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 201–300 of 382
Sidechain conditioning and modeling for full-atom protein sequence design with FAMPNNPreprint
Shuai, R. W., Widatalla, T., Huang, P., & Hie, B. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.02.13.637498 · Cited by 11
Bi, X., Ma, W., Jiang, H., Lu, W., Wei, Z., & Zhang, S. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3599927 · Cited by 10
“In this study, we collected a large number of ∆∆ G samples from the SKEMPI database [48] to construct a ∆∆ G dataset, namely SKEMPI , which is a regression dataset.”
Probing the dark energy in the functional protein universe
Galpern, E. A., Bueno, C., Sanchez, I. E., Wolynes, P. G., & Ferreiro, D. U. (2026) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.2531111123 · Cited by 12
“We can extend this same methodology to a set of Protein-Protein interacting partners for which experimental values of have been annotated in the Skempi database [53] (see Methods).”
A flaw in using pretrained protein language models in protein–protein interaction inference models
Szymborski, J., & Emad, A. (2026) · Nature Machine Intelligence · doi:10.1038/s42256-025-01176-7 · Cited by 19
“https://doi.org/10.1038/s42256-025-01176-7 Using binding affinity data of mutants and their wild types from the SKEMPI 2.0 database 29 , we calculated the Spearman correlation coefficient between Δ ̂ y and ΔΔ G for both pLM-based and non-pLM-based methods (Fig.”
InfluentialArtificial intelligence-enabled multi-scale virtual cell: perspective, challenges, and opportunities
Jiang, H., Huang, X., Bi, X., Ma, W., Ni, H., Wei, Z., Sun, P., Zhang, H., & Zhang, S. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag104 · Cited by 11
“SKEMPI 2.0 focuses on the impact of mutations on protein–protein interactions (PPIs), containing > 6000 experimental data points on the effects of mutations on PPI binding affinity [62].”
InfluentialThe physical logic of protein machines
McBride, J. M., & Tlusty, T. (2024) · Journal of Statistical Mechanics Theory and Experiment · doi:10.1088/1742-5468/ad1be7 · Cited by 6
PPI-hotspotID for detecting protein–protein interaction hot spots from the free protein structure
Chen, Y. C., Sargsyan, K., Wright, J. D., Chen, Y., Huang, Y., & Lim, C. (2024) · eLife · doi:10.7554/elife.96643 · Cited by 10
“…spot prediction methods have mostly been trained, validated, and tested on data from the Alanine Scanning Energetics database (ASEdb) ( Thorn and Bogan, 2001 ) and/or the Structural Kinetic and Energetic database of Mutant Protein Interactions (SKEMPI) 2.0 database ( Jankauskaite et al., 2019 ).”
InfluentialProBID-Net: a deep learning model for protein–protein binding interface design
Chen, Z., Ji, M., Qian, J., Zhang, Z., Zhang, X., Gao, H., Wang, H., Wang, R., & Qi, Y. (2024) · Chemical Science · doi:10.1039/d4sc02233e · Cited by 8
Zhang, C., Sun, Y., & Hu, P. (2025) · Journal of Cheminformatics · doi:10.1186/s13321-025-00979-5 · Cited by 5
“As illustrated in Table 2, the model (called gnn_PPI) could still exhibit higher correlation coefficients than benchmarks on both the S2648 [17] and S3421 datasets, as well as lower RMSE on the S3421 and S4169 [18] datasets.”
InfluentialWells, N. G. M., & Smith, C. A. (2023) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26477 · Cited by 6
Amino acid substitutions in human growth hormone affect secondary structure and receptor binding
Rajkovic, A., Sandesh Kanchugal, P., Abdurakhmanov, E., Howard, R. J., Wärmländer, S. K. T. S., Erwin, J., Barrera-Saldaña, H. A., Gräslund, A., Danielson, U. H., & Flores, S. C. (2023) · PLoS ONE · doi:10.1371/journal.pone.0282741 · Cited by 5
“In [8], Dataset C, of 11 SKEMPI2 [22] mutations with ΔΔGexperimental < -0.”
