Depth of Radiographic Response and Time to Tumor Regrowth Predicts Overall Survival Following Anti-VEGF Therapy in Recurrent Glioblastoma.

PURPOSE: Antiangiogenic therapies are known to cause high radiographic response rates due to reduction in vascular permeability resulting in a lower degree of contrast extravasation. In this study, we investigate the prognostic ability for model-derived parameters describing enhancing tumor volumetric dynamics to predict survival in recurrent glioblastoma treated with antiangiogenic therapy. EXPERIMENTAL DESIGN: N = 276 patients in two phase II trials were used as training data, including bevacizumab ± irinotecan (NCT00345163) and cabozantinib (NCT00704288), and N = 74 patients in the bevacizumab arm of a phase III trial (NCT02511405) were used for validation. Enhancing volumes were estimated using T1 subtraction maps, and a biexponential model was used to estimate regrowth (g) and regression (d) rates, time to tumor regrowth (TTG), and the depth of response (DpR). Response characteristics were compared to diffusion MR phenotypes previously shown to predict survival. RESULTS: Optimized thresholds occurred at g = 0.07 months-1 (phase II: HR = 0.2579, P = 5 × 10-20; phase III: HR = 0.2197, P = 5 × 10-5); d = 0.11 months-1 (HR = 0.3365, P < 0.0001; HR = 0.3675, P = 0.0113); TTG = 3.8 months (HR = 0.2702, P = 6 × 10-17; HR = 0.2061, P = 2 × 10-5); and DpR = 11.3% (HR = 0.6326, P = 0.0028; HR = 0.4785, P = 0.0206). Multivariable Cox regression controlling for age and baseline tumor volume confirmed these factors as significant predictors of survival. Patients with a favorable pretreatment diffusion MRI phenotype had a significantly longer TTG and slower regrowth. CONCLUSIONS: Recurrent glioblastoma patients with a large, durable radiographic response to antiangiogenic agents have significantly longer survival. This information is useful for interpreting activity of antiangiogenic agents in recurrent glioblastoma.

MILCDock: Machine Learning Enhanced Consensus Docking for Virtual Screening in Drug Discovery.

Molecular docking tools are regularly used to computationally identify new molecules in virtual screening for drug discovery. However, docking tools suffer from inaccurate scoring functions with widely varying performance on different proteins. To enable more accurate ranking of active over inactive ligands in virtual screening, we created a machine learning consensus docking tool, MILCDock, that uses predictions from five traditional molecular docking tools to predict the probability a ligand binds to a protein. MILCDock was trained and tested on data from both the DUD-E and LIT-PCBA docking datasets and shows improved performance over traditional molecular docking tools and other consensus docking methods on the DUD-E dataset. LIT-PCBA targets proved to be difficult for all methods tested. We also find that DUD-E data, although biased, can be effective in training machine learning tools if care is taken to avoid DUD-E's biases during training.

Training undergraduate research assistants with an outcome-oriented and skill-based mentoring strategy.

Effective mentoring of undergraduate students is a growing requirement for the promotion of faculty at many universities. It is often challenging for young investigators to define a successful mentoring strategy, partially due to the absence of a broadly accepted definition of what mentoring should entail. To overcome this, an outcome-oriented mentoring framework was developed and used with more than 25 students over three years. It was found that a systematic mentoring approach can help students quickly realize their scientific potential and result in meaningful contributions to science. This report especially shows how the Critical Assessment of Protein Structure Prediction (CASP14) challenge was used to amplify student research efforts. As a result of this challenge, multiple publications, presentations and scholarships were awarded to the participating students. The mentoring framework continues to see much success in allowing undergraduate students, including students from underrepresented groups, to foster scientific talent and make meaningful contributions to the scientific community.

The whole is greater than its parts: ensembling improves protein contact prediction.

The prediction of amino acid contacts from protein sequence is an important problem, as protein contacts are a vital step towards the prediction of folded protein structures. We propose that a powerful concept from deep learning, called ensembling, can increase the accuracy of protein contact predictions by combining the outputs of different neural network models. We show that ensembling the predictions made by different groups at the recent Critical Assessment of Protein Structure Prediction (CASP13) outperforms all individual groups. Further, we show that contacts derived from the distance predictions of three additional deep neural networks-AlphaFold, trRosetta, and ProSPr-can be substantially improved by ensembling all three networks. We also show that ensembling these recent deep neural networks with the best CASP13 group creates a superior contact prediction tool. Finally, we demonstrate that two ensembled networks can successfully differentiate between the folds of two highly homologous sequences. In order to build further on these findings, we propose the creation of a better protein contact benchmark set and additional open-source contact prediction methods.

Engineering and application of a biosensor with focused ligand specificity.

Cell factories converting bio-based precursors to chemicals present an attractive avenue to a sustainable economy, yet screening of genetically diverse strain libraries to identify the best-performing whole-cell biocatalysts is a low-throughput endeavor. For this reason, transcriptional biosensors attract attention as they allow the screening of vast libraries when used in combination with fluorescence-activated cell sorting (FACS). However, broad ligand specificity of transcriptional regulators (TRs) often prohibits the development of such ultra-high-throughput screens. Here, we solve the structure of the TR LysG of Corynebacterium glutamicum, which detects all three basic amino acids. Based on this information, we follow a semi-rational engineering approach using a FACS-based screening/counterscreening strategy to generate an L-lysine insensitive LysG-based biosensor. This biosensor can be used to isolate L-histidine-producing strains by FACS, showing that TR engineering towards a more focused ligand spectrum can expand the scope of application of such metabolite sensors.