ML algorithms to find associations across biological data.pptx

S
Selvajeyanthi SAsst Professor of Microbiology um Shri Nehru Maha Vidyalaya College of Arts and Science
ARTIFICIAL INTELLIGENCE
FOR BIOLOGICAL SCIENCES
ML ALGORITHMS TO FIND ASSOCIATIONS
ACROSS BIOLOGICAL DATA
PREPARED BY:
MS. ABIRAMI.S
M. SC., MICROBIOLOGY
UNDER THE GUIDANCE OF :
MRS. S. SELVAJEYANTHI
ASST PROFESSOR
DEPARTMENT OF MICROBIOLOGY,
SNMV CAS
CONTENT
• Machine Learning
• Types of ML
• ML algorithm
• ML algorithm to find association across biological
data
• Conclusion
MACHINE LEARNING
• ML stands for "machine learning.“
• It's a subset of artificial intelligence that focuses on the development of
algorithms and models that allow computers to learn from data and
improve their performance on specific tasks over time.
• Instead of being explicitly programmed, these algorithms use data to
identify patterns, make predictions, and make decisions.
• Machine learning is used in various applications, such as image recognition,
language processing, recommendation systems, and more.
TYPES OF ML
• Supervised Learning: Algorithms learn from labeled data,
where the input data is paired with the corresponding correct
output. Common algorithms include linear regression, decision
trees, and support vector machines.
• Unsupervised Learning: Algorithms work with unlabeled data
to discover patterns and relationships within the data. Examples
include clustering algorithms like k-means and dimensionality
reduction techniques like principal component analysis (PCA).
• Reinforcement Learning: Algorithms learn through trial and
error, receiving feedback in the form of rewards or penalties
based on their actions. This approach is often used in training
agents to perform specific tasks, like playing games or
controlling robots.
ML ALGORITHM
• A machine learning (ML) algorithm is a set of rules and mathematical
procedures that enables a computer to learn patterns and make
predictions or decisions based on data, without being explicitly
programmed.
• ML algorithms are designed to improve their performance over time as
they process more data, allowing them to adapt and generalize from
examples.
• ML algorithms are a fundamental part of the field of artificial intelligence
(AI), and their applications range from image and speech recognition to
recommendation systems, autonomous vehicles, and more.
• These algorithms can be categorized into different types
ML ALGORITHMS TO FIND ASSOCIATION ACROSS BIOLOGICAL
DATA
Machine learning algorithms play a crucial role in analyzing and identifying
associations across biological data. Here are some commonly used ML
algorithms for this purpose:
• Apriori Algorithm: Widely used in association rule mining, the Apriori
algorithm identifies frequent itemsets in datasets. In biology, it can
discover co-occurrence patterns among genes, proteins, or metabolites,
revealing potential interactions or functional relationships. In genomics, for
example, Apriori can reveal associations between mutations in different
genes that occur together more frequently than by chance. This information
can provide insights into potential genetic interactions and pathways.
• Random Forest: The Random
Forest algorithm excels at
classification tasks and feature
importance analysis. In the
realm of biology, it aids in
predicting gene functions,
identifying associations between
genes and phenotypes, and even
distinguishing between healthy
and disease states based on
intricate biological features.
Image courtesy:
https://images.app.goo.gl/vVGU8VrYV2wdYWq47
• Support Vector Machines (SVM):
SVM is employed to classify and
predict biological interactions,
such as protein-protein
interactions or drug-target
associations. By learning
patterns from known data, SVM
can predict potential
associations within biological
datasets.
Image courtesy:
https://www.javatpoint.com/machine-
learning-support-vector-machine-algorithm
• Deep Learning and Neural Networks:
Deep learning techniques, including
Convolutional Neural Networks (CNNs)
and Recurrent Neural Networks
(RNNs), have revolutionized biological
data analysis. CNNs excel at image
analysis, helping identify associations
by analyzing cellular structures, while
RNNs predict sequences, unveiling
relationships in genetic or protein data.
Image courtesy:https://images.app.goo.gl/1g2MjMhLG2E1Ttr56
• Bayesian Networks: With their
ability to model probabilistic
relationships, Bayesian networks
are invaluable for exploring
associations and dependencies
within biological data. These
networks can reveal causal
relationships between genes,
proteins, and diseases, offering
insights into regulatory networks.
Image courtesy:
https://images.app.goo.gl/GMMBBjqi1bQ65yC
KA
• Graph-based Methods:
Biological entities and their
relationships can be
represented as graphs, with
nodes representing entities
and edges representing
associations. Graph
algorithms, such as
clustering and centrality
analysis, help identify
modules and key entities,
uncovering associations
within intricate biological
networks.
Image courtesy:
https://encrypted-
tbn0.gstatic.com/images?q=tbn:ANd9GcT2GNEMFbiau
Yn_ccmOcy4TzMkCLdAHBVhozw&usqp=CAU
• Dimensionality Reduction
Techniques: Algorithms like Principal
Component Analysis (PCA) and t-
Distributed Stochastic Neighbor
Embedding (t-SNE) reduce the
dimensionality of high-dimensional
biological data. These techniques
can help visualize and identify
associations between samples or
variables.
Image courtesy:
https://www.geeksforgeeks.org/dimensionality-reduction/
• Association Rule Mining
Algorithms: Apart from
Apriori, other association
rule mining algorithms like
FP-Growth and Eclat are
used to uncover hidden
relationships between
biological entities. These
algorithms are particularly
useful in analyzing large-
scale genomic data.
Image courtesy:
https://images.app.goo.gl/EBMjBt9Uf7Q6zQKh9
• Enrichment Analysis: While not
a single algorithm, enrichment
analysis techniques like Gene
Ontology (GO) analysis or
pathway enrichment can reveal
associations between biological
entities based on their
functional annotations. These
methods help interpret the
biological significance of
associations.
• Transfer Learning: Transfer
learning involves leveraging
knowledge from one
biological context to make
predictions in another. It's
valuable for finding
associations across related
biological datasets and
adapting models trained on
one dataset to another.
Image courtesy:
https://images.app.goo.gl/m8DoqrDx7hociC8b7
CONCLUSION
• Machine learning algorithms offer diverse and powerful tools for uncovering
associations within biological data.
• By utilizing these algorithms, researchers can extract meaningful insights that
contribute to our understanding of biological processes, disease mechanisms,
and potential therapeutic targets.
• These algorithms, ranging from traditional techniques to deep learning models,
empower researchers to uncover associations that might otherwise remain
hidden in the intricate web of biological information.
• As technology advances, the synergy between machine learning and biological
research promises to reshape our comprehension of life's complexities, leading
to breakthroughs in medicine, agriculture, and beyond.
REFERENCE
Articles:
• https://www.sciencedirect.com
• https://www.researchgate.net
• https://academic.oup.com
Other resources:
• https://chat.openai.com
THANK YOU
1 von 18

