{[ promptMessage ]}

Bookmark it

{[ promptMessage ]}

ECS124_Lecture14

# ECS124_Lecture14 - ECS 124 Theory and Practice of...

This preview shows pages 1–5. Sign up to view the full content.

ecture 14 : iological Motifs ECS 124 Theory and Practice of Bioinformatics Lecture 14 : Biological Motifs Instructor: Ilias Tagkopoulos Office: Kemper 3063 and GBSF 5313 5/19/2010 1 UC Davis

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
LAST TIME: Building a Naïve Bayes classifier c Now we would like to build a classifier that can tell whether a patient is likely to have cancer or not based on a protein X concentration. c Build a discriminative function: ¸¹º»¼¸ ³¹¾¾ ³¹¾¾ 5/19/2010 UC Davis 2 g G ± ² = ³´µ G ·¸¹º»¼¸ ± | ½³¹¾¾¿² ∙ ¶G½³¹¾¾¿² G ·¸¹º»¼¸ ± | ½³¹¾¾À² ∙ ¶G½³¹¾¾À²
LAST TIME: Putting together multiple features c Discriminative function for multiple features: c But if we assume independence (naïve bayes) gG±² = ³´µ G ·¸¹º»¼¸ ± ½ ,·¸¹º»¼¸ ± ¾ ,… ·¸¹º»¼¸ ± ¿ | À³¹ÁÁ½² ∙ ¶GÀ³¹ÁÁ½² ¶G·¸¹º»¼¸ ± ½ ,·¸¹º»¼¸ ± ¾ ,…·¸¹º»¼¸ ± ¿ |À³¹ÁÁ¾² ∙ ¶GÀ³¹ÁÁ¾² 5/19/2010 UC Davis 3 gG± ½ ,… , ± ¿ ² = ³´µ ∏ ¶G·¸¹º»¼¸ ± Â |À³¹ÁÁ½² ∙ ¶GÀ³¹ÁÁ½² ∏ ¶G·¸¹º»¼¸ ± Â |À³¹ÁÁ¾² ∙ ¶GÀ³¹ÁÁ¾²

This preview has intentionally blurred sections. Sign up to view the full version.

View Full Document
LAST TIME: Classification performance c Binary classification errors Really True Really False Predicted True TP FP Predicted False FN TN 5/19/2010 UC Davis 4 c Statistical measures : c Receiver Operating Characteristics Sensitivity = TP/(TP + FN) Specificity = TN/(TN+FP) Accuracy = (TP + TN)/ (P + N) Precision = TP / (TP + FP)
This is the end of the preview. Sign up to access the rest of the document.

{[ snackBarMessage ]}

### Page1 / 23

ECS124_Lecture14 - ECS 124 Theory and Practice of...

This preview shows document pages 1 - 5. Sign up to view the full document.

View Full Document
Ask a homework question - tutors are online