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
Items 101–200 of 382
Yu, G., Zhao, Q., Bi, X., & Wang, J. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae232 · Cited by 28
“The comparison results on the SKEMPI2 dataset are shown in Supplementary Note S2.”
MethodInfluentialClark, T., Subramanian, V., Jayaraman, A., Fitzpatrick, E., Gopal, R., Pentakota, N., Rurak, T. T., Anand, S., Viglione, A., Raman, R., et al. (2023) · Communications Chemistry · doi:10.1038/s42004-023-01037-7 · Cited by 28
AlphaFold3, a secret sauce for predicting mutational effects on protein-protein interactionsPreprint
Lu, W., Zhang, J., Rao, J., Zhang, Z., & Zheng, S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.25.595871 · Cited by 35
“A commonly used dataset for evaluating methods that predict mutation effects is SKEMPI [33], which manually curates a list of crystallized protein complexes and their mutants with experimentally measured changes in binding affinity, denoted as ∆∆ G values, gathered through literature searches.”
MethodMAVISp: A Modular Structure-Based Framework for Protein Variant Effects
Arnaudi, M., Utichi, M., Degn, K., Tiberti, M., Beltrame, L., Krzesińska, K., Sánchez-Izquierdo Besora, P., Kiachaki, E., Scrima, S., Bauer, L., et al. (2022) · doi:10.1101/2022.10.22.513328 · Cited by 20
Mohseni Behbahani, Y., Laine, E., & Carbone, A. (2023) · Bioinformatics · doi:10.1093/bioinformatics/btad231 · Cited by 23
“Significant efforts have been expended over the past decade to produce, collect and curate binding affinity measurements for wild-type and mutated complexes (Table S 1) [31, 41, 63, 32, 72, 47].”
BackgroundMethodHarnessing computational technologies to facilitate antibody–drug conjugate development
Croitoru, A., Orr, A. A., & MacKerell, A. D. (2025) · Nature Chemical Biology · doi:10.1038/s41589-025-01950-z · Cited by 24
Assessment of software methods for estimating protein-protein relative binding affinities
Gonzalez, T. R., Martin, K., Barnes, J. E., Patel, J. S., & Ytreberg, F. M. (2020) · PLoS ONE · doi:10.1371/journal.pone.0240573 · Cited by 25
Decoding Protein-protein Interactions: An Overview
Slater, O., Miller, B., & Kontoyianni, M. (2020) · Current Topics in Medicinal Chemistry · doi:10.2174/1568026620666200226105312 · Cited by 23
Meseguer, A., Dominguez, L., Bota, P. M., Aguirre‐Plans, J., Bonet, J., Fernández‐Fuentes, N., & Oliva, B. (2020) · Protein Science · doi:10.1002/pro.3930 · Cited by 22
“37 This is a self-consistent test because conditions for maximum correlation are originally obtained with SKEMPI data, but it is not appropriate for a validation of the approach.”
MethodAnalysis of single amino acid variations in singlet hot spots of protein–protein interfaces
Özdemir, E. S., Gürsoy, A., & Keskin, Ö. (2018) · Bioinformatics · doi:10.1093/bioinformatics/bty569 · Cited by 22
Jiang, Y., Quan, L., Li, K., Li, Y., Zhou, Y., Wu, T., & Lyu, Q. (2023) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2022.3233627 · Cited by 22
“Therefore, these data differed from the SKEMPI data [11], [17], which are direct DDG measurements.”
BackgroundMethodNikam, R., Yugandhar, K., & Gromiha, M. M. (2023) · Biochimica et Biophysica Acta (BBA) - Proteins and Proteomics · doi:10.1016/j.bbapap.2023.140948 · Cited by 21
Structural coverage of the human interactome
Kosoglu, K., Aydin, Z., Tuncbag, N., Gursoy, A., & Keskin, O. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad496 · Cited by 21
Shringari, S. R., Giannakoulias, S. G., Ferrie, J. J., & Petersson, E. J. (2020) · Chemical Communications · doi:10.1039/d0cc01959c · Cited by 23
Riahi, S., Lee, J., Wei, S., Cost, R., Masiero, A., Prades, C., Olfati-Saber, R., Wendt, M., Park, A., Qiu, Y., et al. (2021) · Antibody Therapeutics · doi:10.1093/abt/tbab011 · Cited by 19
Praticò, A. D., Falsaperla, R., Comella, M., Belfiore, G., Polizzi, A., & Ruggieri, M. (2023) · Frontiers in Pediatrics · doi:10.3389/fped.2023.1101026 · Cited by 19
“Such results, however, do not provide accurate information on potential gain, loss, or changes of function, thus the “mutated” protein was further tested using the ProAffiMuSeq tool (11, 13), a webserver that calculates the binding free energy change (ΔΔG in kcal/mol) for mutant protein-to-protein complexes.”