Recomendados

Introduction to Biodiversity Informatics von
Introduction to Biodiversity Informatics Introduction to Biodiversity Informatics
Introduction to Biodiversity Informatics David Shorthouse
3.7K views72 Folien
Industrial applications of enzymes von
Industrial applications of enzymesIndustrial applications of enzymes
Industrial applications of enzymeshamail1998
104.6K views18 Folien
Use of Rasmol and study of proteins von
Use of Rasmol and study of proteins Use of Rasmol and study of proteins
Use of Rasmol and study of proteins kamalmodi481
12.6K views23 Folien
The Role of Bioinformatics in The Drug Discovery Process von
The Role of Bioinformatics in The Drug Discovery ProcessThe Role of Bioinformatics in The Drug Discovery Process
The Role of Bioinformatics in The Drug Discovery ProcessAdebowale Qazeem
19.8K views23 Folien
KNIME in Life Science, Cheminformatics and Computational Chemistry von
KNIME in Life Science, Cheminformatics and Computational ChemistryKNIME in Life Science, Cheminformatics and Computational Chemistry
KNIME in Life Science, Cheminformatics and Computational ChemistryGirinath Pillai
131 views42 Folien
Introduction to Biological Network Analysis and Visualization with Cytoscape ... von
Introduction to Biological Network Analysis and Visualization with Cytoscape ...Introduction to Biological Network Analysis and Visualization with Cytoscape ...
Introduction to Biological Network Analysis and Visualization with Cytoscape ...Keiichiro Ono
16.1K views139 Folien

Más contenido relacionado

Was ist angesagt?

