Hypothesis Generation with AGATHA : Accelerate Scientific Discovery with Deep Learning | AISC

Channel:
Canada LLMs Explained - Aggregate Intellect - AI.SCIENCE
Subscribers:
20,600
Published on ● Video Link: https://www.youtube.com/watch?v=Q2po1QZONIg


Duration: 47:09
624 views
26

For slides and more information on the paper, visit https://aisc.ai.science/events/2020-04-01

Discussion lead: Justin Sybrandt
Discussion facilitator(s): Rouzbeh Afrasiabi

Abstract

Medical research is risky and expensive. Drug discovery, as an example, requires that researchers efficiently winnow thousands of potential targets to a small candidate set for more thorough evaluation. However, research groups spend significant time and money to perform the experiments necessary to determine this candidate set long before seeing intermediate results. Hypothesis generation systems address this challenge by mining the wealth of publicly available scientific information to predict plausible research directions. We present AGATHA, a deep-learning hypothesis generation system that can introduce data-driven insights earlier in the discovery process. Through a learned ranking criteria, this system quickly prioritizes plausible term-pairs among entity sets, allowing us to recommend new research directions. We massively validate our system with a temporal holdout wherein we predict connections first introduced after 2015 using data published beforehand. We additionally explore biomedical sub-domains, and demonstrate AGATHA's predictive capacity across the twenty most popular relationship types. This system achieves best-in-class performance on an established benchmark, and demonstrates high recommendation scores across subdomains. Reproducibility: All code, experimental data, and pre-trained models are available online:



Other Videos By LLMs Explained - Aggregate Intellect - AI.SCIENCE


2020-04-29A Literature Review on ML in Health Care : Introducing new AISC Stream | AISC
2020-04-29A Literature Review on ML in Neuroscience - Introducing new AISC Stream | AISC
2020-04-28Model Selection for Optimal Prediction in Statistical Learning (Part 1: 7 Wheels of Stat Learning)
2020-04-28A Literature Review on Machine Learning in Materials Science | AISC
2020-04-23SELFIES: A 100% robust representation of semantically constrained Graphs, for deep generative models
2020-04-23A Literature Review on Reinforcement Learning in Process Control | AISC
2020-04-22Learning to Play Soccer by Reinforcement Learning | AISC
2020-04-21Founders Stream: Customer Journey Maps in a Post-COVID-19 World | AISC
2020-04-16End to end recommender engine using Amazon Glue and SageMaker - Use Case for Data Scientists | AISC
2020-04-16A Literature Review on Graph Neural Networks
2020-04-01Hypothesis Generation with AGATHA : Accelerate Scientific Discovery with Deep Learning | AISC
2020-03-31Trusted Text Classification from Concept to Deployment | NLP Workshop Capstone
2020-03-31Deploying a News Summarizer RSS Feed App | NLP Workshop Capstone
2020-03-31Customer reviews summarization with Seq2Seq architecture and attention | NLP Workshop Capstone
2020-03-31Massive acceleration by using neural networks to emulate mechanism-based biological models
2020-03-26Integrating Privacy is Integrating Ethics: What privacy could have done for Clearview AI | AISC
2020-03-25Are We Really Making Much Progress? A Worrying Analysis of Recent Neural Recommendation Approaches |
2020-03-24[Author speaking] Protein docking model evaluation by 3D convolutional neural networks | AISC
2020-03-23Building and leveraging pragmatic AI solutions for legal services | AISC
2020-03-17Deep learning interpretation of echocardiograms | AISC
2020-03-10News Recommender System Considering Temporal Dynamics and News Taxonomy | AISC