Skip to main content
zenodoopen

Structure conditioned hallucinated CDR sequences

<p><em><strong>Datasets accompanying publication&nbsp;https://doi.org/10.1101/2022.06.06.494991</strong></em> (Published in Frontiers in Immunology). Please refer to the final version of the manuscript on Frontiers.</p> <p><strong>RAbD dataset (Figure 2 in preprint/publication)</strong>: Structure conditioned hallucinated sequences for all 6 CDR loops of&nbsp;60 antibodies (see publication above for more details) with wildtype seeding (runs_wtseed) and without wildtype seeding (runs_noseed). Full sequences are under runs_&lt;&gt;/&lt;benchamark_name&gt;/&lt;cdr&gt;/results/sequences.fasta.</p> <p><strong>DeepAb Testset (SI Table 1, SI Figure 4 in preprint/publication)</strong>: Structure conditioned hallucinated sequences for all 6 CDR loops of 20 antibodies selected from the DeepAb test set (see publication above for more details) with wildtype seeding (runs_wtseed) and without wildtype seeding (runs_noseed). Full sequences are under runs_&lt;&gt;/&lt;benchamark_name&gt;/&lt;cdr&gt;/results/sequences.fasta.</p> <p><strong>Trastuzumab hallucination in various modes described in the manuscript.</strong></p> <p>1. <strong>Unrestricted hallucination</strong>: In <strong>&quot;unrestricted.tar&quot;</strong>. Contains hallucination results in the folder &quot;results&quot;. Forward folded structures and metrics in &quot;forward_folding&quot;, results of virtual screening in &quot;virtual_binding&quot;, results of filtering for both folding and virtual screening in &quot;results_filtered_output&quot;, and the results from comparison of multiple folding methods (DeepAb and IgFold) in &quot;results_folding_methods&quot;.</p> <p>2.&nbsp;<strong>Motif-restricted&nbsp;hallucination (positions 95, 100A on heavy chain)</strong>: In &quot;<strong>res2pos_95and100A.tar&quot;</strong>. Contains hallucination results in the folder &quot;results&quot;. Forward folded structures and metrics in &quot;forward_folding&quot;, results of virtual screening in &quot;virtual_binding&quot;, results of filtering for both folding and virtual screening in &quot;results_filtered_output&quot;, and the results from comparison of multiple folding methods (DeepAb and IgFold) in &quot;results_folding_methods&quot;.</p> <p>3.&nbsp;<strong>Motif-restricted&nbsp;hallucination (positions 99, 100A on heavy chain)</strong>: In &quot;<strong>res2pos_99and100A.tar</strong>&quot;. Contains hallucination results in the folder &quot;results&quot;. Forward folded structures and metrics in &quot;forward_folding&quot;, results of virtual screening in &quot;virtual_binding&quot;, results of filtering for both folding and virtual screening in &quot;results_filtered_output&quot;, and the results from comparison of multiple folding methods (DeepAb and IgFold) in &quot;results_folding_methods&quot;.</p> <p>4.&nbsp;<strong>Motif-restricted&nbsp;hallucination (positions 95, 99, 100, 100A on heavy chain)</strong>: In &quot;<strong>res4pos.tar</strong>&quot;. Contains hallucination results in the folder &quot;results&quot;. Forward folded structures and metrics in &quot;forward_folding&quot;, results of virtual screening in &quot;virtual_binding&quot;, results of filtering for both folding and virtual screening in &quot;results_filtered_output&quot;, and the results from comparison of multiple folding methods (DeepAb and IgFold) in &quot;results_folding_methods&quot;.</p> <p>5.&nbsp;<strong>Motif-restricted&nbsp;(positions 99, 100A on heavy chain) and sequence-restricted (restricted to wildtype sequence) hallucination</strong>: In &quot;<strong>res2pos_95and100A_and_sequence.tar</strong>&quot;. Contains hallucination results in the folder &quot;results&quot;. Forward folded structures and metrics in &quot;forward_folding&quot;, results of virtual screening in &quot;virtual_binding&quot;, results of filtering for both folding and virtual screening in &quot;results_filtered_output&quot;, and the results from comparison of multiple folding methods (DeepAb and IgFold) in &quot;results_folding_methods&quot;.</p> <p>For reproducing data, refer to code and methods in the preprint/published version.</p>

ShareScore

40/100

Overall dataset sharing score

Score breakdown

These five areas show where the dataset supports — or may limit — practical reuse.

Stewardship
8
Harmonization
4
Access
16
Reuse readiness
8
Engagement
4

Topics

Dataset details

Repository
zenodo
Published
September 13, 2022
License
cc-by-4.0
DOI
10.5281/zenodo.7076477

Scored with release 0.9.0

ScienceDex for faculty

Your academic CV and NIH biosketch

Make your CV in your school's format and your NIH biosketch from it, then download both as Word files.