ExUniProt-answers - Revision history

Henni: /* On your own, with and without AI */

2026-09-06T16:21:19Z

On your own, with and without AI

← Older revision		Revision as of 18:21, 6 September 2026
Line 128:		Line 128:
	(protein_name:"Hemoglobin subunit alpha" OR gene_exact:hba1 OR gene_exact:hba2 OR gene_exact:hba)		(protein_name:"Hemoglobin subunit alpha" OR gene_exact:hba1 OR gene_exact:hba2 OR gene_exact:hba)
	:giving 37 hits without false positives, even better.		:giving 37 hits without false positives, even better.
	* ChatGPT (free version): required two prompts before it came up with the query string <tt>(protein_name:"hemoglobin subunit alpha" OR protein_name:"alpha-globin") AND taxonomy_id:9845</tt>, giving 57 hits ~~inlcuding~~ the "Alpha-globin transcription factor CP2" false positives.		* ChatGPT (free version): required two prompts before it came up with the query string <tt>(protein_name:"hemoglobin subunit alpha" OR protein_name:"alpha-globin") AND taxonomy_id:9845</tt>, giving 58 hits including the "Alpha-globin transcription factor CP2" false positives.

	'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.		'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.
			* Google: <tt>gene:HBA* AND organism:"Columba livia"</tt> which does not work. However, it also suggests replacing the last part with <tt>taxonomy_id:8932</tt>, and then you get 3 hits. Whether the last TrEMBL hit ("Hemoglobin subunit alpha-D-like") is a false positive can be discussed.
			* Copilot: gives several suggestion, of which only some are functional, e.g. <tt>organism_id:8932 AND (gene:hbaa OR gene:hbad OR protein_name:"alpha-A globin" OR protein_name:"alpha-D globin")</tt> (3 hits).
			* ChatGPT (free version): <tt>organism_name:"Columba livia" AND (gene_exact:HBAA OR gene_exact:HBAD)</tt> (3 hits).
			Note that you can shorten the last suggestion to <tt>organism_name:"Columba livia" AND (gene_exact:HBA*)</tt>

Henni: /* On your own, with and without AI */

2026-09-06T15:59:37Z

On your own, with and without AI

← Older revision		Revision as of 17:59, 6 September 2026
Line 108:		Line 108:

	Using the prompt "How would you find insulin from as many organisms as possible from UniProt, without including entries that are not insulin?":		Using the prompt "How would you find insulin from as many organisms as possible from UniProt, without including entries that are not insulin?":
	* Google: <tt>family:"insulin family" AND gene:ins AND length:[50 TO 150]</tt> which gives 661 hits. Not bad.		* Google: <tt>family:"insulin family" AND gene:ins AND length:[50 TO 150]</tt> which gives 661 hits (Not bad).
	* Copilot:		* Copilot:
	((protein_name:"Insulin") OR		((protein_name:"Insulin") OR
Line 118:		Line 118:
	protein_name:"Insulin-induced"		protein_name:"Insulin-induced"
	)		)
	which gives 10,353 hits with way too many false positives. But it also suggests <tt>family:"Insulin family"</tt> (8,929 hits) and combining that with filtering on protein name.		:which gives 10,353 hits with way too many false positives. But it also suggests <tt>family:"Insulin family"</tt> (8,929 hits) and combining that with filtering on protein name.
	* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.		* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.

	'''QUESTION 4.4''': <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 15 hits.		'''QUESTION 4.4''':
			* Our answer: <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 15 hits.
			* Google: <tt>(gene:HBA* OR family:"hemoglobin alpha-type family") AND taxonomy_id:9895</tt>, 26 hits, actually better than our answer, because some entries were named "Hemoglobin subunit alpha" ''without'' "alpha globin" as an alternative name.
			* Copilot:
			taxonomy_id:9845 AND
			(protein_name:"Hemoglobin subunit alpha" OR gene_exact:hba1 OR gene_exact:hba2 OR gene_exact:hba)
			:giving 37 hits without false positives, even better.
			* ChatGPT (free version): required two prompts before it came up with the query string <tt>(protein_name:"hemoglobin subunit alpha" OR protein_name:"alpha-globin") AND taxonomy_id:9845</tt>, giving 57 hits inlcuding the "Alpha-globin transcription factor CP2" false positives.

	'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.		'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.

Henni: /* On your own, with and without AI */

2026-09-04T15:32:02Z

On your own, with and without AI

← Older revision		Revision as of 17:32, 4 September 2026
Line 121:		Line 121:
	* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.		* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.

	'''QUESTION 4.4''': <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 17 hits.		'''QUESTION 4.4''': <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 15 hits.

