Exercise:AllergenicityPrediction - Revision history

Carol: /* PART B: Can you beat BLAST? */

2026-09-29T20:39:08Z

PART B: Can you beat BLAST?

← Older revision		Revision as of 22:39, 29 September 2026
Line 93:		Line 93:

	*'''Q6:''' Where does the model make mistakes? Imagine that this predictor is being used as an initial "screening tool for proteins in a novel food".		*'''Q6:''' Where does the model make mistakes? Imagine that this predictor is being used as an initial "screening tool for proteins in a novel food".


	'''Accuracy is not the whole story''' Two models can have similar accuracy while behaving differently towards allergens and non-allergens.		'''Accuracy is not the whole story''' Two models can have similar accuracy while behaving differently towards allergens and non-allergens.

	Inspect the '''ROC curve''' generated by the notebook. The diagonal line represents the performance expected from random classification. An AUC of approximately 0.5 corresponds to random discrimination, whereas a value approaching 1.0 indicates increasingly good separation between the two classes.		Inspect the '''ROC curve''' generated by the notebook. The diagonal line represents the performance expected from random classification. An AUC of approximately 0.5 corresponds to random discrimination, whereas a value approaching 1.0 indicates increasingly good separation between the two classes.


	*'''Q7:''' Why it makes more sense to use AUC than accuracy to report performance. Record the AUC of your model.		*'''Q7:''' Why it makes more sense to use AUC than accuracy to report performance. Record the AUC of your model.

Carol: /* PART A: Investigating Allergenicity */

2026-09-29T20:35:52Z

PART A: Investigating Allergenicity

← Older revision		Revision as of 22:35, 29 September 2026
Line 43:		Line 43:
	We could try to run NetAllergen on our protein of interest, but the server will crash if too many people start to run jobs, instead we will follow an alternative approach		We could try to run NetAllergen on our protein of interest, but the server will crash if too many people start to run jobs, instead we will follow an alternative approach

	*'''Q2:''' Now imagine that no computational predictor specifically designed for allergenicity has yet been developed. How could you attempt to predict allergenicity in silico? Which existing protein predictions or sequence properties could potentially be used as proxies for allergenicity? There is not necessarily a single correct solution here. Think about what biological properties characterize allergens and what computational tools could provide information about those properties.		Now imagine that no computational predictor specifically designed for allergenicity has yet been developed. How could you attempt to predict allergenicity in silico? Which existing protein predictions or sequence properties could potentially be used as proxies for allergenicity? There is not necessarily a single correct solution here. Think about what biological properties characterize allergens and what computational tools could provide information about those properties.

	'''Sequence Similarity and Cross-Reactivity'''		'''Sequence Similarity and Cross-Reactivity'''

	Allergic reactions are not always restricted to the protein that originally caused sensitization. Antibodies recognizing one allergen may sometimes recognize structurally or evolutionarily related proteins from another organism. Is there any approach to search for sequence similarity to a known allergen?		Allergic reactions are not always restricted to the protein that originally caused sensitization. Antibodies recognizing one allergen may sometimes recognize structurally or evolutionarily related proteins from another organism. Is there any approach to search for sequence similarity to a known allergen? Is there another approaches to search than sequence similarity? What about structure

	*'''Q3:''' Based on your investigation, could an immunotherapy ~~targeting an existing allergen~~ potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?		*'''Q2:''' Based on the above is there any other tool beyond NetAllergen that can be used as a proxy to predict allergenicity in silico?

			*'''Q3:''' Based on your investigation, could immunotherapy potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer. What would have to be true about the algal proteins for such cross-reactivity to be plausible?

	== PART B: Can you beat BLAST? ==		== PART B: Can you beat BLAST? ==

Carol at 20:27, 29 September 2026

2026-09-29T20:27:54Z

← Older revision		Revision as of 22:27, 29 September 2026
Line 39:		Line 39:
	Every good bioinformatics investigation starts by asking what information is already available.		Every good bioinformatics investigation starts by asking what information is already available.

	*'''~~Q1A~~:''' What would be your first approach to determine whether brown algae contain potential allergens? Find one database containing experimentally characterized allergens. Consider what biological information you would search for and what properties of the proteins might provide evidence of allergenic potential.		*'''Q1:''' What would be your first approach to determine whether brown algae contain potential allergens? Find one database containing experimentally characterized allergens. Consider what biological information you would search for and what properties of the proteins might provide evidence of allergenic potential.

