The applicability of recurrent neural networks for biological sequence analysis

Selection of machine learning techniques requires a certain sensitivity to the requirements of the problem. In particular, the problem can be made more tractable by deliberately using algorithms that are biased toward solutions of the requisite kind. In this paper, we argue that recurrent neural networks have a natural bias toward a problem domain of which biological sequence analysis tasks are a subset. We use experiments with synthetic data to illustrate this bias. We then demonstrate that this bias can be exploitable using a data set of protein sequences containing several classes of subcellular localization targeting peptides. The results show that, compared with feed forward, recurrent neural networks will generally perform better on sequence analysis tasks. Furthermore, as the patterns within the sequence become more ambiguous, the choice of specific recurrent architecture becomes more critical.

Effects of a nurse-led, clinic and home-based intervention on recurrent hospital use in chronic heart failure

Background: Few studies have examined the potential benefits of specialist nurse-led programs of care involving home and clinic-based follow-up to optimise the post-discharge management of chronic heart failure (CHF). Objective: To determine the effectiveness of a hybrid program of clinic plus home-based intervention (C+HBI) in reducing recurrent hospitalisation in CHF patients. Methods: CHF patients with evidence of left ventricular systolic dysfunction admitted to two hospitals in Northern England were assigned to a C+HBI lasting 6 months post-discharge (n=58) or to usual, post-discharge care (UC: n=48) via a cluster randomization protocol. The co-primary endpoints were death or unplanned readmission (event-free survival) and rate of recurrent, all-cause readmission within 6 months of hospital discharge. Results: During study follow-up, more UC patients had an unplanned readmission for any cause (44% vs. 22%: P=0.0191 OR 1.95 95% CI 1.10-3.48) whilst 7 (15%) versus 5 (9%) UC and C+HBI patients, respectively, died (P=NS). Overall, 15 (26%) C+HBI versus 21 (44%) UC patients experienced a primary endpoint. C+HBI was associated with a non-significant, 45% reduction in the risk of death or readmission when adjusting for potential confounders (RR 0.55, 95% CI 0.28-1.08: P=0.08). Overall, C+HBI patients accumulated significantly fewer unplanned readmissions (15 vs. 45: P

En bloc excision in malignant tumors of the lacrimal drainage apparatus

Purpose: To describe the surgical technique and results of en bloc excision in a series of patients with extensive malignant tumors of the lacrimal drainage apparatus (LDA). Methods: This was a noncomparative, retrospective chart review of the clinical and pathologic findings of 11 patients presenting with a malignant tumor affecting the LDA who underwent en bloc excision of the lacrimal system. Results: Of the 11 patients, 7 were male. The mean age at presentation was 58 years (range, 39 to 81 years), and all cases were unilateral. Histopathology revealed 4 squamous cell carcinomas, 3 transitional cell carcinomas, 2 mucoepidermoid carcinomas, and 2 melanomas. Epiphora and a mass were the most common presentations. An external lesion could be identified in 4 cases. Irrigation of the lacrimal system revealed nasolacrimal duct obstruction in 2 cases and common canaliculus obstruction in another 2 patients. The entire LDA and surrounding bony tissues were excised through a lateral rhinotomy approach. Adjuvant radiotherapy was given in 4 cases. Nine patients remain alive and well after a mean follow-up of 2 years (range, 6 months to 7 years). Three cases showed distant disease and 2 patients died of metastatic melanoma involvement. Conclusions: The use of en bloc excision as a radical treatment to remove the complete LDA and surrounding bony structures affords good local tumor control and may provide the best opportunity for enhanced patient survival.

Supportive care needs of people with brain tumours and their carers

Goals of work: The diagnosis and treatment of a brain tumour may result in long-term changes in a patient's functional and social abilities and/or in a greatly reduced life span. A qualitative investigation was conducted to examine the supportive care needs of patients with brain tumour and their carers. Materials and methods: Overall, 18 patients and 18 carers participated in focus groups or telephone interviews, following a structured interview guide to elicit supportive care services of importance to these patients and carers. Main results: Six major themes were identified using the framework analysis method, including needs for information and coping with uncertainty, practical support, support to return to pretreatment responsibilities or prepare for long-term care, support to deal with social isolation and organize respite care, support to overcome stigma/discrimination and support to discuss potentially reduced life expectancy. Conclusions: Five recommendations to improve service delivery include: assignment of a dedicated member of the care team or case manager; proactive dissemination of information, education and psychosocial support; access to objective assessment of neuropsychological functioning; facilitating easier access to welfare payments; and services facilitating communication about difficult illness-related topics. Provision of services along these recommendations could improve supportive care of brain tumour patients and their carers.

Molecular classification of cutaneous malignant melanoma by gene expression profiling

The most common human cancers are malignant neoplasms of the skin(1,2). Incidence of cutaneous melanoma is rising especially steeply, with minimal progress in non-surgical treatment of advanced disease(3,4). Despite significant effort to identify independent predictors of melanoma outcome, no accepted histopathological, molecular or immunohistochemical marker defines subsets of this neoplasm(2,3). Accordingly, though melanoma is thought to present with different 'taxonomic' forms, these are considered part of a continuous spectrum rather than discrete entities(2). Here we report the discovery of a subset of melanomas identified by mathematical analysis of gene expression in a series of samples. Remarkably, many genes underlying the classification of this subset are differentially regulated in invasive melanomas that form primitive tubular networks in vitro, a feature of some highly aggressive metastatic melanomas(5). Global transcript analysis can identify unrecognized subtypes of cutaneous melanoma and predict experimentally verifiable phenotypic characteristics that may be of importance to disease progression.