	'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.		'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.

Henni: /* On your own, with and without AI */

2026-09-04T15:29:15Z

On your own, with and without AI

← Older revision		Revision as of 17:29, 4 September 2026
Line 118:		Line 118:
	protein_name:"Insulin-induced"		protein_name:"Insulin-induced"
	)		)
	which gives 10,353 hits with way too many false positives. But it also suggests <tt>family:"Insulin family"</tt> (8,929 hits).		which gives 10,353 hits with way too many false positives. But it also suggests <tt>family:"Insulin family"</tt> (8,929 hits) and combining that with filtering on protein name.
	* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.		* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.

Henni: /* On your own, with and without AI */

2026-09-04T15:28:02Z

On your own, with and without AI

← Older revision		Revision as of 17:28, 4 September 2026
Line 98:		Line 98:
	* ChatGPT (free version): "The exact query to run in UniProt is: <tt>taxonomy_id:562</tt>" (Fair enough).		* ChatGPT (free version): "The exact query to run in UniProt is: <tt>taxonomy_id:562</tt>" (Fair enough).

	'''QUESTION 4.2''': <tt>(taxonomy_id:83334)</tt>, 5,999 hits.		'''QUESTION 4.2''': <tt>(taxonomy_id:83334)</tt>, 5,999 hits.<br>
	Using the question verbatim as a prompt yielded:		Using the question verbatim as a prompt yielded:
	* Google: "The raw total climbs into the '''hundreds of thousands of protein entries''', primarily sitting unreviewed within TrEMBL" (!). However, asking it to provide the"UniProt query syntax" gave the correct search string.		* Google: "The raw total climbs into the '''hundreds of thousands of protein entries''', primarily sitting unreviewed within TrEMBL" (!). However, asking it to provide the "UniProt query syntax" gave the correct search string.
	* Copilot: 5,999 (correct). However, it falsely claims that the queries <tt>organism_id:83334</tt> and <tt>taxonomy_id:83334</tt> are equivalent. They are not (try for yourself).		* Copilot: 5,999 (correct). However, it falsely claims that the queries <tt>organism_id:83334</tt> and <tt>taxonomy_id:83334</tt> are equivalent. They are not (try for yourself).
			* ChatGPT (free version): 9,080 (wrong). Asking it to provide the "UniProt query syntax" gave the wrong answer <tt>taxonomy_id:83334</tt>.

	'''QUESTION 4.3''': <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>		'''QUESTION 4.3''': This is a question that does not have one single correct answer. A good attempt could be:<br>
	(~~This is a question that~~ does not ~~have one single correct answer)~~		<tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>

			Using the prompt "How would you find insulin from as many organisms as possible from UniProt, without including entries that are not insulin?":
			* Google: <tt>family:"insulin family" AND gene:ins AND length:[50 TO 150]</tt> which gives 661 hits. Not bad.
			* Copilot:
			((protein_name:"Insulin") OR
			(protein_name:"Insulin-1") OR
			(protein_name:"Insulin-2"))
			NOT (
			protein_name:"Insulin receptor" OR
			protein_name:"Insulin-like growth factor" OR
			protein_name:"Insulin-induced"
			)
			which gives 10,353 hits with way too many false positives. But it also suggests <tt>family:"Insulin family"</tt> (8,929 hits).
			* ChatGPT (free version): does not come up with a useful UniProt query string, but suggests a lengthy workflow involving BLAST.

	'''QUESTION 4.4''': <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 17 hits.		'''QUESTION 4.4''': <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 17 hits.

	'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.		'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.

Henni: /* On your own, with and without AI */

2026-09-04T14:13:09Z

On your own, with and without AI

← Older revision		Revision as of 16:13, 4 September 2026
Line 101:		Line 101:
	Using the question verbatim as a prompt yielded:		Using the question verbatim as a prompt yielded:
	* Google: "The raw total climbs into the '''hundreds of thousands of protein entries''', primarily sitting unreviewed within TrEMBL" (!). However, asking it to provide the"UniProt query syntax" gave the correct search string.		* Google: "The raw total climbs into the '''hundreds of thousands of protein entries''', primarily sitting unreviewed within TrEMBL" (!). However, asking it to provide the"UniProt query syntax" gave the correct search string.
	* Copilot: 5,999 (correct). However, it falsely claims that the queries organism_id:83334 and taxonomy_id:83334 are equivalent. They are not (try for yourself).		* Copilot: 5,999 (correct). However, it falsely claims that the queries <tt>organism_id:83334</tt> and <tt>taxonomy_id:83334</tt> are equivalent. They are not (try for yourself).