BackgroundInfluentialPrediction of Protein–Protein Binding Affinities from Unbound Protein Structures
Meseguer, A., Bota, P. M., Fernández‐Fuentes, N., & Oliva, B. (2021) · Methods in molecular biology · doi:10.1007/978-1-0716-1767-0_16 · Cited by 5
Measures of epitope binding degeneracy from T cell receptor repertoiresPreprint
Mayer, A., & Callan, C. G. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.07.25.501373 · Cited by 5
Co-translational assembly promotes functional diversification of paralogous proteinsPreprint
Mallik, S., Cisneros, A. F., Landry, C. R., & Levy, E. D. (2025) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2025.01.22.634331 · Cited by 6
PPAP: A Protein–protein Affinity Predictor Incorporating Interfacial Contact-Aware Attention
Qian, J., Yang, L., Duan, Z., Wang, R., & Qi, Y. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01390 · Cited by 6
Li, C.-F., Yan, Z., Ge, F., Yu, X., Zhang, J., Zhang, M., & Yu, D. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00478 · Cited by 5
Autonome Entdeckung in den chemischen Wissenschaften, Teil II: Ausblick
Coley, C. W., Eyke, N. S., & Jensen, K. F. (2020) · Angewandte Chemie · doi:10.1002/ange.201909989 · Cited by 4
Densest subgraph-based methods for protein-protein interaction hot spot prediction
Li, R., Lee, J.-Y., Yang, J., & Akutsu, T. (2022) · BMC Bioinformatics · doi:10.1186/s12859-022-04996-1 · Cited by 4
“Another widely used data-base is the SKEMPI database [6], which is new and continually updated (public access to ASEdb and BID is no longer supported).”
MethodInfluentialBiswas, G., Mukherjee, D., Dutta, N., Ghosh, P., & Basu, S. (2023) · Journal of Molecular Modeling · doi:10.1007/s00894-023-05626-0 · Cited by 4
Wang, Y., Shi, X., & Zhou, H. (2023) · IEEE Industrial Electronics Society Annual On-Line Conference (ONCON) · doi:10.1109/oncon60463.2023.10430682 · Cited by 4
“Since the SKEMPIv2 [10] dataset does not provide the ΔΔG value, we must convert the affinity of both the wild-type form and mutant form to obtain their respective ΔG values.”
MethodMachine Learning Optimization Approach to Design Multi-Epitope Marburg Vaccine Construct
Suyash, S., Khan, W. H., Maitra, P., et al. (2024) · Biosciences Biotechnology Research Asia · doi:10.13005/bbra/3318 · Cited by 4
Predicting mutational function using machine learning
Shea, A., Bartz, J., Zhang, L. J., & Dong, X. (2023) · Mutation Research/Reviews in Mutation Research · doi:10.1016/j.mrrev.2023.108457 · Cited by 4
Computational Mutagenesis of Antibody Fragments: Disentangling Side Chains from ΔΔG Predictions
Tandiana, R., Barletta, G. P., Soler, M. A., Fortuna, S., & Rocchia, W. (2024) · Journal of Chemical Theory and Computation · doi:10.1021/acs.jctc.3c01225 · Cited by 6
FLOP: Tasks for Fitness Landscapes Of Protein wildtypesPreprint
Groth, P. M., Richard, M., Salomon, J., Tian, P., & Boomsma, W. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.06.21.545880 · Cited by 7
“While the above all consider protein sequence inputs, the recent Atom3D benchmark [13] presents various prediction tasks using 3D structure as input, including predicting amino acid identity from structural environments (for general proteins), and mutation effects on protein binding, using data originating from the SK…”
MethodBindingGYM: A Large-Scale Mutational Dataset Toward Deciphering Protein-Protein InteractionsPreprint
Lu, W., Zhang, J., Gu, M., & Zheng, S. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.03.626712 · Cited by 7
More Structure, Less Accuracy: ESM3’s Binding Prediction ParadoxPreprint
Loux, T., Wang, D., & Shakhnovich, E. I. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.12.09.627585 · Cited by 7
Optimizing the breadth of SARS-CoV-2-neutralizing antibodies in vivo and in silico
Kuroda, D., Moriyama, S., Sasaki, H., & Takahashi, Y. (2025) · Human Vaccines & Immunotherapeutics · doi:10.1080/21645515.2025.2526873 · Cited by 4
“Following this trend, based on structural and binding experimental data from the SKEMPI 2.0 database, 102 a geometric neural network model was developed to predict how amino acid changes in the CDRs can impact binding affinity and neutralization against different SARS ‐ CoV ‐ 2 variants.”
