Application of Machine Learning and Natural Language Processing for - - PowerPoint PPT Presentation

▶
application of machine learning and natural language
SMART_READER_LITE
LIVE PREVIEW

Application of Machine Learning and Natural Language Processing for - - PowerPoint PPT Presentation

Apr 27, 2023 318 likes •727 views

Application of Machine Learning and Natural Language Processing for Phage Therapy 2.0 Piotr Tynecki with Yana Minina, Iwona witochowska, Joanna Kazimierczak and Arkadiusz Guziski co-op PyWaw, 18.05.2020 Who Am I? 2 3 4 5 6 How can

slide-1
SLIDE 1

Application of Machine Learning and Natural Language Processing for Phage Therapy 2.0

Piotr Tynecki

PyWaw, 18.05.2020

with Yana Minina, Iwona Świętochowska, Joanna Kazimierczak and Arkadiusz Guziński co-op

slide-2
SLIDE 2

Who Am I?

2

slide-3
SLIDE 3

3

slide-4
SLIDE 4

4

slide-5
SLIDE 5

5

slide-6
SLIDE 6

6

slide-7
SLIDE 7

How can we help?

7

Predict which bacteriophages could be applicate as alternatives to antibiotics in Clinical Care

slide-8
SLIDE 8

Who support us

8

Business partners Academic partners

slide-9
SLIDE 9

Phage Life Cycles - issue 1

9

slide-10
SLIDE 10

10

slide-11
SLIDE 11

98,90%

Life cycle recognition accuracy

11

slide-12
SLIDE 12

12

slide-13
SLIDE 13

13

Source: U.S. National Library of Medicine
slide-14
SLIDE 14

14

GGTAGAATGGNTTTCA... GGTAGA GTAGAA TAGAAT AGAATG GAATGG AATGGN ...

[2] 6-mer transformer

slide-15
SLIDE 15

15

GGTAGAATGGNTTTCA... GGTAGA GTAGAA TAGAAT AGAATG GAATGG AATGGN ...

[2] 6-mer transformer

slide-16
SLIDE 16

16

GGTAGAATGGNTTTCA... GGTAGA GTAGAA TAGAAT AGAATG GAATGG AATGGN ...

[2] 6-mer transformer

slide-17
SLIDE 17

17

GGTAGAATGGNTTTCA... GGTAGA GTAGAA TAGAAT AGAATG GAATGG AATGGN ...

[2] 6-mer transformer

slide-18
SLIDE 18

18

6-mers (bag of words) Word2Vec Skip-gram + RFECV

[[ 0.15740727, 0.14283979, 0.01424173, ..., -0.04863179, 0.36005523, 0.04962862], [ 0.14294244, 0.06846078, 0.03159813, ..., -0.02003489, 0.29529446, 0.07867343], [ 0.14319768, 0.06886728, 0.03136309, ..., -0.01986326, 0.29515907, 0.07877837], ..., [ 0.14686785, 0.10228563, 0.02458559, ..., -0.03324442, 0.32741652, 0.04950592], [ 0.16520534, 0.14164333, 0.01523334, ..., -0.01981086, 0.37183095, 0.02930221], [ 0.14716548, 0.05672845, 0.03785585, ..., -0.0188462 , 0.27017442, 0.0712469 ]]

[3] DNA embeddings: average Word2Vec

slide-19
SLIDE 19

19

Virulent and Temperate phages from training set after Word2Vec vectorization and t-SNE decompression.
slide-20
SLIDE 20

20

[5] Training & Tuning

  • MultinomialNB
  • RandomForest
  • MLPClassifier
  • LogisticRegression
  • XGBoost
  • SVM
  • GradientBoosting
  • SGDClassifier
  • KNeighborsClassifier
  • CatBoostClassifier
  • LightGBM
  • TF-IDF
  • Word2Vec (Skip-gram/CBoW)
  • fastText
  • DNA2Vec
  • fastDNA

BayesSearchCV

slide-21
SLIDE 21

EVALUATION

98.90% Validation set (20%) 99.17% Training set (80%) 100.00% Testing set

(61 samples)

21

slide-22
SLIDE 22

Article

22 22

PhageAI - bacteriophage life cycle recognition with Machine Learning and Natural Language Processing Q1 2020

slide-23
SLIDE 23

Taxonomy of Viruses - issue 2

23

slide-24
SLIDE 24

24

Source: nature.com/articles/s41564-020-0709-x
slide-25
SLIDE 25

25

Source: Mohammed AlQuraishi
slide-26
SLIDE 26

26

Source: Mohammed AlQuraishi

39,962,345 proteins sequences

slide-27
SLIDE 27

27

Source: Peters, Matthew E., et al. "Deep contextualized word representations." arXiv preprint arXiv:1802.05365 (2018).
slide-28
SLIDE 28

28

Source: M Heinzinger, et al. "Modeling the Language of Life-Deep Learning Protein Sequences" (2019)
slide-29
SLIDE 29

29 29

F amily Taxonomy: ELMo + SVM

Accuracy: 97.35% AUC: 99.57% Classification report: precision recall f1-score support 0 0.90 0.95 0.93 20 1 1.00 1.00 1.00 1 2 1.00 1.00 1.00 3 3 1.00 1.00 1.00 1 4 1.00 1.00 1.00 4 5 1.00 1.00 1.00 1 6 1.00 1.00 1.00 21 7 1.00 1.00 1.00 19 8 0.80 1.00 0.89 4 9 1.00 1.00 1.00 3 10 1.00 0.99 1.00 119 11 0.92 0.92 0.92 61 12 1.00 1.00 1.00 4 13 1.00 0.97 0.99 35 14 1.00 1.00 1.00 3 15 0.97 0.97 0.97 108 16 1.00 1.00 1.00 2 17 1.00 1.00 1.00 5 18 1.00 1.00 1.00 1 accuracy 0.97 415 macro avg 0.98 0.99 0.98 415 weighted avg 0.97 0.97 0.97 415 Training set score: 99.90% Validation set score: 97.35%
slide-30
SLIDE 30

30 30

F amily Taxonomy: ELMo + SVM (PCA(50) -> UMAP)

slide-31
SLIDE 31

31 31

slide-32
SLIDE 32

Phage-Host matching

  • issue 4

32

Deep Generative Networks for Bacteriophages Genetic Edition

  • issue 5

What else…?

The Structure and Function of Proteins

  • issue 3
slide-33
SLIDE 33

33

The Future of Phages Science will not be Supervised...

slide-34
SLIDE 34

34

Bacteriophages: the cure for antibiotics resistance Phage Therapy: An Effective Alternative to Antibiotics? Using Viruses to Fight Antibiotic-Resistant Infections

Must see & read

slide-35
SLIDE 35

35

Data sources

slide-36
SLIDE 36

Thank you for your attention Any questions?

Twitter: @ptynecki LinkedIn: piotrtynecki E-mail: p.tynecki@doktoranci.pb.edu.pl

36

slide-37
SLIDE 37

37

[5] Evaluation

slide-38
SLIDE 38

38

Virus Activity Detector

for Education and Research

slide-39
SLIDE 39

39