extracting gene names

Question

[venkatarao142152]

I extracted bunch of abstracts from pubmed using the Entrez module. now I have the bunch of abstracts with me from this abstracts I want to extract gene names which are avilable in that abstracts. would anyone say he solution for this problem

[finswimmer]

• How large is "the bunch of abstracts"?
• Can you be sure that only the official gene names were used? Or is it possible that also synonyms are used?
• Are we talking about human genes?

[venkatarao142152]

1) the abstracts are 300 related to cancer 2) I need to extract official gene names seperately 3) I need to extract separately synonyms 4) I need to extract official and synonyms are both at a time 5) yes I am talking about human names' would you please share any ideas are process to complete this task.

[Naomi Most]

Gene Synonyms: https://www.genenames.org/

[Alex Reynolds]

Best Practice For Extracting Gene Names From Pubmed Abstracts

[venkatarao142152]

thankyou Alex Reynolds. I saw this but I didn't understand how its working. could please explain.

my requirement is I extracted all abstracts belongs to cancer now I want to extract gene names from that abstracts. could you please confirm this solution. thanks advance.

[Alex Reynolds]

I suggest reading the answers in the linked thread, which include explanations of what to do and how to do it.

Answer 1

[Emily]

Have you looked at the EuropePMC REST API?

[venkatarao142152]

here I am working in python. where I have extracted bunch of article abstracts. from that abstracts I want to extract gene names which are available in that bunch of abstracts. may I know he procedure. after getting this I have to apply any ML algorithm for the list of genes so I want to download as a list. thanks for your suggestion. now would you please provide a solution for my problem. thanks advance.

[Emily]

No, I have no obligation to provide you with a solution to your problem. I have provided you with a link to the documentation for an API which I know does something similar to what you're asking. It is your responsibility to read that documentation and work out how to do it. If you get stuck, then you can ask for help, but you have to try first.

[venkatarao142152]

thanks for your suggestion Emily. where I have tried maximum what I know and what I can do after that what's the error in my code or what the process to do next I don't no then I posted my query here. anyway thanks Emily

[jessypatricoski]

Thank you for this link, Emily! I've been looking everywhere for something like this (to extract gene names from unstructured clinical trial text) and haven't been able to find anything until now.

Cheers,

Jessica