InfluentialLi, X. D., Perez, R. M., Ferrie, J. J., Petersson, E. J., & Giannakoulias, S. G. (2025) · International Journal of Molecular Sciences · doi:10.3390/ijms26157125 · Cited by 3
“To do so, we performed fine-tuning on data from SKEMPI 2.0 [26], a database containing the change in free energy of binding ( ∆∆ G) associated with mutations present at protein–protein interfaces.”
InfluentialDeep geometric framework to predict antibody–antigen binding affinity
(2025) · doi:10.1016/j.jsb.2025.108257 · Cited by 3
Computational design of protein complexes: influence of binding affinity
Ridha, F., Harini, K., Shanmugam, N. R. S., Nikam, R., & Gromiha, M. M. (2025) · Chemical Communications · doi:10.1039/d5cc04821d · Cited by 4
Phenotypic dominance emerges from activity fitness functions and molecular interactions
Pal, T., Dibyachintan, S., Cisneros, A. F., & Landry, C. R. (2025) · Genetics · doi:10.1093/genetics/iyaf254 · Cited by 3
Benchmarking TCR–pMHC structure prediction: a unified evaluation and CDR3-based functional insights
Lu, J. D., Zhu, X., Hu, X., Zhang, C., & Feng, F. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag289 · Cited by 6
Xu, X., Zhang, H., Liu, Q., Cheng, Q., Guo, Y., Wei, Y., & Chen, X. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01734 · Cited by 6
Sampaio, J. V., Santos-Costa, A. H., Albuquerque, A. O., Souza, J. S., Almeida, D. S., Gaieta, E. M., Almeida, M. V., Sartori, G., & da Silva, J. H. M. (2026) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01924 · Cited by 4
“This cycle continues until none of the other 52 canonical structures yield further improvement.”
ASD: antigen-specific antibody database
Czerwinski, A., Dudzic, P., Wójtowicz, K., Jaszczyszyn, I., Bielska, W., Wrobel, S., Demharter, S., Spreafico, R., Greiff, V., & Krawczyk, K. (2026) · mAbs · doi:10.1080/19420862.2026.2623330 · Cited by 4
“The next three datasets (skempiv2, 44 ab-bind, 26 abdesign) 18 originated from the same already processed dataset – Naturalantibody’s AbDesign Database, with little to no preprocessing needed, with each affinity type already present in the database.”
Using experimental results of protein design to guide biomolecular energy-function development
Haddox, H. K., Rocklin, G. J., Motta, F. C., Strickland, D., Halabiya, S. F., Cordray, C., Park, H., Klavins, E., Baker, D. A., & DiMaio, F. (2026) · PLoS Computational Biology · doi:10.1371/journal.pcbi.1014215 · Cited by 6
“See https://github.com/ Haddox/design_guided_optE/tree/main/atom_pair_benchmark for the 78 and 54 high-resolution crystal structures used in training and validation, the code for relaxing structures and computing atom-pair distance distributions, and output files with the resulting distributions.”
Kumar, A. K., & Rathore, R. S. (2023) · Journal of Biomolecular Structure and Dynamics · doi:10.1080/07391102.2023.2252077 · Cited by 3
“…(Thorn & Bogan, 2001) ATLAS (Borrman et al., 2017), BID (Fischer et al., 2003), DACUM (Geng et al., 2016), dbAMEPNI (Liu et al., 2018), dbMPIKT (Liu et al., 2018), PROXiMATE (Jemimah et al., 2017), SKEMPI 2.0 (Jankauskaite et al., 2019), and ProThermDB (Nikam et al., 2021) have been developed.”
