SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation
Open accessPublished version of a preprint
The DOI matches its Crossref record; 79 of the 80 references it cites were found in a registry or an index.
Abstract
We present SKEMPI 2.0, a major update to our database of binding free energy changes upon mutation for structurally resolved protein-protein interactions. This version now contains manually curated binding data for 7085 mutations, an increase of 133%, including changes in kinetics for 1844 mutations, enthalpy and entropy changes for 443 mutations, and 440 mutations which abolish detectable binding.
Overview
CoChat Summary
## TL;DR
SKEMPI 2.0 is an updated manually curated benchmark of mutation effects on structurally resolved protein–protein interactions, expanding the database to 7085 mutations and adding kinetics, thermodynamics, and non-binding cases. The dataset is broad but strongly biased toward certain interaction classes and well-studied systems, and the paper provides annotations useful for analyzing homology and mutant cycles.
## Key findings
- The database contains 7085 mutations, a 133% increase over the previous version.
- It includes 1844 mutations with kinetics changes, 443 with enthalpy and entropy changes, and 440 mutations that abolish detectable binding.
- The entries span 295 publications and include 610 double mutant cycles, 218 additional double mutant cycles in a third-mutation background, 45 triple mutant cubes, and 14 fourth-order interaction examples.
- Reported ranges include ΔΔG from –12.4 to 12.4 kcal/mol, Δlog10(kon) from –3.6 to 2.4, Δlog10(koff) from –6.0 to 6.8, ΔΔH from –18.3 to 26.5 kcal/mol, and ΔΔS from –61 to 80 cal/mol·K.
## Methods
- Manual literature curation of structurally resolved protein–protein interaction mutations, with stringent checks to match the structure and affinity paper to the same protein, species, cofactors, chains, and post-translational modifications.
- Data were collected from prior SKEMPI entries and new literature searches; the paper states that just over two fifths of the data come from the previous SKEMPI version, and new data were supplemented from sources including ABbind, PROXiMATE, and dbMPIKT.
- Entries were annotated with wild-type and mutant affinities, kinetic and thermodynamic parameters when available, experimental method, residue location, homologous interactions, and cleaned PDB files; the paper also describes calculations from reported values when needed.
## Limitations
- The paper states that the database is biased toward the interests and capabilities of the research community, with over-representation of certain interaction classes and organisms.
- It also notes a structural selection bias: only interactions with structures are included, so there is no representation of “fuzzy” complexes; this is stated in the paper.
- Evident from the text: many error comparisons rely on pairs from different groups or techniques, and the paper notes that some entries near detection limits have large errors, especially very destabilizing mutations.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Figures


Verification
Claims the paper makes
0 Valid · 0 Not valid · 1 Not checked · 74 Own results and interpretations
None of the sources cited for this claim have been checked yet.
In the paper
“The largest contribution comes from the group of the late Michael Laskowski Jr., a systematic study of all possible mutations at selected sites in the turkey ovomucoid third domain and its inhibitory interactions with four proteases (Lu et al., 2001), as well as studies of interactions of the same domain in other bird species and the design of ultra-high affinity broad-spectrum inhibitors.”
§ SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation > 3 Results and discussion > 3.2 Notable studies comprising SKEMPI 2.0 The investigations from which SKEMPI data is derived are diverse, spanning many biological processes and reported in 295 publications including systematic scans, alanine and homolog scanning, design studies including computational design and designs derived from phage display, double mutant cycle studies, antibody engineering, biologic drug design and the evaluation of pathological mutations. The largest contribution comes from the group of the late Michael Laskowski Jr., a systematic study of all possible mutations at selected sites in the turkey ovomucoid third domain and its inhibitory interactions with four proteases (Lu et al., 2001), as well as studies of interactions of the same domain in other bird species and the design of ultra-high affinity broad-spectrum inhibitors. Substantial data also come from investigations into the inhibitory interactions of class A β-lactamases from the groups of Gideon Schreiber (e.g. Reichmann et al., 2007) and Timothy Palzkill (e.g. Brown et al., 2013), as well as cytokine receptor interactions, in particular studies of type I interferons also from the Schreiber group (e.g. Roisman et al., 2001) and that of K. Christopher Garcia (Thomas et al., 2011), but also the study of the GM-CSF/GMRα interaction from the group of Michael W. Parker (Broughton et al., 2016). Other prominent sources of data are studies into hormone receptor interactions, in particular the human growth hormone receptor from the group of Jim Wells (e.g. Cunningham and Wells, 1991) and the prolactin receptor from the group of Michael E. Hodsdon (Kulkarni et al., 2010), as well as studies into antigen recognition including the combined computational and experimental design study to enhance affinity of the AQC2 antibody to integrin α-1 from the group of Herman Van Vlijmen (Clark et al., 2006), the dissection of the interactions of broadly neutralizing antibodies targeting HIV gp120 (Clark et al., 2017) from the group of Richard A. Friesner, and various investigations from the group of Roy A. Mariuzza (e.g. Dall'Acqua et al., 1998). Also notable is the alanine scanning of the urokinase-type plasminogen activator and its receptor from the group of Michael Ploug (Gardsvoll et al., 2006), studies of Ras effector interactions from the group of Christian Herrmann (e.g. Kiel et al., 2004), investigations of pMHC/TCR interactions from the group of Brian Baker (e.g. Piepenbrink et al., 2013), and investigations into the cognate and non-cognate recognition of Escherichia coli colicin DNase bacteriotoxins by their immunity proteins from the group of Colin Kleanthous (e.g. Li et al., 1997).
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For 84% of 1741 such pairs, both entries give a ΔΔG value within 1 kcal.mol−1 of each other.”
§ SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation > 3 Results and discussion > 3.3 Range and error Range: The changes in binding free energy upon mutation range from –12.4 to 12.4 kcal.mol−1, as in SKEMPI 1.1, with Δ log 10kon ranging from –3.6 to 2.4, Δ log 10koff ranging from –6.0 to 6.8, ΔΔH ranging from –18.3 to 26.5 kcal.mol−1, and ΔΔS ranging from –61 to 80 cal.mol−1.K−1. Around 60 mutants are very destabilizing, reducing binding energy by 8 kcal.mol−1 or more. These are all in enzyme/inhibitor complexes such as the inhibition of acetylcholinesterase by the snake venom fasciculin, or the inhibition of enzymes which would be detrimental should they unbind and become active in the wrong location, such as nucleases (barnase/barstar, colicin E9 DNase/Im9, RNase A/angiogenin) and proteases (such as trypsin/BPTI). These interactions tend to be around picomolar affinity and are at the upper limit of what can be detected, due to the time required to reach equilibrium and the low concentrations required by the mass action law to probe informative regions of the binding curve. These very destabilizing mutations reduce affinity into the micromolar range, near the lower limit of what can be quantified using standard methods. As a consequence of both mutant and wild-type affinities being near detection thresholds, errors in these entries are typically large. Further, while some mutations may cause changes in affinity larger than seven orders of magnitude, the absence of affinities for such mutations in the benchmark can be explained by the fact that such mutations would involve affinities beyond the upper or lower limit. Indeed, there are new entries in which single or double substitutions reduce binding from tens of picomolar to having no detectable binding. For many of the highly destabilizing mutations a crystal structure for the mutant has also been solved, and the 30 most stabilizing mutations in the database (ΔΔG ¡ –5 kcal.mol−1) consist of the reverse mutation applied to these structures. These are mostly single or double mutants, but include mutations to up to 27 residues of the non-cognate Colicin E2/Im9 complex, which move it toward the cognate E9/Im9 in sequence space (Li et al., 1997). Errors: Standard errors in KD are typically reported in the order of 50%, around 0.25 kcal.mol−1. These estimates are derived by repeat measurements using the same equipment, environment and protocol, and thus do not include errors arising from systematic bias. Such biases can, however, be estimated from pairs of entries in which the same mutation is evaluated by different groups or using different techniques. For 84% of 1741 such pairs, both entries give a ΔΔG value within 1 kcal.mol−1 of each other. For 704 pairs for which kon is available for both, 80% have Δ log 10(kon) within 0.5 of each other. For 702 pairs for which koff is available, 83% have Δ log 10(koff) within 0.5. For the 62 pair with both ΔΔH and ΔΔS values, 61% have ΔΔH within 3.0 kcal.mol−1 of each other and 58% have ΔΔS within 10 cal.mol−1.K−1 of each other.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: passes — The paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper states — it cites no source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For many of the highly destabilizing mutations a crystal structure for the mutant has also been solved, and the 30 most stabilizing mutations in the database (ΔΔG ¡ –5 kcal.mol−1) consist of the reverse mutation applied to these structures.”
§ SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation > 3 Results and discussion > 3.3 Range and error Range: The changes in binding free energy upon mutation range from –12.4 to 12.4 kcal.mol−1, as in SKEMPI 1.1, with Δ log 10kon ranging from –3.6 to 2.4, Δ log 10koff ranging from –6.0 to 6.8, ΔΔH ranging from –18.3 to 26.5 kcal.mol−1, and ΔΔS ranging from –61 to 80 cal.mol−1.K−1. Around 60 mutants are very destabilizing, reducing binding energy by 8 kcal.mol−1 or more. These are all in enzyme/inhibitor complexes such as the inhibition of acetylcholinesterase by the snake venom fasciculin, or the inhibition of enzymes which would be detrimental should they unbind and become active in the wrong location, such as nucleases (barnase/barstar, colicin E9 DNase/Im9, RNase A/angiogenin) and proteases (such as trypsin/BPTI). These interactions tend to be around picomolar affinity and are at the upper limit of what can be detected, due to the time required to reach equilibrium and the low concentrations required by the mass action law to probe informative regions of the binding curve. These very destabilizing mutations reduce affinity into the micromolar range, near the lower limit of what can be quantified using standard methods. As a consequence of both mutant and wild-type affinities being near detection thresholds, errors in these entries are typically large. Further, while some mutations may cause changes in affinity larger than seven orders of magnitude, the absence of affinities for such mutations in the benchmark can be explained by the fact that such mutations would involve affinities beyond the upper or lower limit. Indeed, there are new entries in which single or double substitutions reduce binding from tens of picomolar to having no detectable binding. For many of the highly destabilizing mutations a crystal structure for the mutant has also been solved, and the 30 most stabilizing mutations in the database (ΔΔG ¡ –5 kcal.mol−1) consist of the reverse mutation applied to these structures. These are mostly single or double mutants, but include mutations to up to 27 residues of the non-cognate Colicin E2/Im9 complex, which move it toward the cognate E9/Im9 in sequence space (Li et al., 1997). Errors: Standard errors in KD are typically reported in the order of 50%, around 0.25 kcal.mol−1. These estimates are derived by repeat measurements using the same equipment, environment and protocol, and thus do not include errors arising from systematic bias. Such biases can, however, be estimated from pairs of entries in which the same mutation is evaluated by different groups or using different techniques. For 84% of 1741 such pairs, both entries give a ΔΔG value within 1 kcal.mol−1 of each other. For 704 pairs for which kon is available for both, 80% have Δ log 10(kon) within 0.5 of each other. For 702 pairs for which koff is available, 83% have Δ log 10(koff) within 0.5. For the 62 pair with both ΔΔH and ΔΔS values, 61% have ΔΔH within 3.0 kcal.mol−1 of each other and 58% have ΔΔS within 10 cal.mol−1.K−1 of each other.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“For the 62 pair with both ΔΔH and ΔΔS values, 61% have ΔΔH within 3.0 kcal.mol−1 of each other and 58% have ΔΔS within 10 cal.mol−1.K−1 of each other.”
§ SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation > 3 Results and discussion > 3.3 Range and error Range: The changes in binding free energy upon mutation range from –12.4 to 12.4 kcal.mol−1, as in SKEMPI 1.1, with Δ log 10kon ranging from –3.6 to 2.4, Δ log 10koff ranging from –6.0 to 6.8, ΔΔH ranging from –18.3 to 26.5 kcal.mol−1, and ΔΔS ranging from –61 to 80 cal.mol−1.K−1. Around 60 mutants are very destabilizing, reducing binding energy by 8 kcal.mol−1 or more. These are all in enzyme/inhibitor complexes such as the inhibition of acetylcholinesterase by the snake venom fasciculin, or the inhibition of enzymes which would be detrimental should they unbind and become active in the wrong location, such as nucleases (barnase/barstar, colicin E9 DNase/Im9, RNase A/angiogenin) and proteases (such as trypsin/BPTI). These interactions tend to be around picomolar affinity and are at the upper limit of what can be detected, due to the time required to reach equilibrium and the low concentrations required by the mass action law to probe informative regions of the binding curve. These very destabilizing mutations reduce affinity into the micromolar range, near the lower limit of what can be quantified using standard methods. As a consequence of both mutant and wild-type affinities being near detection thresholds, errors in these entries are typically large. Further, while some mutations may cause changes in affinity larger than seven orders of magnitude, the absence of affinities for such mutations in the benchmark can be explained by the fact that such mutations would involve affinities beyond the upper or lower limit. Indeed, there are new entries in which single or double substitutions reduce binding from tens of picomolar to having no detectable binding. For many of the highly destabilizing mutations a crystal structure for the mutant has also been solved, and the 30 most stabilizing mutations in the database (ΔΔG ¡ –5 kcal.mol−1) consist of the reverse mutation applied to these structures. These are mostly single or double mutants, but include mutations to up to 27 residues of the non-cognate Colicin E2/Im9 complex, which move it toward the cognate E9/Im9 in sequence space (Li et al., 1997). Errors: Standard errors in KD are typically reported in the order of 50%, around 0.25 kcal.mol−1. These estimates are derived by repeat measurements using the same equipment, environment and protocol, and thus do not include errors arising from systematic bias. Such biases can, however, be estimated from pairs of entries in which the same mutation is evaluated by different groups or using different techniques. For 84% of 1741 such pairs, both entries give a ΔΔG value within 1 kcal.mol−1 of each other. For 704 pairs for which kon is available for both, 80% have Δ log 10(kon) within 0.5 of each other. For 702 pairs for which koff is available, 83% have Δ log 10(koff) within 0.5. For the 62 pair with both ΔΔH and ΔΔS values, 61% have ΔΔH within 3.0 kcal.mol−1 of each other and 58% have ΔΔS within 10 cal.mol−1.K−1 of each other.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
A result the paper reports from its own data — it cites no other source for it, so there is none to check. The quote shows it is in the paper.