MethodLiu, X., Feng, H., Wu, J., & Xia, K. (2022) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.2c00580 · Cited by 23
Pandey, P., Panday, S. K., Rimal, P., Ancona, N., & Alexov, E. (2023) · International Journal of Molecular Sciences · doi:10.3390/ijms241512073 · Cited by 21
“Similarly, SKEMPI (Structural Kinetics and Energetics of Mutant Protein Interactions) is a database of experimentally measured binding free energy changes [18,19].”
BackgroundYue, Y., Li, S., Wang, L., Liu, H., Tong, H. H. Y., & He, S. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad310 · Cited by 23
“The change in binding affinity caused by AA mutations, or G, represents the difference in binding affinity between mutant-type (MT) and wild-type (WT) protein complexes [10].”
BackgroundRecent progress and future challenges in structure-based protein-protein interaction prediction
Yuan, R., Zhang, J., Zhou, J., & Cong, Q. (2025) · Molecular Therapy · doi:10.1016/j.ymthe.2025.04.003 · Cited by 31
“Commonly used databases to derive training datasets or to evaluate model performances for interface mutation effect predictors include ASEdb, 257 SKEMPI, 162,258 and Ab-Bind, 259 but they typically only contain several thousand data points.”
Protein Language Models: Applications and Perspectives
Leclercq, M., & Droit, A. (2025) · Journal of Proteome Research · doi:10.1021/acs.jproteome.5c00506 · Cited by 40
Delaunay, M., & Ha‐Duong, T. (2021) · Methods in molecular biology · doi:10.1007/978-1-0716-1855-4_11 · Cited by 22
Are transient protein-protein interactions more dispensable?
Ghadie, M. A., & Xia, Y. (2022) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1010013 · Cited by 19
“An independent experiment performed by our recent study [20] reported Pearson correlation coefficients of 0.5 and 0.42 for ΔΔ G values predicted by FoldX on co-crystal structures and homology models, respectively, when benchmarked against experimental data in the SKEMPI database [88].”
InfluentialOn the Upper Bounds of the Real-Valued Predictions
Benevenuta, S., & Fariselli, P. (2019) · Bioinformatics and Biology Insights · doi:10.1177/1177932219871263 · Cited by 18
“We computed the empirical R2 for each run using the definition reported in equation (5).”
BackgroundMethodPIIMS Server: A Web Server for Mutation Hotspot Scanning at the Protein–Protein Interface
Wu, F., Yang, J., Mei, L., Wang, F., Hao, G., & Yang, G. (2021) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.0c00966 · Cited by 17
Brysbaert, G., & Lensink, M. F. (2021) · Frontiers in Bioinformatics · doi:10.3389/fbinf.2021.684970 · Cited by 20
“For this purpose, we used the SKEMPI 2 database, which is a benchmark set of changes in protein – protein binding energy, in kinetics, and in thermodynamics upon mutation (Jankauskait ˙ e et al., 2019).”
BackgroundMethodInfluentialHan, J., Liu, T., Zhang, X., Yang, Y., Shi, Y., Li, J., Ma, M., Zhu, W., Gong, L., & Xu, Z. (2022) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2022.106212 · Cited by 18
“The datasets of D3AI-Spike are from two sources, i.e., RBD mutational scanning and SKEMPI2 (Structural database of Kinetics and En-ergetics of Mutant Protein Interactions) [28].”
