Pune, India

Sri Harsha Nistala

This inventor holds 22 USPTO granted patents and 6 published patent applications and 18 EPO patents, primarily in Molecular Property Prediction. Top assignee: Tata Consultancy Services Limited. Active years: 2020-2026.

IDiyas Innovation Intelligence. (2026). Inventor Profile: Sri Harsha Nistala. Retrieved from https://idiyas.com/inventor/sri-harsha-nistala

Data source: USPTO (United States Patent and Trademark Office) public patent records. Weekly synchronization. How IDiyas builds this profile

Calculating rank
USPTO Granted Patents = 22 

% Patents Active = 95.5

 

Average Co-Inventor Count = 4.2

ph-index = 2

Forward Citations = 13(Granted Patents)


Company Filing History:


Years Active: 2020-2026

Loading Chart...
Loading Chart...
Areas of Expertise:
Adaptive Learning
Anomaly Detection
Causal Inference
Cyber-Physical Systems
Deep Learning
Graph Neural Networks
Industrial Optimization
Molecular Prediction
Root Cause Identification
Self-Supervised Training
Time Series Models
22 patents (USPTO):Explore Patents

Title: **Innovative Contributions of Sri Harsha Nistala in Molecular Property Prediction and Time Series Models**

Introduction

Sri Harsha Nistala, based in Pune, India, is a prominent inventor known for his innovative work in the fields of molecular property prediction and deep learning models for time series data. With an impressive portfolio of 12 patents, he has made significant strides in enhancing the efficiency and effectiveness of various computational methodologies.

Latest Patents

Among Sri Harsha Nistala's latest patents is the "System and Method for Molecular Property Prediction Using Hypergraph Message Passing Neural Network (HMPNN)." This patent addresses the limitations of conventional Message Passing Neural Networks (MPNN) in representing chemical graphs. The disclosed system utilizes HyperGraph attention-driven convolution to learn efficient embeddings on high-order molecular graph-structured data by considering transient incidence matrices, which augment molecular hypergraph representation learning.

Another notable patent is the "Method and System for Self-Supervised Training of Deep Learning Based Time Series Models." This innovative approach tackles the issue of missing data through the introduction of missing-ness masks. The deep learning model is trained with distorted input data, incorporating various distortion techniques to learn better features, thus making use of abundant unlabeled data compared to the scarce labeled or annotated data.

Career Highlights

Sri Harsha Nistala is currently associated with Tata Consultancy Services Limited, where he harnesses his expertise to contribute to cutting-edge technological advancement. His research and developments have not only broadened the scope of artificial intelligence applications but have also significantly impacted the efficiency of data processing in various sectors.

Collaborations

In his professional journey, Sri Harsha has collaborated with talented individuals such as Venkataramana Runkana and Pradeep Rathore. These collaborations have resulted in valuable insights and have further propelled innovations in the fields of deep learning and molecular property predictions.

Conclusion

Sri Harsha Nistala's contributions to the realms of molecular property prediction and time series modeling exemplify his commitment to innovation. With his robust patent portfolio and collaborative spirit, he continues to inspire further advancements in computational methodologies, making significant impacts within and beyond the scientific community.

Profile summary based on public USPTO records.
Data Sources: USPTO Patent Grant XML, Patent Center, EPO & CIPO • Normalized by IDiyas Innovation Graph. Methodology & provenance architecturePlease report any incorrect information to [email protected]
Loading…