A researcher has just finished writing a scientific paper. She knows her work could benefit from another perspective. Did she overlook something? Or perhaps there’s an application of her research she hadn’t thought of. A second set of eyes would be great, but even the friendliest of collaborators might not be able to spare the time to read all the required background publications to catch up.
Rapid advances in AI and ML have given way to programs that can generate creative text and useful software code. These general-purpose chatbots have recently captured the public imagination. Existing chatbots—based on large, diverse language models—lack detailed knowledge of scientific sub-domains.
By leveraging a document-retrieval method, Yager’s bot is knowledgeable in areas of nanomaterial science that other bots are not. The details of this project and how other scientists can leverage this AI colleague for their own work have recently been published in Digital Discovery.
Rise of the robots
“CFN has been looking into new ways to leverage AI/ML to accelerate nanomaterial discovery for a long time. Currently, it’s helping us quickly identify, catalog, and choose samples, automate experiments, control equipment, and discover new materials. Esther Tsai, a scientist in the electronic nanomaterials group at CFN, is developing an AI companion to help speed up materials research experiments at the National Synchrotron Light Source II (NSLS-II).” NSLS-II is another DOE Office of Science User Facility at Brookhaven Lab.
At CFN, there has been a lot of work on AI/ML that can help drive experiments through the use of automation, controls, robotics, and analysis, but having a program that was adept with scientific text was something that researchers hadn’t explored as deeply. Being able to quickly document, understand, and convey information about an experiment can help in a number of ways—from breaking down language barriers to saving time by summarizing larger pieces of work.
Watching your language
To build a specialized chatbot, the program required domain-specific text—language taken from areas the bot is intended to focus on. In this case, the text is scientific publications. Domain-specific text helps the AI model understand new terminology and definitions and introduces it to frontier scientific concepts. Most importantly, this curated set of documents enables the AI model to ground its reasoning using trusted facts.
To emulate natural human language, AI models are trained on existing text, enabling them to learn the structure of language, memorize various facts, and develop a primitive sort of reasoning. Rather than laboriously retrain the AI model on nanoscience text, Yager gave it the ability to look up relevant information in a curated set of publications. Providing it with a library of relevant data was only half of the battle. To use this text accurately and effectively, the bot would need a way to decipher the correct context.
“A challenge that’s common with language models is that sometimes they ‘hallucinate’ plausible sounding but untrue things,” explained Yager. “This has been a core issue to resolve for a chatbot used in research as opposed to one doing something like writing poetry. We don’t want it to fabricate facts or citations. This needed to be addressed. The solution for this was something we call ’embedding,’ a way of categorizing and linking information quickly behind the scenes.”
Embedding is a process that transforms words and phrases into numerical values. The resulting “embedding vector” quantifies the meaning of the text. When a user asks the chatbot a question, it’s also sent to the ML embedding model to calculate its vector value. This vector is used to search through a pre-computed database of text chunks from scientific papers that were similarly embedded. The bot then uses text snippets it finds that are semantically related to the question to get a more complete understanding of the context.
The user’s query and the text snippets are combined into a “prompt” that is sent to a large language model, an expansive program that creates text modeled on natural human language, that generates the final response. The embedding ensures that the text being pulled is relevant in the context of the user’s question. By providing text chunks from the body of trusted documents, the chatbot generates answers that are factual and sourced.
“The program needs to be like a reference librarian,” said Yager. “It needs to heavily rely on the documents to provide sourced answers. It needs to be able to accurately interpret what people are asking and be able to effectively piece together the context of those questions to retrieve the most relevant information. While the responses may not be perfect yet, it’s already able to answer challenging questions and trigger some interesting thoughts while planning new projects and research.”
Bots empowering humans
CFN is developing AI/ML systems as tools that can liberate human researchers to work on more challenging and interesting problems and to get more out of their limited time while computers automate repetitive tasks in the background. There are still many unknowns about this new way of working, but these questions are the start of important discussions scientists are having right now to ensure AI/ML use is safe and ethical.
“There are a number of tasks that a domain-specific chatbot like this could clear from a scientist’s workload. Classifying and organizing documents, summarizing publications, pointing out relevant info, and getting up to speed in a new topical area are just a few potential applications,” remarked Yager. “I’m excited to see where all of this will go, though. We never could have imagined where we are now three years ago, and I’m looking forward to where we’ll be three years from now.”
For researchers interested in trying this software out for themselves, the source code for CFN’s chatbot and associated tools can be found in this GitHub repository.
