Your browser doesn't support javascript.
loading
Show: 20 | 50 | 100
Results 1 - 3 de 3
Filter
1.
Bioinformatics ; 36(7): 2202-2208, 2020 04 01.
Article in English | MEDLINE | ID: mdl-31845988

ABSTRACT

MOTIVATION: One way to identify genes possibly associated with ageing is to build a classification model (from the machine learning field) capable of classifying genes as associated with multiple age-related diseases. To build this model, we use a pre-compiled list of human genes associated with age-related diseases and apply a novel Deep Neural Network (DNN) method to find associations between gene descriptors (e.g. Gene Ontology terms, protein-protein interaction data and biological pathway information) and age-related diseases. RESULTS: The novelty of our new DNN method is its modular architecture, which has the capability of combining several sources of biological data to predict which ageing-related diseases a gene is associated with (if any). Our DNN method achieves better predictive performance than standard DNN approaches, a Gradient Boosted Tree classifier (a strong baseline method) and a Logistic Regression classifier. Given the DNN model produced by our method, we use two approaches to identify human genes that are not known to be associated with age-related diseases according to our dataset. First, we investigate genes that are close to other disease-associated genes in a complex multi-dimensional feature space learned by the DNN algorithm. Second, using the class label probabilities output by our DNN approach, we identify genes with a high probability of being associated with age-related diseases according to the model. We provide evidence of these putative associations retrieved from the DNN model with literature support. AVAILABILITY AND IMPLEMENTATION: The source code and datasets can be found at: https://github.com/fabiofabris/Bioinfo2019. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.


Subject(s)
Deep Learning , Machine Learning , Aging , Gene Ontology , Humans , Neural Networks, Computer
2.
J Reprod Immunol ; 137: 102618, 2020 02.
Article in English | MEDLINE | ID: mdl-31698104

ABSTRACT

The cross-talk between endometrium and embryo is not accessible to the researcher for obvious ethical reasons that let understand why implantation remains the black box of reproduction. We aimed to detect of the concentrations of IL-1ß and TNF-α in endometrial secretion at the time of oocyte retrieval for early prediction of implantation. One hundred twenty women participated in the study during ICSI cycles. All women participating in the study included the following criteria; age; 22-36 years, BMI; less than 35 kg/m2, a husband with oligo- or oligoasthenospermia. All women received controlled ovarian hyperstimulation and immediately after ovum pickup, an intrauterine flushing was done. Embryo transfer was done at the blastocyst stage five days after ovum pick up. Serum pregnancy tests were done for all women. The clinical pregnancy was defined as the appearance of the gestational sac and positive embryo cardiac activity was confirmed by TVS. The ongoing pregnancy was detected by abdominal ultrasound at 12 weeks. The participants were divided into two groups: the pregnant group and the non-pregnant group. Thirty-two and half percent of women got pregnant. There were non-significant differences between the two groups regarding the demographic, clinical and laboratory data except for the duration of infertility and concentrations of TNF-α and IL-1ß. The concentrations of TNF-α and IL-1ß were significantly higher in the pregnant group than the non-pregnant group.Therefore,The use of TNF-α and IL-1ß to predict implantation in IVF is promising especially before embryo transfer. Clinical trial.gov registration NCT02854514.


Subject(s)
Embryo Implantation/immunology , Embryo Transfer/methods , Endometrium/metabolism , Interleukin-1beta/analysis , Tumor Necrosis Factor-alpha/analysis , Adult , Asthenozoospermia/therapy , Biomarkers/analysis , Biomarkers/metabolism , Cross-Sectional Studies , Endometrium/immunology , Enzyme-Linked Immunosorbent Assay , Female , Humans , Interleukin-1beta/metabolism , Male , Oligospermia/therapy , Oocyte Retrieval , Ovulation Induction/methods , Predictive Value of Tests , Pregnancy , Pregnancy Rate , Prospective Studies , ROC Curve , Treatment Outcome , Tumor Necrosis Factor-alpha/metabolism , Young Adult
3.
BMC Womens Health ; 17(1): 108, 2017 Nov 13.
Article in English | MEDLINE | ID: mdl-29132339

ABSTRACT

BACKGROUND: Ovarian hyperstimulation syndrome (OHSS) is an important condition with considerable morbidity and a small risk of mortality and most commonly results as an iatrogenic condition following follicular stimulation of the ovaries. We aimed to evaluate safety and efficacy of 3-day cetrotide therapy started on day of oocyte retrieval (Day-0) in women at high-risk for development of ovarian hyperstimulation syndrome (OHSS) after GnRH agonist induction protocol. METHODS: Forty-eight women fulfilling inclusion criteria underwent ultrasound scanning for maximal ovarian diameter (MOD) estimation and ascites grading. Patients underwent embryo freezing, but the study group received 3-day Cetrotide sc injection (0.25 mg/day) started on Day-0. Serum E2, pain scores and MOD were checked daily. Hematocrite value (Ht%), total leucocytic count (TLC), gastrointestinal (GI) manifestations and ascites grading were re-evaluated on Day-3, 6 and 8. RESULTS: Sequential serum E2 levels decreased significantly in both groups with significantly lower levels in the study group. Sequential MOD estimates showed non-significant difference between the two groups and versus Day-0 estimates. On Day-2, pain scores showed progressive significant decrease compared to Day-0 scores in both groups with significantly lower scores in the study group. On Day-3; four control patients still had vomiting and by Day-6, 6 of the control patients still had GI manifestations with significant difference versus the study group. Compared to Day-0 estimates, Ht% and TLC were significantly lower on Day-3, 6 and 8 in the study group, but only on Day-8 in the control group. Day-3 and Day-8 ascites grading in both groups was significantly lower compared to respective Day-0 grading with significant difference in favor of the study group. Six patients required hospitalization, but without mortalities. Day-3 E2 levels in the study group showed positive significant correlation with clinical and other laboratory data and ascites grading, while the correlation was non-significant with MOD. CONCLUSION: The 3-day cetrotide therapy starting after oocyte retrieval with embryo transfer freezing could be an appropriate management policy for women received GnHR-agonist induction protocol and were at high-risk for OHSS. Sequential E2 serum levels could predict outcome more perfectly than sequential MOD estimates. TRIAL REGISTRATION: Trial registration ( clinicaltrial.gov registration) NCT02823080 (retrospective) Initial Release 21-6-2016 Last Release 3-1-2017 Unique Protocol ID: Benha U Secondary IDs: kmsalama.


Subject(s)
Fertility Agents, Female/therapeutic use , Fertilization in Vitro/methods , Gonadotropin-Releasing Hormone/analogs & derivatives , Oocyte Retrieval/methods , Ovarian Hyperstimulation Syndrome/drug therapy , Ovarian Hyperstimulation Syndrome/physiopathology , Ovulation Induction/methods , Adult , Female , Gonadotropin-Releasing Hormone/therapeutic use , Humans , Middle Aged , Retrospective Studies
SELECTION OF CITATIONS
SEARCH DETAIL
...