MethodEstimating dispensable content in the human interactome
Ghadie, M. A., & Xia, Y. (2019) · Nature Communications · doi:10.1038/s41467-019-11180-2 · Cited by 20
PPB-Affinity: Protein-Protein Binding Affinity dataset for AI-based protein drug discovery
Liu, H., Chen, P., Zhai, X., Huo, K.-G., Zhou, S., Han, L., & Fan, G. (2024) · Scientific Data · doi:10.1038/s41597-024-03997-4 · Cited by 42
Repertoire-scale measures of antigen binding
Arora, R., & Arnaout, R. (2022) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2203505119 · Cited by 17
“The experimental measurements used to train our model consisted of 1,328 systematic comparisons between pairs of Kds (11) measured as ΔΔG = RT ln(Kd1/Kd2).”
BackgroundMethodProtein structure-based evaluation of missense variants: Resources, challenges and future directions
David, A., & Sternberg, M. J. E. (2023) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2023.102600 · Cited by 19
Li, M., Shi, Y., Hu, S., Hu, S., Guo, P., Wan, W., Zhang, L. Y., Pan, S., Li, J., Sun, L., et al. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae579 · Cited by 23
“Since SAbDab (Dunbar et al. 2014) is sourced from Kastrictis’ affinity benchmarks (Kastritis et al. 2011, Vreven et al. 2015), and SKEMPI 2.0 (Jankauskaite et al. 2019) is an extension of SKEMPI (Moal and Fern � andez-Recio 2012), we decided to use SAbDab as the dataset for predicting natural…”
InfluentialMacGowan, S. A., & Barton, G. J. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.05.03.074781 · Cited by 14
“It is conceivable that mCSM-PPI2 could be biased towards negative ΔΔG predictions because the training datasets are skewed towards these observations 12, 23 .”
BackgroundATOM3D: Tasks On Molecules in Three DimensionsPreprint
Townshend, R. J. L., Vögele, M., Suriana, P., Derry, A., Powers, A. S., Laloudakis, Y. D., Balachandar, S., Jing, B., Anderson, B., Eismann, S., et al. (2020) · arXiv (Cornell University) · doi:10.13140/rg.2.2.30339.73765 · Cited by 159
Estimating Absolute Protein–Protein Binding Free Energies by a Super Learner Model
Chaves, E. J. F., Sartori, J., Santos, W. M., da Cruz, C. H. B., Mhrous, E. N., Nacimento-Filho, M. F., Ferraz, M. V. F., & Lins, R. D. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01641 · Cited by 18
Gurusinghe, S. N. S., Wu, Y., DeGrado, W. F., & Shifman, J. M. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf270 · Cited by 16
“Until now, researchers have employed the SKEMPI database (Jankauskaite et al. 2019) as a benchmark to assess the effectiveness of various computational methodologies on ΔΔ G bind prediction (Li et al. 2016; Xiong et al. 2017).”
Dhusia, K., Su, Z., & Wu, Y. (2021) · Molecular Immunology · doi:10.1016/j.molimm.2021.07.020 · Cited by 19
MPAD: A Database for Binding Affinity of Membrane Protein–protein Complexes and their Mutants
Ridha, F., Kulandaisamy, A., & Gromiha, M. M. (2022) · Journal of Molecular Biology · doi:10.1016/j.jmb.2022.167870 · Cited by 15
Shen-Gunther, J., Cai, H., & Wang, Y. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26041428 · Cited by 14
“Studies on antigen mutations and their effects on antibody binding, utilizing resources like the SKEMPI 2.0 (https://life.bsc.es/pid/skempi2/ (accessed on 1 February 2025)) database, have provided significant insights [61,62].”
InfluentialBielska, W., Jaszczyszyn, I., Dudzic, P., Janusz, B., Chomicz, D., Wrobel, S., Greiff, V., Feehan, R., Adolf‐Bryfogle, J., & Krawczyk, K. (2025) · Frontiers in Immunology · doi:10.3389/fimmu.2025.1571371 · Cited by 21
Using machine‐learning‐driven approaches to boost hot‐spot's knowledge
Rosário‐Ferreira, N., Bonvin, A. M. J. J., & Moreira, I. S. (2022) · Wiley Interdisciplinary Reviews Computational Molecular Science · doi:10.1002/wcms.1602 · Cited by 13
Liu, Z., Qian, W., Cai, W., Song, W., Wang, W., Maharjan, D. T., Cheng, W., Chen, J., Xu, F., Wang, H., et al. (2023) · Research · doi:10.34133/research.0219 · Cited by 21
Zheng, F., Jiang, X., Wen, Y., Yang, Y., & Li, M. (2024) · Computational and Structural Biotechnology Journal · doi:10.1016/j.csbj.2023.12.018 · Cited by 14
“The training dataset was compiled from four databases/datasets: Protein-Protein Binding Affinity Benchmark version 2 (PPBABv2) [48], SKEMPI 2.0 [49], PROXiMATE [50], and PDBbind version 2020 [51].”
