Supporting Information S1: Metrics of contact correctness

2014

Citations in the corpus

• Assessment of Contact Predictions in CASP12: Co-Evolution and Deep Learning Coming of Age (2017, methodology): “A method using a deep, convolutional neural network relying on the evolutionary coupling inference of a Potts model, using pseudolikelihood maximization 26 and a single multiple sequence alignment generated with jackHMMer.”
• Patterns of coevolving amino acids unveil structural and dynamical domains (2017, methodology): “60, but similar results can be obtained by other approaches, such as gplmDCA and plmDCA20 (42) (Materials and Methods and SI Appendix).”
• Coevolutionary Analysis of Protein Subfamilies by Sequence Reweighting (2019, background): “where the norm is taken over the 20 natural amino-acids, excluding the couplings involving the gap-parameter, following [42].”
• Synthetic protein alignments by CCMgen quantify noise in residue-residue contact prediction (2018, methodology): “…used score for residue contact prediction simply takes the L 2 norm of the 20 × 20-dimensional vector w ij with components w ij ( a, b ) [3, 10, 11, 31, 50], 505 Recap: Average Product Correction The APC subtracts from each score c ij the product of the average score c i • for row i times the…”
• Learning protein constitutive motifs from sequence data (2018, background): “The presence of highorder interactions allows for a significantly better description of gap modes Feinauer et al. (2014), of multiple long-range couplings due to ligand binding, and of outliers sequences (Appendix 1, Fig.”
• Inferring Contacting Residues within and between Proteins: What Do the Probabilities Mean? (2016, background): “Similarly, in the contact prediction problem it has been observed that stretches of consecutive gap positions often occur in a highly correlated manner and incorporating such additional constraints improves contact prediction [31].”