CBE 5734
Transcript Abbreviation:
Molec Informatics
Course Description:
Application of molecular informatics in the development of computational approaches for predicting properties and effects of molecules in chemical and biological systems
Course Levels:
Undergraduate (1000-5000 level)
Graduate
Designation:
Elective
General Education Course
(N/A)
Cross-Listings
(N/A)
Credit Hours (Minimum if “Range”selected):
3.00
Max Credit Hours
(N/A)
Select if Repeatable:
Off
Maximum Repeatable Credits
(N/A)
Total Completions Allowed
(N/A)
Allow Multiple Enrollments in Term:
No
Course Length:
14 weeks (autumn or spring)
12 weeks (summer only)
Off Campus:
Never
Campus Location:
Columbus
Instruction Modes:
Hybrid Class (25-74% campus; 25-74% online)
Prerequisites and Co-requisites:
2345, or Sr or Grad standing in Engineering; or permission of instructor. Computational/programming experience (preferably Python) is highly recommended
Electronically Enforced:
Yes
Exclusions
(N/A)
Course Goals / Objectives:
Understand the basic concepts of molecular informatics, with emphasis on chemoinformatics and its relevance to products and processes of interest to chemical engineers.
Become familiar with databases for chemical and biological data, and methods for extracting information from these.
Understand computable chemical structure representations such as SMILES and SD/ MOL files
Understand methods for quantitatively estimating molecular similarity using structure- and property-based approaches
Understand the use of SMARTS for substructure searches and how this can be used to group chemicals or identify structural rules or alerts for chemical toxicity
Understand machine learning approaches for building quantitative structure-activity relationship (QSAR) models
Understand how molecular descriptors such as physicochemical properties, structural fingerprints, and alerts are used in computational modeling of chemical activity, with emphasis on models for predicting chemical toxicity
Check if concurrence sought:
No
Contact Hours:
| Topic | LEC | REC | LAB | LAB Inst |
|---|---|---|---|---|
| Overview of basic concepts and motivation for chemoinformatics. Online resources: databases (e.g., PubChem, SciFinder) and structure handling (e.g., JSME) | 1.0 | 0.0 | 0.0 | 0 |
| Chemical structure representation: how chemical structures can be represented in computable forms; 2D and 3D representations, stereochemistry; SMILES, InChI codes and keys, MOL and SD files. | 4 | 0 | 0.0 | 0 |
| Chemoinformatics approaches for calculating molecular and physicochemical properties; examples: hydrogen bond donors and acceptors, octanol/water partition coefficients. | 3.0 | 0.0 | 0.0 | 0 |
| Structure fingerprints and molecular pairwise similarity. Dynamic fingerprinting algorithms, quantifying molecular pairwise similarity by taking structure, physiochemical properties and biological activity into account. | 5.0 | 0.0 | 0.0 | 0 |
| ...Tanimoto, Dice, and cosine measures of pairwise structure similarity. Chemoinformatics approaches for handling tautomers, and chemical reactivity when assessing molecular similarity | 0 | 0.0 | 0.0 | 0 |
| Chemical space, similarity and dissimilarity, chemical diversity. Strategies for different types of chemical structure searches (identity, similar, substructure). Using SMARTS for substructure searches and how SMARTS can be used to group chemicals | 5.0 | 0.0 | 0.0 | 0 |
| ...or identify structural rules or alerts for chemical toxicity. | 0 | 0.0 | 0.0 | 0 |
| Quantitative structure-activity relationship (QSAR) models: history and fundamentals. Introduction to QSAR approaches and algorithms, comparison of building prediction models using hypothesis-based statistical methods and machine learning approaches. | 2 | 0 | 0 | 0 |
| Machine learning (ML) key concepts: cross-validation, external validation, feature scaling, regularization, regularized linear models, hyperparameters and hyperparameter tuning. Machine learning in Python with scikit-learn (sklearn). | 5.0 | 0 | 0 | 0 |
| Working with physicochemical property and molecular structure features (e.g., fingerprints) in QSAR modeling: low-variance filtering, univariate feature selection, dimensionality reduction... | 4.0 | 0 | 0 | 0 |
| ...using principal component analysis (PCA) or partial least squares regression (PLS) | 0 | 0 | 0 | 0 |
| QSAR regression models built with property and chemical structure features using common ML approaches: regularized linear models, k-nearest neighbors (kNN) regression, support vector machine (SVM) regression, random forest (RF) regression... | 6 | 0 | 0 | 0 |
| Case study: modeling bioconcentration factors of chemicals in fish | 0 | 0 | 0 | 0 |
| QSAR classification models built with property and chemical structure features using common ML approaches: logistic regression, kNN classification, SVM classification, RF classification. Case study: modeling acute systemic toxicity categories | 4.0 | 0 | 0 | 0 |
| Total | 39 | 0 | 0 | 0 |
Grading Plan:
Letter Grade
Course Components:
Lecture
Grade Roster Component:
Lecture
Credit by Exam (EM):
No
Grades Breakdown:
| Aspect | Percent |
|---|---|
| Homework | 30% |
| Participation (e.g., Top Hat, Kritik) | 20% |
| Midterm Exam | 25% |
| Final Project | 25% |
Representative Textbooks and Other Course Materials:
| Title | Author | Year |
|---|---|---|
| No Textbooks and Other Course Materials Entered. | ||
ABET-CAC Criterion 3 Outcomes
(N/A)
ABET-ETAC Criterion 3 Outcomes
(N/A)
ABET-EAC Criterion 3 Outcomes:
| Outcome | Contribution | Description |
|---|---|---|
| 1 | Significant contribution (7+ hours) | an ability to identify, formulate, and solve complex engineering problems by applying principles of engineering, science, and mathematics |
| 2 | Some contribution (1-2 hours) | an ability to apply engineering design to produce solutions that meet specified needs with consideration of public health, safety, and welfare, as well as global, cultural, social, environmental, and economic factors |
| 3 | Some contribution (1-2 hours) | an ability to communicate effectively with a range of audiences - pre-2019 EAC SLO (g) |
| 4 | Some contribution (1-2 hours) | an ability to recognize ethical and professional responsibilities in engineering situations and make informed judgments, which must consider the impact of engineering solutions in global, economic, environmental, and societal contexts |
| 6 | Substantial contribution (3-6 hours) | an ability to develop and conduct appropriate experimentation, analyze and interpret data, and use engineering judgment to draw conclusions |
| 7 | Significant contribution (7+ hours) | an ability to acquire and apply new knowledge as needed, using appropriate learning strategies |
Embedded Literacies Info
(N/A)
Attachments
(N/A)
Additional Notes or Comments
(N/A)