Design of target specific peptide inhibitors using generative deep learning and molecular dynamics simulations.

We introduce a computational approach for the design of target-specific peptides. Our method integrates a Gated Recurrent Unit-based Variational Autoencoder with Rosetta FlexPepDock for peptide sequence generation and binding affinity assessment. Subsequently, molecular dynamics simulations are employed to narrow down the selection of peptides for experimental assays. We apply this computational strategy to design peptide inhibitors that specifically target ß-catenin and NF-κB essential modulator. Among the twelve ß-catenin inhibitors, six exhibit improved binding affinity compared to the parent peptide. Notably, the best C-terminal peptide binds ß-catenin with an IC50 of 0.010 ± 0.06 µM, which is 15-fold better than the parent peptide. For NF-κB essential modulator, two of the four tested peptides display substantially enhanced binding compared to the parent peptide. Collectively, this study underscores the successful integration of deep learning and structure-based modeling and simulation for target specific peptide design.

Is Additive Manufacturing an Environmentally and Economically Preferred Alternative for Mass Production?

The manufacturing sector accounts for a large percentage of global energy use and greenhouse gas emissions, and there is growing interest in the potential of additive manufacturing (AM) to reduce the sector's environmental impacts. Across multiple industries, AM has been used to reduce material use in final parts by 35-80%, and recent publications have predicted that AM will enable the fabrication of customized products locally and on-demand, reducing shipping and material waste. In many contexts, however, AM is not a viable alternative to traditional manufacturing methods due to its high production costs. And in high-volume mass production, AM can lead to increased energy use and material waste, worsening environmental impacts compared to traditional production methods. Whether AM is an environmentally and economically preferred alternative to traditional manufacturing depends on several hidden aspects of AM that are not readily apparent when comparing final products, including energy-intensive and expensive material feedstocks, excessive material waste during production, high machine costs, and slow rates of production. We systematically review comparative studies of the environmental impacts and costs of AM in contrast with traditional manufacturing methods and identify the conditions under which AM is the environmentally and economically preferred alternative. We find that AM has lower production costs and environmental impacts when production volumes are relatively low (below ∼1,000 per year for environmental impacts and below 42-87,000 per year for costs, depending on the AM process and part geometry) or the parts are small and would have high material waste if traditionally manufactured. In cases when the geometric freedom of AM enables performance improvements that reduce environmental impacts and costs during a product's use phase, these can counteract the higher production impacts of AM, making it the preferred alternative at larger production volumes. AM's ability to be environmentally and economically beneficial for mass manufacturing in a wider variety of contexts is dependent on reducing the cost and energy intensity of material feedstock production, eliminating the need for support structures, raising production speeds, and reducing per unit machine costs. These challenges are not primarily caused by economies of scale, and therefore, they are not likely to be addressed by the increasing expansion of the AM sector. Instead, they will require fundamental advances in material science, AM production technologies, and computer-aided design software.

Soft tissue deformation tracking by means of an optimized fiducial marker layout with application to cancer tumors.

OBJECTIVE: Interventional radiology methods have been adopted for intraoperative control of the surgical region of interest (ROI) in a wide range of minimally invasive procedures. One major obstacle that hinders the success of procedures using interventional radiology methods is the preoperative and intraoperative deformation of the ROI. While fiducial markers (FM) tracing has been shown to be promising in tracking such deformations, determining the optimal placement of the FM in the ROI remains a significant challenge. The current study proposes a computational framework to address this problem by preoperatively optimizing the layout of FM, thereby enabling an accurate tracking of the ROI deformations. METHODS: The proposed approach includes three main components: (1) creation of virtual deformation benchmarks, (2) method of predicting intraoperative tissue deformation based on FM registration, and (3) FM layout optimization. To account for the large variety of potential ROI deformations, virtual benchmarks are created by applying a multitude of random force fields on the tumor surface in physically based simulations. The ROI deformation prediction is carried out by solving the inverse problem of finding the smoothest force field that leads to the observed FM displacements. Based on this formulation, a simulated annealing approach is employed to optimize the FM layout that produces the best prediction accuracy. RESULTS: The proposed approach is capable of finding an FM layout that outperforms the rationally chosen layouts by 40% in terms of ROI prediction accuracy. For a maximum induced displacement of 20 mm on the tumor surface, the average maximum error between the benchmarks and our FM-optimized predictions is about 1.72 mm, which falls within the typical resolution of ultrasound imaging. CONCLUSIONS: The proposed framework can optimize FM layout to effectively reduce the errors in the intraoperative deformation prediction process, thus bridging the gap between preoperative imaging and intraoperative tissue deformation.

