Integrating pathway knowledge with deep neural networks to reduce the dimensionality in single-cell RNA-seq data.

BACKGROUND: Single-cell RNA sequencing (scRNA-seq) data provide valuable insights into cellular heterogeneity which is significantly improving the current knowledge on biology and human disease. One of the main applications of scRNA-seq data analysis is the identification of new cell types and cell states. Deep neural networks (DNNs) are among the best methods to address this problem. However, this performance comes with the trade-off for a lack of interpretability in the results. In this work we propose an intelligible pathway-driven neural network to correctly solve cell-type related problems at single-cell resolution while providing a biologically meaningful representation of the data. RESULTS: In this study, we explored the deep neural networks constrained by several types of prior biological information, e.g. signaling pathway information, as a way to reduce the dimensionality of the scRNA-seq data. We have tested the proposed biologically-based architectures on thousands of cells of human and mouse origin across a collection of public datasets in order to check the performance of the model. Specifically, we tested the architecture across different validation scenarios that try to mimic how unknown cell types are clustered by the DNN and how it correctly annotates cell types by querying a database in a retrieval problem. Moreover, our approach demonstrated to be comparable to other less interpretable DNN approaches constrained by using protein-protein interactions gene regulation data. Finally, we show how the latent structure learned by the network could be used to visualize and to interpret the composition of human single cell datasets. CONCLUSIONS: Here we demonstrate how the integration of pathways, which convey fundamental information on functional relationships between genes, with DNNs, that provide an excellent classification framework, results in an excellent alternative to learn a biologically meaningful representation of scRNA-seq data. In addition, the introduction of prior biological knowledge in the DNN reduces the size of the network architecture. Comparative results demonstrate a superior performance of this approach with respect to other similar approaches. As an additional advantage, the use of pathways within the DNN structure enables easy interpretability of the results by connecting features to cell functionalities by means of the pathway nodes, as demonstrated with an example with human melanoma tumor cells.

A data mining based clinical decision support system for survival in lung cancer.

BACKGROUND: A clinical decision support system (CDSS ) has been designed to predict the outcome (overall survival) by extracting and analyzing information from routine clinical activity as a complement to clinical guidelines in lung cancer patients. MATERIALS AND METHODS: Prospective multicenter data from 543 consecutive (2013-2017) lung cancer patients with 1167 variables were used for development of the CDSS. Data Mining analyses were based on the XGBoost and Generalized Linear Models algorithms. The predictions from guidelines and the CDSS proposed were compared. RESULTS: Overall, the highest (> 0.90) areas under the receiver-operating characteristics curve AUCs for predicting survival were obtained for small cell lung cancer patients. The AUCs for predicting survival using basic items included in the guidelines were mostly below 0.70 while those obtained using the CDSS were mostly above 0.70. The vast majority of comparisons between the guideline and CDSS AUCs were statistically significant (p < 0.05). For instance, using the guidelines, the AUC for predicting survival was 0.60 while the predictive power of the CDSS enhanced the AUC up to 0.84 (p = 0.0009). In terms of histology, there was only a statistically significant difference when comparing the AUCs of small cell lung cancer patients (0.96) and all lung cancer patients with longer (≥ 18 months) follow up (0.80; p < 0.001). CONCLUSIONS: The CDSS successfully showed potential for enhancing prediction of survival. The CDSS could assist physicians in formulating evidence-based management advice in patients with lung cancer, guiding an individualized discussion according to prognosis.

Influence of edge in the structure of the vegetation of an open ombrophilous forest in Alagoas / Influência da borda na estrutura da vegetação de uma floresta ombrófila aberta em Alagoas

