B-Cell Bispecificity?!

Happy New Year, Blopiggers!

Just a quick one from me this time around, to draw your attention to this intriguing paper by Shi et al., published in Nature Cell Discovery late last year.

“More than one antibody of individual B cells revealed by single-cell immune profiling“
Zhan Shi, Qingyang Zhang, Huige Yan, et al.
Nature Cell Discovery (2019) 5:64

Single-cell transcriptomics (e.g. using TenX sequencing) is beginning to yield fascinating insights into the inner workings of our immune system. It has long been thought that a single B cell can only express one antibody variable domain on its surface, accounted for by theories such as allelic exclusion and isotype exclusion.

Continue reading →

The evolution of contact prediction – a new paper

I’m so pleased to be able to write about our work on The evolution of contact prediction: evidence that contact selection in statistical contact prediction is changing (Bioinformatics btz816). Contact prediction – the prediction of parts of the amino-acid chain that are close together – has been critical to improving the ability of scientists to predict protein structures over the last decade. Here we look at the properties of these predictions, and what that might mean for their use.

The paper begins with a question. If contact prediction methods are based on statistical properties of sequence alignments, and those alignments are generated in the presence of ecological and physical constraints, what effect do the physical constraints have on the statistical properties of real sequence alignments? More concisely: when we predict contacts, do we predict particularly important contacts?

Continue reading →

Transforming Parliament – Training and deploying speech generation transformers for parliamentary speakers

Introduction

I recently wanted to explore areas of machine learning that I do not usually interact with as part of my DPhil research on antibody drug discovery. This post explores how to train and deploy a speech generation model for parliamentary speeches in the style of Jeremy Corbyn and Boris Johnson. You can play around with the resulting model at https://con-schneider.github.io/theytalktoyou.html.

Continue reading →

Journal Club: Is our data biased, and should it be?

Jia, X., Lynch, A., Huang, Y. et al. Anthropogenic biases in chemical reaction data hinder exploratory inorganic synthesis. Nature 573, 251–255 (2019) doi:10.1038/s41586-019-1540-5 https://www.nature.com/articles/s41586-019-1540-5

Last week I presented the above paper at group meeting. While a little different from a typical OPIG journal club paper, the data we have access to almost certainly suffers from the same range of (possible) biases explored in this paper.

Continue reading →

IEEEGor Knows What You’re Thinking…

Last month, I, EEGor, took part in the Brain-Computer Interface Designers Hackathon (BR41N.IO), the opening event of the IEEE Systems, Man and Cybernetics Conference in Bari, Italy. Brain-Computer Interfaces (BCIs) are a class of technologies designed to translate brain activity into machine actions to assist (currently in clinical trials) as well as (one day) enhance human beings. BCIs are receiving more and more media attention, most recently with the launch of Elon Musk’s newest company, Neuralink which aims to set up a two-way communication channel between man and machine using a tiny chip embedded in the brain. With the further aim of one-day perhaps making our wildest transhumanist dreams come true…

Continue reading →

Consistent plotting with ggplot

Unlike other OPIGlets (looking at you, Claire), I have neither the skill nor the patience to make good figures from scratch. And making good figures — as well as remaking, rescaling and adapting them — is incredibly important, because they play a huge role in the way we communicate our research. So how does an aesthetically impaired DPhil student do her plotting?

Continue reading →

How to be a Bayesian – ft. a completely ridiculous example

Most of the stats we are exposed to in our formative years as statisticians are viewed through a frequentist lens. Bayesian methods are often viewed with scepticism, perhaps due in part to a lack of understanding over how to specify our prior distribution and perhaps due to uncertainty as to what we should do with the posterior once we’ve got it.

Continue reading →

de novo Small Molecule Design using Deep Learning

This is an interesting paper by Zhavoronkov, et al. that recently got published in Nature Biotechnology as a brief communication: https://www.nature.com/articles/s41587-019-0224-x. The paper describes a new deep generative model called generative tensorial reinforcement learning (GENTRL), which enables optimization for synthetic feasibility, novelty, and biological activity. In this work, authors have deigned, synthesized, and experimentally validated molecules targeting discoidin domain receptor 1 (DDR1) in less than two months. The code for GENTRL is available here: https://github.com/insilicomedicine/gentrl.

Reference: Zhavoronkov, A. et al. Deep learning enables rapid identification of potent DDR1 kinase inhibitors. Nature Biotechnology 2019, 37, 1038-1040.