Evolutionary velocity with protein language models predicts evolutionary dynamics of diverse proteins

Article activity feed

1. Version published to 10.1016/j.cels.2022.01.003

   Apr 1, 2022
2. 

   ScreenIT

   Jun 10, 2021

   SciScore for 10.1101/2021.06.07.447389: (What is this?)

   Please note, not all rigor criteria are appropriate for all manuscripts.

   Table 1: Rigor

   NIH rigor criteria are not applicable to paper type.

   Table 2: Resources

   Software and Algorithms
   Sentences	Resources
   We also used the TAPE transformer model [14] (obtained from https://github.com/songlab-cal/tape) trained on the Pfam database release 32.0 [31].	Pfam suggested: (Pfam, RRID:SCR_004726)
   In practice, x(a) and x(b) can disagree in length, so we first perform a global pairwise sequence alignment using the pairwise2 module in the Biopython Python package version 1.76 with a uniform substitution matrix and alignment parameters meant to discourage the introduction of sequence gaps (following the Biopython recommendations, we use a match score of 5, a mismatch penalty of −4, a gap-open penalty of …

   SciScore for 10.1101/2021.06.07.447389: (What is this?)

   Please note, not all rigor criteria are appropriate for all manuscripts.

   Table 1: Rigor

   NIH rigor criteria are not applicable to paper type.

   Table 2: Resources

   Software and Algorithms
   Sentences	Resources
   We also used the TAPE transformer model [14] (obtained from https://github.com/songlab-cal/tape) trained on the Pfam database release 32.0 [31].	Pfam suggested: (Pfam, RRID:SCR_004726)
   In practice, x(a) and x(b) can disagree in length, so we first perform a global pairwise sequence alignment using the pairwise2 module in the Biopython Python package version 1.76 with a uniform substitution matrix and alignment parameters meant to discourage the introduction of sequence gaps (following the Biopython recommendations, we use a match score of 5, a mismatch penalty of −4, a gap-open penalty of −4, and a gap-extension penalty of −0.1).	Biopython suggested: (Biopython, RRID:SCR_007173)
   We used the scipy version 1.4.1 Python package to compute correlations and statistical tests.	scipy suggested: (SciPy, RRID:SCR_008058) Python suggested: (IPython, RRID:SCR_001658)
   Once these vectors are computed, we use the streamplot and quiver plot functionality of the matplotlib Python package version 3.3.3 to visualize evo-velocity.	matplotlib suggested: (MatPlotLib, RRID:SCR_008624)
   To project evo-velocity into sequence space, we first construct a multiple sequence alignment of all M sequences using MAFFT version 7.475.	MAFFT suggested: (MAFFT, RRID:SCR_011811)
   We obtained a phylogenetic tree of all NP sequences considered in the evo-velocity analysis by first aligning sequences with MAFFT followed by approximate maximum-likelihood tree construction using FastTree version 2.1 using a JTT+CAT model.	FastTree suggested: (FastTree, RRID:SCR_015501)
   We obtained four SIVcpz Gag sequences with high-quality, manual annotation from UniProt (https://www.uniprot.org/) [54].	https://www.uniprot.org/ suggested: (Universal Protein Resource, RRID:SCR_002380)
   We then performed a multiple sequence alignment with MAFFT and performed phylogenetic reconstruction on the alignment with PhyML using a JTT model with gamma-distributed among-site rate variation and empirical state frequencies.	PhyML suggested: (PhyML, RRID:SCR_014629)
   Serpins evo-velocity analysis: We obtained 22,737 serpin sequences from UniProt.	UniProt suggested: (UniProtKB, RRID:SCR_004426)

   ---

   Results from OddPub: Thank you for sharing your code and data.

   ---

   Results from LimitationRecognizer: An explicit section about the limitations of the techniques employed in this study was not found. We encourage authors to address study limitations.

   ---

   Results from TrialIdentifier: No clinical trial numbers were referenced.

   ---

   Results from Barzooka: We did not find any issues relating to the usage of bar graphs.

   ---

   Results from JetFighter: We did not find any issues relating to colormaps.

   ---

   Results from rtransparent:

   • Thank you for including a conflict of interest statement. Authors are encouraged to include this statement when submitting to a journal.
   • Thank you for including a funding statement. Authors are encouraged to include this statement when submitting to a journal.
   • No protocol registration statement was detected.

   ---

   Results from scite Reference Check: We found no unreliable references.

   ---

   Read the original source
3. 

   Version published to 10.1101/2021.06.07.447389v1 on bioRxiv

   Jun 7, 2021