MethodInfluentialJin, W., Chen, X., Vetticaden, A., Sarzikova, S., Raychowdhury, R., Uhler, C., & Hacohen, N. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.12.10.570461 · Cited by 26
“We validate our claim using SKEMPI 2.0 [14], a �� G prediction.”
MethodInfluentialLearning the language of protein-protein interactions
(2026) · doi:10.1038/s41467-025-67971-3 · Cited by 26
“In oncogenic PPI (oncoPPI) analysis, MINT effectively distinguished between pathogenic and non-pathogenic interactions, with its predictions matching 23 of 24 previously experimentally validated mutational effects.”
InfluentialProBAN : Neural network algorithm for predicting binding affinity in protein–protein complexes
Bogdanova, E. A., & Novoseletsky, V. N. (2024) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26700 · Cited by 18
“26 This database reports changes in binding affinity for 7085 mutations out of 348 protein – protein interactions for which the structure of the complex has been determined.”
InfluentialD’Arrigo, G., Kokh, D. B., Nunes‐Alves, A., et al. (2024) · Communications Biology · doi:10.1038/s42003-024-06880-5 · Cited by 13
Li, J., Liao, L., Zhang, C., Huang, K., Zhang, P., Zhang, J. Z. H., Wan, X., & Zhang, H. (2024) · Briefings in Bioinformatics · doi:10.1093/bib/bbae488 · Cited by 15
“This will involve training models using datasets such as the AlphaSeq Antibody Dataset [22, 23] and SKEMPI2 [20].”
MethodWee, J., & Wei, G.-W. (2024) · PubMed · doi:10.48550/arxiv.2406.03979 · Cited by 13
“Here, we use the accessible AlphaFold Server of AF3 to predict the protein-protein complexes from SKEMPI 2.0 database [21].”
MethodInfluentialJanusz, B., Chomicz, D., Demharter, S., Arts, M., de Kanter, J. K., Wilke, Y., Britze, H., Wrobel, S., Gawłowski, T., Dudzic, P., et al. (2025) · mAbs · doi:10.1080/19420862.2025.2567319 · Cited by 15
MuToN Quantifies Binding Affinity Changes upon Protein Mutations by Geometric Deep Learning
Li, P., & Liu, Z. (2024) · Advanced Science · doi:10.1002/advs.202402918 · Cited by 14
NanoBinder: a machine learning assisted nanobody binding prediction tool using Rosetta energy scores
Shrestha, P., Talwar, C. S., Kandel, J., Park, K., Chong, K. T., Woo, E., & Tayara, H. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-01040-1 · Cited by 15
“Notably, NB3_31 and NB3_32, with known mutations, were obtained from the SKEMPI database [42], where the specified mutations were introduced using PyMOL.”
Immunological Diversity with SimilarityPreprint
Arora, R., Burke, H. M., & Arnaout, R. (2018) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/483131 · Cited by 10
Wang, B., Su, Z., & Wu, Y. (2021) · Genomics Proteomics & Bioinformatics · doi:10.1016/j.gpb.2021.03.004 · Cited by 12
“Finally, it is worth mentioning that very recently, the SKEMPI data-base has been upgraded to its 2.0 version [41].”
BackgroundInfluentialRana, M. M., & Nguyen, D. D. (2023) · The Journal of Physical Chemistry Letters · doi:10.1021/acs.jpclett.3c02679 · Cited by 12
Mutational biases favor complexity increases in protein interaction networks after gene duplication
Cisneros, A. F., Nielly‐Thibault, L., Mallik, S., Levy, E. D., & Landry, C. R. (2024) · Molecular Systems Biology · doi:10.1038/s44320-024-00030-z · Cited by 11
Rapid response to fast viral evolution using AlphaFold 3-assisted topological deep learning
Wee, J., & Wei, G. (2025) · Virus Evolution · doi:10.1093/ve/veaf026 · Cited by 17
“Apart from experimental DMS data, TDL or TopNetmAb also employs the SKEMPI 2.0 database Jankauskait ̇ e et al. (2019), an experimental database for PPI BFE changes upon mutation.”
