Writing research papers is critical for disseminating scientific findings, but it does come with efficiency burdens, particularly for early-career researchers and non-native English speakers. A survey published in Nature in 2018 indicated that approximately 37% of respondents reported that they spend more than 20 hours a week on writing and revising scientific papers.
Recent progress in Natural Language Processing (NLP) technology, particularly with the rise of Generative Pre-trained Transformers (GPT) and other Large Language Models (LLMs), has equipped researchers with a powerful set of tools for processing extensive amounts of literature quickly. Insilico Medicine ("Insilico"), a clinical-stage generative AI-driven biotechnology company, has launched a preview version of its draft outline research assistant, Science42:DORA, to streamline the generation of scientific content.
Science42: DORA (aka DORA) integrates multiple AI agents that leverage LLMs, designed to streamline the process of drafting academic papers and other scientific documents including grant and patent applications, internal research summaries, IND applications, etc. It assists researchers in drafting these types of documents with proper referencing through engineered prompts, proprietary databases, and pre-designed content generation workflows.
"Often the most difficult step when it comes to writing is starting the process. Something that I experienced first-hand as a graduate student when I was tasked with writing numerous grants, papers and reports." said Petrina Kamya, PhD, Global head of AI Platform, Vice President of Insilico Medicine. "We developed Science42:DORA to help eliminate that debilitating barrier to writing scientific documents."
To further validate DORA's abilities, Insilico's developers collaborated with researchers at the University of Copenhagen to submit a paper on medRxiv. The paper drafted by DORA and later manually curated and extended, performs a comparative study about radiotherapy outcomes across brain tumor types, namely Glioblastoma Multiform and Low-Grade Gliomas based on radiotherapy phenotype and expression data from 32 cancer datasets. Insilico plans to further test DORA in multiple types of document generation and launch a free trial version of the AI assistant to the public in late 2024.
Here at Insilico, we strive to integrate state-of-art AI innovations with human intelligence for faster and better advancements in research and development, and LLM-based AI agents have been our recent focus. With DORA, we hope not only to streamline the writing process but also to elevate the overall quality of scholarly output, which in turn powers practical applications and meaningful delivery."
Alex Zhavoronkov, PhD, Founder and CEO of Insilico Medicine
Insilico Medicine is a pioneer in using generative AI for drug discovery and development. The Company first described the concept of using generative AI for the design of novel molecules in a peer-reviewed journal in 2016. Then, Insilico developed and validated multiple approaches and features for its generative adversarial network (GAN)-based AI platform and integrated those algorithms into the commercially available Pharma.AI platform, which includes generative biology, chemistry, and medicine.
Since 2021, Insilico has nominated 18 preclinical candidates in its comprehensive portfolio of over 30 promising therapeutic assets and has advanced seven molecules to the clinical stage. In March 2024, the Company published a paper in Nature Biotechnology that discloses the raw experimental data and the preclinical and clinical evaluation of its lead drug – a potentially first-in-class TNIK inhibitor for the treatment of idiopathic pulmonary fibrosis discovered and designed using generative AI currently in Phase II trials with patients.
New research explores how omega-3 and omega-6 fatty acids may impact cancer rates