Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The business of extracting knowledge from academic publications

theseedsofscience.pub

Post reply on HN
Print view View original

81–85 of 85 posts

Re: The business of extracting knowledge from academic publications

#81

Post by pfisherman »

dilawar wrote: post #65
pfisherman wrote: post #14

Word of advice to all those who are chomping at the bit to disrupt pharma with AI. A pharmaceutical company that heavily leverages computation is called a pharmaceutical company. All modern pharmaceutical companies heavily leverage computational tools - including some powered by deep learning. Any company building a computational platform to accelerate drug discovery / development is not a pharmaceutical company. The…

Thanks for commenting. I've been thinking a bit about taking some computational insights we have developed over years to bioinformatics. During my Ph.D., my PI wanted to do some work on signalling pathway analysis. He was interested in knowing when and why sometimes body starts assuming that the sick state is the right state and start acting against drugs given to patients. This making treatment very hard. I don't kn…

Depends on what you want to use the data for. In general, you should take a trust but verify approach to new results, methods, data, etc.

Re: The business of extracting knowledge from academic publications

#82

Post by pama »

riku_iki wrote: post #75
pama wrote: post #70

Earlier quoted context omitted.

Also, and totally minor: there are nowhere close to 19k different approved small molecules. The same drug can be included in multiple products or formulations bringing that number you mentioned to 19k marketed products. Each generic formulation of iboprofen increases the latter count by 1. Counting all the marketed products of pure orange juice may add up to a large number but it is still one ingredient.

Yes, I compare drugs with drugs, not molecules with drugs.

No. The analysis in the paper above referred to molecules vs the snippet in the fda referred to products. More generally, other than marketing materials to doctors or patients or very rare exceptions talking about formulations etc, the scientific literature refers to the molecular entity as a drug not the particular named/branded product. I hope that the tool you are building will not mix up such concepts.

Re: The business of extracting knowledge from academic publications

#83

Post by riku_iki »

pama wrote: post #82
riku_iki wrote: post #75

Earlier quoted context omitted.

Yes, I compare drugs with drugs, not molecules with drugs.

No. The analysis in the paper above referred to molecules vs the snippet in the fda referred to products. More generally, other than marketing materials to doctors or patients or very rare exceptions talking about formulations etc, the scientific literature refers to the molecular entity as a drug not the particular named/branded product. I hope that the tool you are building will not mix up such concepts.

The link you posted found "1,578 US FDA-approved drugs"(exact citation).

Re: The business of extracting knowledge from academic publications

#84

Post by pama »

riku_iki wrote: post #83
pama wrote: post #82

Earlier quoted context omitted.

No. The analysis in the paper above referred to molecules vs the snippet in the fda referred to products. More generally, other than marketing materials to doctors or patients or very rare exceptions talking about formulations etc, the scientific literature refers to the molecular entity as a drug not the particular named/branded product. I hope that the tool you are building will not mix up such concepts.

The link you posted found "1,578 US FDA-approved drugs"(exact citation).

Yes that is the standard language in the field. It does not refer to the number of marketed products. Look up the number of novel drugs approved by the FDA per year. It only recently exceeded 40 per year, and the FDA has not existed for very long.

Re: The business of extracting knowledge from academic publications

#85

Post by riku_iki »

pama wrote: post #84
riku_iki wrote: post #83

Earlier quoted context omitted.

The link you posted found "1,578 US FDA-approved drugs"(exact citation).

Yes that is the standard language in the field. It does not refer to the number of marketed products. Look up the number of novel drugs approved by the FDA per year. It only recently exceeded 40 per year, and the FDA has not existed for very long.

if we consider that you are not making things up(which I am very not confident), then your link is useless in this discussion, because it doesn't give a sense how many non-protein targeting drugs were approved by FDA.
Post reply on HN