Bayesian analysis and model selection for interval-censored survival data

Interval-censored data occur in survival analysis when the survival time of each patient is only known to be within an interval and these censoring intervals differ from patient to patient. For such data, we present some Bayesian discretized semiparametric models, incorporating proportional and nonproportional hazards structures, along with associated statistical analyses and tools for model selection using sampling-based methods. The scope of these methodologies is illustrated through a reanalysis of a breast cancer data set (Finkelstein, 1986, Biometrics 42, 845-854) to test whether the effect of covariate on survival changes over time.     

The commoner laboratory accidents—their prevention and treatment

The three common laboratory accidents, Cuts, Burns and Fainting, are considered from the aspects of First Aid treatment and prevention. Emphasis is placed upon the need for those in charge of school laboratories to give real consideration to the prevention of accidents and to the provisions for dealing with any that do occur.     

Weighting Class Importance in Agricultural Crop Classification from Remotely Sensed Data with an Artificial Neural Network

In some classifications the importance of classes varies and it is desirable to weight allocation to selected classes. This is common in classifications of remotely sensed imagery, especially as class occurrence can vary markedly. If, for instance, there is prior knowledge on the distribution of class occurrence this weighting can be achieved with widely used statistical classifiers by setting appropriate a priori probabilities of class membership. With an arificial neural network the incorporation of prior knowledge is more problematic. An approach to weight class allocation in an artificial neural network classifcation by replicating selected training patterns is discussed. In comparison against a discriminant analysis for the classification of synthetic aperture radar imagery the results showed that training pattern replication could be used to weight class allocation with an effect similar to that of incorporating a priori probabilities of class membership into the discriminant analysis and resulted in a significant increase in classification accuracy.     

Incorporating Prior Beliefs in Treatment Allocation for Clinical Trials

Recently Faraggi and Reiser (1991) introduced a general dynamic treatment allocation scheme which incorporates the permuted block allocation procedure and the Begg Iglewicz procedure as special cases. A drawback of previous allocation methods is that they did not allow incorporation of prior knowledge of the relative importance of the prognostic factors. In this paper we extend our allocation model to incorporate the weighting of prognostic factors. A simulation study examines the effects of this procedure and an example of its implementation is given.     

Interspecific dominance does not exclude sub-dominant blennies from offshore petroleum platforms

Interspecific interactions can determine the abundance and distributions of animals. Seaweed blennies, Parablennius marmoreus, and tesselated blennies, Hypsoblennius invemar, are found in barnacle cavities on offshore petroleum platforms in the northern Gulf of Mexico. I measured the interspecific resource defense interactions between these fishes in aquaria. Seaweed blennies were dominant over tesselated blennies when equal-sized fishes were tested. No difference in dominance was found when tesselated blennies had a 10% advantage in size. However, tesselated blennies were able to successfully defend cavities against equal-sized competitors when given the advantage of prior residence. This prior residence advantage persisted despite seaweed blennies having the advantage of past experience. Seaweed blennies attain a larger size on petroleum platforms, but empty barnacle cavities are common in this environment. Tesselated blennies are able to colonize and successfully spawn because they can enter an empty barnacle cavity, gain the advantage of prior residence, and successfully defend this cavity.     

Reflexes in prior polio and their relation to weakness and anterior horn cell loss

The aim of this study was to evaluate the reflex pattern in patients with prior polio and to relate these findings to the degree of anterior horn cell (AHC) involvement and loss of muscle force.

Twenty-five prior polio subjects were investigated with electromyography (EMG), force testing and reflex studies, which included the patellar and Achilles reflex, H-reflex, T-response and interlimb reflex (ILR).

The clinical reflexes, H/M-ratio and T-response amplitude at rest were positively correlated with force and negatively correlated with the degree of AHC loss. The H/M-ratio was decreased compared with age matched controls.

ILR was present in 68% of the prior polio patients but did not exist in controls. The presence of the ILR was not correlated with the degree of AHC loss or force.

