Saama Blog

Recurrent Neural Networks (RNNs) are powerful neural network architectures used for modeling sequences. LSTM (Long Short Term Memory) based RNNs are surprisingly good at capturing long-term dependencies in the sequences. A barebones sequence-to-sequence/encoder-decoder architecture performs incredibly well in tasks like Machine Translation. A typical sequence-sequence architecture consists of an encoder and a decoder RNN. The…

The uses and application of blockchain technology are vast and far-reaching. In this article, Tushar Sinkar explores some blockchain uses that can be applied for drug discovery and development, such as eliminating data tampering and ensuring IP protection, among other uses.

AI and its applications are here to stay, even if they bring with them new challenges, as their advantages seem to outweigh the risks. However, in the light of latest controversies and concerns over privacy breach by social companies, the efforts to ensure privacy of users need to be redoubled. Arjun Bahuguna discusses the solutions that manage the vulnerabilities of machine learning and instead leverages its strength to guard information privacy.

An interconnected ecosystem is the need of the hour in the pharmaceutical world, where it is more important than ever to enable sharing of information among patients, researchers, and manufacturers and supply chain organizations. However, sharing entails risk to data security. Tushar Sinkar discusses the merits of using blockchain to solve the data security issue and facilitate easy sharing of information.

It is well-known that there are far fewer women techies and those that do choose work in tech, somehow avoid data science. Archana Iyer discusses the merits of having more women in the field of data science and presents some reasons why she feels that women’s innate temperament is highly suited to data science.

AI capabilities, such as machine learning, have emerged as optimum tools for optimizing clinical trials. Leon Surgeon discusses the challenges of using traditional methods for designing clinical studies and why adapting AI is the best way forward.

Blockchain is a digital ledger in which cryptocurrency transactions are recorded. In this article, Arjun Bahuguna discusses ethereum, a public blockchain, as it is the most popular platform for writing smart contracts and building decentralized applications.

Embeddings are the best way to create efficient representations of words and graphs. In this article, Soham Chatterjee talks about problems in the Euclidean plane representations and explains how Hyperbolic Poincaré Embeddings work.

Archana dives into the world of TPUs and discusses quantization, the process that is really responsible for making predictions in a neural network, lending a magical touch to the machine learning process. Read on to understand how quantization can be both a boon and a bane, depending on where it is used.

All clinical trial processes are witnessing rapid transformation due to the demand for faster and completion of trials at lower costs. Insights gleaned from Real World Data (RWD) in the past few years have offered several avenues for improving clinical trials. Sagar Anisingaraju discusses the upcoming trends of 2018 in this light. Read on to learn about the technologies poised to make a wave this year.

Adverse reaction caused by drugs is a potentially dangerous problem which may lead to mortality and morbidity in patients. Adverse Drug Event (ADE) extraction is a significant problem in biomedical research. We model ADE extraction as a Question-Answering problem and take inspiration from Machine Reading Comprehension (MRC) literature, to design our model. Our objective in…

As I look back at our accomplishments in 2017, I am delighted at the progress we have made on many fronts to make Saama a very relevant contributor to the life sciences industry. Over the course of the year, we have expanded our global presence, achieved significant technological milestones, and added several industry luminaries to…

Convolutional Neural Networks have brought about huge changes in computer vision and other image related tasks. Soham Chatterjee discusses how different convolution operations work and uses illustrations of design techniques for different filters to explain them in depth.

Data is available abundantly in today’s world. However, it is noisy most of the time. In this article, Archana Iyer discusses some filter processing techniques that can help us get a better quality of data. With the advent of IoT, many types of medical data are now available in the form of sensor data. This…

Most of the time, not enough sample clinical data is available due to various reasons. This sample data is essential for running analytics for development and testing. Rajeev Gangal discusses the way they tackled their need for generating simulated data for a project. Read on to know more. To paraphrase a recent statement by The…