InfluentialLi, J., Chen, X., Huang, H., Zeng, M., Yu, J., Gong, X., & Ye, Q. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf120 · Cited by 5
AI designed, mutation resistant broad neutralizing antibodies against multiple SARS-CoV-2 strains
Kang, Y., Jiao, Y., Jin, K., & Pan, L. (2025) · Scientific Reports · doi:10.1038/s41598-025-98979-w · Cited by 5
“We examined the following publicly available curated datasets for model development: SKEMPI database 15 Antibody-Bind (AB-Bind) database 16 , Observed Antibody Space 17 , and UniProt 18 .”
A Guide for Protein–Protein Docking Using SwarmDock
Moal, I. H., Chaleil, R. A. G., Torchala, M., & Bates, P. A. (2020) · Methods in molecular biology · doi:10.1007/978-1-0716-0708-4_11 · Cited by 3
Self-citationAn ultra‐high affinity protein–protein interface displaying sequence‐robustness
Møller, M. S., Olesen, S. V., & André, I. (2021) · Protein Science · doi:10.1002/pro.4080 · Cited by 2
Classification of protein–protein association rates based on biophysical informatics
Dhusia, K., & Wu, Y. (2021) · BMC Bioinformatics · doi:10.1186/s12859-021-04323-0 · Cited by 3
“0, includes data of 345 wild-type protein complexes and their 7085 associated mutants [71].”
BackgroundFragment hopping protocol for the design of small-molecule protein–protein interaction inhibitors
Kell, S. R., Wang, Z., & Ji, H. (2022) · Bioorganic & Medicinal Chemistry · doi:10.1016/j.bmc.2022.116879 · Cited by 3
PROT-ON: A structure-based detection of designer PROTein interface MutatiONs
Koşaca, M., Yılmazbilek, İ., & Karaca, E. (2023) · Frontiers in Molecular Biosciences · doi:10.3389/fmolb.2023.1063971 · Cited by 3
Islam, S., Chauhan, V. M., & Pantazes, R. J. (2024) · mAbs · doi:10.1080/19420862.2024.2440586 · Cited by 4
Wang, R., Chen, J., Gao, K., & Wei, G. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.08023 · Cited by 3
“0 [11]) was carried out using gradient boosted regression tree (GBRTs).”
MethodDeep Local Analysis estimates effects of mutations on protein-protein interactionsPreprint
Behbahani, Y. M., Laine, É., & Carbone, A. (2022) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2022.10.09.511484 · Cited by 3
“0 [19], the most complete source for experimentally measured binding affinities of wild-type and mutated protein complexes.”
BackgroundHERMES: Holographic Equivariant neuRal network model for Mutational Effect and Stability predictionPreprint
Visani, G. M., Galvin, W., Jones, Z., Pun, M. N., Daniel, E., Borisiak, K., Wagura, U., & Nourmohammad, A. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.07.09.602403 · Cited by 3
“0 dataset [55], which spans a substantially broader range of protein-protein interactions and binding-affinity perturbations.”
InfluentialLeveraging Neural Networks to Correct FoldX Free Energy Estimates
Barnes, J. E., Chi, L. A., Pandey, S. K., Ytreberg, F. M., & Patel, J. S. (2026) · ACS Omega · doi:10.1021/acsomega.6c01409 · Cited by 3
Zaverdas, H., Stojceski, F., Romero‐Zaliz, R., Androutsos, L., Makrygiannis, P., Pallante, L., Martos, V., Grasso, G., Deriu, M. A., Theofilatos, K., et al. (2025) · npj Science of Food · doi:10.1038/s41538-025-00478-9 · Cited by 2
Prediction of Interleukin-binding Sites Combining Multi-Source Features with Integrated Algorithm
Niu, X., & Feng, Y. (2025) · Current Bioinformatics · doi:10.2174/0115748936372515250801173324 · Cited by 2
Review of Antibody Structure Prediction-Based on Artificial Intelligence
Makram, D., Maghraby, F. A., Shaheen, M., & Mabrouk, M. S. (2025) · Archives of Computational Methods in Engineering · doi:10.1007/s11831-025-10404-7 · Cited by 4
Zhang, L., Zhou, X., Liang, L., & Lin, J. (2025) · ACS Omega · doi:10.1021/acsomega.5c08777 · Cited by 4
“31 SKEMPI compiles experimental data on changes in thermodynamic and kinetic parameters due to mutations in protein − protein complexes, which have 3D structures stored in the PDB. 32 From the SKEMPI 1.0 database, a nonredundant set of interface mutations was obtained, encompassing 114 protein…”
InfluentialZhang, Y., Liu, Y., Zhang, Y., Wang, Z., Lu, X., Ge, S., & Min, X. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf645 · Cited by 3
“0, AB-Bind, etc. [23, 33, 34] contain similar homologous proteins or mutation samples.”