Elsi in genome studies von
Elsi in genome studiesElsi in genome studies
Elsi in genome studiesSamruddhiKunte
597 views9 Folien
PubMed von
PubMedPubMed
PubMedAlicia Tiny
2.5K views21 Folien
Protein identification and analysis on ExPASy server von
Protein identification and analysis on ExPASy serverProtein identification and analysis on ExPASy server
Protein identification and analysis on ExPASy serverEkta Gupta
1.7K views12 Folien
Structural Bioinformatics - Homology modeling & its Scope von
Structural Bioinformatics - Homology modeling & its ScopeStructural Bioinformatics - Homology modeling & its Scope
Structural Bioinformatics - Homology modeling & its ScopeNixon Mendez
2.9K views13 Folien
SDS-PAGE electrophoresis by Dr. Anurag Yadav von
SDS-PAGE electrophoresis by Dr. Anurag YadavSDS-PAGE electrophoresis by Dr. Anurag Yadav
SDS-PAGE electrophoresis by Dr. Anurag YadavDr Anurag Yadav
36.7K views15 Folien
Alkaline protease von
Alkaline proteaseAlkaline protease
Alkaline proteaseEffat Jahan Tamanna
5.2K views14 Folien

Was ist angesagt?(20)

Protein identification and analysis on ExPASy server von Ekta Gupta
Protein identification and analysis on ExPASy serverProtein identification and analysis on ExPASy server
Protein identification and analysis on ExPASy server
Ekta Gupta1.7K views
Structural Bioinformatics - Homology modeling & its Scope von Nixon Mendez
Structural Bioinformatics - Homology modeling & its ScopeStructural Bioinformatics - Homology modeling & its Scope
Structural Bioinformatics - Homology modeling & its Scope
Nixon Mendez2.9K views
SDS-PAGE electrophoresis by Dr. Anurag Yadav von Dr Anurag Yadav
SDS-PAGE electrophoresis by Dr. Anurag YadavSDS-PAGE electrophoresis by Dr. Anurag Yadav
SDS-PAGE electrophoresis by Dr. Anurag Yadav
Dr Anurag Yadav36.7K views
Construction of gene library von Achu dhan
Construction of gene libraryConstruction of gene library
Construction of gene library
Achu dhan23.4K views
Flux balance analysis von JyotiBishlay
Flux balance analysisFlux balance analysis
Flux balance analysis
JyotiBishlay1.2K views
Basics of Data Analysis in Bioinformatics von Elena Sügis
Basics of Data Analysis in BioinformaticsBasics of Data Analysis in Bioinformatics
Basics of Data Analysis in Bioinformatics
Elena Sügis3.9K views
MEGA (Molecular Evolutionary Genetics Analysis) von Athar Mutahari
MEGA (Molecular Evolutionary Genetics Analysis)MEGA (Molecular Evolutionary Genetics Analysis)
MEGA (Molecular Evolutionary Genetics Analysis)
Athar Mutahari8.1K views
Bioinformatic in drug designing von Salman Khan
Bioinformatic in drug designingBioinformatic in drug designing
Bioinformatic in drug designing
Salman Khan1.5K views
Protein isolation von hayakhan66
Protein isolationProtein isolation
Protein isolation
hayakhan6613K views
2018 scopus 저자 프로파일 수정 (scopus/scival) von POSTECH Library
2018 scopus 저자 프로파일 수정 (scopus/scival)2018 scopus 저자 프로파일 수정 (scopus/scival)
2018 scopus 저자 프로파일 수정 (scopus/scival)
POSTECH Library1K views
Workshop: Introduction to Cytoscape at UT-KBRIN Bioinformatics Summit 2014 (4... von Keiichiro Ono
Workshop: Introduction to Cytoscape at UT-KBRIN Bioinformatics Summit 2014 (4...Workshop: Introduction to Cytoscape at UT-KBRIN Bioinformatics Summit 2014 (4...
Workshop: Introduction to Cytoscape at UT-KBRIN Bioinformatics Summit 2014 (4...
Keiichiro Ono7.6K views
Bioinformatics resources and search tools - report on summer training proj... von Sapan Anand
Bioinformatics   resources and search tools -  report on summer training proj...Bioinformatics   resources and search tools -  report on summer training proj...
Bioinformatics resources and search tools - report on summer training proj...
Sapan Anand2.6K views