Understanding the influence of fragmentation on the behavior of forest essential elements in different vegetation formations is fundamental for the definition of conservation strategies. In this study, the aim was to evaluate the influence of the edge environment on the phytosociological structure of a fragment of Open Ombrophylous Forest, in Rio Largo, Alagoas. Five transects of 10.0 x 100.0 m were subdivided into ten 10.0 x 10.0 m plots to collect the data. All tree individuals with Chest Height Circumference ≥ 15 cm were sampled, measured and later identified in the herbarium of the Institute of the Environment of Alagoas. For the analysis, the phytosociological parameters Shannon-Wiener diversity (H'), Pielou equability (J') were calculated after defined the successional classes and dispersion syndromes of the species sampled. The edge effect was analyzed by comparing the richness, diversity, equability and number of individuals in the interior and at the edge of the fragment, using the Venn diagram technique. There were 581 arboreal individuals, of which 434 were identified as belonging to 20 families, 24 genera and 30 morphospecies. Among the raised species, there were higher occurrences of early secondary (46.67%) and late (23.33%), as well as those of zoocoric dispersion (53.33%). The diversity was 2.89 nats/ind., and the Pielou (J') equability was 0.8497. The edge environment did not influence the establishment of species. This may have occurred due to the environmental characteristics of the open ombrophylous forest.

Compreender a influência da fragmentação sobre o comportamento das essências florestais em diferentes formações vegetacionais é fundamental para que se possa definir estratégias de conservação. Neste trabalho,objetivou-se de avaliar a influência do ambiente de borda sobre estrutura fitossociológica de um fragmento de Floresta Ombrófila Aberta, em Rio Largo, Alagoas. Para a coleta dos dados foram alocados cinco transectos de 10,0 x 100,0 m, subdivididos em dez parcelas de 10,0 x 10,0 m. Foram amostrados todos osindivíduos arbóreos com Circunferência à Altura do Peito ≥ 15 cm, que foram mensurados e posteriormente identificados no herbário do Instituto do Meio Ambiente de Alagoas. Para a análise foram calculados osparâmetros fitossociológicos, a diversidade de Shannon-Wiener (H'), a equabilidade de Pielou (J'), definidas as classes sucessionais e síndromes de dispersão das espécies amostradas. O efeito de borda foi analisado por meio de comparação da riqueza, diversidade, equabilidade e número de indivíduos no interior e na borda do fragmento, empregando-se a técnica diagrama de Venn. Foram registrados 581 indivíduos arbóreos, dos quais 434 foram identificados como pertencentes a 20 famílias, 24 gêneros e 30 morfoespécies. Entre as espécies levantadas, houve maior ocorrência de secundárias iniciais (46,67%) e tardias (23,33%), assim como de dispersão zoocórica (53,33%). A diversidade foi de 2,89 nats/ind., e a equabilidade de Pielou (J') foi de 0,8497. O ambiente de borda não influenciou no estabelecimento de espécies. Isso pode ter ocorrido em virtude das características da floresta ombrófila aberta.

Ethnic difference in risk of toxicity in prostate cancer patients treated with dynamic arc radiation therapy.

AIMS AND BACKGROUND: The objective of this study was to assess the influence of ethnicity on toxicity in patients treated with dynamic arc radiation therapy (ART) for prostate cancer (PC). METHODS: From June 2006 to May 2012, 162 cT1-T3 cN0 cM0 PC patients were treated with ART (primary diagnosis, n = 125; post-prostatectomy/brachytherapy biochemical recurrence, n = 26; adjuvant post-prostatectomy, n = 11) at 2 institutions. Forty-five patients were Latin Americans and 117 were Europeans. The dose prescribed to the prostate ranged between 68 Gy and 81 Gy. RESULTS: The median age was 69 years (range 43-87 years). The median follow-up was 18 months (range 2-74 months). Overall, only 3 patients died, none due to a cancer-related cause. Biochemical recurrence was seen in 7 patients. The rates of acute grade 2 gastrointestinal (GI) and genitourinary (GU) toxicities were 19.7% and 17%, respectively. Only 1 patient experienced acute grade 3 GI toxicity, whereas 11 patients (6.7%) experienced acute grade 3 GU toxicity. Multivariate analysis showed that undergoing whole pelvic lymph node irradiation was associated with a higher grade of acute GI toxicity (OR: 3.46; p = 0.003). In addition, older age was marginally associated with a higher grade of acute GI toxicity (OR: 2.10; p = 0.074). Finally, ethnicity was associated with acute GU toxicity: Europeans had lower-grade toxicity (OR: 0.27; p = 0.001). CONCLUSIONS: Our findings suggest an ethnic difference in GU toxicity for PC patients treated with ART. In addition, we found that ART is associated with a very low risk of severe toxicity and a low recurrence rate.