High-density and high coverage composite mapping of repetitive atrial activation patterns.

BACKGROUND: Repetitive atrial activation patterns (RAAPs) during atrial fibrillation (AF) may be associated with localized mechanisms that maintain AF. Current electro-anatomical mapping systems are unsuitable for analyzing RAAPs due to the trade-off between spatial coverage and electrode density in clinical catheters. This work proposes a technique to overcome this trade-off by constructing composite maps from spatially overlapping sequential recordings. METHODS: High-density epicardial contact mapping was performed during open-chest surgery in goats (n=16, left and right atria) with 3 or 22 weeks of sustained AF (249-electrode array, electrode distance 2.4 mm). A dataset mimicking sequential recordings was generated by segmenting the grid into four spatially overlapping regions (each region 6.5 cm2, 48±10% overlap) without temporal overlap. RAAPs were detected in each region using recurrence plots of activation times. RAAPs in two different regions were joined in case of RAAP cross-recurrence between overlapping electrodes. We quantified the reconstruction success rate and quality of the composite maps. RESULTS: Of 1021 RAAPs found in the full mapping array (32±13 per recording), 328 spatiotemporally stable RAAPs were analyzed. 247 composite maps were generated (75% success) with a quality of 0.86±0.21 (Pearson correlation). Success was significantly affected by the RAAP area. Quality was weakly correlated with the number of repetitions of RAAPs (r=0.13, p<0.05) and not affected by the atrial side (left or right) or AF duration (3 or 22 weeks of AF). CONCLUSIONS: Constructing composite maps by combining spatially overlapping sequential recordings is feasible. Interpretation of these maps can play a central role in ablation planning.

State Space Embedding of Atrial Electrograms to Detect Repetitive Conduction Patterns During Atrial Fibrillation.

Repetitive atrial conduction patterns are often observed during human atrial fibrillation (AF). Repetitive patterns may be associated with AF drivers such as focal and micro-reentrant mechanisms. Therefore, tools for repetitive activity detection are of great interest as they may allow to identify the leading electrophysiological AF mechanism in an individual patient. Recurrence plots (RP) are efficient tools for repetitive activity visualization. Construction of an RP requires embedding of epicardial atrial electrograms into a phase space. In this study, we compared the conventional Takens' embedding approach and three novel approaches based on a priori AF cycle length (AFCL) information. Approaches were bench-marked based on the similarity of the RPs they produce with a previously proposed technique, the sensitivity and specificity to detect the repetitive patterns, as well as the capability to estimate overall repetitive pattern prevalence. All techniques were applied to high-density epicardial direct contact mapping recordings in AF patients with paroxysmal AF (n=12) and persistent AF (n=9). Compared to a reference method the proposed novel techniques achieved significantly higher similarity and sensitivity values (p<0.01) than conventional embedding, in both paroxysmal and persistent patients. Moreover, estimated prevalences were robust against the various degrees of AF complexity present in the recordings.Clinical relevance- This study presents three novel approaches for detection of repetitive patterns of conduction during AF in atrial direct contact recordings, which may aid in the identification of the leading AF mechanism in an individual patient.

A Convolutional Deep Clustering Framework for Gene Expression Time Series.

The functional or regulatory processes within the cell are explicitly governed by the expression levels of a subset of its genes. Gene expression time series captures activities of individual genes over time and aids revealing underlying cellular dynamics. An important step in high-throughput gene expression time series experiment is clustering genes based on their temporal expression patterns and is conventionally achieved by unsupervised machine learning techniques. However, most of the clustering techniques either suffer from the short length of gene expression time series or ignore temporal structure of the data. In this work, we propose DeepTrust, a novel deep learning-based framework for gene expression time series clustering which can overcome these issues. DeepTrust initially transforms time series data into images to obtain richer data representations. Afterwards, a deep convolutional clustering algorithm is applied on the constructed images. Analyses on both simulated and biological data sets exhibit the efficiency of this new framework, compared to widely used clustering techniques. We also utilize enrichment analyses to illustrate the biological plausibility of the clusters detected by DeepTrust. Our code and data are available from http://github.com/tanlab/DeepTrust.

Drug response prediction by ensemble learning and drug-induced gene expression signatures.

Chemotherapeutic response of cancer cells to a given compound is one of the most fundamental information one requires to design anti-cancer drugs. Recently, considerable amount of drug-induced gene expression data has become publicly available, in addition to cytotoxicity databases. These large sets of data provided an opportunity to apply machine learning methods to predict drug activity. However, due to the complexity of cancer drug mechanisms, none of the existing methods is perfect. In this paper, we propose a novel ensemble learning method to predict drug response. In addition, we attempt to use the drug screen data together with two novel signatures produced from the drug-induced gene expression profiles of cancer cell lines. Finally, we evaluate predictions by in vitro experiments in addition to the tests on data sets. The predictions of the methods, the signatures and the software are available from http://mtan.etu.edu.tr/drug-response-prediction/.