	*'''~~Q1B~~:''' Now imagine that no computational predictor specifically designed for allergenicity has yet been developed. How could you attempt to predict allergenicity in silico? Which existing protein predictions or sequence properties could potentially be used as proxies for allergenicity? There is not necessarily a single correct solution here. Think about what biological properties characterize allergens and what computational tools could provide information about those properties.		We could try to run NetAllergen on our protein of interest, but the server will crash if too many people start to run jobs, instead we will follow an alternative approach

			*'''Q2:''' Now imagine that no computational predictor specifically designed for allergenicity has yet been developed. How could you attempt to predict allergenicity in silico? Which existing protein predictions or sequence properties could potentially be used as proxies for allergenicity? There is not necessarily a single correct solution here. Think about what biological properties characterize allergens and what computational tools could provide information about those properties.

	'''Sequence Similarity and Cross-Reactivity'''		'''Sequence Similarity and Cross-Reactivity'''

	Allergic reactions are not always restricted to the protein that originally caused sensitization. Antibodies recognizing one allergen may sometimes recognize structurally or evolutionarily related proteins from another organism.		Allergic reactions are not always restricted to the protein that originally caused sensitization. Antibodies recognizing one allergen may sometimes recognize structurally or evolutionarily related proteins from another organism. Is there any approach to search for sequence similarity to a known allergen?

	~~ALK has developed allergen immunotherapy treatments against house dust mites. One of the major allergens from Dermatophagoides pteronyssinus is Der p 1.~~

	~~Following prolonged allergen immunotherapy, many patients show reduced allergic symptoms towards house dust mites. Interestingly, reductions in reactions~~ to ~~some other allergens have also been observed.~~

	~~Let us investigate one possible explanation.~~
	~~Retrieve the protein~~ sequence ~~of Der p 1 and investigate whether similar proteins occur among known allergens from other species.~~

	Go to ~~the [https://blast.ncbi.nlm.nih.gov/Blast.cgi NCBI BLAST server] In particular, consider allergens associated with papaya and pineapple (Ananas).~~

	*'''Q2:''' Can you identify a possible molecular explanation for cross-reactivity between these allergens? Consider: Sequence similarity, Protein family and function, Conserved regions that could potentially be recognized by the same antibodies. Do your observations support the hypothesis that these proteins could exhibit immunological cross-reactivity? ~~Explain your reasoning.~~

	~~Back to Brown Algae~~
	~~We can now return to our original food-safety problem.~~

	*'''Q3:''' Based on your investigation, could an immunotherapy targeting an existing allergen potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?		*'''Q3:''' Based on your investigation, could an immunotherapy targeting an existing allergen potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?

Carol: /* PART C Can you beat the baseline? */

2026-09-29T20:12:21Z

PART C Can you beat the baseline?

← Older revision		Revision as of 22:12, 29 September 2026
Line 132:		Line 132:
	You may use '''ChatGPT or other language models''' to help you modify the code. However, you should understand what you changed and be able to explain why you expected it to help.		You may use '''ChatGPT or other language models''' to help you modify the code. However, you should understand what you changed and be able to explain why you expected it to help.

	'''Q9:''' Provide a rationale for the change and report the new performance.		*'''Q9:''' Provide a rationale for the change and report the new performance.

	'''Q10:''' Did your modification improve allergenicity prediction?		*'''Q10:''' Did your modification improve allergenicity prediction?

	== Conclusion ===		== Conclusion ===

Carol: /* PART B: Can you beat BLAST */

2026-09-29T20:11:21Z

PART B: Can you beat BLAST

← Older revision		Revision as of 22:11, 29 September 2026
Line 63:		Line 63:
	*'''Q3:''' Based on your investigation, could an immunotherapy targeting an existing allergen potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?		*'''Q3:''' Based on your investigation, could an immunotherapy targeting an existing allergen potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?

	== PART B: Can you beat BLAST ==		== PART B: Can you beat BLAST? ==

	You will now develop your own allergenicity predictor using a Random Forest classifier in Google Colab. If you have not used Google Colab before, you can find an introduction [https://colab.research.google.com/notebooks/basic_features_overview.ipynb here]		You will now develop your own allergenicity predictor using a Random Forest classifier in Google Colab. If you have not used Google Colab before, you can find an introduction [https://colab.research.google.com/notebooks/basic_features_overview.ipynb here]

Carol: /* PART B: Can you beat BLAST */

2026-09-29T20:11:09Z

PART B: Can you beat BLAST

Carol: /* PART A: Investigating Allergenicity */

2026-09-29T20:10:32Z

PART A: Investigating Allergenicity

← Older revision		Revision as of 22:10, 29 September 2026
Line 56:		Line 56:
	Go to the [https://blast.ncbi.nlm.nih.gov/Blast.cgi NCBI BLAST server] In particular, consider allergens associated with papaya and pineapple (Ananas).		Go to the [https://blast.ncbi.nlm.nih.gov/Blast.cgi NCBI BLAST server] In particular, consider allergens associated with papaya and pineapple (Ananas).

