Deep Learning Model for Efficient Protein-Ligand Docking with Implicit Side-Chain Flexibility.

Protein-ligand docking is an essential tool in structure-based drug design with applications ranging from virtual high-throughput screening to pose prediction for lead optimization. Most docking programs for pose prediction are optimized for redocking to an existing cocrystallized protein structure, ignoring protein flexibility. In real-world drug design applications, however, protein flexibility is an essential feature of the ligand-binding process. Flexible protein-ligand docking still remains a significant challenge to computational drug design. To target this challenge, we present a deep learning (DL) model for flexible protein-ligand docking based on the prediction of an intermolecular Euclidean distance matrix (EDM), making the typical use of iterative search algorithms obsolete. The model was trained on a large-scale data set of protein-ligand complexes and evaluated on independent test sets. Our model generates high quality poses for a diverse set of protein and ligand structures and outperforms comparable docking methods.

Elucidating the multiple roles of hydration for accurate protein-ligand binding prediction via deep learning.

Accurate and efficient prediction of protein-ligand interactions has been a long-lasting dream of practitioners in drug discovery. The insufficient treatment of hydration is widely recognized to be a major limitation for accurate protein-ligand scoring. Using an integration of molecular dynamics simulations on thousands of protein structures with novel big-data analytics based on convolutional neural networks and deep Taylor decomposition, we consistently identify here three different patterns of hydration to be essential for protein-ligand interactions. In addition to desolvation and water-mediated interactions, the formation of enthalpically favorable networks of first-shell water molecules around solvent-exposed ligand moieties is identified to be essential for protein-ligand binding. Despite being currently neglected in drug discovery, this hydration phenomenon could lead to new avenues in optimizing the free energy of ligand binding. Application of deep neural networks incorporating hydration to docking provides 89% accuracy in binding pose ranking, an essential step for rational structure-based drug design.

Efficient and Accurate Hydration Site Profiling for Enclosed Binding Sites.

Molecular dynamics (MD) simulations allow for accurate prediction of the thermodynamic profile of binding-site water molecules critical for protein-ligand association. Whereas this hydration-site profiling converges rapidly for solvent-exposed sites independent of the initial water placement, an accurate and reliable placement is required for water molecules in occluded binding sites. Here, we present an accurate and efficient hydration-site prediction method for occluded binding sites combining water placement based on 3D-RISM and MD simulations using WATsite.

Limb Position Tolerant Pattern Recognition for Myoelectric Prosthesis Control with Adaptive Sparse Representations From Extreme Learning.

Myoelectric signals can be used to predict the intended movements of an amputee for prosthesis control. However, untrained effects like limb position changes influence myoelectric signal characteristics, hindering the ability of pattern recognition algorithms to discriminate among motion classes. Despite frequent and long training sessions, these deleterious conditional influences may result in poor performance and device abandonment. GOAL: We present a robust sparsity-based adaptive classification method that is significantly less sensitive to signal deviations resulting from untrained conditions. METHODS: We compare this approach in the offline and online contexts of untrained upper-limb positions for amputee and able-bodied subjects to demonstrate its robustness compared against other myoelectric classification methods. RESULTS: We report significant performance improvements () in untrained limb positions across all subject groups. SIGNIFICANCE: The robustness of our suggested approach helps to ensure better untrained condition performance from fewer training conditions. CONCLUSIONS: This method of prosthesis control has the potential to deliver real-world clinical benefits to amputees: better condition-tolerant performance, reduced training burden in terms of frequency and duration, and increased adoption of myoelectric prostheses.

Implantable neurotechnologies: bidirectional neural interfaces--applications and VLSI circuit implementations.

A bidirectional neural interface is a device that transfers information into and out of the nervous system. This class of devices has potential to improve treatment and therapy in several patient populations. Progress in very large-scale integration has advanced the design of complex integrated circuits. System-on-chip devices are capable of recording neural electrical activity and altering natural activity with electrical stimulation. Often, these devices include wireless powering and telemetry functions. This review presents the state of the art of bidirectional circuits as applied to neuroprosthetic, neurorepair, and neurotherapeutic systems.

Towards better understanding and reducing the effect of limb position on myoelectric upper-limb prostheses.

Myoelectric control of prosthetic devices tend to rely on classification schemes of extracted features of EMG data. Those features however, may be sensitive to arm position resulting in decreased performance in real-world applications. The effect of varying limb position in a pattern recognition system have been illustrated by documenting the change in classification accuracy as the user achieves particular limb configurations. We continue to investigate this limb position effect by observing its impact on classification accuracy as well as through an analysis of how each extracted feature of the raw EMG varies in each position. Finally, LDA classification schemes are applied both to demonstrate the effect varying limb position has on classification accuracy and to increase classification accuracy without the use of additional hardware or sensors such as accelerometers as has been done in the past. It is shown that high classification accuracy can be achieved by (1) training an LDA classifier with data from many positions, as well as (2) by utilizing an extra position LDA classifier which can weigh the grasp classifiers appropriately. The classification accuracies achieved by these methods approached that of a model relying on a perfect knowledge of arm position.