A primer on why computational predictive toxicology is hard
substack.com · 3,446 words · saved by 1 readers
3.4k words, 16 minutes reading time
Introduction Some background The hard stuff The relevance of toxicity datasets to the clinical problem Methodological problems in toxicity datasets Intraspecies toxicity variability Toxicity synergism Conclusions There are now (claimed) foundation models for protein sequences, DNA sequences, RNA sequences, molecules, scRNA-seq, chromatin accessibility, pathology slides, medical images, electronic health records, and clinical free-text. It’s a dizzying rate of progress. But there’s a few problems in biology that, interestingly enough, have evaded a similar level of ML progress,…
saved by
related reading
- A primer on why computational predictive toxicology is hardowlposting.com
- AI After Drug Developmentasteriskmag.substack.com
- A Conversation With Navvye Anand (Bindwell) | Rowanrowansci.com
- Generative ML in chemistry is bottlenecked by synthesisowlposting.com
- Gap Mapgap-map.org
- The ML drug discovery startup trying really, really hard to not cheat (Leash Bio)owlposting.com
- We Need Better Benchmarks for Machine Learning in Drug Discoverypracticalcheminformatics.blogspot.com
- Practical Cheminformatics Index - Practical Cheminformaticspatwalters.github.io
- So where are we with deep learning for biochem?ladanuzhna.xyz
- Why is progress in biology so slow?sam-rodriques.com
- Five things to keep in mind while reading biology ML papersowlposting.com
- What will it take for AI to change drug discovery?writingruxandrabio.com