In the paper
“Standard errors in KD are typically reported in the order of 50%, around 0.25 kcal.mol−1.”
§ SKEMPI 2.0: an updated benchmark of changes in protein–protein binding energy, kinetics and thermodynamics upon mutation > 3 Results and discussion > 3.3 Range and error Range: The changes in binding free energy upon mutation range from –12.4 to 12.4 kcal.mol−1, as in SKEMPI 1.1, with Δ log 10kon ranging from –3.6 to 2.4, Δ log 10koff ranging from –6.0 to 6.8, ΔΔH ranging from –18.3 to 26.5 kcal.mol−1, and ΔΔS ranging from –61 to 80 cal.mol−1.K−1. Around 60 mutants are very destabilizing, reducing binding energy by 8 kcal.mol−1 or more. These are all in enzyme/inhibitor complexes such as the inhibition of acetylcholinesterase by the snake venom fasciculin, or the inhibition of enzymes which would be detrimental should they unbind and become active in the wrong location, such as nucleases (barnase/barstar, colicin E9 DNase/Im9, RNase A/angiogenin) and proteases (such as trypsin/BPTI). These interactions tend to be around picomolar affinity and are at the upper limit of what can be detected, due to the time required to reach equilibrium and the low concentrations required by the mass action law to probe informative regions of the binding curve. These very destabilizing mutations reduce affinity into the micromolar range, near the lower limit of what can be quantified using standard methods. As a consequence of both mutant and wild-type affinities being near detection thresholds, errors in these entries are typically large. Further, while some mutations may cause changes in affinity larger than seven orders of magnitude, the absence of affinities for such mutations in the benchmark can be explained by the fact that such mutations would involve affinities beyond the upper or lower limit. Indeed, there are new entries in which single or double substitutions reduce binding from tens of picomolar to having no detectable binding. For many of the highly destabilizing mutations a crystal structure for the mutant has also been solved, and the 30 most stabilizing mutations in the database (ΔΔG ¡ –5 kcal.mol−1) consist of the reverse mutation applied to these structures. These are mostly single or double mutants, but include mutations to up to 27 residues of the non-cognate Colicin E2/Im9 complex, which move it toward the cognate E9/Im9 in sequence space (Li et al., 1997). Errors: Standard errors in KD are typically reported in the order of 50%, around 0.25 kcal.mol−1. These estimates are derived by repeat measurements using the same equipment, environment and protocol, and thus do not include errors arising from systematic bias. Such biases can, however, be estimated from pairs of entries in which the same mutation is evaluated by different groups or using different techniques. For 84% of 1741 such pairs, both entries give a ΔΔG value within 1 kcal.mol−1 of each other. For 704 pairs for which kon is available for both, 80% have Δ log 10(kon) within 0.5 of each other. For 702 pairs for which koff is available, 83% have Δ log 10(koff) within 0.5. For the 62 pair with both ΔΔH and ΔΔS values, 61% have ΔΔH within 3.0 kcal.mol−1 of each other and 58% have ΔΔS within 10 cal.mol−1.K−1 of each other.
plain- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
50 more claims
Create a free account to see all 75 claims and every source verdict.
- Probably not a substantial claim. 12
- It may state two separate claims as one. 11
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“Additional dedicated datasets summarize curated information about properties and structure of antibodies.These databases include the structural database of kinetics and energetics of mutant protein interactions (SKEMPI) [17], and the antibody binding mutational database (AB-Bind) [18].”
From Computational and artificial intelligence-based methods for antibody development (2023) · cites this paper as [17]
The cited source says what the claim attributes to it.
In the citing paper
“This dataset contains 7,085 entries, including single- and multi-point mutations.”
From A topology-based network tree for the prediction of protein–protein binding affinity changes following mutation (2020) · cites this paper as [39]
In the citing paper
“This model was evaluated by split-by-complex fivefold cross-validation over the Structural Kinetic and Energetic database of Mutant Protein Interactions (SKEMPI) V2.0 dataset (38).”
From Deep learning guided optimization of human antibody against SARS-CoV-2 variants with broad neutralization (2022) · cites this paper as [38]
In the citing paper
“The training and validation datasets were constructed from the SKEMPI V2.0 dataset (38), the largest antibody–antigen binding affinity dataset, which contains 342 complexes and 5,318 mutations in total.”
From Deep learning guided optimization of human antibody against SARS-CoV-2 variants with broad neutralization (2022) · cites this paper as [38]
Citations
Cites
Berman, H. M. (2000) · Nucleic Acids Research · doi:10.1093/nar/28.1.235 · Cited by 40,196 · cited 2×
“Processed PDB files: The PDB files for the interactions, as downloaded from the Protein Data Bank [8], often contain multiple copies of the interacting proteins in the unit cell or other chains irrelevant to the interaction.”
MethodOverview of the CCP 4 suite and current developments
Winn, M. D., Ballard, C. C., Cowtan, K. D., Dodson, E. J., Emsley, P., Evans, P. R., Keegan, R. M., Krissinel, E. B., Leslie, A. G. W., McCoy, A., et al. (2011) · Acta Crystallographica Section D Biological Crystallography · doi:10.1107/s0907444910045749 · Cited by 12,353 · cited 10×
“, 289, 5528–5533. Kastritis,P.L. et al. (2011) A structure-based benchmark for protein-protein”
BackgroundInfluentialmCSM: Predicting the effects of mutations in proteins using graph-based signatures
Pires, D. E. V., Ascher, D. B., & Blundell, T. L. (2014) · Bioinformatics · doi:10.1093/bioinformatics/btt691 · Cited by 1,066
Computational Design of Proteins Targeting the Conserved Stem Region of Influenza Hemagglutinin
Fleishman, S. J., Whitehead, T. A., Ekiert, D. C., Dreyfus, C., Corn, J. E., Strauch, E.-M., Wilson, I. A., & Baker, D. (2011) · Science · doi:10.1126/science.1202617 · Cited by 585
Vreven, T., Moal, I. H., Vangone, A., Pierce, B. G., Kastritis, P. L., Torchala, M., Chaleil, R., Jiménez-García, B., Bates, P. A., Fernandez-Recio, J., et al. (2015) · Journal of Molecular Biology · doi:10.1016/j.jmb.2015.07.016 · Cited by 424
Self-citationThorn, K. S., & Bogan, A. A. (2001) · Bioinformatics · doi:10.1093/bioinformatics/17.3.284 · Cited by 403 · cited 3×
“1 were found by checking the references in the ASEdb [71] and PINT [36] databases,”
MethodInfluentialStructural Linkage between Ligand Discrimination and Receptor Activation by Type I Interferons
Thomas, C., Moraga, I., Levin, D., Krutzik, P. O., Podoplelova, Y., Trejo, A., Lee, C., Yarden, G., Vleck, S. E., Glenn, J. S., et al. (2011) · Cell · doi:10.1016/j.cell.2011.06.048 · Cited by 356
Plattner, N., Doerr, S., De Fabritiis, G., & Noé, F. (2017) · Nature Chemistry · doi:10.1038/nchem.2785 · Cited by 345
BeAtMuSiC: prediction of changes in protein–protein binding affinity on mutations
Dehouck, Y., Kwasigroch, J. M., Rooman, M., & Gilis, D. (2013) · Nucleic Acids Research · doi:10.1093/nar/gkt450 · Cited by 338
Strategy for analysing the co-operativity of intramolecular interactions in peptides and proteins
Horovitz, A., & Fersht, A. R. (1990) · Journal of Molecular Biology · doi:10.1016/0022-2836(90)90275-q · Cited by 335 · cited 2×
“Higher order interaction terms can be garnered from higher cycles, such as triple mutant cubes, constructed from the energies of the wild-type, three single mutants, three corresponding double mutants and the triple mutant (Horovitz and Fersht, 1990).”