More information: Kevin G. Yager, Domain-specific chatbots for science using embeddings, Digital Discovery (2023). DOI: 10.1039/D3DD00112A
News
A Deadly Ebola-Like Virus Is Spreading. Are We Ready?
BU virologist Nancy Sullivan says the Bundibugyo outbreak in the Democratic Republic of the Congo underscores the need for broader outbreak preparedness. The death of a nurse marked the moment health officials recognized that [...]
Why Most Animal Viruses Never Become Human Pandemics
From receptor mismatch to risky human-animal interfaces, this article explains why spillover is common but true pandemic emergence remains rare. Introduction Humans are constantly exposed to animal viruses through farming, wildlife contact, and the [...]
Stem cell organoids repair heart microvessels in coronary artery disease models
A Stanford University team has shown that vascular organoids derived from human stem cells can repair the heart’s microvessel network in pigs with ischaemic heart disease – a proof-of-concept advancement that could open new therapeutic [...]
Goodbye GP waiting rooms, hello prevention at home
Prevention is suddenly everywhere in NHS reform. The recent £340m community pharmacy deal is moving more services onto the high street. Community Diagnostic Centres are being expanded, and the Neighbourhood Health Framework sets out [...]
Ebola control is weakened by mistrust and cultural insensitivity
Effective response depends on cooperation with communities and frontline workers, writes Zaeem ul Haq The current Bundibugyo Ebola outbreak in the Democratic Republic of the Congo (DRC) and Uganda is exposing dangerous gaps in [...]
Building the Brain Requires Millions of Dangerous DNA Breaks
Scientists discovered that building a healthy brain involves an unexpected step: young neurons routinely break and rapidly repair their own DNA. As the brain develops, newly formed nerve cells must travel through tightly packed tissue [...]
One Tiny Change May Explain How Viruses Jump From Bats to Humans
Scientists found that one tiny genetic change may determine whether a bat virus stays in bats or becomes a human threat. Most infectious disease outbreaks begin when a virus or other pathogen crosses from animals into [...]
Scientists Discover 250+ Genes That Could Lead to New Ways To Prevent Melanoma
The world’s largest study of mole genetics identified hundreds of genes tied to melanoma risk, uncovering potential new drug targets and paving the way for more accurate melanoma screening and prevention. Researchers at QIMR [...]
Breakthrough Diabetes Treatment Reprograms the Immune System
An engineered stem cell therapy reversed new-onset Type 1 diabetes in mice by shifting the immune system away from attacking insulin-producing cells. For more than a century, people with Type 1 diabetes have relied [...]
Taking the world’s temperature: WHO chief spotlights global health emergencies
Taking the world’s temperature on pressing health matters, WHO Director-General Tedros Adhanom Ghebreyesus provided the latest on current global challenges - and successes when it comes to international cooperation. “The outbreaks of hantavirus, Ebola and Marburg all show [...]
Scientists Create Tiny “Mini Livers” That Could One Day Replace Liver Transplants
Engineered tissue grafts could help perform key liver functions and benefit thousands of people living with liver failure. The liver is one of the body’s hardest-working organs, carrying out hundreds of vital jobs, from [...]
NanoMedical Brain/Cloud Interface – Explorations and Implications. A new book from Frank Boehm
New book from Frank Boehm, NanoappsMedical Inc Founder: This book explores the future hypothetical possibility that the cerebral cortex of the human brain might be seamlessly, safely, and securely connected with the Cloud via [...]
Scientists Discover Surprising Way To Help the Brain Recover After Stroke
A new study suggests that strengthening the body’s natural circadian rhythms may help the brain recover after stroke, even when treatment begins days after the injury. Every year, millions of people survive a stroke, [...]
Our books now available worldwide!
Online Sellers other than Amazon, Routledge, and IOPP Indigo Global Health Care Equivalency in the Age of Nanotechnology, Nanomedicine and Artifcial Intelligence Global Health Care Equivalency In The Age Of Nanotechnology, Nanomedicine And Artificial [...]
Younger Generations Are Aging Faster – and It May Be Fueling a Surge in Cancer
Younger generations may be aging biologically faster than those before them, and that shift could help explain rising rates of cancer at younger ages. For decades, cancer was viewed largely as a disease of [...]
Using Cannabis Could Raise Your Stroke Risk by 37%, Massive Study Reveals
Large-scale evidence suggests cannabis, cocaine, and amphetamines may directly raise stroke risk, including in younger adults. As recreational drug use becomes increasingly common, researchers are uncovering evidence that its health consequences may extend far beyond [...]