An equivariant pretrained transformer for unified 3D molecular representation learning
Jiao, R., Kong, X., Zhang, L., Yu, Z., Ren, F., Tan, W., Huang, W., & Liu, Y. (2026) · Nature Communications · doi:10.1038/s41467-026-69185-7 · Cited by 20
Zhang, J., Wang, S., Gao, L., & Li, Q. (2026) · Journal of Biotechnology · doi:10.1016/j.jbiotec.2026.03.012 · Cited by 4
MAVISp : A modular structure‐based framework for protein variant effects
(2026) · doi:10.1002/pro.70548 · Cited by 3
MAMMAL - Molecular Aligned Multi-Modal Architecture and Language for biomedical discovery
Shoshan, Y., Raboh, M., Ozery-Flato, M., Ratner, V., Golts, A., Weber, J. K., Barkan, E., Rabinovici‐Cohen, S., Polaczek, S., Amos, I., et al. (2026) · npj Drug Discovery. · doi:10.1038/s44386-026-00047-4 · Cited by 24
Prediction of protein–protein interactions and co-complex models with deep learning
Zhang, Z., Liu, Y., & Yu, H. (2026) · Current Opinion in Chemical Biology · doi:10.1016/j.cbpa.2026.102703 · Cited by 3
DVA: predicting the functional impact of single nucleotide missense variants
Wang, D., Li, J., Wang, E., & Wang, Y. (2024) · BMC Bioinformatics · doi:10.1186/s12859-024-05709-6 · Cited by 3
“There are several problems to be fixed: (1) Although the wild protein structures are accessible in several database [26–28], the mutated protein structure usually is not provided; (2) Protein structure is complicated.”
BackgroundA benchmark for evaluation of structure-based online tools for antibody-antigen binding affinity
Jiayi, X., Gong, J., Bo, X., Tong, Y., Ren, Z., & Ni, M. (2024) · Biophysical Chemistry · doi:10.1016/j.bpc.2024.107253 · Cited by 2
Biswas, G., Mukherjee, D., & Basu, S. (2024) · Journal of Computational Biology · doi:10.1089/cmb.2024.0554 · Cited by 2
Liu, C., Cai, S., Pan, T., Ogata, H., Song, J., & Akutsu, T. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c00130 · Cited by 5
Barhoon, M., & Mahdiuni, H. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.5c01029 · Cited by 3
AbTune: layer-wise selective fine-tuning of protein language models for antibodies
Xu, X., & Bonvin, A. M. J. J. (2026) · Briefings in Bioinformatics · doi:10.1093/bib/bbag374 · Cited by 2
PDBe-KB: collaboratively defining the biological context of structural data
Armstrong, D. (2022) · Acta Crystallographica Section A Foundations and Advances · doi:10.1107/s2053273322094116 · Cited by 3
Matthews, B. (2017) · Protein Science · doi:10.1002/pro.3351 · Cited by 2
Koirala, M., & Alexov, E. (2019) · Journal of Theoretical and Computational Chemistry · doi:10.1142/s0219633619300015 · Cited by 3
Review of COVID-19 Antibody TherapiesPreprint
Chen, J., Gao, K., Wang, R., Nguyen, D. D., & Wei, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2006.10584 · Cited by 2
Emerging vaccine-breakthrough SARS-CoV-2 variantsPreprint
Wang, R., Chen, J., Hozumi, Y., Yin, C., & Wei, G. (2021) · PubMed · doi:10.48550/arxiv.2109.04509 · Cited by 15
“0 dataset [38] is used as the basic training set, while next-generation sequencing datasets are added as assistant training sets.”
