Showing papers by "Ron Weiss published in 2013"

Rapid, modular and reliable construction of complex mammalian gene circuits

Abstract: We developed a framework for quick and reliable construction of complex gene circuits for genetically engineering mammalian cells. Our hierarchical framework is based on a novel nucleotide addressing system for defining the position of each part in an overall circuit. With this framework, we demonstrate construction of synthetic gene circuits of up to 64 kb in size comprising 11 transcription units and 33 basic parts. We show robust gene expression control of multiple transcription units by small molecule inducers in human cells with transient transfection and stable chromosomal integration of these circuits. This framework enables development of complex gene circuits for engineering mammalian cells with unprecedented speed, reliability and scalability and should have broad applicability in a variety of areas including mammalian cell fermentation, cell fate reprogramming and cell-based assays.

Nonlinear latent factorization by embedding multiple user interests

Abstract: Classical matrix factorization approaches to collaborative filtering learn a latent vector for each user and each item, and recommendations are scored via the similarity between two such vectors, which are of the same dimension In this work, we are motivated by the intuition that a user is a much more complicated entity than any single item, and cannot be well described by the same representation Hence, the variety of a user's interests could be better captured by a more complex representation We propose to model the user with a richer set of functions, specifically via a set of latent vectors, where each vector captures one of the user's latent interests or tastes The overall recommendation model is then nonlinear where the matching score between a user and a given item is the maximum matching score over each of the user's latent interests with respect to the item's latent representation We describe a simple, general and efficient algorithm for learning such a model, and apply it to large scale, real-world datasets from YouTube and Google Music, where our approach outperforms existing techniques

Learning to rank recommendations with the k-order statistic loss

Abstract: Making recommendations by learning to rank is becoming an increasingly studied area. Approaches that use stochastic gradient descent scale well to large collaborative filtering datasets, and it has been shown how to approximately optimize the mean rank, or more recently the top of the ranked list. In this work we present a family of loss functions, the k-order statistic loss, that includes these previous approaches as special cases, and also derives new ones that we show to be useful. In particular, we present (i) a new variant that more accurately optimizes precision at k, and (ii) a novel procedure of optimizing the mean maximum rank, which we hypothesize is useful to more accurately cover all of the user's tastes. The general approach works by sampling N positive items, ordering them by the score assigned by the model, and then weighting the example as a function of this ordered set. Our approach is studied in two real-world systems, Google Music and YouTube video recommendations, where we obtain improvements for computable metrics, and in the YouTube case, increased user click through and watch duration when deployed live on www.youtube.com.

Microbead-based biomimetic synthetic neighbors enhance survival and function of rat pancreatic β-cells.

Abstract: Diabetes is caused by the loss or dysfunction of insulin-secreting β-cells in the pancreas. β-cells reduce their mass and lose insulin-producing ability in vitro, likely due to insufficient cell-cell and cell-extracellular matrix (ECM) interactions as β-cells lose their native microenvironment. Herein, we built an ex-vivo cell microenvironment by culturing primary β-cells in direct contact with ‘synthetic neighbors', cell-sized soft polymer microbeads that were modified with cell-cell signaling factors as well as components from pancreatic-tissue-specific ECMs. This biomimetic 3D microenvironment was able to promote native cell-cell and cell-ECM interactions. We obtained sustained maintenance of β-cell function in vitro enhanced cell viability from the few days usually observed in 2D culture to periods exceeding three weeks, with enhanced β-cell stability and insulin production. Our approach can be extended to create a general 3D culture platform for other cell types.

Affinity Weighted Embedding

Abstract: Supervised (linear) embedding models like Wsabie and PSI have proven successful at ranking, recommendation and annotation tasks. However, despite being scalable to large datasets they do not take full advantage of the extra data due to their linear nature, and typically underfit. We propose a new class of models which aim to provide improved performance while retaining many of the benefits of the existing class of embedding models. Our new approach works by iteratively learning a linear embedding model where the next iteration's features and labels are reweighted as a function of the previous iteration. We describe several variants of the family, and give some initial results.