	'''Q2:''' Can you identify a possible molecular explanation for cross-reactivity between these allergens? Consider: Sequence similarity, Protein family and function, Conserved regions that could potentially be recognized by the same antibodies. Do your observations support the hypothesis that these proteins could exhibit immunological cross-reactivity? Explain your reasoning.		*'''Q2:''' Can you identify a possible molecular explanation for cross-reactivity between these allergens? Consider: Sequence similarity, Protein family and function, Conserved regions that could potentially be recognized by the same antibodies. Do your observations support the hypothesis that these proteins could exhibit immunological cross-reactivity? Explain your reasoning.

	Back to Brown Algae		Back to Brown Algae
	We can now return to our original food-safety problem.		We can now return to our original food-safety problem.

	'''Q3:''' Based on your investigation, could an immunotherapy targeting an existing allergen potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?		*'''Q3:''' Based on your investigation, could an immunotherapy targeting an existing allergen potentially reduce allergic responses to proteins found in brown algae? Use sequence or protein-family evidence to justify your answer.What would have to be true about the algal proteins for such cross-reactivity to be plausible?

	== PART B: Can you beat BLAST ==		== PART B: Can you beat BLAST ==

Carol: /* PART A: Investigating Allergenicity */

2026-09-29T20:10:16Z

PART A: Investigating Allergenicity

← Older revision		Revision as of 22:10, 29 September 2026
Line 34:		Line 34:

	== PART A: Investigating Allergenicity ==		== PART A: Investigating Allergenicity ==


	'''Where Would You Start?'''		'''Where Would You Start?'''
Line 40:		Line 39:
	Every good bioinformatics investigation starts by asking what information is already available.		Every good bioinformatics investigation starts by asking what information is already available.

	'''Q1A:''' What would be your first approach to determine whether brown algae contain potential allergens? Find one database containing experimentally characterized allergens. Consider what biological information you would search for and what properties of the proteins might provide evidence of allergenic potential.		*'''Q1A:''' What would be your first approach to determine whether brown algae contain potential allergens? Find one database containing experimentally characterized allergens. Consider what biological information you would search for and what properties of the proteins might provide evidence of allergenic potential.

	~~'''Q1B:''' Which approach would you use to predict allergic responses of a new protein? NetAllergen~~

	~~Now imagine that no computational predictor specifically designed for allergenicity has yet been developed~~.

	'''~~Q1C~~:''' How could you attempt to predict allergenicity in silico? Which existing protein predictions or sequence properties could potentially be used as proxies for allergenicity? There is not necessarily a single correct solution here. Think about what biological properties characterize allergens and what computational tools could provide information about those properties.		*'''Q1B:''' Now imagine that no computational predictor specifically designed for allergenicity has yet been developed. How could you attempt to predict allergenicity in silico? Which existing protein predictions or sequence properties could potentially be used as proxies for allergenicity? There is not necessarily a single correct solution here. Think about what biological properties characterize allergens and what computational tools could provide information about those properties.

	'''Sequence Similarity and Cross-Reactivity'''		'''Sequence Similarity and Cross-Reactivity'''

Carol: /* PART B: Can you beat BLAST */

2026-09-29T20:05:46Z

PART B: Can you beat BLAST

Carol: /* PART B: Can you beat BLAST */

2026-09-29T19:57:46Z

PART B: Can you beat BLAST

← Older revision		Revision as of 21:57, 29 September 2026
Line 117:		Line 117:
	'''Q7:''' Why it makes more sense to use AUC than accuracy to report performance. Record the AUC of your model.		'''Q7:''' Why it makes more sense to use AUC than accuracy to report performance. Record the AUC of your model.

	You now have a ~~'''~~baseline model'''		You now have a baseline model. Let's play with one of the random forest parameters. Number of estimators.

	'''Q8:''' How the number of estimators 10, 100, 1000 affects model performance?		'''Q8:''' How the number of estimators 10, 100, 1000 affects model performance?

	~~Keep these performance values. In Part C, your task will be to determine whether you can improve them.~~

	== PART C Can you beat the baseline? ==		== PART C Can you beat the baseline? ==

← Older revision		Revision as of 22:11, 29 September 2026
Line 74:		Line 74:
	You will first need to upload the data to google Colab. The data is placed in DTU Learn as data.csv		You will first need to upload the data to google Colab. The data is placed in DTU Learn as data.csv

	'''Q4:''' What will the model see? Inspect the data. How is the data structured? List the type of input features.		*'''Q4:''' What will the model see? Inspect the data. How is the data structured? List the type of input features.