Background
Cited by
gmx_MMPBSA: A New Tool to Perform End-State Free Energy Calculations with GROMACS
Valdés-Tresanco, M. S., Valdés-Tresanco, M. E., Valiente, P. A., & Moreno, E. (2021) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.1c00645 · Cited by 3,393
Omicron Variant (B.1.1.529): Infectivity, Vaccine Breakthrough, and Antibody Resistance
Chen, J., Wang, R., Gilby, N. B., & Wei, G.-W. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.1c01451 · Cited by 653
Mutations Strengthened SARS-CoV-2 Infectivity
Chen, J., Wang, R., Wang, M., & Wei, G.-W. (2020) · Journal of Molecular Biology · doi:10.1016/j.jmb.2020.07.009 · Cited by 466
“There are many standard databases available, including the AB-Bind database of mutation-induced antibody–antigen complex BFE changes [24] and SKEMPI for protein–protein BFE changes upon mutation (ΔΔG) [25,26].”
MethodLearning inverse folding from millions of predicted structures
Hsu, C., Verkuil, R., Liu, J., Lin, Z., Hie, B., Sercu, T., Lerer, A., & Rives, A. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.04.10.487779 · Cited by 416
“We evaluate models on zero-shot prediction of mutational effects on protein complex interfaces, using the Atom3D benchmark (Townshend et al., 2020) which incorporates binding free energy changes in the SKEMPI database (Jankauskait ˙ e et al., 2019) as a binary classification task.”
MethodmCSM-PPI2: predicting the effects of mutations on protein–protein interactions
Rodrigues, C. H. M., Myung, Y., Pires, D. E. V., & Ascher, D. B. (2019) · Nucleic Acids Research · doi:10.1093/nar/gkz383 · Cited by 369
“…changes in thermodynamic and kinetic parameters on mutation for protein–protein complexes that have 3D structures deposited in the PDB. SKEMPI 2.0 (36) includes new mutations identified in the literature after its first release, including data available from three other databases: ABbind (37),…”
BackgroundInfluentialTubiana, J., Schneidman-Duhovny, D., & Wolfson, H. J. (2022) · Nature Methods · doi:10.1038/s41592-022-01490-7 · Cited by 274
Autonomous Discovery in the Chemical Sciences Part II: Outlook
Coley, C. W., Eyke, N. S., & Jensen, K. F. (2020) · Angewandte Chemie International Edition · doi:10.1002/anie.201909989 · Cited by 245
Capturing variation impact on molecular interactions in the IMEx Consortium mutations data set
The IMEx Consortium Curators, Khadake, J., Meldal, B., Panni, S., Thorneycroft, D., van Roey, K., Abbani, S., Salwinski, L., Pellegrini, M., Iannuccelli, M., et al. (2019) · Nature Communications · doi:10.1038/s41467-018-07709-6 · Cited by 247
“Currently, the only resources that represent the impact of amino acid substitutions on binding events are the SKEMPI 2.0 database 14 , UniProtKB and IMEx Consortium member databases through IntAct (see Table 3 for a detailed comparison).”
BackgroundInfluentialComputational approaches to therapeutic antibody design: established methods and emerging trends
Norman, R. A., Ambrosetti, F., Bonvin, A. M. J. J., Colwell, L. J., Kelm, S., Kumar, S., & Krawczyk, K. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbz095 · Cited by 219
Wang, R., Chen, J., Gao, K., & Wei, G.-W. (2021) · Genomics · doi:10.1016/j.ygeno.2021.05.006 · Cited by 191
Machine Learning-Guided Protein Engineering
Kouba, P., Kohout, P., Haddadi, F., Bushuiev, A., Samusevich, R., Sedlar, J., Damborsky, J., Pluskal, T., Sivic, J., & Mazurenko, S. (2023) · ACS Catalysis · doi:10.1021/acscatal.3c02743 · Cited by 209
Wang, M., Cang, Z., & Wei, G.-W. (2020) · Nature Machine Intelligence · doi:10.1038/s42256-020-0149-6 · Cited by 202
Wang, R., Chen, J., Gao, K., Hozumi, Y., Yin, C., & Wei, G.-W. (2021) · Communications Biology · doi:10.1038/s42003-021-01754-6 · Cited by 202
MutaBind2: predicting the impacts of single and multiple mutations on protein-protein interactions
Zhang, N., Chen, Y., Lu, H., Zhao, F., Alvarez, R. V., Goncearenco, A., Panchenko, A. R., & Li, M. (2020) · iScience · doi:10.1016/j.isci.2020.100939 · Cited by 199
“In addition, a “CV5” cross-validation accounted for similarities between binding sites of different complexes (the definition of similar binding sites is taken from (Jankauskaite et al., 2019; Moal and Fernandez-Recio, 2012)).”
BackgroundLazim, R., Suh, D., & Choi, S. (2020) · International Journal of Molecular Sciences · doi:10.3390/ijms21176339 · Cited by 185
Computational and artificial intelligence-based methods for antibody development
Kim, J., McFee, M., Fang, Q., Abdin, O., & Kim, P. M. (2023) · Trends in Pharmacological Sciences · doi:10.1016/j.tips.2022.12.005 · Cited by 178
Shan, S., Luo, S., Yang, Z., Hong, J., Su, Y., Ding, F., Fu, L., Li, C., Chen, P., Ma, J., et al. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2122954119 · Cited by 157
Deep geometric representations for modeling effects of mutations on protein-protein binding affinity
Liu, X., Luo, Y., Li, P., Song, S., & Peng, J. (2021) · PLOS Computational Biology · doi:10.1371/journal.pcbi.1009284 · Cited by 140
“0 (Jankauskaitė et al., 2019) is composed of 7085 single- or multi-point mutations from 345 complexes.”