InfluentialPXDesign: Fast, Modular, and Accurate De Novo Design of Protein BindersPreprint
Protenix Team, Ren, M., Sun, J., Guan, J., Liu, C., Gong, C., Wang, Y. X., Wang, L., Cai, Q., Ma, W., et al. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.08.15.670450 · Cited by 34
“• SKEMPI subset [25]: point mutations with measured ddG, curated to retain high-confidence AF3 structures by Lu et al. [34].”
Persistent Tor-algebra for protein–protein interaction analysis
Liu, X., Feng, H., Lü, Z., & Xia, K. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad046 · Cited by 13
Reliable prediction of protein–protein binding affinity changes upon mutations with Pythia-PPI
Tao, F., Sun, J., Gao, P., Gao, G. F., & Wu, B. (2025) · National Science Review · doi:10.1093/nsr/nwaf231 · Cited by 10
Lan, T., Su, S., Ping, P., Hutvágner, G., Liu, T., Pan, Y. F., & Li, J. (2024) · Nature Machine Intelligence · doi:10.1038/s42256-024-00803-z · Cited by 14
Zhang, Y., Dong, M., Deng, J., Wu, J., Zhao, Q., Gao, X., & Xiong, D. (2024) · Communications Biology · doi:10.1038/s42003-024-07066-9 · Cited by 10
Unveiling the ghost: machine learning’s impact on the landscape of virology
Bowyer, S., Allen, D. J., & Furnham, N. (2025) · Journal of General Virology · doi:10.1099/jgv.0.002067 · Cited by 13
Zhang, R., Wu, H., Liu, C., Yang, Q., Xiu, Y., Li, K., Chen, N., Wang, Y., Wang, Y., Gao, X., et al. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf367 · Cited by 30
“In addition to these sequence-based classification tasks, we also evaluate the performance of PepLand on binding affinity prediction for linear peptides using data from the SKEMPI 2.0 database [33], as detailed in Case Study 3 in the Supplementary Materials.”
InfluentialSearching similar local 3D micro-environments in protein structure databases with MicroMiner
Sieg, J., & Rarey, M. (2023) · Briefings in Bioinformatics · doi:10.1093/bib/bbad357 · Cited by 9
Analysis of conformational stability of interacting residues in protein binding interfaces
Chauhan, V. M., & Pantazes, R. J. (2022) · Protein Engineering Design and Selection · doi:10.1093/protein/gzad016 · Cited by 10
Growing ecosystem of deep learning methods for modeling protein–protein interactions
Rogers, J. R., Nikolényi, G., & AlQuraishi, M. (2023) · Protein Engineering Design and Selection · doi:10.1093/protein/gzad023 · Cited by 15
Mathematical artificial intelligence design of mutation-proof COVID-19 monoclonal antibodies
Chen, J., & Wei, G. (2022) · Communications in Information and Systems · doi:10.4310/cis.2022.v22.n3.a3 · Cited by 9
ppdx : Automated modeling of protein–protein interaction descriptors for use with machine learning
Conti, S., Ovchinnikov, V., & Karplus, M. (2022) · Journal of Computational Chemistry · doi:10.1002/jcc.26974 · Cited by 10
Ozono, H., Mimoto, K., & Ishikawa, T. (2022) · The Journal of Physical Chemistry B · doi:10.1021/acs.jpcb.2c05033 · Cited by 9
Lombardi, G., & Carbone, A. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.08.24.609515 · Cited by 11
“0 dataset (Jankauskait et al. , 2018) has significantly enhanced the precision and efficiency of methods like iSEE (Geng et al. , 2019b), mCSM-PPI2 (Rodrigues et al. , 2019), BindProfX (Xiong et al. , 2017), MuPIPR (Zhou et al. , 2020), MutaBind2 (Zhang et al. , 2020), GeoPPI (Liu et al. , 2021),…”
BackgroundMethodYu, G., Bi, X., Ma, T., Li, Y., & Wang, J. (2025) · Bioinformatics · doi:10.1093/bioinformatics/btaf228 · Cited by 12
Rimal, P., Panday, S. K., Wang, X., Peng, Y., & Alexov, E. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae544 · Cited by 10
“The existing machine learning methods for predicting ΔΔ G due to mutations in protein–protein complexes were trained on the SKEMPI (Jankauskait _ e et al. 2019) database, which is composed of various kinds of protein complexes.”
