Physics to the Rescue: Deep Non-Line-of-Sight Reconstruction for High-Speed Imaging.

Computational approach to imaging around the corner, or non-line-of-sight (NLOS) imaging, is becoming a reality thanks to major advances in imaging hardware and reconstruction algorithms. A recent development towards practical NLOS imaging, Nam et al. [1] demonstrated a high-speed non-confocal imaging system that operates at 5 Hz, 100x faster than the prior art. This enormous gain in acquisition rate, however, necessitates numerous approximations in light transport, breaking many existing NLOS reconstruction methods that assume an idealized image formation model. To bridge the gap, we present a novel deep model that incorporates the complementary physics priors of wave propagation and volume rendering into a neural network for high-quality and robust NLOS reconstruction. This orchestrated design regularizes the solution space by relaxing the image formation model, resulting in a deep model that generalizes well on real captures despite being exclusively trained on synthetic data. Further, we devise a unified learning framework that enables our model to be flexibly trained using diverse supervision signals, including target intensity images or even raw NLOS transient measurements. Once trained, our model renders both intensity and depth images at inference time in a single forward pass, capable of processing more than 5 captures per second on a high-end GPU. Through extensive qualitative and quantitative experiments, we show that our method outperforms prior physics and learning based approaches on both synthetic and real measurements. We anticipate that our method along with the fast capturing system will accelerate future development of NLOS imaging for real world applications that require high-speed imaging.

An approachable, flexible and practical machine learning workshop for biologists.

SUMMARY: The increasing prevalence and importance of machine learning in biological research have created a need for machine learning training resources tailored towards biological researchers. However, existing resources are often inaccessible, infeasible or inappropriate for biologists because they require significant computational and mathematical knowledge, demand an unrealistic time-investment or teach skills primarily for computational researchers. We created the Machine Learning for Biologists (ML4Bio) workshop, a short, intensive workshop that empowers biological researchers to comprehend machine learning applications and pursue machine learning collaborations in their own research. The ML4Bio workshop focuses on classification and was designed around three principles: (i) emphasizing preparedness over fluency or expertise, (ii) necessitating minimal coding and mathematical background and (iii) requiring low time investment. It incorporates active learning methods and custom open-source software that allows participants to explore machine learning workflows. After multiple sessions to improve workshop design, we performed a study on three workshop sessions. Despite some confusion around identifying subtle methodological flaws in machine learning workflows, participants generally reported that the workshop met their goals, provided them with valuable skills and knowledge and greatly increased their beliefs that they could engage in research that uses machine learning. ML4Bio is an educational tool for biological researchers, and its creation and evaluation provide valuable insight into tailoring educational resources for active researchers in different domains. AVAILABILITY AND IMPLEMENTATION: Workshop materials are available at https://github.com/carpentries-incubator/ml4bio-workshop and the ml4bio software is available at https://github.com/gitter-lab/ml4bio. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.

Modeling Analysis of Potential Target of Dolastatin 16 by Computational Virtual Screening.

Dolastatin 16 is a cyclic depsipeptide isolated from the marine invertebrates and cyanobacterium Lyngbya majuscula, however, its bioactivity has been a historical question. In this study, peptidyl-prolyl cis-trans isomerase FKBP1A (FKBP12) was predicted as a potential target of dolastatin 16 via PharmMapper as well as verified using chemical-protein interactome (CPI) and molecular docking. FKBP1A has been previously identified as a target for the natural polyketide FK506 (tacrolimus), an immune suppressor inhibiting the rejection of organ transplantation in clinical use. The comparison study via the reverse pharmacophore screening and molecular docking of dolastatin 16 and FK506 indicated the good consistency of analysis with the computational approach. As the results, the lowest binding energy of dolastatin 16-FKBP1A complex was -7.4 kcal/mol and FK506-FKBP1A complex was -8.7 kcal/mol. The ligand dolastatin 16 formed three hydrogen bonds vs. four of FK506, as well as seven hydrophobic interactions vs. six of FK506 within the active site residues. These functional residues are highly repetitive and consistent with previously reported active site of model of FK506-FKBP1A complex, and the pharmacophore model was shown feasibly matching with the molecular feature of dolastatin 16.

CNS angiogenesis and barriergenesis occur simultaneously.

The blood-brain barrier (BBB) plays a vital role in the central nervous system (CNS). A comprehensive understanding of BBB development has been hampered by difficulties in observing the differentiation of brain endothelial cells (BECs) in real-time. Here, we generated two transgenic zebrafish line, Tg(glut1b:mCherry) and Tg(plvap:EGFP), to serve as in vivo reporters of BBB development. We showed that barriergenesis (i.e. the induction of BEC differentiation) occurs immediately as endothelial tips cells migrate into the brain parenchyma. Using the Tg(glut1b:mCherry) transgenic line, we performed a genetic screen and identified a zebrafish mutant with a nonsense mutation in gpr124, a gene known to play a role in CNS angiogenesis and BBB development. We also showed that our transgenic plvap:EGFP line, a reporter of immature brain endothelium, is initially expressed in newly formed brain endothelial cells, but subsides during BBB maturation. Our results demonstrate the ability to visualize the in vivo differentiation of brain endothelial cells into the BBB phenotype and establish that CNS angiogenesis and barriergenesis occur simultaneously.