BackgroundAkbar, R., Bashour, H., Rawat, P., Robert, P. A., Smorodina, E., Cotet, T.-S., Flem-Karlsen, K., Frank, R., Mehta, B. B., Vu, M. H., et al. (2022) · mAbs · doi:10.1080/19420862.2021.2008790 · Cited by 113
SAAMBE-3D: Predicting Effect of Mutations on Protein–Protein Interactions
Pahari, S., Li, G., Murthy, A. K., Liang, S., Fragoza, R., Yu, H., & Alexov, E. (2020) · International Journal of Molecular Sciences · doi:10.3390/ijms21072563 · Cited by 124
“0 [31] using the XGBoost machine learning method and achieves PCC ranging from 0.”
MethodGeng, C., Xue, L. C., Roel‐Touris, J., & Bonvin, A. M. J. J. (2019) · WIREs Computational Molecular Science · doi:10.1002/wcms.1410 · Cited by 100
“Databases, such as SKEMPI, 28,32 provide the Protein Data Bank (PDB) 46 entry of the highest resolution wildtype complex if more than one structure has been deposited.”
BackgroundPandurangan, A. P., & Blundell, T. L. (2020) · Protein Science · doi:10.1002/pro.3774 · Cited by 101
“The mCSM predictive models for protein stability, protein – protein, and protein-nucleic acid interactions are trained using thermodynamic data sets taken from ProTherm, 21 SKEMPI, 23 and ProNIT 21 databases, respectively. mCSM is available at http://biosig.unimelb.edu.au/mcsm/.”
BackgroundMethodComputational Approaches to Predict Protein–Protein Interactions in Crowded Cellular Environments
Grassmann, G., Miotto, M., Desantis, F., Rienzo, L. D., Tartaglia, G. G., Pastore, A., Ruocco, G., Monti, M. M., & Milanetti, E. (2024) · Chemical Reviews · doi:10.1021/acs.chemrev.3c00550 · Cited by 118
Omicron BA.2 (B.1.1.529.2): High Potential for Becoming the Next Dominant Variant
Chen, J., & Wei, G. (2022) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.2c00469 · Cited by 112
Masked inverse folding with sequence transfer for protein representation learning
(2022) · doi:10.1093/protein/gzad015 · Cited by 110
Villoutreix, B. O., Cálvez, V., Marcelin, A., & Khatib, A. (2021) · International Journal of Molecular Sciences · doi:10.3390/ijms22041695 · Cited by 97
Romero‐Molina, S., Ruiz‐Blanco, Y. B., Mieres‐Pérez, J., Harms, M., Münch, J., Ehrmann, M., & Sánchez‐García, E. (2022) · Journal of Proteome Research · doi:10.1021/acs.jproteome.2c00020 · Cited by 100
Pearce, R., Huang, X., Setiawan, D., & Zhang, Y. (2019) · Journal of Molecular Biology · doi:10.1016/j.jmb.2019.02.028 · Cited by 83
“Second, the 14 weights for E interResidueDiffChain were determined using the mutation-induced protein-protein binding affinity change data Δ Δ G bindingWTmut , which contained 2,204 non-redundant mutant samples from 177 dimeric complexes collected from the latest version of the SKEMPI database [27].”
MethodmCSM-AB2: guiding rational antibody design using graph-based signatures
Myung, Y., Rodrigues, C. H. M., Ascher, D. B., & Pires, D. E. V. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz779 · Cited by 92
Geng, C., Vangone, A., Folkers, G. E., Xue, L. C., & Bonvin, A. M. J. J. (2019) · Proteins: Structure, Function, and Bioinformatics · doi:10.1002/prot.25630 · Cited by 82
PDBe-KB: collaboratively defining the biological context of structural data
PDBe-KB consortium, Varadi, M., Anyango, S., Armstrong, D., Berrisford, J., Choudhary, P., Deshpande, M., Nadzirin, N., Nair, S. S., Pravda, L., et al. (2022) · Nucleic Acids Research · doi:10.1093/nar/gkab988 · Cited by 82
mmCSM-PPI: predicting the effects of multiple point mutations on protein–protein interactions
Rodrigues, C. H. M., Pires, D. E. V., & Ascher, D. B. (2021) · Nucleic Acids Research · doi:10.1093/nar/gkab273 · Cited by 86
“The data used in this work was derived from SKEMPI2 (12), a manually curated database of experimental data on thermodynamics and kinetic parameters for wild-type and mutant protein–protein complexes which have been mapped to protein structures available on the Protein Data Bank (54).”
BackgroundMethodInfluentialChen, C., Boorla, V. S., Banerjee, D., Chowdhury, R., Cavener, V. S., Nissly, R. H., Gontu, A., Boyle, N. R., Vandegrift, K. J., Nair, M. S., et al. (2021) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2106480118 · Cited by 83
“0 (50) dataset, which is not SARS-CoV-2 specific.”
Wang, G., Liu, X., Wang, K., Gao, Y., Li, G., Baptista‐Hon, D. T., Yang, X. H., Xue, K., Tai, W. H., Jiang, Z., et al. (2023) · Nature Medicine · doi:10.1038/s41591-023-02483-5 · Cited by 94
“PADBs used here were constructed from the SKEMPI v.2.0 database 14 and literature 13,23–25 .”
BackgroundMethodInfluentialMachine learning solutions for predicting protein–protein interactions
Casadio, R., Martelli, P. L., & Savojardo, C. (2022) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1618 · Cited by 95
“Specific and derived databases organize structures according to given properties, 39 like ProtCID, a data resource for structural information on protein interactions.”
BackgroundRecent advances in predicting and modeling protein–protein interactions
Durham, J., Zhang, J., Humphreys, I. R., Pei, J., & Cong, Q. (2023) · Trends in Biochemical Sciences · doi:10.1016/j.tibs.2023.03.003 · Cited by 88
Wee, J., & Wei, G. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c00976 · Cited by 119
Omicron (B.1.1.529): Infectivity, vaccine breakthrough, and antibody resistancePreprint
Chen, J., Wang, R., Gilby, N. B., & Wei, G. (2021) · PubMed · doi:10.48550/arxiv.2112.01318 · Cited by 78
“0 [25], together with SARSCoV-2 related datasets.”
BackgroundEmerging Vaccine-Breakthrough SARS-CoV-2 Variants
Wang, R., Chen, J., Hozumi, Y., Yin, C., & Wei, G. (2022) · ACS Infectious Diseases · doi:10.1021/acsinfecdis.1c00557 · Cited by 87
Recent advances in user-friendly computational tools to engineer protein function
Sequeiros-Borja, C. E., Surpeta, B., & Brezovský, J. (2020) · Briefings in Bioinformatics · doi:10.1093/bib/bbaa150 · Cited by 82
“0 database [114], iSEE exhibited a PCC of”
BackgroundMethodA Review of Deep Learning Methods for Antibodies
Graves, J., Byerly, J., Priego, E., Makkapati, N., Parish, S., Medellin, B., & Berrondo, M. (2020) · Antibodies · doi:10.3390/antib9020012 · Cited by 72
Zhou, G., Chen, M., Ju, C. J. ‐., Wang, Z., Jiang, J., & Wang, W. W. (2020) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqaa015 · Cited by 84
“SKEMPI v2 is a recently released dataset (51).”