Private Antibody Repertoires Are PublicPreprint
Arora, R., & Arnaout, R. (2020) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2020.06.18.159699 · Cited by 6
Preventing future zoonosis: SARS-CoV-2 mutations enhance human–animal cross-transmission
Wee, J., Chen, J., & Wei, G. (2024) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2024.109101 · Cited by 7
InSty: A ProDy Module for Evaluating Protein Interactions and Stability
Mikulska‐Ruminska, K., Krieger, J., Banerjee, A., Cao, X., Wu, G. D., Bogetti, A. T., Zhang, F., Simmerling, C. L., Coutsias, E. A., & Bahar, İ. (2025) · Journal of Molecular Biology · doi:10.1016/j.jmb.2025.169009 · Cited by 6
Artificial intelligence in therapeutic antibody design: Advances and future prospects
Park, S., Jeong, W., Kim, Y., Lee, C., & Seok, C. (2025) · Current Opinion in Structural Biology · doi:10.1016/j.sbi.2025.103084 · Cited by 10
A Survey of Deep Learning Methods and Tools for Protein Binding Site Prediction
Rohulia, A., Wang, Y., & Cheng, J. (2025) · Methods in molecular biology · doi:10.1007/978-1-0716-4662-5_5 · Cited by 7
Koenekoop, L., van de Brug, N., Jespers, W., Åqvist, J., & Gutiérrez‐de‐Terán, H. (2025) · Communications Chemistry · doi:10.1038/s42004-025-01771-0 · Cited by 8
“To help advancing a detailed understanding of PPIs, the SKEMPI database collects binding free energy changes upon mutation for structurally resolved protein – protein interactions 48 .”
Biomolecular Topology: Modelling and Analysis
Liu, J., Xia, K., Wu, J., Yau, S. S. ‐., & Wei, G. (2022) · Acta Mathematica Sinica English Series · doi:10.1007/s10114-022-2326-5 · Cited by 13
“…(SKEMPI) [147], a database of binding affinity change upon mutations (DACUM) [79], antibody-bind database (AB-Bind) [177], protein-protein complex mutation thermodynamics (PROXiMATE) [105], kinetic and thermodynamic database of mutant protein interactions (dbMPIKT) [126], and SKEMPI 2.0 [103].”
BackgroundInfluentialMulti-level bioinformatics resources support drug target discovery of protein–protein interactions
Liu, J., Zhang, X., Huang, Y., Hao, G., & Yang, G. (2024) · Drug Discovery Today · doi:10.1016/j.drudis.2024.103979 · Cited by 8
Amengual-Rigo, P., Fernández‐Recio, J., & Guallar, V. (2020) · Bioinformatics · doi:10.1093/bioinformatics/btaa708 · Cited by 8
Self-citationAbbasi, W. A., Abbas, S. A., & Andleeb, S. (2021) · Journal of Bioinformatics and Computational Biology · doi:10.1142/s0219720021500153 · Cited by 9
“This dataset contains the experimentally determined ΔΔG(kcal/mol) values for both wild type and mutated protein complexes (Jankauskaitė et al., 2019; Moal and Fernández-Recio, 2012).”
BackgroundUsing Coarse-Grained Simulations to Characterize the Mechanisms of Protein–Protein Association
Dhusia, K., Su, Z.-Q., & Wu, Y. (2020) · Biomolecules · doi:10.3390/biom10071056 · Cited by 8
“0, includes data of 345 wild-type protein complexes and their 7085 associated mutants [64].”