The reflex studies gave two main findings. The first is reduced excitability of monosynaptic connections in the motor neuron pool, which is related to weakness. The other is the presence of ILR as an indicator of interneuronal hyper-excitability, which is not related to weakness.     

Effects of prior self-pollination on outcrossed seed set in tristylous Pontederia sagittata (Pontederiaceae)

The potential inhibitory effects of incompatible pollen on outcrossed seed set were investigated in mass-flowering, self-incompatible, tristylous Pontederia sagittata. Prior application of self pollen, followed after 2, 4, or 6 h by compatible pollen, was conducted on five genotypes of each of the three style morphs under uniform glasshouse conditions. The greatest reductions in seed set occurred in pollinations of the long-styled (L) morph at the 6 h time interval. Smaller reductions were also found for this treatment in the mid-styled (M) morph. No significant reductions in seed set were observed in the short-styled (S) morph or in the other morphs at shorter time intervals. Observations of pollen germination and pollen tube growth indicated that the lack of inhibitory effects in the S morph may occur because relatively few pollen grains adhered to stigmas in selfpollinations. In the L and M morphs, early germination of self pollen may cause physical clogging of the stigma and style, resulting in a reduced number of compatible pollen tubes in styles. Observations of the structural integrity of styles indicated that prior germination of self pollen resulted in more rapid onset of pistil senescence, particularly in the L morph. These influences may contribute to the morph-specific differences in seed set observed following prior self-pollination of outcrossed flowers. The negative effects of incompatible pollen are likely to be most evident where ecological factors cause delays in the delivery of outcross pollen to stigmas.     

Bayesian area–age–period–cohort model with carcinogenesis age effects in estimating cancer mortality

Objective: Area–age–period–cohort (AAPC) model has been widely used in studying the spatial and temporal pattern of disease incidence and mortality rates. However, lack of biological plausibility and ease of interpretability on temporal components especially for age effects are generally the weakness of AAPC models. We develop a Bayesian AAPC model where carcinogenesis age effect is incorporated to explain age effects from the underlying disease process. An autoregressive prior structure and an arbitrary linear constraint are used to solve the nonidentifiability issues. Methods: Two multistage carcinogenesis models are employed to derive the hazard functions to substitute the age effects in the AAPC models. The Iowa county-wide lung cancer mortality data are used for the model fitting and Deviance Information Criteria (DIC) is used for model comparison. Results: Our study shows that conventional AAPC model (DIC = 19,231.30), AAPC model with Armitage–Doll age effect (DIC = 19,233.00) and with two-stage clonal expansion (TSCE) age effect (DIC = 19,234.70) achieved the similar DIC values which indicated consistent model fitting among three models. The spatial pattern shows that the high spatial effects are clustered in the south of Iowa and also in largely populated areas. The lung cancer mortality rate is continuously declining by birth cohorts while increasing by the calendar period until 2000–2004. The age effects show an increasing pattern over time which can be easily explained by Armitage–Doll carcinogenesis model since we assume a log-linear relationship between age and hazard function. Conclusions: Our finding suggests that the proposed Bayesian AAPC model can be used to replace the conventional AAPC model without affecting model performance while providing a more biological sound approach from the underlining disease process.     

不同地位克氏原螯虾对社会环境改变的行为反应

为探究不同社会地位的亚成体克氏原螯虾(Procambarus clarkii)对利益的分配,以及对社会环境改变(体型较大的入侵同类)各自做出的行为反应,本文统计已确立等级序列的成对同性别螯虾对隐蔽所的占有情况,并视频拍摄同性别螯虾入侵时,入侵者及不同地位的原居者的格斗行为,分析格斗次数、格斗时间、首次攻击及被首次攻击对象多个参数。在隐蔽所占有实验中,71%为优势者占有隐蔽所,7%为从属者占有,共同占有或没有占有的各11%。在入侵-反入侵实验中,雄性入侵者对2只原居虾之间的攻击选择无显著差异,雌性入侵者首次攻击显著选择与原优势者格斗;雄性原居者中优势者对入侵者和原从属者的攻击无显著差异,雌性优势者则显著选择与入侵者格斗;雄性原居者中从属者显著选择与入侵者格斗,雌性从属者对入侵者和原优势者的攻击无显著差异。上述结果表明,优势者优先占有资源;雌雄螯虾在入侵和面临入侵时有各自不同的策略;不同地位的螯虾在反入侵时行为反应也各有不同。     

