Gtx 980

All novel compounds were docked in the protein binding site using the docking software GOLD, version 5.5 (www.ccdc.cam.ac.uk). For each compound, 25 diverse poses were generated and analysed. A radius of 10 Å was used to define the pocket extension. Automatic default parameters were set for the Genetic Algorithm. Shape constraints were imposed using as template the structure of GR24 co-crystallized within the target (PDB code 5dj5; Zhao et al., 2015 (link)). ChemScore was used as the scoring function. All calculations were performed on a Dell Precision workstation, having two Intel Xeon processors, twelve core 1TB 7.2K 6GBPS SAS Hard Drive, NVidia GTX 980 graphic card, and a Linux operating system centos 7, kernel version 3.10.0-514.10.2.el7.x86_64. Molecular interaction fields were calculated using FLAP (Fingerprints for Ligands and Proteins, Baroni et al., 2007 (link); Grossert et al., 2015 (link)), using the DRY probe to describe potential hydrophobic interactions, and the sp2 carbonyl oxygen O and the amide N1 probes for hydrogen-bond donor and acceptor regions, respectively.

This study implemented multivariate linear regression, LSTM, and CNN networks to model the relationship between SRS and MOCAP signals and estimate joint angles in sagittal and frontal planes. Models estimate FLX and INV signals of MOCAP system based on the DFX, PFX, INV, and EVR signals of the SRS system and their first and second derivatives. Data analysis was performed using Python 3.7. Regression models were trained using Sklearn library. All DL models are developed using TensorFlow 2.4.0. and Nvidia Cuda 11.0.3 on an Nvidia GTX 980 with i7-5960X CPU and 128 GB of RAM.