Similar a ML algorithms to find associations across biological data.pptx

INTERNSHIP ON MAcHINE LEARNING.pptx von
INTERNSHIP ON MAcHINE LEARNING.pptxINTERNSHIP ON MAcHINE LEARNING.pptx
INTERNSHIP ON MAcHINE LEARNING.pptxsrikanthkallem1
96 views16 Folien
Evolutionary Computing Based Approach For Unsupervised... von
Evolutionary Computing Based Approach For Unsupervised...Evolutionary Computing Based Approach For Unsupervised...
Evolutionary Computing Based Approach For Unsupervised...Shannon Joy
2 views40 Folien
A Brief Note On Data Mining And Machine Learning von
A Brief Note On Data Mining And Machine LearningA Brief Note On Data Mining And Machine Learning
A Brief Note On Data Mining And Machine LearningRenee Countryman
3 views42 Folien
Pattern recognition in ML.pdf von
Pattern recognition in ML.pdfPattern recognition in ML.pdf
Pattern recognition in ML.pdfMatthewHaws4
13 views11 Folien
machine_learning_section1_ebook.pdf von
machine_learning_section1_ebook.pdfmachine_learning_section1_ebook.pdf
machine_learning_section1_ebook.pdfagfi
41 views12 Folien
BIG DATA AND MACHINE LEARNING von
BIG DATA AND MACHINE LEARNINGBIG DATA AND MACHINE LEARNING
BIG DATA AND MACHINE LEARNINGUmair Shafique
59 views28 Folien

Similar a ML algorithms to find associations across biological data.pptx(20)

Evolutionary Computing Based Approach For Unsupervised... von Shannon Joy
Evolutionary Computing Based Approach For Unsupervised...Evolutionary Computing Based Approach For Unsupervised...
Evolutionary Computing Based Approach For Unsupervised...
Shannon Joy2 views
A Brief Note On Data Mining And Machine Learning von Renee Countryman
A Brief Note On Data Mining And Machine LearningA Brief Note On Data Mining And Machine Learning
A Brief Note On Data Mining And Machine Learning
Pattern recognition in ML.pdf von MatthewHaws4
Pattern recognition in ML.pdfPattern recognition in ML.pdf
Pattern recognition in ML.pdf
MatthewHaws413 views
machine_learning_section1_ebook.pdf von agfi
machine_learning_section1_ebook.pdfmachine_learning_section1_ebook.pdf
machine_learning_section1_ebook.pdf
agfi41 views
Metabolomic data analysis and visualization tools von Dmitry Grapov
Metabolomic data analysis and visualization toolsMetabolomic data analysis and visualization tools
Metabolomic data analysis and visualization tools
Dmitry Grapov7.2K views
International journal of computer science and innovation vol 2015-n1-paper4 von sophiabelthome
International journal of computer science and innovation  vol 2015-n1-paper4International journal of computer science and innovation  vol 2015-n1-paper4
International journal of computer science and innovation vol 2015-n1-paper4
sophiabelthome50 views
2005) von butest
2005)2005)
2005)
butest206 views
Machine learning to solve bioinformatics problems von JunaidAKG
Machine learning to solve bioinformatics problemsMachine learning to solve bioinformatics problems
Machine learning to solve bioinformatics problems
JunaidAKG66 views
A Comparative Analysis Of Force Directed Layout Algorithms... von Jenny Mancini
A Comparative Analysis Of Force Directed Layout Algorithms...A Comparative Analysis Of Force Directed Layout Algorithms...
A Comparative Analysis Of Force Directed Layout Algorithms...
Jenny Mancini2 views

Más de Selvajeyanthi S

Preparation of serum and plasma .pptx von
Preparation of serum and plasma .pptxPreparation of serum and plasma .pptx
Preparation of serum and plasma .pptxSelvajeyanthi S
38 views12 Folien
Computational tools for reasearch.pptx von
Computational tools for reasearch.pptxComputational tools for reasearch.pptx
Computational tools for reasearch.pptxSelvajeyanthi S
7 views22 Folien
Genetic Engineering .pptx von
Genetic Engineering .pptxGenetic Engineering .pptx
Genetic Engineering .pptxSelvajeyanthi S
16 views19 Folien
Corneybacterium diptheriae von
Corneybacterium diptheriaeCorneybacterium diptheriae
Corneybacterium diptheriaeSelvajeyanthi S
97 views27 Folien
Mycobacterium tuberculosis-TB von
Mycobacterium tuberculosis-TBMycobacterium tuberculosis-TB
Mycobacterium tuberculosis-TBSelvajeyanthi S
469 views35 Folien
Staphylococcus aureus von
Staphylococcus aureusStaphylococcus aureus
Staphylococcus aureusSelvajeyanthi S
559 views40 Folien

