow, J; Hansen, KD; Haugen, E; Hickey, PF; Hou, L; Jasmine, F; Jian, R; Jiang, L; Johnson, A; Kaul, R; Kellis, M; Kibriya, MG; Lee, K; Li, JB; Li, Q; Li, X; Lin, J; Lin, S; Linder, S; Linke, C; Liu, Y; Maurano, MT; Molinie, B; Montgomery, SB; Nelson, J; Neri, FJ; Oliva, M; Park, Y; Pierce, BL; Rinaldi, NJ; Rizzardi, LF; Sandstrom, R; Skol, A; Smith, KS; Snyder, MP; Stamatoyannopoulos, J; Stranger, BE; Tang, H; Tsang, EK; Wang, L; Wang, M; Van Wittenberghe, N; Wu, F; Zhang, R; Nierras, CR; Branton, PA; Carithers, LJ; Guan, P; Moore, HM; Rao, A; Vaught, JB; Gould, SE; Lockart, NC; Martin, C; Struewing, JP; Volpi, S; Addington, AM; Koester, SE; Little, AR; Brigham, LE; Hasz, R; Hunter, M; Johns, C; Johnson, M; Kopen, G; Leinweber, WF; Lonsdale, JT; McDonald, A; Mestichelli, B; Myer, K; Roe, B; Salvatore, M; Shad, S; Thomas, JA; Walters, G; Washington, M; Wheeler, J; Bridge, J; Foster, BA; Gillard, BM; Karasik, E; Kumar, R; Miklos, M; Moser, MT; Jewell, SD; Montroy, RG; Rohrer, DC; Valley, DR; Davis, DA; Mash, DC; Undale, AH; Smith, AM; Tabor, DE; Roche, NV; McLean, JA; Vatanian, N; Robinson, KL; Sobin, L; Barcus, ME; Valentino, KM; Qi, L; Hunter, S; Hariharan, P; Singh, S; Um, KS; Matose, T; Tomaszewski, MM; Barker, LK; Mosavel, M; Siminoff, LA; Traino, HM; Flicek, P; Juettemann, T; Ruffier, M; Sheppard, D; Taylor, K; Trevanion, SJ; Zerbino, DR; Craft, B; Goldman, M; Haeussler, M; Kent, WJ; Lee, CM; Paten, B; Rosenbloom, KR; Vivian, J; Zhu, J; Lappalainen, T; Regev, A; Ardlie, KG; Hacohen, N; MacArthur, DG;
Publicação
Nature
Abstract
X chromosome inactivation (XCI) silences transcription from one of the two X chromosomes in female mammalian cells to balance expression dosage between XX females and XY males. XCI is, however, incomplete in humans: up to one-third of X-chromosomal genes are expressed from both the active and inactive X chromosomes (Xa and Xi, respectively) in female cells, with the degree of 'escape' from inactivation varying between genes and individuals1,2. The extent to which XCI is shared between cells and tissues remains poorly characterized3,4, as does the degree to which incomplete XCI manifests as detectable sex differences in gene expression5 and phenotypic traits6. Here we describe a systematic survey of XCI, integrating over 5,500 transcriptomes from 449 individuals spanning 29 tissues from GTEx (v6p release) and 940 single-cell transcriptomes, combined with genomic sequence data. We show that XCI at 683 X-chromosomal genes is generally uniform across human tissues, but identify examples of heterogeneity between tissues, individuals and cells. We show that incomplete XCI affects at least 23% of X-chromosomal genes, identify seven genes that escape XCI with support from multiple lines of evidence and demonstrate that escape from XCI results in sex biases in gene expression, establishing incomplete XCI as a mechanism that is likely to introduce phenotypic diversity6,7. Overall, this updated catalogue of XCI across human tissues helps to increase our understanding of the extent and impact of the incompleteness in the maintenance of XCI.
2017
Autores
Nogueira, DM; Ferreira, CA; Jorge, AM;
Publicação
PROGRESS IN ARTIFICIAL INTELLIGENCE (EPIA 2017)
Abstract
Phonocardiogram signals contain very useful information about the condition of the heart. It is a method of registration of heart sounds, which can be visually represented on a chart. By analyzing these signals, early detections and diagnosis of heart diseases can be done. Intelligent and automated analysis of the phonocardiogram is therefore very important, to determine whether the patient's heart works properly or should be referred to an expert for further evaluation. In this work, we use electrocardiograms and phonocardiograms collected simultaneously, from the Physionet challenge database, and we aim to determine whether a phonocardiogram corresponds to a "normal" or "abnormal" physiological state. The main idea is to translate a 1D phonocardiogram signal into a 2D image that represents temporal and Mel-frequency cepstral coefficients features. To do that, we develop a novel approach that uses both features. First we segment the phonocardiogram signals with an algorithm based on a logistic regression hidden semi-Markov model, which uses the electrocardiogram signals as reference. After that, we extract a group of features from the time and frequency domain (Mel-frequency cepstral coefficients) of the phonocardiogram. Then, we combine these features into a two-dimensional time-frequency heat map representation. Lastly, we run a binary classifier to learn a model that discriminates between normal and abnormal phonocardiogram signals. In the experiments, we study the contribution of temporal and Mel-frequency cepstral coefficients features and evaluate three classification algorithms: Support Vector Machines, Convolutional Neural Network, and Random Forest. The best results are achieved when we map both temporal and Mel-frequency cepstral coefficients features into a 2D image and use the Support Vector Machines with a radial basis function kernel. Indeed, by including both temporal and Mel-frequency cepstral coefficients features, we obtain sligthly better results than the ones reported by the challenge participants, which use large amounts of data and high computational power.
The access to the final selection minute is only available to applicants.
Please check the confirmation e-mail of your application to obtain the access code.