We present a new multi-objective optimization approach for synthesizing interpretations that 'explain' the behavior of black-box machine learning models. Constructing human-understandable interpretations for black-box models often requires balancing conflicting objectives. A simple interpretation may be easier to understand for humans while being less precise in its predictions vis-a-vis a complex interpretation. Existing methods for synthesizing interpretations use a single objective function and are often optimized for a single class of interpretations. In contrast, we provide a more general and multi-objective synthesis framework that allows users to choose (1) the class of syntactic templates from which an interpretation should be synthesized, and (2) quantitative measures on both the correctness and explainability of an interpretation. For a given black-box, our approach yields a set of Pareto-optimal interpretations with respect to the correctness and explainability measures. We show that the underlying multi-objective optimization problem can be solved via a reduction to quantitative constraint solving, such as weighted maximum satisfiability. To demonstrate the benefits of our approach, we have applied it to synthesize interpretations for black-box neural-network classifiers. Our experiments show that there often exists a rich and varied set of choices for interpretations that are missed by existing approaches.

Following severe injuries that result in disorders of consciousness, recovery can occur over many months or years post-injury. While post-injury synaptogenesis, axonal sprouting and functional reorganization are known to occur, the network-level processes underlying recovery are poorly understood. Here, we test a network-level functional rerouting hypothesis in recovery of patients with disorders of consciousness following severe brain injury. This hypothesis states that the brain recovers from injury by restoring normal functional connections via alternate structural pathways that circumvent impaired white matter connections. The so-called network diffusion model, which relates an individual's structural and functional connectomes by assuming that functional activation diffuses along structural pathways, is used here to capture this functional rerouting. We jointly examined functional and structural connectomes extracted from MRIs of 12 healthy and 16 brain-injured subjects. Connectome properties were quantified via graph theoretic measures and network diffusion model parameters. While a few graph metrics showed groupwise differences, they did not correlate with patients' level of consciousness as measured by the Coma Recovery Scale - Revised. There was, however, a strong and significant partial Pearson's correlation (accounting for age and years post-injury) between level of consciousness and network diffusion model propagation time (r = 0.76, p < 0.05, corrected), i.e. the time functional activation spends traversing the structural network. We concluded that functional rerouting via alternate (and less efficient) pathways leads to increases in network diffusion model propagation time. Simulations of injury and recovery in healthy connectomes confirmed these results. This work establishes the feasibility for using the network diffusion model to capture network-level mechanisms in recovery of consciousness after severe brain injury.

Computer tomography (CT) imaging plays an important role in cancer detection and quantitative assessment in clinical trials. High-resolution imaging studies on large cohorts of patients generate vast data sets, which are infeasible to analyze through manual interpretation. In this article we describe a comprehensive architecture for computer-aided detection (CAD) and surveillance on lung nodules in CT images. Central to this architecture are the analytic components: an automated nodule detection system, nodule tracking capabilities and volume measurement, which are integrated within a data management system that includes mechanisms for receiving and archiving images, a database for storing quantitative nodule measurements and visualization, and reporting tools. We describe two studies to evaluate CAD technology within this architecture, and the potential application in large clinical trials. The first study involves performance assessment of an automated nodule detection system and its ability to increase radiologist sensitivity when used to provide a second opinion. The second study investigates nodule volume measurements on CT made using a semi-automated technique and shows that volumetric analysis yields significantly different tumor response classifications than a 2D diameter approach. These studies demonstrate the potential of automated CAD tools to assist in quantitative image analysis for clinical trials.

Background:Lymphedema-cholestasis syndrome (LCS; Aagenaes syndrome) is a rare autosomal recessive disorder, characterized by 1) neonatal intrahepatic cholestasis, often lessening and becoming intermittent with age, and 2) severe chronic lymphedema, mainly

Aims

Modulation of DNA base excision repair (BER) has the potential to enhance response to chemotherapy and improve outcomes in tumours such as melanoma and glioma. APE1, a critical protein in BER that processes potentially cytotoxic abasic sites (AP sites), is a promising new target in cancer. In the current study, we aimed to develop small molecule inhibitors of APE1 for cancer therapy.

Methods

An industry-standard high throughput virtual screening strategy was adopted. The Sybyl8.0 (Tripos, St Louis, MO, USA) molecular modelling software suite was used to build inhibitor templates. Similarity searching strategies were then applied using ROCS 2.3 (Open Eye Scientific, Santa Fe, NM, USA) to extract pharmacophorically related subsets of compounds from a chemically diverse database of 2.6 million compounds. The compounds in these subsets were subjected to docking against the active site of the APE1 model, using the genetic algorithm-based programme GOLD2.7 (CCDC, Cambridge, UK). Predicted ligand poses were ranked on the basis of several scoring functions. The top virtual hits with promising pharmaceutical properties underwent detailed in vitro analyses using fluorescence-based APE1 cleavage assays and counter screened using endonuclease IV cleavage assays, fluorescence quenching assays and radiolabelled oligonucleotide assays. Biochemical APE1 inhibitors were then subjected to detailed cytotoxicity analyses.

Results

Several specific APE1 inhibitors were isolated by this approach. The IC(50) for APE1 inhibition ranged between 30 nM and 50 μM. We demonstrated that APE1 inhibitors lead to accumulation of AP sites in genomic DNA and potentiated the cytotoxicity of alkylating agents in melanoma and glioma cell lines.

Conclusions

Our study provides evidence that APE1 is an emerging drug target and could have therapeutic application in patients with melanoma and glioma.

Drug-resistant tuberculosis (DR-TB) is a growing public health problem, and for the first time in decades, new drugs for the treatment of this disease have been developed. These new drugs have prompted strengthened efforts in DR-TB clinical trials research, and there are now multiple ongoing and planned DR-TB clinical trials. To facilitate comparability and maximise policy impact, a common set of core research definitions is needed, and this paper presents a core set of efficacy and safety definitions as well as other important considerations in DR-TB clinical trials work. To elaborate these definitions, a search of clinical trials registries, published manuscripts and conference proceedings was undertaken to identify groups conducting trials of new regimens for the treatment of DR-TB. Individuals from these groups developed the core set of definitions presented here. Further work is needed to validate and assess the utility of these definitions but they represent an important first step to ensure there is comparability in clinical trials on multidrug-resistant TB.