BackgroundRevealing the Threat of Emerging SARS-CoV-2 Mutations to Antibody Therapies
Chen, J., Gao, K., Wang, R., & Wei, G. (2021) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.167155 · Cited by 76
FoldX force field revisited, an improved version
Delgado, J., Reche, R., Cianferoni, D., Orlando, G., van der Kant, R., Rousseau, F., Schymkowitz, J. W. H., & Serrano, L. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf064 · Cited by 108
“…fact that the number of 3D structures has increased dramatically since its conception, as well as the datasets for changes upon mutation for stability as ProTherm (Nikam et al. 2021) or VariBench, and for binding as Skempy (Jankauskait _ e et al. 2019). et al. (2021) to improve FoldX force field.”
Persistent Laplacian projected Omicron BA.4 and BA.5 to become new dominating variants
Chen, J., Qiu, Y., Wang, R., & Wei, G. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106262 · Cited by 94
“0 [22] database is an updated version of the original SKEMPI database with new mutations from three other databases: AB-bind [44], PROXiMATE [23], and dbMPIKT [27].”
BackgroundMethodInfluentialDirect observation of individual tubulin dimers binding to growing microtubules
Mickolajczyk, K. J., Geyer, E. A., Kim, T., Rice, L. M., & Hancock, W. O. (2019) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.1815823116 · Cited by 71
“This attenuation is consistent with the fact that the mutation adds bulky charged residues in place of smaller neutral ones and with the observation that the mutant cannot assemble MTs by itself (32), and it is plausible, given that single mutations are commonly observed to decrease binding affinity by 3 or more order…”
BackgroundOmicron BA.2 (B.1.1.529.2): high potential to becoming the next dominating variantPreprint
Chen, J., & Wei, G. (2022) · Research Square · doi:10.21203/rs.3.rs-1362445/v1 · Cited by 78
“1’s impact on GlaxoSmithKline’s mAb, called sotrovimab, was predicted to be mild [1].”
InfluentialVakser, I. A. (2020) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2020.07.001 · Cited by 62
Zhou, Y., Myung, Y., Rodrigues, C. H. M., & Ascher, D. B. (2024) · Nucleic Acids Research · doi:10.1093/nar/gkae412 · Cited by 74
Huang, X., Zheng, W. H., Pearce, R., & Zhang, Y. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz926 · Cited by 64
A dynamical view of protein-protein complexes: Studies by molecular dynamics simulations
Martin, J., & Frezza, E. (2022) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2022.970109 · Cited by 62
Dewaker, V., Morya, V. K., Kim, Y. H., Park, S. T., Kim, H. S., & Koh, Y. H. (2025) · Biomarker Research · doi:10.1186/s40364-025-00764-4 · Cited by 63
A survey of geometric graph neural networks: data structures, models and applications
Han, J., Cen, J., Wu, L., Li, Z., Kong, X., Jiao, R., Yu, Z., Xu, T., Wu, F., Wang, Z., et al. (2025) · Frontiers of Computer Science · doi:10.1007/s11704-025-41426-w · Cited by 125
“GeoPPI [164] SAbDab [50] 8.1K Antibody Design RefineGNN [123] RAbD [1] 0.06K Antibody Design RefineGNN [123] SKEMPI 2.0 [115] 7.1K Antibody Design ATOM3D [247] Binding Affinity Pred. mmCSM-PPI [209] Cov-abdab [206] 2.4K Antibody Design RefineGNN [123] PepBDB [270] 13K Peptide Design CAMP [150] LNR…”
InfluentialmmCSM-AB: guiding rational antibody engineering through multiple point mutations
Myung, Y., Pires, D. E. V., & Ascher, D. B. (2020) · Nucleic Acids Research · doi:10.1093/nar/gkaa389 · Cited by 55
Pretrainable geometric graph neural network for antibody affinity maturation
Cai, H., Zhang, Z., Wang, M., Zhong, B., Li, Q., Zhong, Y., Wu, Y., Ying, T., & Tang, J. (2024) · Nature Communications · doi:10.1038/s41467-024-51563-8 · Cited by 76
“0 [12], contains only 89 7085 ∆∆Gbind measurements, a tiny amount compared to the training set sizes 90 of successful deep learning models such as AlphaFold2 [13] and ESM2 [14].”
MethodHummer, A. M., Schneider, C., Chinery, L., & Deane, C. M. (2025) · Nature Computational Science · doi:10.1038/s43588-025-00823-8 · Cited by 52
“We benchmarked the performance of Flex ddG under these conditions on the Experimental_ΔΔ G _608 dataset, derived from the SKEMPI 2.0 database 31 .”
InfluentialVariation benchmark datasets: update, criteria, quality and applications
Sarkar, A., Yang, Y., & Vihinen, M. (2019) · Database · doi:10.1093/database/baz117 · Cited by 57
“Links are available to data in some external databases, including AmyLoad (38) and WALTZ-DB (39) for protein aggregation, DBASS3 and DBASS5 (40, 41) for splicing variants, SKEMPI (42), cancer datasets in KinMutBase (43), Kin-Driver (44), dbCPM (45), DoCM (46), OncoKB (47) and tolerance predictor training set in DANN (…”
BackgroundAntibody design using deep learning: from sequence and structure design to affinity maturation
Joubbi, S., Micheli, A., Milazzo, P., Maccari, G., Ciano, G., Cardamone, D., & Medini, D. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae307 · Cited by 67
“An updated version, SKEMPI v2 [49], has been introduced, which provides meticulously verified binding information for 7085 mutations.”
BackgroundWee, J., & Xia, K. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac024 · Cited by 57
Pan, Q., Nguyen, T., Ascher, D. B., & Pires, D. E. V. (2022) · Briefings in Bioinformatics · doi:10.1093/bib/bbac025 · Cited by 57
“Over the years, considerable efforts have been dedicated to extracting and manually curating experimentally derived protein thermodynamics information from the literature, including the effects of mutations on stability [64–67] and interactions [68,69], and linking these to high-resolution protein structures.”
BackgroundJemimah, S., Sekijima, M., & Gromiha, M. M. (2019) · Bioinformatics · doi:10.1093/bioinformatics/btz829 · Cited by 48
Emerging Dominant SARS-CoV-2 Variants
Chen, J., Wang, R., Hozumi, Y., Liu, G., Qiu, Y., Wei, X., & Wei, G. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c01352 · Cited by 53
“0 dataset [27] and deep mutational scanning datasets [28–31].”
