No abstract

The current dominant paradigm for imitation learning relies on strong supervision of expert actions to learn both what and how to imitate. We pursue an alternative paradigm wherein an agent first explores the world without any expert supervision and then distills its experience into a goal-conditioned skill policy with a novel forward consistency loss. In our framework, the role of the expert is only to communicate the goals (i.e., what to imitate) during inference. The learned policy is then employed to mimic the expert (i.e., how to imitate) after seeing just a sequence of images demonstrating the desired task. Our method is "zero-shot" in the sense that the agent never has access to expert actions during training or for the task demonstration at inference. We evaluate our zero-shot imitator in two real-world settings: complex rope manipulation with a Baxter robot and navigation in previously unseen office environments with a TurtleBot. Through further experiments in VizDoom simulation, we provide evidence that better mechanisms for exploration lead to learning a more capable policy which in turn improves end task performance. Videos, models, and more details are available at https://pathak22.github.io/zeroshot-imitation/. * Denotes equal contribution.

Background Copy number alterations (CNAs), due to their large impact on the genome, have been an important contributing factor to oncogenesis and metastasis. Detecting genomic alterations from the shallow-sequencing data of a low-purity tumor sample remains a challenging task. Results We introduce Accucopy, a method to infer total copy numbers (TCNs) and allele-specific copy numbers (ASCNs) from challenging low-purity and low-coverage tumor samples. Accucopy adopts many robust statistical techniques such as kernel smoothing of coverage differentiation information to discern signals from noise and combines ideas from time-series analysis and the signal-processing field to derive a range of estimates for the period in a histogram of coverage differentiation information. Statistical learning models such as the tiered Gaussian mixture model, the expectation–maximization algorithm, and sparse Bayesian learning were customized and built into the model. Accucopy is implemented in C++ /Rust, packaged in a docker image, and supports non-human samples, more at http://www.yfish.org/software/. Conclusions We describe Accucopy, a method that can predict both TCNs and ASCNs from low-coverage low-purity tumor sequencing data. Through comparative analyses in both simulated and real-sequencing samples, we demonstrate that Accucopy is more accurate than Sclust, ABSOLUTE, and Sequenza.

The outcomes of FLT3-ITD acute myeloid leukaemia (AML) have been improved since the approval of FLT3 inhibitors (FLT3i). However, approximately 30-50% of patients exhibit primary resistance (PR) to FLT3i with poorly defined mechanisms, posing a pressing clinical unmet need. Here, we identify C/EBPα activation as a top PR feature by analyzing data from primary AML patient samples in Vizome. C/EBPα activation limit FLT3i efficacy, while its inactivation synergistically enhances FLT3i action in cellular and female animal models. We then perform an in silico screen and identify that guanfacine, an antihypertensive medication, mimics C/EBPα inactivation. Furthermore, guanfacine exerts a synergistic effect with FLT3i in vitro and in vivo. Finally, we ascertain the role of C/EBPα activation in PR in an independent cohort of FLT3-ITD patients. These findings highlight C/EBPα activation as a targetable PR mechanism and support clinical studies aimed at testing the combination of guanfacine with FLT3i in overcoming PR and enhancing the efficacy of FLT3i therapy.