Skip to main content

Table 4 Toxin identification on tuning data set

From: Classifying literature mentions of biological pathogens as experimentally studied using natural language processing

Dictionary

TP

Positives

FP + TP

Precision

Recall

F1

aflatoxins

9106

10,131

9109

0.9997

0.8988

0.9466

botulinum

9903

16,780

9915

0.9988

0.5902

0.7419

ciguatoxins

386

529

390

0.9897

0.7297

0.8400

conotoxins

2340

3144

2453

0.9539

0.7443

0.8362

Regex

TP

Positives

FP + TP

Precision

Recall

F1

aflatoxins

9127

10,131

9130

0.9988

0.9009

0.9477

botulinum

13,664

16,780

13,697

0.9976

0.8143

0.8967

ciguatoxins

386

529

390

0.9897

0.7297

0.8400

conotoxins

2352

3144

2465

0.9542

0.7481

0.8387