	* Now pick a random seed (replace the default 42) and run the feature-generation and Random Forest training steps in the notebook.		Now pick a random seed (replace the default 42) and run the feature-generation and Random Forest training steps in the notebook.

	The notebook trains and tests the model using the different sequence partitions. For simplicity these partitions are provided to you in the data. However, remember that these are not random partitions of the data, instead the sequences have been clustered according to sequence homology so no similar proteins are contained across partitions. Predictions from the independent test partitions are then combined to obtain an overall evaluation of the model.		The notebook trains and tests the model using the different sequence partitions. For simplicity these partitions are provided to you in the data. However, remember that these are not random partitions of the data, instead the sequences have been clustered according to sequence homology so no similar proteins are contained across partitions. Predictions from the independent test partitions are then combined to obtain an overall evaluation of the model.
Line 91:		Line 91:
	ROC-AUC — ability of the model to discriminate allergens from non-allergens across different classification thresholds.		ROC-AUC — ability of the model to discriminate allergens from non-allergens across different classification thresholds.

	'''Q5:''' How well does it work? Report the performance of your predictor		*'''Q5:''' How well does it work? Report the performance of your predictor

	Inspect the '''confusion matrix''' produced by the notebook.		Inspect the '''confusion matrix''' produced by the notebook.
Line 102:		Line 102:
	False negative (FN): allergen → predicted non-allergen		False negative (FN): allergen → predicted non-allergen

	'''Q6:''' Where does the model make mistakes? Imagine that this predictor is being used as an initial "screening tool for proteins in a novel food".		*'''Q6:''' Where does the model make mistakes? Imagine that this predictor is being used as an initial "screening tool for proteins in a novel food".


Line 110:		Line 110:


	'''Q7:''' Why it makes more sense to use AUC than accuracy to report performance. Record the AUC of your model.		*'''Q7:''' Why it makes more sense to use AUC than accuracy to report performance. Record the AUC of your model.

	You now have a baseline model. Let's play with one of the random forest parameters. Number of estimators.		You now have a baseline model. Let's play with one of the random forest parameters. Number of estimators.

	'''Q8:''' How the number of estimators 10, 100, 1000 affects model performance?		*'''Q8:''' How the number of estimators 10, 100, 1000 affects model performance?

	== PART C Can you beat the baseline? ==		== PART C Can you beat the baseline? ==

← Older revision		Revision as of 22:05, 29 September 2026
Line 89:		Line 89:
	It will report several performance measures:		It will report several performance measures:

	:Accuracy — fraction of all predictions that are correct		Accuracy — fraction of all predictions that are correct
	:Precision — fraction of proteins predicted as allergens that actually are allergens		Precision — fraction of proteins predicted as allergens that actually are allergens
	:Recall (sensitivity) — fraction of allergens correctly identified by the predictor		Recall (sensitivity) — fraction of allergens correctly identified by the predictor
	:Specificity — fraction of non-allergens correctly identified.		Specificity — fraction of non-allergens correctly identified.
	:MCC (Matthews Correlation Coefficient) — overall agreement between predictions and observations, taking all four outcomes of the confusion matrix into account.		MCC (Matthews Correlation Coefficient) — overall agreement between predictions and observations, taking all four outcomes of the confusion matrix into account.
	:ROC-AUC — ability of the model to discriminate allergens from non-allergens across different classification thresholds.		ROC-AUC — ability of the model to discriminate allergens from non-allergens across different classification thresholds.

	'''Q5:''' How well does it work? Report the performance of your predictor		'''Q5:''' How well does it work? Report the performance of your predictor
Line 102:		Line 102:
	The four possible outcomes are:		The four possible outcomes are:

	:True positive (TP): allergen → predicted allergen		True positive (TP): allergen → predicted allergen
	:True negative (TN): non-allergen → predicted non-allergen		True negative (TN): non-allergen → predicted non-allergen
	:False positive (FP):non-allergen → predicted allergen		False positive (FP):non-allergen → predicted allergen
	:False negative (FN): allergen → predicted non-allergen		False negative (FN): allergen → predicted non-allergen

	'''Q6:''' Where does the model make mistakes? Imagine that this predictor is being used as an initial "screening tool for proteins in a novel food".		'''Q6:''' Where does the model make mistakes? Imagine that this predictor is being used as an initial "screening tool for proteins in a novel food".