So where are we with deep learning for biochem? — lada nuzhna

ladanuzhna.xyz · 3,090 words · saved by 2 readers

I have been periodically noticing an impression that for ages biology and chemistry have been done with rocks and sticks in caves until deep learning was brought to wet labs by computer scientists, akin to Prometheus bringing fire to mankind. Here I tried to address that impression and go over all t

So where are we with deep learning for biochem? We have forty million compounds and their screenings in Pubmed, zetta-bases of newly sequenced data every year, the full transcriptome of aging mice, and comprehensive maps of the epigenome, yet machine learning and deep learning haven't generated much radical insight from all of this (quite yet). Computational tools are currently in an assistant role at best and, arguably, there is nothing new here. Computer-aided drug design has been around since the 60s (e.g., Dendral). Structure-activity relationship analysis and chemoinformatics, both comput

So where are we with deep learning for biochem? — lada nuzhna

saved by

related reading