Más de Selvajeyanthi S(14)

Preparation of serum and plasma .pptx von Selvajeyanthi S
Preparation of serum and plasma .pptxPreparation of serum and plasma .pptx
Preparation of serum and plasma .pptx
Selvajeyanthi S38 views
Neisseria meninigitidis-brain infection,meningococcal von Selvajeyanthi S
Neisseria meninigitidis-brain infection,meningococcalNeisseria meninigitidis-brain infection,meningococcal
Neisseria meninigitidis-brain infection,meningococcal
Selvajeyanthi S228 views
Mycobacterium leprae (Leprosy)- "Hansen's disease" von Selvajeyanthi S
Mycobacterium leprae (Leprosy)- "Hansen's disease"Mycobacterium leprae (Leprosy)- "Hansen's disease"
Mycobacterium leprae (Leprosy)- "Hansen's disease"
Selvajeyanthi S1.8K views
milestones of Medical microbiology-lecture notes von Selvajeyanthi S
milestones of  Medical microbiology-lecture notesmilestones of  Medical microbiology-lecture notes
milestones of Medical microbiology-lecture notes
Selvajeyanthi S546 views
Milestones of Medical Microbiology von Selvajeyanthi S
Milestones of Medical MicrobiologyMilestones of Medical Microbiology
Milestones of Medical Microbiology
Selvajeyanthi S224 views
Isolation of RNA and its application von Selvajeyanthi S
Isolation of RNA and its applicationIsolation of RNA and its application
Isolation of RNA and its application
Selvajeyanthi S1.8K views

Último

Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor... von
Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor...Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor...
Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor...Trustlife
114 views17 Folien
BLOTTING TECHNIQUES SPECIAL von
BLOTTING TECHNIQUES SPECIALBLOTTING TECHNIQUES SPECIAL
BLOTTING TECHNIQUES SPECIALMuhammadImranMirza2
7 views56 Folien
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy... von
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...Anmol Vishnu Gupta
7 views10 Folien
Vegetable grafting: A new crop improvement approach.pptx von
Vegetable grafting: A new crop improvement approach.pptxVegetable grafting: A new crop improvement approach.pptx
Vegetable grafting: A new crop improvement approach.pptxHimul Suthar
8 views69 Folien
ALGAL PRODUCTS.pptx von
ALGAL PRODUCTS.pptxALGAL PRODUCTS.pptx
ALGAL PRODUCTS.pptxRASHMI M G
7 views17 Folien
Indian council for child welfare von
Indian council for child welfareIndian council for child welfare
Indian council for child welfareRenuWaghmare2
7 views21 Folien

Último(20)

Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor... von Trustlife
Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor...Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor...
Ellagic Acid and Its Metabolites as Potent and Selective Allosteric Inhibitor...
Trustlife114 views
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy... von Anmol Vishnu Gupta
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...
Evaluation and Standardization of the Marketed Polyherbal drug Patanjali Divy...
Vegetable grafting: A new crop improvement approach.pptx von Himul Suthar
Vegetable grafting: A new crop improvement approach.pptxVegetable grafting: A new crop improvement approach.pptx
Vegetable grafting: A new crop improvement approach.pptx
Himul Suthar8 views
Indian council for child welfare von RenuWaghmare2
Indian council for child welfareIndian council for child welfare
Indian council for child welfare
RenuWaghmare27 views
Note on the Riemann Hypothesis von vegafrank2
Note on the Riemann HypothesisNote on the Riemann Hypothesis
Note on the Riemann Hypothesis
vegafrank28 views
Presentation on experimental laboratory animal- Hamster von Kanika13641
Presentation on experimental laboratory animal- HamsterPresentation on experimental laboratory animal- Hamster
Presentation on experimental laboratory animal- Hamster
Kanika136416 views
Experimental animal Guinea pigs.pptx von Mansee Arya
Experimental animal Guinea pigs.pptxExperimental animal Guinea pigs.pptx
Experimental animal Guinea pigs.pptx
Mansee Arya40 views
Study on Drug Drug Interaction Through Prescription Analysis of Type II Diabe... von Anmol Vishnu Gupta
Study on Drug Drug Interaction Through Prescription Analysis of Type II Diabe...Study on Drug Drug Interaction Through Prescription Analysis of Type II Diabe...
Study on Drug Drug Interaction Through Prescription Analysis of Type II Diabe...
Determination of color fastness to rubbing(wet and dry condition) by crockmeter. von ShadmanSakib63
Determination of color fastness to rubbing(wet and dry condition) by crockmeter.Determination of color fastness to rubbing(wet and dry condition) by crockmeter.
Determination of color fastness to rubbing(wet and dry condition) by crockmeter.
ShadmanSakib636 views
A giant thin stellar stream in the Coma Galaxy Cluster von Sérgio Sacani
A giant thin stellar stream in the Coma Galaxy ClusterA giant thin stellar stream in the Coma Galaxy Cluster
A giant thin stellar stream in the Coma Galaxy Cluster
Sérgio Sacani19 views
Effect of Integrated Nutrient Management on Growth and Yield of Solanaceous F... von SwagatBehera9
Effect of Integrated Nutrient Management on Growth and Yield of Solanaceous F...Effect of Integrated Nutrient Management on Growth and Yield of Solanaceous F...
Effect of Integrated Nutrient Management on Growth and Yield of Solanaceous F...
SwagatBehera95 views
Oral_Presentation_by_Fatma (2).pdf von fatmaalmrzqi
Oral_Presentation_by_Fatma (2).pdfOral_Presentation_by_Fatma (2).pdf
Oral_Presentation_by_Fatma (2).pdf
fatmaalmrzqi8 views
별헤는 사람들 2023년 12월호 전명원 교수 자료 von sciencepeople
별헤는 사람들 2023년 12월호 전명원 교수 자료별헤는 사람들 2023년 12월호 전명원 교수 자료
별헤는 사람들 2023년 12월호 전명원 교수 자료
sciencepeople68 views
Small ruminant keepers’ knowledge, attitudes and practices towards peste des ... von ILRI
Small ruminant keepers’ knowledge, attitudes and practices towards peste des ...Small ruminant keepers’ knowledge, attitudes and practices towards peste des ...
Small ruminant keepers’ knowledge, attitudes and practices towards peste des ...
ILRI6 views
Factors affecting fluorescence and phosphorescence.pptx von SamarthGiri1
Factors affecting fluorescence and phosphorescence.pptxFactors affecting fluorescence and phosphorescence.pptx
Factors affecting fluorescence and phosphorescence.pptx
SamarthGiri17 views