BackgroundStrokach, A. V., Lu, T., & Kim, P. M. (2021) · Journal of Molecular Biology · doi:10.1016/j.jmb.2021.166810 · Cited by 43
Assigning function to SNPs: Considerations when interpreting genetic variation
Fadason, T., Farrow, S. L., Gokuladhas, S., Golovina, E., Nyaga, D. M., O'Sullivan, J. M., & Schierding, W. S. (2021) · Seminars in Cell and Developmental Biology · doi:10.1016/j.semcdb.2021.08.008 · Cited by 51
Li, S., Wu, S., Wang, L., Li, F., Jiang, H., & Bai, F. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2022.102344 · Cited by 42
Li, G., Pahari, S., Murthy, A. K., Liang, S., Fragoza, R., Yu, H., & Alexov, E. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa761 · Cited by 45
HADDOCK3: A Modular and Versatile Platform for Integrative Modeling of Biomolecular Complexes
Giulini, M., Reys, V., Teixeira, J. M. C., Jiménez-García, B., V. Honorato, R., Kravchenko, A., Xu, X., Versini, R., Engel, A., Verhoeven, S., et al. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00969 · Cited by 51
Self-citationFrom language to action: a review of large language models as autonomous agents and tool users
Chowa, S. S., Alvi, R., Rahman, S. S., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11471-9 · Cited by 50
Measures of epitope binding degeneracy from T cell receptor repertoires
Mayer, A., & Callan, C. G. (2023) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2213264120 · Cited by 45
“Importantly, the predicted level of local degeneracy is in rough accord with measured distributions of binding affinity changes between point-mutated TCRs (56, 57) and results from systematic mutational scans of specific binding upon changes in TCR hypervariable regions (58).”
Machine learning methods for protein-protein binding affinity prediction in protein design
Guo, Z., & Yamaguchi, R. (2022) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2022.1065703 · Cited by 47
“The equilibrium dissociation constant (Kd) or Gibbs free energy (ΔG), which can be derived from the Kd, is commonly used to quantify protein-protein interactions (Wang et al., 2004; Kastritis et al., 2011; Moal and Fernandez-Recio, 2012; Jankauskaitė et al., 2019).”
BackgroundMethoddbMPIKT: a database of kinetic and thermodynamic mutant protein interactions
Liu, Q., Chen, P., Wang, B., Zhang, J., & Li, J. (2018) · BMC Bioinformatics · doi:10.1186/s12859-018-2493-7 · Cited by 38
“0 [34], the description of mutation data in our database is more consistent with scientific research compared with SKEMPI2.”
ResultImplications of disease-related mutations at protein–protein interfaces
Xiong, D., Lee, D., Li, L., Zhao, Q., & Yu, H. (2022) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2021.11.012 · Cited by 38
Review of COVID-19 Antibody Therapies
Chen, J., Gao, K., Wang, R., Nguyen, D. D., & Wei, G. (2020) · Annual Review of Biophysics · doi:10.1146/annurev-biophys-062920-063711 · Cited by 38
“0 data set (35), which has 4,169 variants in 319 different complexes.”
Aligning protein generative models with experimental fitness via Direct Preference OptimizationPreprint
Widatalla, T., Rafailov, R., & Hie, B. L. (2024) · bioRxiv · doi:10.1101/2024.05.20.595026 · Cited by 61
“We evaluated scoring on this dataset the same as with SKEMPIv2 [22], however we reported the average correlations across each antibody-antigen complex as there were an ample number of variants per complex.”
BackgroundMethodInfluentialPPI-HotspotDB: Database of Protein–Protein Interaction Hot Spots
Chen, Y. C., Chen, Y., Wright, J. D., & Lim, C. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00025 · Cited by 39
Accurate prediction of antibody function and structure using bio-inspired antibody language model
Jing, H., Gao, Z., Xu, S. Y., Shen, T., Peng, Z., He, S., You, T., Ye, S., Lin, W. J., & Sun, S. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae245 · Cited by 41
“Moreover, given that different positions in antibodies exhibit varyingevolutionaryrates,itbecomescrucialforlanguagemodels to allocate more attention to learning the distribution of amino acids at those highly diverse positions.”
Artificial intelligence based methods for hot spot prediction
Ovek, D., Abali, Z., Zeylan, M. E., Keskin, Ö., Gürsoy, A., & Tunçbağ, N. (2021) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2021.11.003 · Cited by 40
Kim, D. N., McNaughton, A. D., & Kumar, N. (2024) · Bioengineering · doi:10.3390/bioengineering11020185 · Cited by 39
“The highly successful attention DL-based Binding-ddg-predictor [15] (Supplementary Note S2) redesigned the CDR to enhance Ab affinity (toward multiple virus variants) and was validated with SKEMPI (Structural database of Kinetics and Ener-getics of Mutant Protein Interactions) version 2 [51].”
MethodBaseline Model for Predicting Protein–Ligand Unbinding Kinetics through Machine Learning
Amangeldiuly, N., Karlov, D. S., & Fedorov, M. V. (2020) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00450 · Cited by 35
Jin, R., Ye, Q., Wang, J., Cao, Z., Jiang, D., Wang, T., Kang, Y., Xu, W., Hsieh, C., & Hou, T. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae304 · Cited by 43
“In the pursuit of rigorous computational affinity predictions for antigen–antibody complexes, we leveraged two well-established and extensively utilized databases: AB-Bind [62] and Skempi 2.0 [63].”
MethodInfluentialDocking-based identification of small-molecule binding sites at protein-protein interfaces
Rosell, M., & Fernández‐Recio, J. (2020) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2020.11.029 · Cited by 34
“There is experimental information on the energetic impact of mutations for a limited number of cases [35], but for large-scale applications a variety of bioinformatics approaches have been reported, from statistical analyses to molecular modeling and energetic calculations.”
Self-citationImplementing and Assessing an Alchemical Method for Calculating Protein–Protein Binding Free Energy
Patel, D. J., Patel, J. S., & Ytreberg, F. M. (2021) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.0c01045 · Cited by 33
Protein Function Analysis through Machine Learning
Avery, C., Patterson, J., Grear, T. J., Frater, T. D., & Jacobs, D. J. (2022) · Biomolecules · doi:10.3390/biom12091246 · Cited by 31
“One such database is SKEMPI, which lists ∆∆Gs in response to many mutations that can be used for ML training [426].”
