AI Integrated Computational Drug Design Platform
There are well known screening methods like bioinformatics and cheminformatics tools, quantitative structure property relations and drug-target docking. However these methods are not capable of capturing the effect of the dynamics of target, and environment (physiological conditions, thermodynamic conditions). Therefore, the available computation methods have limited applicability and can only be implemented at the rudimentary screening stage. Also, structural insight and the mechanistic details are missing from such available screening tools. Hence the feedback mechanism in the drug development cycle is missing. We are developing a machine learning guided library of force fields (parameters for all atom atom covalent and non-covalent interactions) for finding highly specific targets for a set of drug like ligands. Screening of large number of drug molecules before taking them to the experimental bench can be achieved considering the effect of dynamics of the target, and the chemical environment of both drug and the target. Such a protocol will be capable of making more accurate predictions and can narrow down the set of target molecules with high specificity.
GPU Computing Platform and Cloud
Current state of the art high performance computers (CPU based servers) are not cost effective for such projects as the computational demand is very high. In recent times we have innovated and redesigned our codes to run in much cheaper gaming personal computers/workstations. With Graphical Processing Units (GPU) we received 3X more performance at 3X lower cost than any comparable enterprise level CPU based server or any cloud service provider. So we are developing and optimising all our codes for GPU ready and assembling and using our own innovative high performance GPU workstation. We are offering our software platform to all interested partners to test on our computational resource.
Quantum Chemical and Molecular Modelling Platform for Materials
Advanced materials (smart materials) are superior in properties e.g., materials which can sense, lighter in weight but stronger than steel, super-hydrophobic, deliver drugs to the specific targets and so on. We help industries in design and innovate such materials by performing computer simulation at a molecular scale. So, we develop and perform atomic level quantum chemical calculations and take it forward to nanoscale to mesoscale simulations to predict properties of these newly designed materials. We build highly predictive models to design new/smart advanced materials for industries e.g., rubber (tyre), additive, energy (oil and gas), lubricants, adhesive, coatings, membrane, drug delivery vectors etc.
AI Augmented Force Field Generation Platform
Industry and academia face challenges in developing force fields for performing molecular level calculations. The standard softwares available for molecular mechanics/simulations/Monte Carlo/Coarse Graining/Mesoscale methods only provide force fields for standard (few) molecules and those are mostly for small molecules. Development of force fields is always a challenge and only tackled by few experts in the field. We have developed our own platform to solve this challenge and in record time generate and validate force fields. We use AI/ML augmented methods and quantum chemical calculations to solve force fields for new molecules/supramolecules/macromolecules. We develop and provide well validated force fields for 100s of new drug candidates, polymers (block copolymer of any topology) for rubber, membrane, coatings, adhesives, biomolecules, biopolymers etc.