Prior specification in Bayesian statistics: three cautionary tales

One of the most important differences between Bayesian and traditional techniques is that the former combines information available beforehand-captured in the prior distribution and reflecting the subjective state of belief before an experiment is carried out-and what the data teach us, as expressed in the likelihood function. Bayesian inference is based on the combination of prior and current information which is reflected in the posterior distribution. The fast growing implementation of Bayesian analysis techniques can be attributed to the development of fast computers and the availability of easy to use software. It has long been established that the specification of prior distributions should receive a lot of attention. Unfortunately, flat distributions are often (inappropriately) used in an automatic fashion in a wide range of types of models. We reiterate that the specification of the prior distribution should be done with great care and support this through three examples. Even in the absence of strong prior information, prior specification should be done at the appropriate scale of biological interest. This often requires incorporation of (weak) prior information based on common biological sense. Very weak and uninformative priors at one scale of the model may result in relatively strong priors at other levels affecting the posterior distribution. We present three different examples intu?vely illustrating this phenomenon indicating that this bias can be substantial (especially in small samples) and is widely present. We argue that complete ignorance or absence of prior information may not exist. Because the central theme of the Bayesian paradigm is to combine prior information with current data, authors should be encouraged to publish their raw data such that every scientist is able to perform an analysis incorporating his/her own (subjective) prior distributions.     

Long-term territoriality and mate acquisition in the lefteye flounder Engyprosopon grandisquama

Reproductive ecology and function of long-term territoriality in the lefteye flounder Engyprosopon grandisquama were investigated in the southwest of Kyushu Island, Japan. Field observations of marked individuals and monthly sampling suggested that the spawning season was from June to September with a peak in June–July. During the spawning season, males maintained their mating territories, although spawning behavior was not observed in August–September. Some males stayed until the next spawning season and then acquired more mates than newly appearing males, most of which could not acquire mates. Long-term retention of territory may be more advantageous for establishing a mating territory and acquiring mates in the next spawning season.     

基于极大似然准则的生物序列模体的贝叶斯假设检验

针对生物信息学中序列模体的显著性检验问题,提出了一种基于极大似然准则的贝叶斯假设检验方法.将模体的显著性检验转化为多项分布的拟合优度检验问题,选取Dirichlet分布作为多项分布的先验分布并采用Newton-Raphson算法估计Dirichlet分布的超参数,使得数据的预测分布达到最大.应用贝叶斯定理得到贝叶斯因子进行模型选择,用于评价模体检验的统计显著性,这种方法克服了传统多项分布检验中构造检验统计量并计算其在零假设下确切分布的困难.选择JASPAR数据库中107个转录因子结合位点和100组随机模拟数据进行实验,采用皮尔逊积矩相关系数作为评价检验质量的一个标准,发现实验结果好于传统的模体检验的一些方法.     

CRISPR-OTE: Prediction of CRISPR On-Target Efficiency Based on Multi-Dimensional Feature Fusion

