Mining frequent patterns in protein structures: A study of protease families Dr. Charles Yan CS6890 (Section 001) ST: Bioinformatics The Machine Learning Approach Presented By: Bhavendra Matta

Presentation Structure Problem Problem Introduction Introduction Method Proposed Method Proposed Results Results Findings Findings About Authors About Authors Questions Questions

Problem Mining frequent patterns in protein structure: Mining frequent patterns in protein structure: Analysis of protein sequence and structure databases usually reveal frequent patterns (FP) associated with biological function. Data mining techniques generally consider the physicochemical and structural properties of amino acids and their microenvironment in the folded structures.

Important Terminology Frequent Patterns in Protein Structures : Frequent Patterns in Protein Structures : The primary structure of proteins is the sequence of amino acids in the polypeptide chain. FP here refers to frequent patterns found in each type of Amino acids. Conserved Residue: Conserved Residue: These are used to determine structural relationships between the sequences of a multiple sequence alignment. VHAVOYJBIO BHAVJOYBIO OYJVHAVBIO Here BIO is Conserved Residue. Protease : Protease : Protease refers to a group of enzymes whose catalytic function is to breakdown peptide bonds of proteins.

continue.. Catalytic triad Catalytic triad It refers to three amino acid residues found inside the active site of certain proteases. These include Asp 102, His 57, and Ser 195. It refers to three amino acid residues found inside the active site of certain proteases. These include Asp 102, His 57, and Ser 195. Unsupervised Learning. Unsupervised Learning. It is a method of machine learning where a model is fit to observations output. Here the unsupervised learning is clustering forming type. Microenvironment refers to the local structure assumed by residues close in space, but not necessarily contiguous along the sequence. There are strong correlations between function and microenvironment.

Introduction The paper presents a novel unsupervised learning approach to discover frequent patterns in the protein families. The paper presents a novel unsupervised learning approach to discover frequent patterns in the protein families. FP calculation are based on three features (with no prior Functional motifs knowledge) FP calculation are based on three features (with no prior Functional motifs knowledge) 1. Biochemical Features 1. Biochemical Features 2. Geometric Features 2. Geometric Features 3. Dynamic Features 3. Dynamic Features The identified FP’s for each amino acids belongs to three protease subfamilies. The identified FP’s for each amino acids belongs to three protease subfamilies. Chymotrypsin Chymotrypsin Subtillsin subfamilies of Serine proteases Subtillsin subfamilies of Serine proteases Papain subfamily Cysteine proteases Papain subfamily Cysteine proteases The catalytic triad residues are distinguished by their strong spatial coupling (high interconnectivity) to other conserved residues. The catalytic triad residues are distinguished by their strong spatial coupling (high interconnectivity) to other conserved residues.

continue…. Proteins Function is associated with a particular sequences or structure motif. Proteins Function is associated with a particular sequences or structure motif. Few catalytic residue database are: Few catalytic residue database are: PDB ( Protein Data Base) PDB ( Protein Data Base) PROCAT: Geometric hashing Function. PROCAT: Geometric hashing Function. WEBFEATURE: Bayesian Network WEBFEATURE: Bayesian Network PINTS: PINTS: TRILOGY: TRILOGY:

Method Training Dataset Training Dataset Feature Extraction Feature Extraction FP Discovery FP Discovery Conserved Residue Identification. Conserved Residue Identification. Rank of Conserved Residue. Rank of Conserved Residue.

Dataset A set of proteins belonging to a given family is selected as the training dataset. Features are extracted from all the amino acids in this dataset. Two classes of enzymes, serine proteases and cysteine proteases are analyzed here. Mainly all proteases typically have a catalytic triad at the active site. These enzymes are classified into evolutionary subfamilies S1-Chymotrypsin (S1) S8-Subtilisin of serine proteases C1-Papain of Cysteine proteases

Feature Extraction Each amino acid is characterized in terms of its   Dynamic features   Biochemical features   Geometric features of the residues in its microenvironment.