Reconstruction of a Deformed Tumor Based on Fiducial Marker Registration: A Computational Feasibility Study.

Interstitial photodynamic therapy has shown promising results in the treatment of locally advanced head and neck cancer. In this therapy, systemic administration of a light-sensitive drug is followed by insertion of multiple laser fibers to illuminate the tumor and its margins. Image-based pretreatment planning is employed in order to deliver a sufficient light dose to the complex locally advanced head-and-neck cancer anatomy, in order to meet clinical requirements. Unfortunately, the tumor may deform between pretreatment imaging for the purpose of planning and intraoperative imaging when the plan is executed. Tumor deformation may result from the mechanical forces applied by the light fibers and variation of the patient's posture. Pretreatment planning is frequently done with the assistance of computed tomography or magnetic resonance imaging in an outpatient suite, while treatment monitoring and control typically uses ultrasound imaging due to considerations of costs and availability in the operation room. This article presents a computational method designed to bridge the gap between the 2 imaging events by taking a tumor geometry, reconstructed during preplanning, and by following the displacement of fiducial markers, which are initially placed during the preplanning procedure. The deformed tumor shape is predicted by solving an inverse problem, seeking for the forces that would have resulted in the corresponding fiducial marker displacements. The computational method is studied on spheres of variable sizes and demonstrated on computed tomography reconstructed locally advanced head and neck cancer model. Results of this study demonstrate an average error of less than 1 mm in predicting the deformed tumor shape, where 1 mm is typically the order of uncertainty in distance measurements using magnetic resonance imaging or computed tomography imaging and high-quality ultrasound imaging. This study further demonstrates that the deformed shape can be calculated in a few seconds, making the proposed method clinically relevant.

Computer-Aided Patient-Specific Coronary Artery Graft Design Improvements Using CFD Coupled Shape Optimizer.

This study aims to (i) demonstrate the efficacy of a new surgical planning framework for complex cardiovascular reconstructions, (ii) develop a computational fluid dynamics (CFD) coupled multi-dimensional shape optimization method to aid patient-specific coronary artery by-pass graft (CABG) design and, (iii) compare the hemodynamic efficiency of the sequential CABG, i.e., raising a daughter parallel branch from the parent CABG in patient-specific 3D settings. Hemodynamic efficiency of patient-specific complete revascularization scenarios for right coronary artery (RCA), left anterior descending artery (LAD), and left circumflex artery (LCX) bypasses were investigated in comparison to the stenosis condition. Multivariate 2D constraint optimization was applied on the left internal mammary artery (LIMA) graft, which was parameterized based on actual surgical settings extracted from 2D CT slices. The objective function was set to minimize the local variation of wall shear stress (WSS) and other hemodynamic indices (energy dissipation, flow deviation angle, average WSS, and vorticity) that correlate with performance of the graft and risk of re-stenosis at the anastomosis zone. Once the optimized 2D graft shape was obtained, it was translated to 3D using an in-house "sketch-based" interactive anatomical editing tool. The final graft design was evaluated using an experimentally validated second-order non-Newtonian CFD solver incorporating resistance based outlet boundary conditions. 3D patient-specific simulations for the healthy coronary anatomy produced realistic coronary flows. All revascularization techniques restored coronary perfusions to the healthy baseline. Multi-scale evaluation of the optimized LIMA graft enabled significant wall shear stress gradient (WSSG) relief (~34%). In comparison to original LIMA graft, sequential graft also lowered the WSSG by 15% proximal to LAD and diagonal bifurcation. The proposed sketch-based surgical planning paradigm evaluated the selected coronary bypass surgery procedures based on acute hemodynamic readjustments of aorta-CA flow. This methodology may provide a rational to aid surgical decision making in time-critical, patient-specific CA bypass operations before in vivo execution.

Beautification of Design Sketches Using Trainable Stroke Clustering and Curve Fitting.

We propose a new sketch parsing and beautification method that converts digitally created design sketches into beautified line drawings. Our system uses a trainable, sequential bottom-up and top-down stroke clustering method that learns how to parse input pen strokes into groups of strokes each representing a single curve, followed by point-cloud ordering that facilitates curve fitting and smoothing. This approach enables greater conceptual freedom during visual ideation activities by allowing designers to develop their sketches using multiple, casually drawn strokes without requiring them to indicate the separation between different stroke groups. With the proposed method, raw sketches are seamlessly converted into vectorized geometric models, thus, facilitating downstream assessment and editing activities.