Immune-checkpoint blockade (ICB) has demonstrated efficacy in many tumor types, but predictors of responsiveness to anti-PD1 ICB are incompletely characterized. In this study, we analyzed a clinically annotated cohort of patients with melanoma (n = 144) treated with anti-PD1 ICB, with whole-exome and whole-transcriptome sequencing of pre-treatment tumors. We found that tumor mutational burden as a predictor of response was confounded by melanoma subtype, whereas multiple novel genomic and transcriptomic features predicted selective response, including features associated with MHC-I and MHC-II antigen presentation. Furthermore, previous anti-CTLA4 ICB exposure was associated with different predictors of response compared to tumors that were naive to ICB, suggesting selective immune effects of previous exposure to anti-CTLA4 ICB. Finally, we developed parsimonious models integrating clinical, genomic and transcriptomic features to predict intrinsic resistance to anti-PD1 ICB in individual tumors, with validation in smaller independent cohorts limited by the availability of comprehensive data. Broadly, we present a framework to discover predictive features and build models of ICB therapeutic response. Analysis of fully clinically annotated and sequenced melanoma tumor samples collected before anti-PD1 treatment suggests that determinants of response differ on the basis of previous anti-CTLA4 therapy, and that tumor mutational burden may not be a strong predictor of response across melanoma subtypes.

/pdf/integrative-molecular-and-clinical-modeling-of-clinical-29ou1qf1aa.pdf

Integrative molecular and clinical modeling of clinical outcomes to PD1 blockade in patients with metastatic melanoma

De novo protein design holds promise for creating small stable proteins with shapes customized to bind therapeutic targets. We describe a massively parallel approach for designing, manufacturing and screening mini-protein binders, integrating large-scale computational design, oligonucleotide synthesis, yeast display screening and next-generation sequencing. We designed and tested 22,660 mini-proteins of 37-43 residues that target influenza haemagglutinin and botulinum neurotoxin B, along with 6,286 control sequences to probe contributions to folding and binding, and identified 2,618 high-affinity binders. Comparison of the binding and non-binding design sets, which are two orders of magnitude larger than any previously investigated, enabled the evaluation and improvement of the computational model. Biophysical characterization of a subset of the binder designs showed that they are extremely stable and, unlike antibodies, do not lose activity after exposure to high temperatures. The designs elicit little or no immune response and provide potent prophylactic and therapeutic protection against influenza, even after extensive repeated dosing.

Massively parallel de novo protein design for targeted therapeutics

Data on the detailed clinical progression of COVID-19 in conjunction with epidemiological and virological characteristics are limited. In this case series, we describe the first 12 US patients confirmed to have COVID-19 from 20 January to 5 February 2020, including 4 patients described previously1,2,3. Respiratory, stool, serum and urine specimens were submitted for SARS-CoV-2 real-time reverse-transcription polymerase chain reaction (rRT-PCR) testing, viral culture and whole genome sequencing. Median age was 53 years (range: 21–68); 8 patients were male. Common symptoms at illness onset were cough (n = 8) and fever (n = 7). Patients had mild to moderately severe illness; seven were hospitalized and demonstrated clinical or laboratory signs of worsening during the second week of illness. No patients required mechanical ventilation and all recovered. All had SARS-CoV-2 RNA detected in respiratory specimens, typically for 2–3 weeks after illness onset. Lowest real-time PCR with reverse transcription cycle threshold values in the upper respiratory tract were often detected in the first week and SARS-CoV-2 was cultured from early respiratory specimens. These data provide insight into the natural history of SARS-CoV-2. Although infectiousness is unclear, highest viral RNA levels were identified in the first week of illness. Clinicians should anticipate that some patients may worsen in the second week of illness.

/pdf/clinical-and-virologic-characteristics-of-the-first-12-4e5rpez9b5.pdf

Clinical and virologic characteristics of the first 12 patients with coronavirus disease 2019 (COVID-19) in the United States.

Model-based reinforcement learning (MBRL) is widely seen as having the potential to be significantly more sample efficient than model-free RL. However, research in model-based RL has not been very standardized. It is fairly common for authors to experiment with self-designed environments, and there are several separate lines of research, which are sometimes closed-sourced or not reproducible. Accordingly, it is an open question how these various existing MBRL algorithms perform relative to each other. To facilitate research in MBRL, in this paper we gather a wide collection of MBRL algorithms and propose over 18 benchmarking environments specially designed for MBRL. We benchmark these algorithms with unified problem settings, including noisy environments. Beyond cataloguing performance, we explore and unify the underlying algorithmic differences across MBRL algorithms. We characterize three key research challenges for future MBRL research: the dynamics bottleneck, the planning horizon dilemma, and the early-termination dilemma. Finally, to maximally facilitate future research on MBRL, we open-source our benchmark in this http URL.

/pdf/benchmarking-model-based-reinforcement-learning-3o1aw85vqb.pdf

Benchmarking Model-Based Reinforcement Learning

The COVID-19 pandemic has highlighted that new diagnostic technologies are essential for controlling disease transmission. Here, we develop SHINE (Streamlined Highlighting of Infections to Navigate Epidemics), a sensitive and specific diagnostic tool that can detect SARS-CoV-2 RNA from unextracted samples. We identify the optimal conditions to allow RPA-based amplification and Cas13-based detection to occur in a single step, simplifying assay preparation and reducing run-time. We improve HUDSON to rapidly inactivate viruses in nasopharyngeal swabs and saliva in 10 min. SHINE’s results can be visualized with an in-tube fluorescent readout — reducing contamination risk as amplification reaction tubes remain sealed — and interpreted by a companion smartphone application. We validate SHINE on 50 nasopharyngeal patient samples, demonstrating 90% sensitivity and 100% specificity compared to RT-qPCR with a sample-to-answer time of 50 min. SHINE has the potential to be used outside of hospitals and clinical laboratories, greatly enhancing diagnostic capabilities. The COVID-19 pandemic has highlighted the need for user-friendly diagnostic techniques. Here, the authors present SHINE, a streamlined and optimised Cas13-based method with accompanying smartphone app for visual diagnosis.

/pdf/streamlined-inactivation-amplification-and-cas13-based-298ugoceoe.pdf

Streamlined inactivation, amplification, and Cas13-based detection of SARS-CoV-2

seaborn is a library for making statistical graphics in Python. It provides a high-level interface to matplotlib and integrates closely with pandas data structures. Functions in the seaborn library expose a declarative, dataset-oriented API that makes it easy to translate questions about data into graphics that can answer them. When given a dataset and a specification of the plot to make, seaborn automatically maps the data values to visual attributes such as color, size, or style, internally computes statistical transformations, and decorates the plot with informative axis labels and a legend. Many seaborn functions can generate figures with multiple panels that elicit comparisons between conditional subsets of data or across different pairings of variables in a dataset. seaborn is designed to be useful throughout the lifecycle of a scientific project. By producing complete graphics from a single function call with minimal arguments, seaborn facilitates rapid prototyping and exploratory data analysis. And by offering extensive options for customization, along with exposing the underlying matplotlib objects, it can be used to create polished, publication-quality figures.

Saulius Lukauskas

Papers

seaborn: Statistical data visualization

mwaskom/seaborn: v0.8.1 (September 2017)

mwaskom/seaborn: v0.9.0 (July 2018)

mwaskom/seaborn: v0.10.1 (April 2020)

mwaskom/seaborn: v0.10.0 (January 2020)