BackgroundZhou, Z., Yin, Y., Han, H., Jia, Y., Koh, J. H., Kong, A. W.-K., & Mu, Y. (2024) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01850 · Cited by 30
Beyond sequence: Structure-based machine learning
Durairaj, J., de Ridder, D., & van Dijk, A. D. J. (2022) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2022.12.039 · Cited by 32
DG-Affinity: predicting antigen–antibody affinity with language models from sequences
Yuan, Y., Chen, Q., Mao, J., Li, G., & Pan, X. (2023) · BMC Bioinformatics · doi:10.1186/s12859-023-05562-z · Cited by 41
Insights into changes in binding affinity caused by disease mutations in protein-protein complexes
Jemimah, S., & Gromiha, M. M. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.103829 · Cited by 30
SPOTONE: Hot Spots on Protein Complexes with Extremely Randomized Trees via Sequence-Only Features
Preto, A. J., & Moreira, I. S. (2020) · International Journal of Molecular Sciences · doi:10.3390/ijms21197281 · Cited by 29
Heyne, M., Shirian, J., Cohen, I., Peleg, Y., Radisky, E. S., Papo, N., & Shifman, J. M. (2021) · Journal of the American Chemical Society · doi:10.1021/jacs.1c08707 · Cited by 30
Free energy perturbation calculations of mutation effects on SARS-CoV-2 RBD::ACE2 binding affinity
Sergeeva, A. P., Katsamba, P. S., Liao, J., Sampson, J. M., Bahna, F., Mannepalli, S., Morano, N. C., Shapiro, L., Friesner, R. A., & Honig, B. (2023) · Journal of Molecular Biology · doi:10.1016/j.jmb.2023.168187 · Cited by 27
“The mutations we used in our study are not a part of common ML training databases such as SKEMPI [77]; hence, our dataset for methods evaluation can be considered as “blind”.”
Luo, S., Su, Y., Wu, Z., Su, C., Peng, J., & Ma, J. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.02.28.530137 · Cited by 54
“The SKEMPI2 database (Jankauskait˙e et al., 2019) is used to train the models for ∆∆ G prediction described in Section 3.4.”
MethodInfluentialUsing protein language models for protein interaction hot spot prediction with limited data
Sargsyan, K., & Lim, C. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05737-2 · Cited by 24
“These PPI-hot spots were derived from two sources: (i) mutations in the ASEdb [24] and SKEMPI 2.0 [25] database that resulted in a reduction of protein binding free energy by ≥ 2 kcal/mol, and (ii) mutations in UniProtKB [26] that were manually curated to significantly impair/disrupt PPIs.”
MethodInfluentialValdés‐Tresanco, M. E., Tresanco, M. S. V., Moreno, E., & Valiente, P. A. (2023) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c07079 · Cited by 28
Deep learning in preclinical antibody drug discovery and development
Zhou, Y., Huang, Z., Li, W., Wei, J., Jiang, Q., Yang, W., & Huang, J. H. (2023) · Methods · doi:10.1016/j.ymeth.2023.07.003 · Cited by 26
Protein–Protein Interaction Methods and Protein Phase Separation
Savojardo, C., Martelli, P. L., & Casadio, R. (2020) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-011720-104428 · Cited by 27
Quantification of biases in predictions of protein–protein binding affinity changes upon mutations
Tsishyn, M., Pucci, F., & Rooman, M. J. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad491 · Cited by 40
“More precisely, we evaluated their predictions on a set of mutations with experimentally measured ∆∆ G b values taken from [25], and on high-throughput data on the binding between the human angiotensin-converting enzyme 2 (ACE2) and the receptor binding domain (RBD) of the SARS-CoV-2 spike protein…”
BackgroundMethodInfluentialPredicting antibody affinity changes upon mutations by combining multiple predictors
Kurumida, Y., Saitō, Y., & Kameda, T. (2020) · Scientific Reports · doi:10.1038/s41598-020-76369-8 · Cited by 23
Differential nuclear import sets the timing of protein access to the embryonic genome
Nguyen, T., Costa, E. J., Deibert, T., Reyes, J. F. M., Keber, F. C., Tomschik, M., Stadlmeier, M., Gupta, M., Kumar, C. K., Cruz, E. R., et al. (2022) · Nature Communications · doi:10.1038/s41467-022-33429-z · Cited by 29
Sampson, J. M., Cannon, D. A., Duan, J., Epstein, J. C. K., Sergeeva, A. P., Katsamba, P. S., Mannepalli, S. M., Bahna, F. A., Adihou, H., Guéret, S. M., et al. (2024) · Journal of Molecular Biology · doi:10.1016/j.jmb.2024.168640 · Cited by 24
Pennica, C., Hanna, G., Islam, S. A., Sternberg, M. J. E., & David, A. (2023) · Journal of Molecular Biology · doi:10.1016/j.jmb.2023.168060 · Cited by 25
“18 However, most of these in silico prediction tools have been trained on engineered protein variants deposited in databases, such as Skempi 19 and Protherm 20 and do not perform equally well when used on other datasets of variants.”
Metadata
- Authors
- Jankauskaitė, J., Jiménez-García, B., Dapkūnas, J., Fernández-Recio, J., & Moal, I. H.
- Affiliations
- Vilnius University (LT)
- Barcelona Supercomputing Center (BSC), Barcelona, Spain
- European Bioinformatics Institute (GB)
- Corresponding author
- Moal, Iain H
- Venue
- Bioinformatics
- Publisher
- Oxford University Press (OUP)
- Published
- 2018-07-18
- Volume
- 35
- Issue
- 3
- Pages
- 462-469
- ISSN
- 1367-4803 (ISSN-L)
- 1367-4811
- PMC
- PMC6361233
- OpenAlex
- W2953103783
- Cited by
- 389
- References
- 80
- Citations by year
- 2026: 63 · 2025: 75 · 2024: 61 · 2023: 50 · 2022: 46 · 2021: 37 · 2020: 33 · 2019: 18 · 2018: 5
- FWCI
- 8.26
- Type
- journal article
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- Bioinformatics (publishedVersion, cc-by)
- bioRxiv (Cold Spring Harbor Laboratory) (acceptedVersion, cc-by-nc-nd)
- Europe PMC (PubMed Central) (publishedVersion, cc-by)
- PubMed Central (publishedVersion, cc-by)
- PubMed (publishedVersion)
- LA Referencia (Red Federada de Repositorios Institucionales de Publicaciones Científicas) (acceptedVersion, cc-by-nc-nd)
- UPCommons institutional repository (Universitat Politècnica de Catalunya) (acceptedVersion, cc-by-nc-nd)
- DIGITAL.CSIC (Spanish National Research Council (CSIC)) (submittedVersion)
- RIUR (Universidad de La Rioja) (submittedVersion, other-oa)
- RECERCAT (Consorci de Serveis Universitaris de Catalunya) (submittedVersion, cc-by-nc-nd)
- Funders
- European Molecular Biology Laboratory
- Biotechnology and Biological Sciences Research Council
- Future Leader Fellowship (BB/N011600/1)
- Spanish Ministry of Economy and Competitiveness
- MINECO (BIO2016-79930-R)
- Interreg POCTEFA (EFA086/15)
- European Commission (676566)
- Topics
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Protein Structure and Dynamics
- Physical Sciences › Chemistry › Physical and Theoretical Chemistry › thermodynamics and calorimetric analyses
- Life Sciences › Biochemistry, Genetics and Molecular Biology › Molecular Biology › Bioinformatics and Genomic Networks
- Keywords
- protein-protein interaction, point mutations, binding kinetics, enthalpy and entropy changes, binding thermodynamics, sequence-structure-function relationships, protein engineering
- MeSH terms
- Kinetics, Mutation, Protein Binding, Thermodynamics, Databases, Protein
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.