A5101771743- Monoclonal and Polyclonal Antibodies Research
- Academic Publishing and Open Access
- Advanced Biosensing Techniques and Applications
- scientometrics and bibliometrics research
- Computational Drug Discovery Methods
- RNA and protein synthesis mechanisms
- Machine Learning in Materials Science
- Protein purification and stability
- vaccines and immunoinformatics approaches
- Biosimilars and Bioanalytical Methods
- Meta-analysis and systematic reviews
- Protein Structure and Dynamics
- Academic integrity and plagiarism
- Cell Image Analysis Techniques
- Machine Learning and Algorithms
- Various Chemistry Research Topics
- Viral Infectious Diseases and Gene Expression in Insects
- Gene Regulatory Network Analysis
University of California, San Diego
2021-2024
UC San Diego Health System
2023
Antibodies are critical reagents to detect and characterize proteins. It is commonly understood that many commercial antibodies do not recognize their intended targets, but information on the scope of problem remains largely anecdotal, as such, feasibility goal at least one potent specific antibody targeting each protein in a proteome cannot be assessed. Focusing for human proteins, we have scaled standardized characterization approach using parental knockout cell lines (Laflamme et al.,...
Antibodies are ubiquitous key biological research resources yet tricky to use as they prone performance issues and represent a major source of variability across studies. Understanding what antibody was used in published study is therefore necessary repeat and/or interpret given study. However, reagents still frequently not cited with sufficient detail determine which experiments. The Antibody Registry public, open database that enables citation antibodies by providing persistent record for...
Preprints, versions of scientific manuscripts that precede peer review, are growing in popularity. They offer an opportunity to democratize and accelerate research, as they have no publication costs or a lengthy review process. Preprints often later published peer-reviewed venues, but these publications the original preprints frequently not linked any way. To this end, we developed tool, PreprintMatch, find matches between their corresponding papers, if exist. This tool outperforms existing...
Antibodies are critical reagents to detect and characterize proteins. It is commonly understood that many commercial antibodies do not recognize their intended targets, but information on the scope of problem remains largely anecdotal, as such, feasibility goal at least one potent specific antibody targeting each protein in a proteome cannot be assessed. Focusing for human proteins, we have scaled standardized characterization approach using parental knockout cell lines (Laflamme et al.,...
Background Improving rigor and transparency measures should lead to improvements in reproducibility across the scientific literature; however, assessment of tends be very difficult if performed manually. Objective This study addresses enhancement Rigor Transparency Index (RTI, version 2.0), which attempts automatically assess journals, institutions, countries using manuscripts scored on criteria found guidelines (eg, Materials Design, Analysis, Reporting checklist criteria). Methods The RTI...
Predicting the activities of new compounds against biophysical or phenotypic assays based on known one a few existing is common goal in early stage drug discovery. This problem can be cast as "few-shot learning" challenge, and prior studies have developed few-shot learning methods to classify active versus inactive. However, ability go beyond classification rank by expected affinity more valuable. We describe Few-Shot Compound Activity Prediction (FS-CAP), novel neural architecture trained...
Antibodies are critical reagents to detect and characterize proteins. It is commonly understood that many commercial antibodies do not recognize their intended targets, but information on the scope of problem remains largely anecdotal, as such, feasibility goal at least one potent specific antibody targeting each protein in a proteome cannot be assessed. Focusing for human proteins, we have scaled standardized characterization approach using parental knockout cell lines (Laflamme et al.,...
Current generative models for drug discovery primarily use molecular docking to evaluate the quality of generated compounds. However, such are often not useful in practice because even compounds with high scores do consistently show experimental activity. More accurate methods activity prediction exist, as dynamics based binding free energy calculations, but they too computationally expensive a model. We propose multi-fidelity approach, Multi-Fidelity Bind (MFBind), achieve optimal trade-off...
Generation of drug-like molecules with high binding affinity to target proteins remains a difficult and resource-intensive task in drug discovery. Existing approaches primarily employ reinforcement learning, Markov sampling, or deep generative models guided by Gaussian processes, which can be prohibitively slow when generating calculated computationally-expensive physics-based methods. We present Latent Inceptionism on Molecules (LIMO), significantly accelerates molecule generation an...
Antibodies are critical reagents to detect and characterize proteins. It is commonly understood that many commercial antibodies do not recognize their intended targets, but information on the scope of problem remains largely anecdotal, as such, feasibility goal at least one potent specific antibody targeting each protein in a proteome cannot be assessed. Focusing for human proteins, we have scaled standardized characterization approach using parental knockout cell lines (Laflamme et al.,...
Current generative models for drug discovery primarily use molecular docking as an oracle to guide the generation of active compounds. However, such are often not useful in practice because even compounds with high scores do consistently show experimental activity. More accurate methods activity prediction exist, dynamics based binding free energy calculations, but they too computationally expensive a model. To address this challenge, we propose Multi-Fidelity Latent space Active Learning...
This technical report investigates variants of the Latent Inceptionism on Molecules (LIMO) framework to improve properties generated molecules. We conduct ablative studies molecular representation, decoder model, and surrogate model training scheme. The experiments suggest that an autogressive Transformer with GroupSELFIES achieves best average for random generation task.
Predicting the activities of compounds against protein-based or phenotypic assays using only a few known and their is common task in target-free drug discovery. Existing few-shot learning approaches are limited to predicting binary labels (active/inactive). However, real-world discovery, degrees compound activity highly relevant. We study Few-Shot Compound Activity Prediction (FS-CAP) design novel neural architecture meta-learn continuous across large bioactivity datasets. Our model...
Abstract Preprints occupied the spotlight early in pandemic, as scientists, media and public sought information on evolving pandemic. While some scientific community embraced this shift, others were concerned about quality of these papers, which had not yet undergone peer review. Furthermore, flood COVID-19 preprints quickly overwhelmed community's ability to monitor assess new preprints. Automated screening tools that detect beneficial practices, or common problems, are one potential...
<sec> <title>BACKGROUND</title> Improving rigor and transparency measures should lead to improvements in reproducibility across the scientific literature; however, assessment of tends be very difficult if performed manually. </sec> <title>OBJECTIVE</title> This study addresses enhancement Rigor Transparency Index (RTI, version 2.0), which attempts automatically assess journals, institutions, countries using manuscripts scored on criteria found guidelines (eg, Materials Design, Analysis,...
Preprints, versions of scientific manuscripts that precede peer review, are growing in popularity. They offer an opportunity to democratize and accelerate research, as they have no publication costs or a lengthy review process. Preprints often later published peer-reviewed venues, but these publications the original preprints frequently not linked any way. To this end, we developed tool, PreprintMatch, find matches between their corresponding papers, if exist. This tool outperforms existing...