Support vector machines for learning to identify the critical positions of a protein

Dubey, Anshul; Park, Jongwoo; Lee, Jay H.; Bommarius, Andreas S.

doi:10.1016/j.jtbi.2004.11.037

Cited by 15 publications

(4 citation statements)

References 43 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These predictors can feed into subsequent rounds of protein engineering, giving confidence in the construction of small focused libraries that require minimal screening. In general, the utilization of machine learning algorithms in protein engineering is quickly gaining popularity, and has been successfully applied in various targets other than α/β hydrolases [12,13].…”

Section: Recent Methods Developments In Hydrolase Engineeringmentioning

confidence: 99%

Recent progress in engineering α/β hydrolase‐fold family members

Qian¹,

Fields²,

Yu³

et al. 2007

Biotechnology Journal

View full text Add to dashboard Cite

The members of the alpha/beta hydrolase-fold family represent a functionally versatile group of enzymes with many important applications in biocatalysis. Given the technical significance of alpha/beta hydrolases in processes ranging from the kinetic resolution of enantiomeric precursors for pharmaceutical compounds to bulk products such as laundry detergent, optimizing and tailoring enzymes for these applications presents an ongoing challenge to chemists, biochemists, and engineers alike. A review of the recent literature on alpha/beta hydrolase engineering suggests that the early successes of "random processes" such as directed evolution are now being slowly replaced by more hypothesis-driven, focused library approaches. These developments reflect a better understanding of the enzymes' structure-function relationship and improved computational resources, which allow for more sophisticated search and prediction algorithms, as well as, in a very practical sense, the realization that bigger is not always better.

show abstract

Section: Recent Methods Developments In Hydrolase Engineeringmentioning

confidence: 99%

Recent progress in engineering α/β hydrolase‐fold family members

Qian¹,

Fields²,

Yu³

et al. 2007

Biotechnology Journal

View full text Add to dashboard Cite

show abstract

“…Subsequent work by Fox [77] showed that the concept can be extended to the combinatorial evolution of full-sized proteins, particularly when a limited set of the total protein residues is altered. Machine-learning techniques, trained on small sets of experimental data, can be used to predict important positions in proteins and to design new libraries aimed toward the optimization of protein properties [78][79][80]. The advantage of machine-learning techniques is their ability to detect hidden patterns relating the input (sequence) and output (function) that can be used for predictive purposes.…”

Section: Modeling Of Sequence-activity Relationshipsmentioning

confidence: 99%

Better library design: data‐driven protein engineering

Chaparro‐Riggers

Polizzi

Bommarius

2007

Biotechnology Journal

Self Cite

View full text Add to dashboard Cite

Data-driven protein engineering is increasingly used as an alternative to rational design and combinatorial engineering because it uses available knowledge to limit library size, while still allowing for the identification of unpredictable substitutions that lead to large effects. Recent advances in computational modeling and bioinformatics, as well as an increasing databank of experiments on functional variants, have led to new strategies to choose particular amino acid residues to vary in order to increase the chances of obtaining a variant protein with the desired property. Strategies for limiting diversity at each position, design of small sub-libraries, and the performance of scouting experiments, have also been developed or even automated, further reducing the library size.

show abstract

“…It classifies the data based on the similarity between the examples measured by the similarity function or kernel function. This function can be chosen according to the problem at hand, and thus making the algorithm flexible in handling a wide variety of problems (Dubey et al, 2005). Moreover, previous studies demonstrated that the SVM is superior to the conventional neural networks in predicting chemical and biological variables (Liu et al, 2004;Lu and Wang, 2005).…”

Section: Project Purposementioning

confidence: 99%

A comparative study: Prediction of constructed treatment wetland performance with k-nearest neighbors and neural networks

Lee

Scholz

2006

Water Air Soil Pollut

View full text Add to dashboard Cite

K-nearest neighbors (KNN), support vector machine (SVM) and self-organizing map (SOM) were applied to predict five-day @ 20 • C N-Allylthiourea biochemical oxygen demand (BOD) and suspended solids (SS), and to assess novel alternative methods of analyzing water quality performance indicators for constructed treatment wetlands. Concerning the accuracy of prediction, SOM showed a better performance compared to both KNN and SVM. Moreover, SOM had the potential to visualize the relationship between complex biochemical variables. However, optimizing the SOM requires more time in comparison to KNN and SVM because of its trial and error process in searching for the optimal map. The results suggest that BOD and SS can be efficiently estimated by applying machine learning tools with input variables such as redox potential and conductivity, which can be monitored in real time. Their performances are encouraging and support the potential for future use of these models as management tools for the day-to-day process control.

show abstract

Support vector machines for learning to identify the critical positions of a protein

Cited by 15 publications

References 43 publications

Recent progress in engineering α/β hydrolase‐fold family members

Recent progress in engineering α/β hydrolase‐fold family members

Better library design: data‐driven protein engineering

A comparative study: Prediction of constructed treatment wetland performance with k-nearest neighbors and neural networks

Contact Info

Product

Resources

About