	'''QUESTION 4.3''': <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>		'''QUESTION 4.3''': <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>

Henni: /* On your own, with and without AI */

2026-09-04T14:12:07Z

On your own, with and without AI

← Older revision		Revision as of 16:12, 4 September 2026
Line 96:		Line 96:
	* Google: "Searching broadly for all ''E. coli'' strains captures a pool of '''30 to 45 million entries'''" (!).		* Google: "Searching broadly for all ''E. coli'' strains captures a pool of '''30 to 45 million entries'''" (!).
	* Copilot: 68,344 UniProtKB protein entries (that's an error of 2).		* Copilot: 68,344 UniProtKB protein entries (that's an error of 2).
	* ChatGPT (free version): "The exact query to run in UniProt is: <tt>taxonomy_id:562</tt>". Fair enough.		* ChatGPT (free version): "The exact query to run in UniProt is: <tt>taxonomy_id:562</tt>" (Fair enough).

	'''QUESTION 4.2''': <tt>(taxonomy_id:83334)</tt>, 5,999 hits.		'''QUESTION 4.2''': <tt>(taxonomy_id:83334)</tt>, 5,999 hits.
			Using the question verbatim as a prompt yielded:
			* Google: "The raw total climbs into the '''hundreds of thousands of protein entries''', primarily sitting unreviewed within TrEMBL" (!). However, asking it to provide the"UniProt query syntax" gave the correct search string.
			* Copilot: 5,999 (correct). However, it falsely claims that the queries organism_id:83334 and taxonomy_id:83334 are equivalent. They are not (try for yourself).

	'''QUESTION 4.3''': <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>		'''QUESTION 4.3''': <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>

Henni: /* On your own */

2026-09-04T13:53:24Z

On your own

← Older revision		Revision as of 15:53, 4 September 2026
Line 89:		Line 89:
	AGEPKLDAGV		AGEPKLDAGV

	== On your own ==		== On your own, with and without AI ==

	QUESTION 4.1: <tt>(taxonomy_id:562)</tt>, ~~762~~,~~443~~ hits.		'''QUESTION 4.1''': <tt>(taxonomy_id:562)</tt>, 68,346 hits.

	~~QUESTION 4~~.2: <tt>(taxonomy_id:~~83334)~~</tt>~~, 18,197 hits~~.		Using the question verbatim as a prompt yielded:
			* Google: "Searching broadly for all ''E. coli'' strains captures a pool of '''30 to 45 million entries'''" (!).
			* Copilot: 68,344 UniProtKB protein entries (that's an error of 2).
			* ChatGPT (free version): "The exact query to run in UniProt is: <tt>taxonomy_id:562</tt>". Fair enough.

	QUESTION 4.3: <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>		'''QUESTION 4.2''': <tt>(taxonomy_id:83334)</tt>, 5,999 hits.

			'''QUESTION 4.3''': <tt>(protein_name:insulin) AND (gene:ins) NOT (protein_name:insulin-like) NOT (protein_name:"insulin related")</tt>, 602 hits<br>
	(This is a question that does not have one single correct answer)		(This is a question that does not have one single correct answer)

	QUESTION 4.4: <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 17 hits.		'''QUESTION 4.4''': <tt>(protein_name:"alpha globin") AND (taxonomy_id:9845) NOT (protein_name:"transcription factor")</tt>, 17 hits.

	QUESTION 4.5: <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.		'''QUESTION 4.5''': <tt>(protein_name:"alpha-* globin") AND (taxonomy_id:8932)</tt>, 2 hits.

Henni: /* Text format */

2026-09-03T16:11:44Z

Text format

← Older revision		Revision as of 18:11, 3 September 2026
Line 48:		Line 48:
	===Text format===		===Text format===

	''~~No questions asked here~~.''		'''QUESTION 2.7:''' Find the two feature table lines that describe the signal peptide and copy them to your answer.
			FT SIGNAL 1..24
			FT /evidence="ECO:0000269\|PubMed:14426955"

	==Advanced search==		==Advanced search==

Henni: /* Other databases linked from UniProt */

2026-09-03T15:40:31Z

← Older revision		Revision as of 17:40, 3 September 2026
Line 44:		Line 44:
	[[Image:PDB9R4E.png]]		[[Image:PDB9R4E.png]]

	'''QUESTION 2.6:''' What is the InterPro identifier of the family that is just called "Insulin" and nothing else?		'''QUESTION 2.6:''' What is the InterPro identifier of the family that is just called "Insulin" and nothing else? <br>IPR004825.

	===Text format===		===Text format===