Blog

Research: Biomedical relation extraction (BERT)

In natural language processing, words must be given numerical representations before they can be passed as input to a machine learning model.

A word is usually represented as a vector (a list of numbers). These word vectors must adequately capture the meaning of the words; semantically related words should have similar numbers. The better these representations, the stronger the performance of the machine learning model is likely to be.

Often, many methods of learning word vectors give a word the same vector regardless of the context that it appears in. However, it is not unusual for a word to have several different meanings. A classic example of this is the word “bank” in the following two sentences:

“I walked along the river bank”,
“I deposited some money into my bank account”.

If the same vector is used to represent “bank” in both instances, this impairs the performance of the downstream machine learning model which takes these word vectors as input.

Over the last few years, a lot of research has been done on learning contextual word vectors; these are word vectors which vary depending on the context in which the word appears. This enables the same word to have different vectors depending on how it is used in a sentence. A recent paper (Devlin et al, 2018) introduced BERT (Bidirectional Encoder Representations from Transformers), a new way of learning contextual word vectors. BERT utilises a powerful encoder architecture which is capable of modelling longer range dependencies between words. It also proposed an innovative way of capturing the context both before and after the word in the sentence. With these better contextual vectors, BERT achieved state of the art performance on several tasks within natural language processing.

In a recent paper, we proposed a new relation extraction model built on top of BERT. Given any paragraph of text (for example, the abstract of a biomedical journal article), our model will extract all gene-disease pairs which exhibit a pre-specified relation. In our paper, the relations we were interested in concerned the function change experienced by a gene mutation which affects the disease progression. The word vectors supplied by BERT provide our model with a way of encoding the meaning expressed in the text in regard to our entities of interest. We then further fine-tune this encoding so that it can more accurately identify when a paragraph of text contains a gene-disease relation of interest. Such relation extraction models are crucial in drug discovery; there are too many journal articles published every day for a human to read and summarise. A machine learning model capable of automatically extracting relevant gene-disease pairs can greatly accelerate this process.

More Posts

You Might Also Like

Video
Data & Digital Innovation for Climate & Health
Joanna Shields, CEO BenevolentAI, joined the Wellcome Trust Panel at the World Economic forum to discuss opportunities for data and digital innovation to impact positively climate and health.
Jan 26, 2023
News
BenevolentAI submits CTA for BEN-8744, an oral PDE10 inhibitor, as a first-in-class treatment for ulcerative colitis
BenevolentAI submits clinical trial application for BEN-8744, with a Phase I clinical trial planned for H1 2023.
Dec 21, 2022
News
BenevolentAI to present at 41st Annual J.P. Morgan Healthcare Conference
BenevolentAI ​​(Euronext Amsterdam: BAI), a leading clinical-stage AI drug discovery company, announces that it will participate in the upcoming 41st Annual J.P. Morgan Healthcare Conference in San Francisco, US from 9-12 January 2023.
Dec 1, 2022
Blog
FAIR Data Foundation: An Enabler for AI Drug Discovery
Biomedical data used in AI-enabled drug discovery should adhere to the FAIR Data Principles — Findability, Accessibility, Interoperability and Reusability. This blog explains why this is, how one can make data FAIR and challenges that remain.
Nov 8, 2022
News
BenevolentAI to present at Jefferies Investor Conference in November
BenevolentAI’s Investor Relations and Business Development team will be attending the Jefferies Healthcare London conference, with Nick Keher, CFO, presenting on Thursday 17th November.
Nov 4, 2022
News
BenevolentAI achieves further milestones in AI-enabled target identification collaboration with AstraZeneca
Two additional AI-generated novel targets selected by AstraZeneca for its drug development portfolio, resulting in two milestone payments for BenevolentAI.
Oct 6, 2022