MethodLiu, Y., Armstrong, G. A., Tam, J. Z., & Chen, B. Y. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.26.564257 · Cited by 2
“Datasets used to construct the model were from the SKEMPI v.2.0 database [ 15 ] .”
MethodInfluentialGeoAB: Towards Realistic Antibody Design and Reliable Affinity MaturationPreprint
Lin, H., Wu, L., Huang, Y., Liu, Y., Zhang, O., Zhou, Y., Sun, R., & Li, S. Z. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.15.594274 · Cited by 16
“4 gives performance on the accuracy of predicting ∆∆ G and structures on the test set on SKEMPI2.”
MethodInfluentialYe, Q., li, J., Chen, X., Huang, H., Zeng, M., Yu, J., & Gong, X. (2024) · Research Square · doi:10.21203/rs.3.rs-4647798/v1 · Cited by 2
Effects of protein interface mutations on protein quality and affinityPreprint
de Kanter, J. K., Smorodina, E., Minnegalieva, A. R., Arts, M., Blaabjerg, L. M., Frolenkova, M., Rawat, P., Wolfram, L., Britze, H., Wilke, Y., et al. (2026) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.64898/2026.03.24.713863 · Cited by 5
Data-Driven Discovery of Biophysical T Cell Receptor Cospecificity Rules
Pyo, A. G. T., Nagano, Y., Milighetti, M., Henderson, J., Callan, C. G., Chain, B., Wingreen, N. S., & Tiffeau-Mayer, A. (2025) · PRX Life · doi:10.1103/14j1-wrh5 · Cited by 4
“To test whether the observed decrease in the significance of hydrophobic properties—and the corresponding increase in the significance of steric properties—extends to other classes of protein-protein interactions, we analyzed thermodynamic measurements from the SKEMPI database [49].”
Yue, Y., Cheng, Y., Marquet, C., Xiao, C., Guo, J., Li, S., & He, S. (2025) · Journal of Chemical Information and Modeling · doi:10.1021/acs.jcim.4c01607 · Cited by 2
Lebedenko, O. O., Polovinkin, M. S., Kazovskaia, A. A., & Skrynnikov, N. R. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26821 · Cited by 2
“0 [22] and MPAD [23] databases.”
Wang, Y., Zhu, Y., Shi, X., & Wang, L. (2025) · Proteins Structure Function and Bioinformatics · doi:10.1002/prot.26837 · Cited by 2
“By extracting mutated side chain information from the SKEMPI [22, 23] data sets and the PDB files available in the RCSB PDB databases [25], we acquire the requisite data for subsequent processing.”
Recent advances in antibody optimization based on deep learning methods
Jin, R., Zhou, R., & Zhang, D. (2025) · Journal of Zhejiang University SCIENCE B · doi:10.1631/jzus.b2400387 · Cited by 2
“As one of the latest datasets, the SKEMPI database has been em ‐ ployed for model training and testing in several recent studies aimed at antibody optimization ( Jankauskaitė et al., 2019; Soleymani et al., 2022).”
AFToolkit: a framework for molecular modeling of proteins with AlphaFold-derived representations
Sindeeva, M., Telepov, A., Ivanisenko, N. V., Shashkova, T., Khrabrov, K., Tsypin, A., Kadurin, A., & Kardymon, O. L. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf324 · Cited by 1
Energy-Based Models for Predicting Mutational Effects on Proteins
Soga, P., Lei, Z., He, Y., Bilodeau, C., & Li, J. (2025) · ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) · doi:10.1145/3711896.3736931 · Cited by 3
“0 [20] and antibody optimization against SARS-CoV-2 [49].”
InfluentialCheng, L., Wei, T., Cui, X., Chen, H.-F., & Yu, Z. (2025) · Briefings in Bioinformatics · doi:10.1093/bib/bbaf391 · Cited by 1
“Details of the training procedure are in the supplementary materials (Supplementary Table S2 available online at http://bib.oxfordjournals.org/).”