ObjectiveClustered Regularly Interspaced Short Palindromic Repeats (CRISPR) is a powerful genome editing technology. Guide RNA (gRNA) plays an essential guiding role in the CRISPR system by complementary base pairing with target DNA. Since the CRISPR targeting mechanism problem has not yet been fully resolved, it remains a challenge to predict gRNA on-target efficiency. Current gRNA design tools often lack efficient information extraction and cannot learn the target efficiency patterns thoroughly.Material and methodsIn this study, CRISPR-OTE is proposed to consider both multi-dimensional sequence information and important complementary prior knowledge based on a simple but effective framework. CRISPR-OTE consists of the local-contextual information branch and the prior knowledge branch. The local-contextual information branch extracts multi-dimensional sequence features from the DNA primary sequence by a parallel framework of Convolutional Neural Networks (CNN) and bidirectional Long Short-Term Memory networks (biLSTM). The prior knowledge branch selects the optimal subset of physicochemical features to provide the neural network with complementary knowledge, such as complex secondary structures. A simple feature fusion strategy is also adopted to fully utilize multi-modal data from the two branches.ResultsThe experimental results show that the optimal subset of physicochemical features (RNA secondary structure and melting temperature of 34nt target) can effectively improve the prediction performance. Additionally, combining multi-dimensional sequence features and multi-modal features can extract information more comprehensively. Through transfer learning, CRISPR-OTE trained on the CRISPR-Cpf1 system can also be successfully applied to the CRISPR-Cas9 system.ConclusionThe performance of CRISPR-OTE is superior to other methods in different CRISPR systems and species. Therefore, CRISPR-OTE is a simple on-target efficiency prediction framework with better accuracy and generalization performance.     

24-hour assessment of performance on a palmtop computer: validating a self-constructed test battery

A test battery was constructed on a palmtop computer for ambulatory purposes. This study explored whether the test battery could assess circadian rhythmicity under constant routine conditions. Performance, body temperature, and subjective sleepiness of 12 healthy subjects were measured. The test battery consisted of a sleepiness questionnaire and three performance tests: a vigilance detection test, a working memory test, and a choice-reaction time test. The subjects were divided into early-start and late-start groups and were subjected to the constant-routine protocol. All tests showed a trough in performance in the early morning around 07:00h and a peak in the evening between 21:00 and 23:00h. In addition, an afternoon decrement in performance was observed between 15:00 and 17:00h. On average, the circadian (peak-to-trough) variation of the performance variables amounted to 16.9%±1.7 SEM of the maximum across subjects. The late starters showed a larger impairment in performance during the morning than the early starters. This could be attributed to prior wakefulness. The characteristics of the performance rhythms found in this study replicate findings in several other studies carried out under constant routine conditions. In conclusion, the present test battery appeared to be a good tool for future assessment of performance under natural conditions.     

Internal estimation and controlled selection with applications to sheep

Summary This paper examines the relationship of economic weights, a _i, with a general economic value surface. It is inferred that the a _i may vary across the population, as they can depend on the mean vector for the characters of interest. It is shown how these ideas extend to provide simple mechanisms for controlled selection. The problem of estimation is raised, and it is suggested that the procedures can be efficiently implemented, even in small populations, by a system of internal parameter estimation. This makes the entire selection programme independent of externally generated estimates of genetic parameters.     

The Prior Distribution of the Minimum and Maximum Distance between Several Marker Loci and Quantitative Trait Loci

In order to control linkage experiments, exact formulas and approximations are derived for the minimum distance between quantitative trait loci and the nearest marker locus. The locations of the loci are assumed to be uniformly distributed over the genome. The locations of the marker loci may be known or unknown. The number and length of the chromosomes are arbitrary and therefore the results are applicable for all kinds of species. Analogous formulas are derived for the maximum distance between the quantitative trait loci and the nearest marker loci. For the probability of linkage more simple expressions are derived. The accuracy of the approximations is checked by a simulation.     

Empirical Bayes estimation for combinations of multivariate bioassays

This article presents a new empirical Bayes estimator (EBE) and a shrinkage estimator for determining the relative potency from several multivariate bioassays by incorporating prior information on the model parameters based on Jeffreys' rules. The EBE can account for any extra variability among the bioassays, and if this extra variability is 0, then the EBE reduces to the maximum likelihood estimator for combinations of multivariate bioassays. The shrinkage estimator turns out to be a compromise of the prior information and the estimator from each multivariate bioassay, with the weights depending on the prior variance.