26 research outputs found
Abstract LB-271: SplashRNA, a sequential classification algorithm for ultra-potent RNAi
No full textAbstract
We present SplashRNA, a sequential classifier - analogous to face detection algorithms - to predict ultra-potent microRNA-based short hairpin RNAs (shRNAs) for virtually any gene. Trained on existing and novel large-scale datasets, SplashRNA outperforms previous algorithms and reliably predicts the most efficient shRNAs for a given gene. Combined with the optimized miR-E backbone, >90% of high-scoring SplashRNA predictions trigger >85% protein knockdown when expressed from a single genomic integration. SplashRNA can significantly improve the accuracy of loss-of-function genetics studies and facilitates the generation of compact shRNA libraries. The open source SplashRNA platform completes the RNAi toolkit to harness microRNA-based shRNAs for robust single-gene and multiplexed inducible and reversible target inhibition.
Citation Format: Raphael Pelossof, Lauren Fairchild, Christina S. Leslie, Christof Fellmann. SplashRNA, a sequential classification algorithm for ultra-potent RNAi [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2017; 2017 Apr 1-5; Washington, DC. Philadelphia (PA): AACR; Cancer Res 2017;77(13 Suppl):Abstract nr LB-271. doi:10.1158/1538-7445.AM2017-LB-271</jats:p
Rapid Learning with Stochastic Focus of Attention
No full textWe present a method to determine when to stop the evaluation of a decision-making process. The method determines to stop the evaluation process when the result of the full evaluation is obvious. This trait is highly desirable for margin-based Machine Learning algorithms where a classifier traditionally evaluates all the features for every example. However, some examples are easier to classify than others, a phenomenon which is characterized by the event when most of the features agree on the class of an example. By stopping the feature evaluation when encountering an easy to classify example, a margin-based Machine Learning algorithm can achieve substantial reduction in running times. To determine when to stop the feature evaluation, we develop a set of novel sequential tests, the Sequential Thresholded Sum Tests (STST). These tests stop the partial evaluation of the sum when the result of the full summation is guaranteed with high probability. By making different assumptions on the data and the features different tests arise. In general we look at the feature evaluation process as a random walk and apply different Brownian motion early stopping inequalities to determine when to stop the walk. From these inequalities we derive a family of stopping thresholds for sequential feature evaluations under different assumptions. We demonstrate the effectiveness of the different STST by speeding up several Online Learning algorithms on synthetic and real data
Recommended from our members
Curtailed Online Boosting
No full textThe purpose of this work is to lower the average number of features that are evaluated by an online algorithm. This is achieved by merging Sequential Analysis and Online Learning. Many online algorithms use the example's margin to decide whether the model should be updated. Usually, the algorithm's model is updated when the margin is smaller than a certain threshold. The evaluation of the margin for each example requires the algorithm to evaluate all the model's features. Sequential Analysis allows us to early stop the computation of the margin when uninformative examples are encountered. It is desirable to save computation on uninformative examples since they will have very little impact on the final model. We show the successful speedup of Online Boosting while maintaining accuracy on a synthetic and the MNIST data sets
An SVM learning approach to robotic grasping
No full textAbstract — Finding appropriate stable grasps for a hand (either robotic or human) on an arbitrary object has proved to be a challenging and difficult problem. The space of grasping parameters coupled with the degrees-of-freedom and geometry of the object to be grasped creates a high-dimensional, non- smooth manifold. Traditional search methods applied to this manifold are typically not powerful enough to find appropriate stable grasping solutions, let alone optimal grasps. We address this issue in this paper, which attempts to find optimal grasps of objects using a grasping simulator. Our unique approach to the problem involves a combination of numerical methods to recover parts of the grasp quality surface with any robotic hand, and contemporary machine learning methods to interpolate that surface, in order to find the optimal grasp. I
Grasp planning via decomposition trees
No full textAbstract — Planning realizable and stable grasps on 3D objects is crucial for many robotics applications, but grasp planners often ignore the relative sizes of the robotic hand and the object being grasped or do not account for physical joint and positioning limitations. We present a grasp planner that can consider the full range of parameters of a real hand and an arbitrary object, including physical and material properties as well as environmental obstacles and forces, and produce an output grasp that can be immediately executed. We do this by decomposing a 3D model into a superquadric ‘decomposition tree ’ which we use to prune the intractably large space of possible grasps into a subspace that is likely to contain many good grasps. This subspace can be sampled and evaluated in GraspIt!, our 3D grasping simulator, to find a set of highly stable grasps, all of which are physically realizable. We show grasp results on various models using a Barrett hand
An integrated model for detecting significant chromatin interactions from high-resolution Hi-C data
No full textAbstractHere we present HiC-DC, a principled method to estimate the statistical significance (P values) of chromatin interactions from Hi-C experiments. HiC-DC uses hurdle negative binomial regression account for systematic sources of variation in Hi-C read counts—for example, distance-dependent random polymer ligation and GC content and mappability bias—and model zero inflation and overdispersion. Applied to high-resolution Hi-C data in a lymphoblastoid cell line, HiC-DC detects significant interactions at the sub-topologically associating domain level, identifying potential structural and regulatory interactions supported by CTCF binding sites, DNase accessibility, and/or active histone marks. CTCF-associated interactions are most strongly enriched in the middle genomic distance range (∼700 kb–1.5 Mb), while interactions involving actively marked DNase accessible elements are enriched both at short (<500 kb) and longer (>1.5 Mb) genomic distances. There is a striking enrichment of longer-range interactions connecting replication-dependent histone genes on chromosome 6, potentially representing the chromatin architecture at the histone locus body.</jats:p
