🤖 TXGemma-2B-Predict Property Prediction

Enter a prompt below, or select a task from the table to load its template, and the model (google/txgemma-2b-predict) will generate text. Adjust the parameters for different results. Prompt templates loaded from tdc_prompts.json. Selected templates will use the SMILES string C1=CC=CC=C1 (Benzene) as a placeholder.

10 500
0 1.5

Select a Prompt Template

Prompt Templates

Prompt Templates
m1_muscarinic_receptor_antagonists_butkiewicz
Instructions: Answer the following question about CRISPR repair outcomes. Context: CRISPR-Cas9 is a gene editing technology that allows targeted deletion or modification of specific regions of the DNA within an organism. This is achieved through designing a guide RNA sequence that binds upstream of the target site which is then cleaved through a Cas9-mediated double stranded DNA break. The cell responds by employing DNA repair mechanisms (such as non-homologous end joining) that result in heterogeneous outcomes including gene insertion or deletion mutations (indels) of varying lengths and frequencies. Primary T cells are a promising cell type for therapeutic genome editing, as they can be engineered efficiently ex vivo and transferred to patients. An experiment is carried out to quantify the DNA repair outcomes of CRISPR-CAS9 knockout experiments on primary CD4+ T cells drawn from donors. For a genomic location, a GuideSeq sequence is provided, which is a 20-nucleotide guide sequence along with the 3-nucletoide PAM sequence. The PAM (protospacer adjacent motif) is a short DNA sequence that follows the DNA region targeted for cleavage by the CRISPR-Cas9 system. One particular measure of interest for repair outcome quantification is the fraction of repair outcomes with a frameshift. Question: Given a GuideSeq sequence, predict its normalized fraction of repair outcomes with a frameshift from 000 to 1000, where 000 is minimum fraction of repair outcomes with a frameshift and 1000 is maximum fraction of repair outcomes with a frameshift. GuideSeq: {GuideSeq} Answer: