Life Sciences

Deep Learning Analytics for Life Sciences from R&D to Manufacturing

SDF file handling for compound structure analytics
Advanced A.I. chemistry analytics
Highly scalable image management and A.I. analytics
Vyasa Vector enables de novo compound structure generation

Life Sciences Use Cases

Target Finding & Drug Repurposing

Vyasa Neural Concept Recognition AI technology can be trained on concept types (e.g. drugs, diseases, pathways, conditions, side effects, genes) in both structured and unstructured content. Once trained, Vyasa Cortex builds a dynamic knowledge graph of everything known about those concepts across all sources. Because everything in Cortex is converted into a vector space, each concept in the knowledge graph is connected to everything else in that vector space. This allows users to query Cortex for proximity of concepts across very large knowledge sets, yielding unexpected relationships between mechanisms of action and disease conditions that might be otherwise missed. This type of vector space analysis is an excellent tool for drug repurposing and target finding.
Vyasa Cortex enables users to apply a wide range of deep learning image analytics to life sciences related image sets. Vyasa has finely-tuned these algorithms for specialized life sciences images types. Furthermore, the highly scalable Cortex platform makes it easy to connect to large image repositories or image streams and apply image analytics to those sources with just a few clicks of a mouse.

AI Driven de novo Compound Design

Vyasa has developed ChemVector, a proprietary deep learning algorithm for /de novo/ small compound design. ChemVector utilizes an autoencoder-based neural network that can achieve >98% reconstruction accuracy on SMILES strings, along with Bayesian optimization. Available in Cortex, the analytic module can identify and generate novel compounds that optimize variables such as log-p, molecular weight and synthetic viability.

Deep Learning Chemistry Analytical Library

Cortex provides a wide range of deep learning analytical modules for chemical analysis. From toxicity analysis to molecular modeling, Cortex makes it easy to apply deep learning algorithms to compound sets imported into the system.

Electronic Laboratory Notebook Mining

Cortex provides organizations with more effective discovery tools for the valuable content stored in their Electronic Laboratory Notebooks (ELN) systems. ELNs are widely-used tools for capturing the research performed in laboratories, but it can be challenging to gain a bird’s eye view of the information stored in these systems, and the potential connections within the content. Vyasa Neural Concept Recognition technology can be trained to scan for specific types of content in ELN records (e.g. compound structures, drug names, reaction mechanisms, reagents, instrumentation) and enables a user to conduct analytics on the concepts found.