ML algorithms to find associations across biological data.pptx

  • 1. ARTIFICIAL INTELLIGENCE FOR BIOLOGICAL SCIENCES ML ALGORITHMS TO FIND ASSOCIATIONS ACROSS BIOLOGICAL DATA PREPARED BY: MS. ABIRAMI.S M. SC., MICROBIOLOGY UNDER THE GUIDANCE OF : MRS. S. SELVAJEYANTHI ASST PROFESSOR DEPARTMENT OF MICROBIOLOGY, SNMV CAS
  • 2. CONTENT • Machine Learning • Types of ML • ML algorithm • ML algorithm to find association across biological data • Conclusion
  • 3. MACHINE LEARNING • ML stands for "machine learning.“ • It's a subset of artificial intelligence that focuses on the development of algorithms and models that allow computers to learn from data and improve their performance on specific tasks over time. • Instead of being explicitly programmed, these algorithms use data to identify patterns, make predictions, and make decisions. • Machine learning is used in various applications, such as image recognition, language processing, recommendation systems, and more.
  • 4. TYPES OF ML • Supervised Learning: Algorithms learn from labeled data, where the input data is paired with the corresponding correct output. Common algorithms include linear regression, decision trees, and support vector machines. • Unsupervised Learning: Algorithms work with unlabeled data to discover patterns and relationships within the data. Examples include clustering algorithms like k-means and dimensionality reduction techniques like principal component analysis (PCA). • Reinforcement Learning: Algorithms learn through trial and error, receiving feedback in the form of rewards or penalties based on their actions. This approach is often used in training agents to perform specific tasks, like playing games or controlling robots.
  • 5. ML ALGORITHM • A machine learning (ML) algorithm is a set of rules and mathematical procedures that enables a computer to learn patterns and make predictions or decisions based on data, without being explicitly programmed. • ML algorithms are designed to improve their performance over time as they process more data, allowing them to adapt and generalize from examples. • ML algorithms are a fundamental part of the field of artificial intelligence (AI), and their applications range from image and speech recognition to recommendation systems, autonomous vehicles, and more. • These algorithms can be categorized into different types
  • 6. ML ALGORITHMS TO FIND ASSOCIATION ACROSS BIOLOGICAL DATA Machine learning algorithms play a crucial role in analyzing and identifying associations across biological data. Here are some commonly used ML algorithms for this purpose: • Apriori Algorithm: Widely used in association rule mining, the Apriori algorithm identifies frequent itemsets in datasets. In biology, it can discover co-occurrence patterns among genes, proteins, or metabolites, revealing potential interactions or functional relationships. In genomics, for example, Apriori can reveal associations between mutations in different genes that occur together more frequently than by chance. This information can provide insights into potential genetic interactions and pathways.
  • 7. • Random Forest: The Random Forest algorithm excels at classification tasks and feature importance analysis. In the realm of biology, it aids in predicting gene functions, identifying associations between genes and phenotypes, and even distinguishing between healthy and disease states based on intricate biological features. Image courtesy: https://images.app.goo.gl/vVGU8VrYV2wdYWq47
  • 8. • Support Vector Machines (SVM): SVM is employed to classify and predict biological interactions, such as protein-protein interactions or drug-target associations. By learning patterns from known data, SVM can predict potential associations within biological datasets. Image courtesy: https://www.javatpoint.com/machine- learning-support-vector-machine-algorithm
  • 9. • Deep Learning and Neural Networks: Deep learning techniques, including Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs), have revolutionized biological data analysis. CNNs excel at image analysis, helping identify associations by analyzing cellular structures, while RNNs predict sequences, unveiling relationships in genetic or protein data. Image courtesy:https://images.app.goo.gl/1g2MjMhLG2E1Ttr56
  • 10. • Bayesian Networks: With their ability to model probabilistic relationships, Bayesian networks are invaluable for exploring associations and dependencies within biological data. These networks can reveal causal relationships between genes, proteins, and diseases, offering insights into regulatory networks. Image courtesy: https://images.app.goo.gl/GMMBBjqi1bQ65yC KA
  • 11. • Graph-based Methods: Biological entities and their relationships can be represented as graphs, with nodes representing entities and edges representing associations. Graph algorithms, such as clustering and centrality analysis, help identify modules and key entities, uncovering associations within intricate biological networks. Image courtesy: https://encrypted- tbn0.gstatic.com/images?q=tbn:ANd9GcT2GNEMFbiau Yn_ccmOcy4TzMkCLdAHBVhozw&usqp=CAU
  • 12. • Dimensionality Reduction Techniques: Algorithms like Principal Component Analysis (PCA) and t- Distributed Stochastic Neighbor Embedding (t-SNE) reduce the dimensionality of high-dimensional biological data. These techniques can help visualize and identify associations between samples or variables. Image courtesy: https://www.geeksforgeeks.org/dimensionality-reduction/
  • 13. • Association Rule Mining Algorithms: Apart from Apriori, other association rule mining algorithms like FP-Growth and Eclat are used to uncover hidden relationships between biological entities. These algorithms are particularly useful in analyzing large- scale genomic data. Image courtesy: https://images.app.goo.gl/EBMjBt9Uf7Q6zQKh9
  • 14. • Enrichment Analysis: While not a single algorithm, enrichment analysis techniques like Gene Ontology (GO) analysis or pathway enrichment can reveal associations between biological entities based on their functional annotations. These methods help interpret the biological significance of associations.
  • 15. • Transfer Learning: Transfer learning involves leveraging knowledge from one biological context to make predictions in another. It's valuable for finding associations across related biological datasets and adapting models trained on one dataset to another. Image courtesy: https://images.app.goo.gl/m8DoqrDx7hociC8b7
  • 16. CONCLUSION • Machine learning algorithms offer diverse and powerful tools for uncovering associations within biological data. • By utilizing these algorithms, researchers can extract meaningful insights that contribute to our understanding of biological processes, disease mechanisms, and potential therapeutic targets. • These algorithms, ranging from traditional techniques to deep learning models, empower researchers to uncover associations that might otherwise remain hidden in the intricate web of biological information. • As technology advances, the synergy between machine learning and biological research promises to reshape our comprehension of life's complexities, leading to breakthroughs in medicine, agriculture, and beyond.
  • 17. REFERENCE Articles: • https://www.sciencedirect.com • https://www.researchgate.net • https://academic.oup.com Other resources: • https://chat.openai.com