Survey Maker Survey Templates Contact Privacy & Security

Machine Learning x Protein Engineering Proposal

An abstract representation combining elements of machine learning and protein engineering, featuring neural networks, protein structures, and data analysis visuals, vibrant colors

Machine Learning x Protein Engineering Insights

Welcome to the Machine Learning x Protein Engineering proposal quiz! This interactive quiz aims to gather insights and innovative ideas on how machine learning can advance protein engineering.

Define key problem statements
Explore differentiating factors
Identify potential areas of interest
Share your expertise and contribute to the proposal

13 Questions3 MinutesCreated by InnovateMolecule247

Please select your name.

Adrian Matthew Mak

Ang Ee Lui

Ann Koay

Chandra Verma

Chen Xixian

Derek Smith

Giulia Rancati

Kumar Selvarajoo

Marco Klaehn

Michael Sullivan

Nic Lindley

Sebastian Maurer-Stroh

Shawn Hoon

Tan Teck Leong

Wong Han Teng

Wong Fong Tian

Thomas Lautier

Define the problem statements for this Machine Learning x Protein Engineering proposal.

What will be the differentiating factor for this ML X PE proposal? What has not been covered by PIPS and ACDP?

Following last week's discussion, which of the following areas continue to be of interest to you? For additional suggestions, please list them at the end of the survey (Question 13).

Swapping domains as a parameter for Machine Learning (beyond single point mutation)

Predicting non-naturally occurring catalysts/substrates/compounds/pathways

Extrapolate learning beyond training data

ML X Gene Annotation (benchmark: DeepRibo, DeepEC, UniRep; Splice AI, SpliceFinder)

ML X Retrosynthesis Pathway Design (benchmark: RetroPath 2.0; SMARTS; Apply ML principles from chemical retrosynthesis to enzymatic reactions; Semisupervised Gaussian Process for Automated Enzyme Search)

ML X Fermentation Process Optimisation (benchmark: DoE; Oyetunde et al. PLoS One. 15 Jan 2019)

ML X Transcription-Metabolic Network Regulation (includes: improve Transcription Factor-DNA binding; identification of key parameters; prevent lost flux and overcome bottlenecks)

What are the drivers for exploring the areas you have selected in Question 4?

What are the constraints preventing exploration of areas you have selected in Question 4? (Examples: de novo predictions; "missing" information from external databases as input; "noise"/variability among different conditions; single common output for various reaction conditions; predictions are specific to one type of organism/organ/strain/catalyst, etc.)

Please define areas that should be included in this proposal.

Please define areas that should be excluded from this proposal (out of scope)?

Please state how you can contribute to the ML X PE proposal?

Give examples of new and/or improved products/processes that can be expected from this proposal? (Examples: novel/improved ML methodology; creation of new ML platform; ML-driven novel enzyme production using synthetic biology, etc.)

Please nominate a suitable lead for this proposal.

Adrian Matthew Mak

Ang Ee Lui

Chen Xixian

Derek Smith

Kumar Selvarajoo

Marco Klaehn

Michael Sullivan

Tan Teck Leong

Who would benefit from this program in A*STAR and the wider Singapore ecosystem?

Additional remarks/comments.

{"name":"Machine Learning x Protein Engineering Proposal", "url":"https://www.supersurvey.com/QPREVIEW","txt":"Welcome to the Machine Learning x Protein Engineering proposal quiz! This interactive quiz aims to gather insights and innovative ideas on how machine learning can advance protein engineering.Define key problem statementsExplore differentiating factorsIdentify potential areas of interestShare your expertise and contribute to the proposal","img":"https:/images/course8.png"}