BackgroundDecoding the effects of mutation on protein interactions using machine learning
Wang, X., Li, A., Zhao, Y., & Peng, Y. (2025) · Biophysics Reviews · doi:10.1063/5.0249920 · Cited by 8
Benchmarking inverse folding models for antibody CDR sequence design
Li, Y., Lang, Y., Xu, C., Zhou, Y., Pang, Z., & Greisen, P. J. (2025) · PLoS ONE · doi:10.1371/journal.pone.0324566 · Cited by 11
Leverton, L., Bains, A. K., Isa, I., Ricard‐Blum, S., & Naba, A. (2025) · FEBS Journal · doi:10.1111/febs.70344 · Cited by 5
“…space. interacting domains (3did, [57]), Protein – Protein Inter-actions Domain Miner (PPD, [58]), the BioPlex inter-actome [59], the Structural Database of Kinetics and Energetics of Mutant Protein Interactions (SKEMPI, [60]), and the Protein Common Interfaces Database (ProtCID, [61]).”
Protein foundation models: a comprehensive survey
Xu, H., Li, L., Pan, S., Cheng, P., Wang, Y., Rong, Z., Feng, L., Huang, X., Wang, S., & Shu, W. (2026) · Science China Life Sciences · doi:10.1007/s11427-025-3147-2 · Cited by 10
Li, Z., Chen, X., Wen, H., ZHANG, R. Q., Li, M., Zhang, X., Yin, H., Yang, Q., Lam, K.-Y., Lió, P., et al. (2026) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.5c02081 · Cited by 13
Nikam, R., Jemimah, S., & Gromiha, M. M. (2024) · Bioinformatics · doi:10.1093/bioinformatics/btae309 · Cited by 8
“It includes 19 mutations from NM dataset for interleukin4-receptor complex (Benedix et al. 2009), S487 dataset with 487 mutations in 56 protein complexes (Jankauskaite et al. 2019) and 33 mutations in MDM2-p53 complex (Geng et al. 2019).”
MethodSearching for a mechanistic description of pairwise epistasis in protein systems
Barnes, J. E., Miller, C. R., & Ytreberg, F. M. (2022) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26328 · Cited by 6
Zeng, X., Wang, T., Kang, Y., Bai, G., & Ma, B. (2023) · Antibodies · doi:10.3390/antib12030058 · Cited by 8
“, both curated antibody–antigen complexes with single-site and multi-site mutations and corresponding This model is trained on SKEMPI [27] Antibody–Bind (AB-Bind) [28] datasets, both curated antibody–antigen complexes with single-site and multi-site mutations and corresponding free energy change values ( ∆∆ G). free e…”
MethodGonzález, J. E. H., & de Araújo, A. S. (2023) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.3c00972 · Cited by 7
Developing similarity matrices for antibody-protein binding interactions
Islam, S., & Pantazes, R. J. (2023) · PLoS ONE · doi:10.1371/journal.pone.0293606 · Cited by 7
Cross-Gate MLP with Protein Complex Invariant Embedding Is a One-Shot Antibody Designer
Tan, C., Gao, Z., Wu, L., Xia, J., Zheng, J., Yang, X., Liu, Y., Hu, B., & Li, S. Z. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i14.29445 · Cited by 21
Wu, R., Prabhu, R., Ozkan, A., & Sitharam, M. (2020) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1008357 · Cited by 10
“Besides a planned comparison of our interface-scale crucial interaction prediction method with a host of prevailing hotspot PPI prediction methods [26] on the SKEMPI database [43], there are several observations we made during the development of the method that may lead to future work.”
MethodImprove hot region prediction by analyzing different machine learning algorithms
Hu, J., Zhou, L., Li, B., Zhang, X., & Chen, N. (2021) · BMC Bioinformatics · doi:10.1186/s12859-021-04420-0 · Cited by 7
“0 [15, 16].”
Mutations strengthened SARS-CoV-2 infectivityPreprint
Chen, J., Wang, R., Wang, M., et al. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.14669 · Cited by 6
“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].”
MethodClark, T., Subramanian, V., Jayaraman, A., Fitzpatrick, E. G., Gopal, R., Pentakota, N., Rurak, T. T., Anand, S., Viglione, A., Raman, R., et al. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.02.543458 · Cited by 6
Accurate Prediction of Antibody Function and Structure Using Bio-Inspired Antibody Language ModelPreprint
Jing, H., Gao, Z., Xu, S. Y., Shen, T., Peng, Z., He, S., You, T., Ye, S., Lin, W., & Sun, S. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.08.30.555473 · Cited by 6
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.