Abstract: This disclosure presents a method and system aimed at improving the efficiency of conformation sampling for drug discovery or molecular design. An example method employs an iterative process with energy evaluations and Monte Carlo sampling to create a conformation pool. Initially, it calculates the energy of a ligand's initial conformation and detects rotatable bonds. The Monte Carlo algorithm randomly samples and rotates these bonds to generate new conformations, whose energies are assessed. Favorable, lower-energy conformations are directly stored, while higher-energy ones may be stored based on calculated probabilities inversely related to energy differences. The process continues iteratively until a specified exit condition is met, signifying convergence. Notably, this method extends beyond conformational analysis to offer binding guidance, facilitating the design of ligands with enhanced affinity and specificity.

Abstract: This disclosure presents a method and system aimed at facilitating drug development using electrostatics-based preconditioning. An example method may include computing electrostatic potentials of atoms in a protein molecule. Also, the method may include obtaining a drug molecule for binding to the protein molecule. Furthermore, the method may include modifying (i.e., preconditioning) the drug molecule based on the electrostatic potentials of the atoms in the protein molecule, where the modifying may include: placing charged functional groups on the drug molecule based on absolute values of the electrostatic potentials of the atoms in the protein molecule; and placing polar functional groups or heteroatoms into the drug molecule based on relative values of the electrostatic potentials of the atoms in the protein molecule.

Abstract: This disclosure presents a method and system aimed at improving the shape complementarity between pockets and ligands. The method involves several steps, such as determining non-polar interactions among atoms within each region of a molecule, creating point clouds to represent these regions, and generating a mesh that overlays the molecular structure. This mesh enables users to make adjustments to the shape of a ligand, which is intended to enhance the compatibility with the pockets. Additionally, the method provides a visualization of the mesh on the molecular structure, allowing users to observe the precise locations of the regions and the potential fields associated with them.

Abstract: Systems and methods of deep learning coordinate prediction using satellite and service data are disclosed herein. In some example embodiments, for each one of a plurality of places, a computer system trains a deep learning model based on training data of the plurality of places. The deep leaning model is configured to generate a predicted geographical location of a place based on satellite image data and service data associated with the place. The training data for each place comprises satellite image data of the place, service data, and a ground truth geographical location of the place. The service data comprises at least one of pick-up data indicating a geographical location at which a provider started transporting a requester in servicing a request associated with the place or drop-off data indicating a geographical location at which the provider completed transporting the requester in servicing the request associated with the place.

Abstract: Systems and methods of deep learning coordinate prediction using satellite and service data are disclosed herein. In some example embodiments, for each one of a plurality of places, a computer system trains a deep learning model based on training data of the plurality of places. The deep leaning model is configured to generate a predicted geographical location of a place based on satellite image data and service data associated with the place. The training data for each place comprises satellite image data of the place, service data, and a ground truth geographical location of the place. The service data comprises at least one of pick-up data indicating a geographical location at which a provider started transporting a requester in servicing a request associated with the place or drop-off data indicating a geographical location at which the provider completed transporting the requester in servicing the request associated with the place.