Reading Derek Lowe with Perplexity

😵‍💫 Always stimulated by Derek Lowe's writings (in spite of an average 50% agreement rate), I tried (a condensed version of) his OpenAI Deep Research prompt on the toxic effects of thalidomide with Perplexity Deep Research:

"I want you to write a research report on summarize the toxic effects of thalidomide with respect to different species and different isomers of the compound, and what’s known about the mechanism for those effects. This report should be constrained to (1) the toxic effects of thalidomide with respect to (a) different species (b) different isomers of the compound and (2) What is known about the mechanism for those effects. Within this scope, it would be preferable to be quite detailed as your work will be scrutinized by a subject matter expert."

I didn't need to add the following: "Please conduct multi-step research across the web to find the best possible sources. You may: 1. Search for initial keywords and refine as you learn more. 2. Visit reputable sites, journals, or official databases related to the topic. 3. Synthesize information from multiple articles, PDFs, or studies. 4. Expand or pivot the search as needed based on new insights" because Perplexity does that by construction and lists all references.

💡 The resulting report touches all the important points, e.g., enantiomer interconversion and in vivo racemization or the 2010 discovery of cereblon (CRBN) binding ("Recent structural studies using deuterium-stabilized enantiomers reveal that the (S)-isomer binds CRBN with 10-fold higher affinity than the (R)-form, inhibiting its E3 ubiquitin ligase activity"). It gives recent research more weight and... even includes Derek Lowe's Science Magazine blog post as a reference (link). Protein degradation and PROTACs are cited but the report does not go into the creation of the field of protein degradation as a consequence of the CRBN finding. But unlike Derek, I don't think it was an obligation implicit in the prompt: the focus was clearly stated and the system complied. You can't complain about the system not following orders and also about the system following orders.

You could ask explicitly for the broader impact of the CRBN discovery and you shall receive: "The identification of cereblon (CRBN) as the primary target of thalidomide and its derivatives marked a paradigm shift in drug discovery, catalyzing advancements across structural biology, chemical synthesis, and therapeutic design. This breakthrough not only elucidated the molecular basis of thalidomide's teratogenicity and anti-cancer activity but also laid the foundation for novel technologies such as proteolysis-targeting chimeras (PROTACs) and molecular glue degraders (MGDs)."

I ❤️ Perplexity