No abstract

Subgroup detection has received increasing attention recently in different fields such as clinical trials, public management and market segmentation analysis. In these fields, people often face time‐to‐event data, which are commonly subject to right censoring. This paper proposes a semiparametric Logistic‐Cox mixture model for subgroup analysis when the interested outcome is event time with right censoring. The proposed method mainly consists of a likelihood ratio‐based testing procedure for testing the existence of subgroups. The expectation–maximization iteration is applied to improve the testing power, and a model‐based bootstrap approach is developed to implement the testing procedure. When there exist subgroups, one can also use the proposed model to estimate the subgroup effect and construct predictive scores for the subgroup membership. The large sample properties of the proposed method are studied. The finite sample performance of the proposed method is assessed by simulation studies. A real data example is also provided for illustration.

We consider causal inference in randomized survival studies with right censored outcomes and all-or-nothing compliance, using semiparametric transformation models to estimate the distribution of survival times in treatment and control groups, conditional on covariates and latent compliance type. Estimands depending on these distributions, for example, the complier average causal effect (CACE), the complier effect on survival beyond time t, and the complier quantile effect are then considered. Maximum likelihood is used to estimate the parameters of the transformation models, using a specially designed expectation-maximization (EM) algorithm to overcome the computational difficulties created by the mixture structure of the problem and the infinite dimensional parameter in the transformation models. The estimators are shown to be consistent, asymptotically normal, and semiparametrically efficient. Inferential procedures for the causal parameters are developed. A simulation study is conducted to evaluate the finite sample performance of the estimated causal parameters. We also apply our methodology to a randomized study conducted by the Health Insurance Plan of Greater New York to assess the reduction in breast cancer mortality due to screening.

Intellectual disability (ID) has emerged as the commonest manifestation of underlying genomic abnormalities. Given that molecular genetic tests for diagnosis of ID usually require high costs and yield relatively low diagnostic rates, identification of additional phenotypes or comorbidities may increase the genetic diagnostic yield and are valuable clues for pediatricians in general practice. Here, we enrolled consecutively 61 children with unexplained moderate or severe ID and performed chromosomal microarray (CMA) and sequential whole-exome sequencing (WES) analysis on them. We identified 13 copy number variants in 12 probands and 24 variants in 25 probands, and the total diagnostic rate was 60.7%. The genetic abnormalities were commonly found in ID patients with movement disorder (100%) or with autistic spectrum disorder (ASD) (93.3%). Univariate analysis showed that ASD was the significant risk factor of genetic abnormality (P = 0.003; OR 14, 95% CI 1.7–115.4). At least 14 ID-ASD associated genes were identified, and the majority of ID-ASD associated genes (85.7%) were found to be expressed in the cerebellum based on database analysis. In conclusion, genetic testing on ID children, particularly in those with ASD is highly recommended. ID and ASD may share common cerebellar pathophysiology.

Human metallothionein-3 (hMT3), also named human neuronal growth inhibitory factor (hGIF), is attractive due to its distinct neuronal growth inhibitory activity, which is not shown by other human MT isoforms. It has been reported that the neuronal growth inhibitory activity arises from the N-terminal beta-domain rather than its C-terminal alpha-domain. However, previous bioassay results have shown that the single beta-domain is less effective at inhibiting the neuron growth than that in intact hMT3 on a molar basis, which suggests that the alpha-domain is indispensable to the neuronal growth inhibitory activity of hMT3. In order to confirm this assumption, we constructed two domain-hybrid mutants, the beta(MT3)-beta(MT3) mutant and the beta(MT3)-alpha(MT1) mutant, and investigated their structural and metal binding properties by UV-vis spectroscopy, CD spectroscopy, pH titration, DTNB reaction, EDTA reaction, etc. The results showed that stability of the Cd(3)S(9) cluster of the beta(MT3)-beta(MT3) mutant decreased significantly while the Cd(3)S(9) cluster of the beta(MT3)-alpha(MT1) mutant had a similar stability and solvent accessibility to that of hMT3. Interestingly, the bioassay results showed that the neuronal growth inhibitory activity of the beta(MT3)-beta(MT3) mutant decreased significantly, while the beta(MT3)-alpha(MT1) mutant showed similar inhibitory activity to hMT3. Based on these results, we conclude that the alpha-domain is indispensable and plays an important role in modulating the stability of the metal cluster in the beta-domain by domain-domain interactions, thus influencing the bioactivity of hMT3.