Multimodal Learning of Protein–Protein Interactions for Accurate Binding Affinity Prediction
Mo, J., Guo, J., & Duan, H. (2025) · ACS Omega · doi:10.1021/acsomega.5c06443 · Cited by 1
Ma, X., Dey, S., Vaishnavey, S. R., Zelinski, C., Li, Q., & Chowdhury, R. (2025) · NAR Genomics and Bioinformatics · doi:10.1093/nargab/lqaf154 · Cited by 3
Zhang, L., Bian, Z., Wang, X., & Kong, L. (2025) · Biosystems · doi:10.1016/j.biosystems.2025.105688 · Cited by 1
AI-Driven De Novo Binder Design: From Structure Prediction to Closed-Loop Optimization
Li, X., Fan, Z., Yang, J., Jiang, R., Cao, F., Li, J., Xie, D., Meng, X., Sun, M., & Wang, L. (2026) · Computational and Structural Biotechnology Journal · doi:10.34133/csbj.0070 · Cited by 1
“However, their absolute calibration is limited by training data biases, label noise, and distribution shift [ 39 ], and they may not faithfully approximate physical binding free energies [ 73 ].”
Toward Quantitative Domain–Motif Interactomes: State of the Art, Challenges, and Perspectives
Alvarado-Valverde, J., & Luck, K. (2026) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-092624-110614 · Cited by 1
Medina-Ortiz, D., Salinas, P., Cabas-Mora, G., Durán-Verdugo, F., Olivera‐Nappa, Á., & Uribe-Paredes, R. (2023) · Lecture notes in computer science · doi:10.1007/978-3-031-36805-9_16 · Cited by 2
Predicting interacting hotspots for nanobodies' binding using triplets of residues
Hamdani, R., Cianferoni, D., Reche, R., Delgado, J., & Serrano, L. G. (2025) · Protein Science · doi:10.1002/pro.70220
PLNet : Persistent Laplacian neural network for protein–protein binding free energy prediction
Xu, X., Wang, C., Wei, G., & Chen, J. (2025) · Protein Science · doi:10.1002/pro.70377 · Cited by 6
(2022) · Frontiers in Ocean Engineering · doi:10.38007/foe.2022.030304 · Cited by 1
Characterizing SARS-CoV-2 mutations in the United StatesPreprint
Wang, R., Chen, J., Gao, K., Hozumi, Y., Yin, C., & Wei, G. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2007.12692
Beyond gene expression: novel methods and applications of transcript expression analyses in RNA-Seq
Gupta, R. (2021) · Research Publications (Maastricht University) · doi:10.26481/dis.20210304rg · Cited by 1
Carvalho, P. P. D. (2021) · Digital Library of Theses and Dissertations (Universidade de São Paulo) · doi:10.11606/d.59.2021.tde-24082021-145318 · Cited by 3
Omicron BA.2 (B.1.1.529.2): high potential to becoming the next dominating variant.Preprint
Chen, J., & Wei, G. (2022) · PubMed · Cited by 3
Searching for a mechanistic description of pairwise epistasis in protein systemsPreprint
Barnes, J. E., Miller, C. R., & Ytreberg, F. M. (2021) · doi:10.22541/au.162290894.41749480/v1 · Cited by 1
Chen, Y. C., Sargsyan, K., Wright, J. D., Chen, Y., Huang, Y., & Lim, C. (2023) · Research Square · doi:10.21203/rs.3.rs-3400169/v1 · Cited by 1
Cisneros, A. F., Nielly‐Thibault, L., Mallik, S., Levy, E. D., & Landry, C. R. (2023) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2023.10.31.565025 · Cited by 1
Chen, Y. C., Sargsyan, K., Wright, J. D., Chen, Y., Huang, Y., & Lim, C. (2024) · eLife · doi:10.7554/elife.96643.1 · Cited by 1
Chen, Y. C., Sargsyan, K., Wright, J. D., Chen, Y., Huang, Y., & Lim, C. (2024) · eLife · doi:10.7554/elife.96643.2 · Cited by 2
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.