Dynamic features It uses Gaussian network model, an elastic network model for describing the equilibrium dynamics of proteins, is used for characterizing the dynamics features. GNM, the α-carbons (C) form the network nodes, and the nodes located within an interaction cut-off distance of 7.0. Å are connected via uniform elastic springs. Another structural property CN too have a strong impact on equilibrium dynamics is the CN, which is defined as the number of amino acids (or α- carbons) that coordinate the central amino acid within a first interaction shell of 7.0 Å.

Biochemical features It defines the Amino acid amino acid type and property. The classification is based here on both the specific amino acid identity chemical features or functional groups Chain mining multiple level association rules.

Geometric features It uses a 3D reference frame to define each residue, using the three backbone atoms N, Cα and C (carbonyl C). It uniquely defines the position and orientation of the residue in the 3D space..

FP Discovery It uses Apriori algorithm. It uses Apriori algorithm. Algorithm Algorithm Calculate occurrence and support of each feature to build the FP. Calculate occurrence and support of each feature to build the FP. Discard FPs with the support smaller than predefined minimum support. Discard FPs with the support smaller than predefined minimum support. Join the FPs to generate augmented FPs if length is FP is x then augmented FP length is x+1. Join the FPs to generate augmented FPs if length is FP is x then augmented FP length is x+1. Defining minimum support is based on the degree of FP to be considered. Defining minimum support is based on the degree of FP to be considered.

FP Discovery

Identification of Conserved Residue Applying Apriori Algorithm to proteins reveal FP with maximum length. Applying Apriori Algorithm to proteins reveal FP with maximum length. The FP occurs at least once in examined subfamily of proteins is considered to conserved FP. The FP occurs at least once in examined subfamily of proteins is considered to conserved FP. Next, the conserved residues are removed from the original dataset, and the Apriori algorithm is applied again to the modified dataset. All the conserved patterns of 20 types of amino acids were identified by this iterative search for each family.

Rank of Conserved Residue Once the conserved residues are identified by the Apriori algorithm, a ranking method is needed to distinguish the catalytic residues. It is assumed that the catalytic residues are optimally coupled with other conserved residues to achieve the highest cooperativity. The amino acids that show the lowest interconnectivity (smallest number of connected neighbors) are removed from the list of considered residues. The ‘core’ residues are assigned the score zero, and the others are scored according to the number of iterations required to reach the ‘core’ residues.

Results Consider the serine residues in the serine protease family. Information for a set of 111 serine residues is extracted from the 5 proteins in S1, and for a set of 250 serine residues from the 7 proteins in S8. This is consistent with the fact that the conservation of the microenvironment and global dynamics is a more restrictive (and discriminative) feature than sequence conservation. Another observation is that amino acids that sequentially neighbor the catalytic residues tend to be conserved. The present unsupervised learning algorithm identified 22, 22 and 26 conserved residues in the S1, S8 and C1 subfamilies.

continues…

Result Continues…

Conclusion A novel unsupervised leaning approach to discover biologically meaningful FPs in protein structures The approach incorporates features associated with collective dynamics (GNM slow mode shapes) as well as the biochemical (amino acid types and physicochemical properties) and geometric (3D coordination directions) features in the microenvironment. This approach can be used to discover and annotate all frequent patterns in the protein structure database. It can help to predict structure and function of uncharacterized proteins, and identify the important amino acids or structural regions.

About Authors Ivet Bahar   She is currently Chair and Professor of Department of Computational Biology, University of Pittsburgh, Pittsburgh.   She has more than 21 years of research work.  Currently Research Areas:  Characterization of Proteins Structural Classes  Characterization of Anti-Cancer Agents  Conformational Dynamics of Proteins  Protein Folding Kinetics

About Author Shann-Ching Chen Carnegie Mellon University, Pittsburgh Main focus on Machine Learning. Current Project Areas Retrieval of 3D Protein and Nucleic Acid Structures Retrieval of 3D Protein and Nucleic Acid Structures Multimodal Biometrics Multimodal Biometrics

Questions??? Thank You