NNA |
Update: April 30, 2022 5:04 p.m. STI

New Delhi [India], April 30 (ANI/PNN): The machine learning team from the Department of Chemical Engineering at KnowDis and IIT-Delhi have teamed up to solve a critical drug discovery problem for neurodegenerative diseases such as Alzheimer’s disease and Parkinson’s disease. This collaboration aims to develop state-of-the-art artificial intelligence models that could uncover potential antibodies critical to treating brain diseases.
The human brain is a surprisingly complex and fascinating creation. It is the control center for the whole body and is responsible for everything from breathing to thinking to feeling. Thus, finding a cure for brain disease is one of the greatest challenges in medical science. The confluence of KnowDis and IIT Delhi brings together a multidisciplinary team to accelerate drug discovery with AI.
What happens when something goes wrong with the brain?
Because the brain holds such immense power, malfunctioning of it inevitably affects a person’s daily activities, emotions, and feelings. Often the impact is so great that it can significantly affect quality of life. For example, Alzheimer’s disease (AD) and Parkinson’s disease (PD) are among the most common age-related neurodegenerative disorders.
The curious case of alpha-synuclein and antibodies
Alpha-synuclein is a protein found in large amounts in the brain and is thought to play a role in nerve signaling.
In certain disease states, alpha-synuclein molecules begin to come together to form large aggregates. These appear as insoluble deposits in the brain. Diseases where this occurs include Parkinson’s disease, certain types of dementia, and Alzheimer’s disease. Thus, they are collectively called synucleinopathies.
One possible way to prevent unusual alpha-synuclein aggregation is to design drugs that would bind to alpha-synuclein molecules at various stages of aggregation. Drug binding would disrupt further aggregation and possibly break up already formed aggregates.
Antibodies are a class of naturally occurring proteins that help the human immune system track down invaders, such as pathogenic bacteria. Antibodies are custom designed by nature to bind to specific targets – to be precise, an antibody binds to an antigen, which is a molecule on the surface of the pathogen. Therefore, an antibody designed to bind to alpha-synuclein aggregates could become a treatment for synucleinopathies.
However, the process of designing and producing antibodies is time consuming and expensive. If a computer program could predict which antibodies would bind to alpha-synuclein aggregates, it would be invaluable in streamlining laboratory work, which could save a lot of time and resources. By using AI, one can also design new antibodies that do not exist in nature.
KnowDis & IIT-Delhi collaboration: AI for drug discovery

The computer-aided design of new antibodies against specific antigenic targets requires expertise in molecular biology, protein chemistry and artificial intelligence. KnowDis and Professor Gaurav Goel’s lab from the Department of Chemical Engineering at IIT Delhi have teamed up to create such a synergy. Coincidentally, KnowDis Founder Saurabh Singal and Professor Gaurav Goel both hold BTech degrees from IIT Delhi.
The collaboration aims to develop an AI-based algorithm that will predict, at high throughput, which antibodies are effective in binding to alpha-synuclein aggregates. The development of such a high-throughput algorithm will be a step up from current algorithms, which are much slower. The final goal of the algorithm would be to narrow down candidate antibodies that have a much better chance of being validated experimentally. As a result, drugs will become more affordable. It will also lead to faster development of effective therapies for synucleinopathies, thereby reducing the long wait for treatment.
This new approach to antibody design using AI will benefit mankind.
hot field
Antibodies can be computer-fitted as drug candidates in a fraction of the time and resources that would be required in a wet-lab experimental setting. Many pharmaceutical companies are only beginning to adapt to this changed drug discovery landscape. The trend has been spurred by recent advances and successes in AI algorithms applied to protein structure prediction and design.
AI-based drug discovery is expected to grow steadily with a projected market volume reaching $1.4 billion by 2024, while the overall antibody market is expected to exceed $300 billion by 2025. Several companies well-known tech and pharma companies such as Google, Nvidia, AstraZeneca, and Novartis are foraying into this space by establishing long-term collaborations with startups and spin-offs from academia. Many startups have attracted multi-million dollar venture capital funding to develop AI-based drug discovery platforms for tomorrow’s biotherapy.
KnowDis is an AI product company founded by Saurabh Singal, a computer scientist from IIT Delhi and Carnegie Mellon.
KnowDis has built and deployed AI applications specifically designed for the growing field of e-commerce. Its deep learning models bolster IndiaMART’s B2B platform.
KnowDis and its team of researchers are not new to the field of using AI for the biomedical field. They have previously worked on applying machine learning to analyze drug efficacy; a computer vision-based application for use in hospitals; and deep learning-based programs for binding affinity and in silico drug discovery and design.
In collaboration with the School of AI at IIT Delhi, KnowDis organizes a prestigious annual machine learning conference that includes topics that explore the applications of AI in drug discovery and genomics.
Dr. Gaurav Goel and his team at the highly regarded Department of Chemical Engineering at IIT Delhi are working on the development of multiscale simulation models to study pico-to-microscale dynamics of soft matter systems to enable the determination of their stability, morphology and dynamic properties. Particular emphasis is placed on performing end-to-end investigation to understand synergistic interactions in multi-component and multi-phase systems leading to computer-aided design of new product formulations for specific target properties.
Some recent and ongoing applications involve the development of biotherapeutic formulations with acceptable high temperature stability, a durable packaging solution involving high oxygen and vapor barrier biopolymer blends, and conductive materials based on polymers with high energy density and good cyclability.
This story is provided by PNN. ANI will not be responsible for the content of this article. (ANI/PNN)